JÉRÔME MENDES
.01

ABOUT

How to describe myself in one sentence?

Passionate about Technology, Innovation, and Entrepreneurship.

 

BIO

ABOUT ME

EXPERIENCE:
  • Development of intelligent solutions based on Artificial Intelligence for the industry.
  • Co-supervisor and Team Member in several R&D projects.
  • Writer of several EU/Portuguese projects proposals.
EDUCATION:
  • PhD on “Computational Intelligence Methodologies for Control of Industrial Processes”.
  • Post-graduated in Small and medium enterprises (SMEs) Management.

Interests

Computational intelligence methodologies for Industry

  • Intelligent control and identification.
  • Fault and defect detection.
  • Automatic decision making systems.
  • Auto-tuning of processes/machines.
  • optimization problems.
  • Design of interpretable models and controllers for experts operators.
  • Evolving systems.
  • Prediction.
.02

RESUME

EDUCATION
  • 2009
    2014
    COIMBRA, PORTUGAL

    PHD, ELECTRICAL AND COMPUTER ENGINEERING

    UNIVERSITY OF COIMBRA

    Subject: “Computational Intelligence Methodologies for Control of Industrial Processes”
    • Development of intelligent control algorithms.
    • Focus on industrial applications.
    • Partnership with company.
    • Approved unanimously with distinction and honors.
  • 2015
    2015
    COIMBRA, PORTUGAL

    Technology-based Entrepreneurship Course

    UNIVERSITY OF COIMBRA, CEBT Iberian course

    • Purposes of stimulating the capacities and skills needed to create technology-based companies.
    • An innovative methodology, based on workshops, mentoring and coaching sessions.
    • Team of mentors with vast know-how and experience in entrepreneurship and innovation.
  • 2011
    2012
    COIMBRA, PORTUGAL

    SME MANAGEMENT - POST GRADUATION

    COIMBRA BUSINESS SCHOOL- ISCAC

    Main course::
    • Strategic Management.
    • Entrepreneurship.
    • Marketing Strategy and Planning.
    • Internationalization.
    • Financial Analysis.
  • 2003
    2009
    COIMBRA, PORTUGAL

    MSC, ELECTRICAL AND COMPUTER ENGINEERING

    UNIVERSITY OF COIMBRA

    • Specialization: Automation and Robotics.
    • Master thesis: Implementation of intelligent control algorithms for industrial processes.
ACADEMIC AND PROFESSIONAL POSITIONS
  • 2015
    Present
    COIMBRA, PORTUGAL

    POSTDOCTORAL RESEARCHER

    INSTITUTE OF SYSTEMS AND ROBOTICS

    Computational intelligence methodologies for Industry:
    • Intelligent control and identification.
    • Fault and defect detection.
    • Automatic decision making systems.
    • Auto-tuning of processes/machines.
    • optimization problems.
    • Design of interpretable models and controllers for experts operators.
    • Evolving systems.
    • Prediction.

    Co-supervisor, and Team Member of several R&D projects in partnership with companies.

    Elaboration of several projects proposals.

  • 2014
    2015
    COIMBRA, PORTUGAL

    RESEARCHER & WRITER OF EUROPEAN PROJECTS PROPOSALS

    IPN - PEDRO NUNES INSTITUTE

    • End user needs analysis
    • Requirements analysis.
    • Writer of H2020 projects proposals
  • 2009
    2014
    COIMBRA, PORTUGAL

    RESEARCHER

    INSTITUTE OF SYSTEMS AND ROBOTICS & ACONTROL COMPANY

    • Development of intelligent solutions for industrial processes.
    • Elaboration of projects proposals.
    • Co-supervisor, and Team Member in several R&D projects in partnership with companies.
CONFERENCE CO-CHAIR
  • 2012
    2012
    Kraków, Poland

    Co-chair of ETFA 2012 Conference

    International Conference on Emerging Technologies and Factory Automation

    Co-chair of the Session "Industrial Control Track"
  • 2011
    2011
    Toulouse, France

    Co-chair of ETFA 2011 Conference

    International Conference on Emerging Technologies and Factory Automation

    Co-chair of the Session "Industrial Control Track"
.03

PROJECTS

RESEARCH PROJECTS
Current Projects

CONNECTA-X

CONNECTA-X

About The Project

CONNECTA-X – Interoperable System and Modules for Appliance Integration in Intelligent Home Ecosystems [2018-Present]


My Role: Team Member.
Host institutions: University of Coimbra (UC); Critical Software, SA (leader partner)
Financing: co-financing by “Portugal 2020” (PT2020), in the framework of the “Competitiveness and Internationalization Operational Programme” (COMPETE 2020), and by the European Union through the European Regional Development Fund (ERDF);
Reference number: CONNECTA-X/2017/33354.


Abstract: The CONNECTA-X project performed R&D on interoperable system and modules for integration of appliances in intelligent homes; including R&D on themonitoring integration of “Internet of Things” (IoT) and Smart Meters and aims to develop a structure for the embedded market, a platform for communication, gathering, and treatment of data in the computational intelligence and monitoring device monitoring domains, that should support the development of new added-value products and services on the IoT and Smartt Meters domain.
Recently, we have been watching processing technology and connectivity integration with all those everyday things, making them a part of our lives. This reality, created the IoT concept, in which the number of smart objects have been dramatically increasing over time. However, there still exists some barriers that have a negative impact on IoT market spread and maturity. Essentially, they are related to interoperability, and/or high costs and longer design and production times.
On another level, we have “smart” concepts like smart grids, smart cities, smart homes, smart meters, etc., which dissemination has been increasing fast. More efficiency, interoperability between systems, connectivity have been achive thanks to the interconnection between those objects.
This project was born from the combination of those two realities, IoT and Smart Meters, which are the project basis. CONNECTA-X aims to develop a communication, data collection and processing platform, for computational intelligence and device monitoring, which will support the development of new value-added products and services IoT related. From that platform, a solution for the embedded market, specifically smart home appliances, will be searched and developed. It will allow smart meters and Household appliances communication. This solution will be attractive for consumer appliance manufacturers, thanks to is cost-effective and time-to-market, and it will allow appliances faster conversion into smart appliances, and smart metering network compatible.

Current Projects

SIICEI

SIICEI

About The Project

SIICEI – Intelligent System for Identification of Electrical Loads in Industrial Equipment [2018-Present]


My Role: Team Member.
Host institutions: University of Coimbra (UC); OnControl Technologies, Lda (leader partner); Advanced Home, Lda.
Financing: co-financing by “Portugal 2020” (PT2020), in the framework of the “Centro Region Operational Programme” (CENTRO 2020), and by the European Union through the European Regional Development Fund (ERDF).
Reference number: SIICEI/2017/33338.


Abstract: The SIICEI project has the main goal of research and development of an electrical loads separation and identification system for industrial applications, and subsequent processing, for energy consumption and operation monitoring. The system to be developed shall allow the energy consumption profile identification of each electrically-powered equipment (charge), in real-time, using computational intelligence and signal processing methodologies, and using only the electrical energy signals only at the industrial installations energy input. So, with a reduced investment and quick installation it is possible to identify the energy consumption, measure equipment operation periods, and also, drive new applications of the gathered data.
The paradigm shift that the consortium shall realize allows monitoring of several equipment performance metrics (consumption, operation period, durability, to name a few) as well as the quick and automatic equipment failure detection. The real implementation of the results of this project shall result in the increase of the energy and productivity efficiency of industrial units. In an early phase the technology shall be validated in small to medium sized industrial units, which, typically possess the bare minimum of technology in their production lines.

Current Projects

TOOLING4G

TOOLING4G

About The Project

TOOLING4G – Advanced Tools for Smart Manufacturing [2018-Present]


My Role: Team Member.
Host institutions: University of Coimbra (UC); CENTIMFE – Technological Center for Moulds, Special Tools and Plastics (overall management); Aníbal H. Abrantes – Industries of Moulds and Plastics, S.A. (leader); and the project a partnership between 30 entities, including 20 companies, and 10 non-corporate R&D institutions, higher education entities, and technological interface centers.
Financing: co-financing by the “Competitiveness and Internationalization Operational Programme” (COMPETE 2020), Lisbon Regional Operational Program 20142020 (LISBOA2020), Portugal 2020 (PT2020), and by the European Union through the European Regional Development Fund (ERDF);
Reference number: TOOLING4G2016/24516.


Abstract: The TOOLING4G project aims to make an important contribution to the moulds and plastics industry, enabling the partner companies to create the conditions to become competitive and to overcome global market challenges, by creating internally conditions for production flexibility. The project is structured in 7 large PPSs (Product, Process or Service), including hybrid manufacturing processes; intelligent toolssystems; efficient tools for multi-material products’ manufacturing; multi-process tools; industry digitalization; sustainable “zero defect” production chain; management and dissemination. The consortium consists of 21 mould-making and plastics companies and 10 entities of the research and innovation system, including higher education institutions and technology interface centres, that possess a set of complementary skills and human capital resources. Several innovations are expected to be developed in the project, mainly centred in materials, products and processes, and also in the endogenization of technologies and organizational paradigms in the context of the Industry 4.0 concept.
The participation of the University of Coimbra (UC) in the “PPS2 – Intelligent Tools
Systems” of TOOLING4G includes the development of a system of algorithms for communication in the mould-machine complex for real-time monitoring, prediction and control of parameters, variables, and defects in the injection process and in the mould-machine complex, in order to optimize the process and the moulded parts. In this participation, the UC is represented by the Intelligent Control research group of the “Institute of Systems and Robotics – University of Coimbra” (ISR-UC). In this context, computational intelligence and intelligent control methodologies are investigated and developed for monitoring, prediction, and control of parameters, variables, and defects.

Current Projects

KhronoSim

KhronoSim

About The Project

KhronoSim – System for Simulation and Test of Complex Systems [2016-Present]


My Role: Team Member.
Host institutions: University of Coimbra (UC); Critical Software, SA; Institute of Engineering of Porto.
Financing: co-financing by “Portugal 2020” (PT2020), in the framework of the “Competitiveness and Internationalization Operational Program” (COMPETE 2020), and by the European Union through the European Structural and Investment Funds (ESIF);
Reference number: KhronoSim201617611.


Abstract: Concepts such as “Fourth Industrial Revolution (Industry 4.0)” and “Internet of the Things (IoT)” boasted into the technology speech like a blizzard, touching those who use and interest themselves of technology almost as much as those developing it. Such concepts are not surprisingly more used than understood; more are those using the concepts than those actually understanding their implications. Surprisingly enough, the increase of use of technology by the population at large, makes that security is not the least well-known aspect, though still not fully grasped however. Less well-known are the implications of complex systems working tightly coupled, with little or no human intervention, or possibility of human intervention, whatsoever. In such a scenario, testing components individually, one-by-one, is not sufficient to assert the correct functioning of the overall system. KhronoSim aims at developing a platform for testing cyber-physical systems in closed-loop. A platform that is modular, extensible and usable in multiple application domains. A platform featuring hard-real-time control, enabling the integration of simulation models to build a closed loop test environment and allowing the use of physical and virtual systems alike. The application case of the project is the simulation, control, and test of a sun-synchronous satellite.

Current Projects

Self-Learning FLC

Self-Learning FLC

About The Project

Self-Learning Fuzzy Logic Control for Industrial Processes [2015-Present]


My Role: Principal Investigator (Post-Doctoral Researcher)
Host institutions: Institute of Systems and Robotics (ISR-UC)
Financing: Foundation of Science and Technology (FCT)
Reference number: SFRH/BPD/99708/2014.


Abstract: The main objective is to research and contribute for the automatic learning of a Fuzzy Logic Controller (FLC) from data obtained from a given process while it is being manually or automatically controlled, in order to control nonlinear industrial processes. Additionally, the methodologies may also be used to understand a process for which there is little or no information available, since the FLCs are able to gather a knowledge-base about the process control. A current challenge in FLC research is to determine the most suitable fuzzy rules and membership functions of a FLC using data obtained from a given process while it is being manually or automatically controlled. Even, after the learning of the FLC, it is crucial that it can work properly over time, controlling as accurately as possible output variable of the plant, even under operating areas where the train dataset may be not sufficiently representative of the plant, and “unknown changes” of the process. To address these problems, iterative rule learning techniques will be a starting point, where for the unknown operating areaschanges the learning process may create a new fuzzy rule, modify the parameters of an existing one, or merge similar rules. Know issuesproblems with data collection, such as sampling time, missing data, and outliers will be studied due to their influence in the iterative rule learning techniques. Thus, the methodology to be developed should be efficient in terms of performance, adaptivity and robustness.

Current Projects

IMPROVE

IMPROVE

About The Project

IMPROVE – Nonlinear Control, Estimation and Fault-Detection Tools with Provably Guarantees for Mobile Robotic Systems [2018-Present]


My Role: Team Member.
Host institutions: Institute of Systems and Robotics – University of Coimbra (ISR-UC); Faculty of Engineering of the University of Porto (FEUP) (leader partner); Institute of Systems and Robotics – University of Porto (ISR-UP).
Financing: co-financing by the by the Foundation for Science and Technology (FCT), the “Competitiveness and Internationalization Operational Programme” (COMPETE 2020), Portugal 2020 (PT2020), and the European Union through the European Regional Development Fund (ERDF);
Reference number: POCI-01-0145-FEDER-031823.


Abstract: The aim of this project is to develop system theoretical tools and algorithms in framework of mobile robotic systems that explicitly integrate in the conceptual formulation not only the desired main task but also other key objectives (e.g., economic, performance, robustness, safety, system observability properties, communication behavior and interaction with other systems, etc.) in the presence of challenging restrictions and unstructured environments. The emphasis will be placed on the design of nonlinear and optimization based control and estimation procedures that are provably accurate by construction for single and multiple robotic systems including fault-detection and isolation strategies in order to obtain high performance robotic systems capable of meeting the end-user requirements.
To assure that the research is driven by high-impact application areas, the project will focus on the following case studies:

  • Shop floor logistics and manipulation: The aim is to study and contribute to the development of innovative manufacturing solutions with particular emphasis on logistics and robotic co-workers scenarios using mobile manipulators. Key research points include the development of robust and high performance torque control strategies for robotic manipulators, active and reliable perception algorithms, reactive planning, navigation and control systems to enable mobile robots to operate autonomously in unstructured environments with effective human-robot collaboration with safety guarantees.
  • Cooperation of air and marine autonomous robotic vehicles for ocean monitoring and sampling: The motivating scenario is the detection and tracking of some eventfeature of particular interest in the ocean (e.g., oil spill pollution) where a network of heterogeneous robotic vehicles (air, surface, and underwater) that can interact autonomously with the environment and among themselves, works in cooperation to obtain measurements with adequate temporal and spatial resolutions. The same network can also adapt in real-time its behaviorgeometrical configuration in response to environmental variables measured in-situ in order to improve performance and optimize the detection and measurement strategy. This proposal brings together experts from the areas mentioned above. The merit of this research program is that it targets fundamental research well motivated by applications. The theoretical solutions envisioned will be strongly rooted in research work done by the team. Obtaining formal proofs of robustness, stability, and performance of the control and estimation algorithms is a key objective.
    At practical level, one key objective is to demonstrate and integrate some of algorithms developed in the software tools for command and control of the robotic systems, simulate and test within hardware in the loop, and validate through field tests.
Current Projects

SMITEn

SMITEn

About The Project

SMITEn – Smart Meter Integrated Test Environment [2017-Present]


My Role: Team Member.
Host institutions: Institute of Systems and Robotics – University of Coimbra (ISR-UC); Critical Software, SA.
Financing: co-financing by the “Competitiveness and Internationalization Operational Programme” (COMPETE 2020), Portugal 2020 (PT2020), and by the European Union through the European Regional Development Fund (ERDF);
Reference number: SMITEn2016023613


Abstract: Smart-Grids are an integrated vision for the future of energy supply networks in response to the current challenges of environmental sustainability, reliability and quality of the European energy supply. These infrastructures integrate various heterogeneous elements that should be well interconnected and whose interoperability will become increasingly complex and critical for the security and world economy.
Smart meters are the key instrument to implement these infrastructures and should be installed in nearly 80% of the European households by 2020. However, one of the great difficulties in the development of these complex systems is the ability to test them in an environment close to that where they operate, due to the cost and time needed to make tests in a real environment, as well as to the necessary interconnection between all components of such a system.
The SMITEn project proposes R&D activities to develop an innovative solution for testing and validating smart meters, enabling a wide range of global organizations to implement and execute all the needed tests to fulfill technical requirements and validate the interoperability required by each country’s government. The validation infrastructure should integrate a toolkit that should support all test scenarios. It provides real and emulated connectivity to suit different situations and enables easy replication of issues and verifiable fixes.
Proposing a reliable and flexible solution to enable and help spread smart meters all over the world, SMITEn project may provide an effective response to the transition to a low carbon economy and an important contribution to an affordable, secure and sustainable energy.
An important aspect in SMITEn are the R&D activities regarding the integration of simulators, and the design of closed loop smart metering simulators.

Previous Projects

SCIAD

SCIAD

About The Project

SCIAD – Self-Learning Industrial Control Systems Through Process Data [2012-2014]


My Role:Team Member and Reseacher..
Host institutions: University of Coimbra (UC), and Acontrol;
Financing: co-financing by QREN, in the framework of the “Mais Centro – Regional Operational Program of the Centro”, and by the European Union through the European Regional Development Fund (ERDF);
Reference number: SCIAD201121531.


Abstract: The objectives and scope of the project are in R&D on data-based control methodologies based auto-tuning and auto-adaptive approaches for PID and other controlers for linear and non-linear systems; R&D control methodologies based on process data for auto-design and auto-adaptation of controllers for linear and nonlinear systems; R&D on nonlinear control systems applying methods based on neural networks using processa data, and other methods; R&D on linear and non-linear multi-variable control methodologies; R&D of model predictive control (MPC) methodologies, considering knowledge driven and data driven approaches; R&D of MPC methods that are able to auto-tune, auto-adjust, auto-adapt, and learn the system model from observation of system variables; Research on the identification of process models by cognitive algorithms (neural networks, support vector regression (SVR), fuzzy systems, etc); Research of mathematical prediction methods andfor application on the optimisation of the MPC methods; R&D of mathematical optimisation, stability, and robustness of the researched control methodologies; R&D of learning methodologies for the determination of linguistic values of linguistic fuzzy variables, as well as for the determination of the control rules: R&D on evolutionary algorithms andor genetic algorithms andor hybrid andor optimization methodologies and/or unsupervised learning methodologies for learning the linguistic variables and the rules for the knowledge base of a fuzzy controller; R&D on application to simulated processes, real prototype processes, and real industrial processes.

Previous Projects

CIMCIP

CIMCIP

About The Project

CIMCIP – Computational Intelligence Methodologies for Control of Industrial Processes [2010-2014]


My Role: Principal Investigator (PhD Student)
Host institutions: University of Coimbra (UC), and Acontrol.
Financing: Foundation of Science and Technology (FCT);
Reference number: SFRH/BD/63383/2009.


Abstract (original summary proposal): This thesis is devoted to research on adaptive fuzzy controllers, predictive control, and intelligent control methodologies such as neural and neuro-fuzzy control for industrial nonlinear andor time-varying plants. Nonlinear andor time varying processes are difficult to control due to their complexity. The issues of varying parameters, presence of disturbances, non-modeled dynamics, robustness, and stability will be addressed. The developed methodologies will be validated on a main case study concerning the control of NOx and SOx emissions on a cement kiln. The process is nonlinear time-varying exhibiting the above mentioned problems. Presently, there are no automatic methodologies to control these emissions under the legal limits. We intend to research control methodologies, integrating human knowledge and/or adaptivity towards improved solutions, for the kiln and treatment systems, having large impact on the amount emission removal chemicals. These chemicals have large economic costs comparable to the maintenance costs of all the kiln electrical systems.

Previous Projects

SInCACI

SInCACI

About The Project

SInCACI – Intelligent Systems for Industrial Control, Acquisition and Communication [2009-2012]


My Role:Reseacher.
Host institutions: University of Coimbra (UC), and Acontrol;
Financing: “Mais Centro Operacional Program”, financed by “European Regional Development Fund” (ERDF), and “Agência de Inovação” (AdI);
Reference number: SInCACI31202009


Abstract: The objectives and scope of the project are performing R&D on intelligent control and decision methods; Development of a general-purpose Fuzzy Control System (FCS); On-line process control and monitoring; Controller specification and implementation; Visualization of the process state; Devicesprocess failure reports; Direct application to industry problems; Research computational intelligence techniques for the development of soft sensors for industrial application; R&D on industrial communication and processing modules: industrial distributed real-time communication fieldbus protocols: ControlNet, EthernetIP, DeviceNet; ProfiNet. Relevant properties to industrial fieldbuses: Real-time operation, Reliability, Deterministic, Error-proof, Easy to extend and maintain. Direct application to industry problems; Selling on market.

Previous Projects

FAir-Control

FAir-Control

About The Project

FAir-Control – Factory Air Pollution Control [2011-2013]


My Role: Team Member.
Host institutions: University of Coimbra (UC), and Acontrol;
Financing: Eurostars Programme of the EUREKA network, financed by “Fundação para a Ciência e a Tecnologia” (FCT), of the Ministry of Education and Science, “Agência de Inovação” (AdI), and the Seventh Framework Programme for Research and Technological Development (FP7) of the European Union;
Reference number: E!6498


Abstract: The aim of this project is to develop advanced real-time control methodologies for cost optimization of air pollutants mitigation systems. The goal is the automatic control and optimization of the feed rates of mitigation chemicals introduced into the production process (Selective Non-Catalytic Reduction), in order to control the pollutants output on the stack within the legal limits, i.e. always taking in consideration the non-violation of regulations. The main objective is to control the pollutants output on the stack within the legal limits by optimally and automatically selecting the chemicals injection rate into the cement production process, always taking in consideration the non-violation of regulations. Controlling the pollutants ration is a quite difficult problem due to the large instability of the chemicals reactions. Hence the operators work to comply to a worst case scenario, protecting themselves by injecting a quantity of chemicals much higher than needed, wasting resources and increasing the production costs. This project proposes the development of a software-based product, with embedded computational intelligence, capable of selecting the optimal chemical injection quantities for minimizing the operational cost. The base computational intelligence technology for this project is the Fuzzy Logic control. The chemical reactions generated by the chemicals introduced in the cement kiln are very complex and its effectiveness highly depends on several factors such as: temperature, pollutants concentration and dispersion of the chemicals into the gas. One other aim of this project is to develop a systems that is capable to change its strategy of injecting chemicals according to the variations in the process. To successfully achieve these objectives, it will be formed a consortium composed by 3 organizations: (1) Industrial control expert company (Acontrol), (2) Burner and kiln process expert company (Pricast), (3) University research group with expertise in advanced control and cognitive systems (UC). The impact of the project results on the process optimization, with direct reduction of factory costs, will add a high market potential to the consortium participants.

Previous Projects

R&D Acontrol

R&D Acontrol

About The Project

Project of Creation of the Research & Development Division of Acontrol [2008-2011]


My Role: Reseacher.
Host institutions: University of Coimbra (UC); Principal contractor: Acontrol;
Financing: “IAPMEI – Instituto de Apoio às Pequenas e Médias Empresas e à Inovação” and “AControl – Automação e Controle, Lda”. Financed within ‘‘Projectos de Criação e Reforço de Competências Internas de I&DT’’ of ‘‘Sistema de Incentivos à Investigação e Desenvolvimento Tecnológico nas Empresas’’ (SI I&DT) of ‘‘Quadro de Referência Estratégico Nacional Portugal 2007-2013’’ (QREN);
Reference number: CENTRO-07-0202-FEDER-002502.


Abstract: The University of Coimbra participates as a specialized consultant in the area of intelligent systems and algorithms.

Previous Projects

FUZCTR

FUZCTR

About The Project

FUZCTR – Development of Fuzzy Controllers for Modules of Manufacturing Systems [2007-2009]


My Role: Reseacher
Host institutions: Institute of Systems and Robotics – University of Coimbra (ISR-UC);
Financing: “AControl – Automação e Controle Industrial, Lda” company;
Reference number: ACONTROLISR001/2007.


Abstract: In this project the goal is to study and implement a fuzzy control system for industrial process control applications. The first applications will be in a cement kiln plant, including, as a first step, the control of the raw mill process.

Previous Projects

STRNET

STRNET

About The Project

STRNET – Development of Hardware/Software for Industrial Distributed Real-Time Systems Using the ControlNet Protocol [2007-2009]


My Role: Reseacher.
Host institutions: Institute of Systems and Robotics – University of Coimbra (ISR-UC);
Financing: “AControl – Automação e Controle Industrial, Lda” company;
Reference number: ACONTROLISR002/2007.


Abstract: In this project the goal is to study and develop hardware and software of real-time system containint digital processing (microcontrollers) having the capacity of performing network communication with other modules using the ControlNet protocol, as well as the capacity of performing relevant processings in industrial automation and control environments.

.04

PUBLICATIONS

PUBLICATIONS LIST
Jan 2018

Neo-fuzzy neuron learning using backfitting algorithm

Neural Computing and Applications


Journal Jérôme Mendes, Francisco Souza, Rui Araújo, and Saeid Rastegar
-->
Neo-fuzzy neuron learning using backfitting algorithm
Jérôme Mendes, Francisco Souza, Rui Araújo, and Saeid Rastegar
Journal
About The Publication

This paper proposes an automatic and simple approach to design a neo-fuzzy neuron for identification purposes. The proposed approach uses the backfitting algorithm to learn multiple univariate additive models, where each additive model is a zero-order T-S fuzzy system which is a function of one input variable, and there is one additive model for each input variable. The multiple zero-order T-S fuzzy models constitute a neo-fuzzy neuron. The structure of the model used in this paper allows to have results with good interpretability and accuracy. To validate and demonstrate the performance and effectiveness of the proposed approach, it is applied on 10 benchmark data sets and compared with the extreme learning machine (ELM), support vector regression (SVR) algorithms, and two algorithms for design neo-fuzzy neuron systems, an adaptive learning algorithm for a neo-fuzzy neuron systems (ALNFN), and a fuzzy Kolmogorov’s network (FKN). A statistical paired t test analysis is also presented to compare the proposed approach with ELM, SVR, ALNFN, and FKN with the aim to see whether the results of the proposed approach are statistically different from ELM, SVR, ALNFN, and FKN. The results indicate that the proposed approach outperforms ELM and FKN in all data sets and outperforms SVR and ALNFN in almost all data sets that they were statistically different in almost all data sets and that in most data sets the number of fuzzy rules selected by cross-validation was small obtaining a model with a small complexity and good interpretability capability.

Dec 2017

Self-tuning pid controllers in pursuit of plug and play capacity

Control Engineering Practice


Journal Jérôme Mendes, Luís Osório, and Rui Araújo
-->
Self-tuning pid controllers in pursuit of plug and play capacity
Jérôme Mendes, Luís Osório, and Rui Araújo
Journal
About The Publication

This work addresses the problem of controlling unknown and time varying plants for industrial applications. The concept of “plug-and-play” was pursued using control algorithms that auto-adapt their control parameters in order to control unknown and time-varying plants. Self Tuning Controllers (STC) with PID form were studied and tested on a real process setup. The setup is composed of two coupled DC motors and a variable load. Controllers’ performances were compared in order to distinguish which controllers perform better, which are easier to set up, which have a better initial response, and which enable faster reaction to plant variations and load disturbances.

May 2017

Online Identification of Takagi–Sugeno Fuzzy Models Based on Self-Adaptive Hierarchical Particle Swarm Optimization Algorithm

Applied Mathematical Modelling


Journal Saeid Rastegar, Rui Araújo, and Jérôme Mendes
-->
Online Identification of Takagi–Sugeno Fuzzy Models Based on Self-Adaptive Hierarchical Particle Swarm Optimization Algorithm
Saeid Rastegar, Rui Araújo, and Jérôme Mendes
Journal
About The Publication

This paper presents an approach for online learning of Takagi–Sugeno (T-S) fuzzy models. A novel learning algorithm based on a Hierarchical Particle Swarm Optimization (HPSO) is introduced to automatically extract all fuzzy logic system (FLS)’s parameters of a T–S fuzzy model. During online operation, both the consequent parameters of the T–S fuzzy model and the PSO inertia weight are continually updated when new data becomes available. By applying this concept to the learning algorithm, a new type T–S fuzzy modeling approach is constructed where the proposed HPSO algorithm includes an adaptive procedure and becomes a self-adaptive HPSO (S-AHPSO) algorithm usable in real-time processes. To improve the computational time of the proposed HPSO, particles positions are initialized by using an efficient unsupervised fuzzy clustering algorithm (UFCA). The UFCA combines the K-nearest neighbour and fuzzy C-means methods into a fuzzy modeling method for partitioning of the input–output data and identifying the antecedent parameters of the fuzzy system, enhancing the HPSO’s tuning. The approach is applied to identify the dynamical behavior of the dissolved oxygen concentration in an activated sludge reactor within a wastewater treatment plant. The results show that the proposed approach can identify nonlinear systems satisfactorily, and reveal superior performance of the proposed methods when compared with other state of the art methods. Moreover, the methodologies proposed in this paper can be involved in wider applications in a number of fields such as model predictive control, direct controller design, unsupervised clustering, motion detection, and robotics.

Mar 2017

A Novel Robust Control Scheme for LTV Systems Using Output Integral Discrete-Time Synergetic Control Theory

European Journal of Control


Journal Saeid Rastegar, Rui Araújo, Jalil Sadati and Jérôme Mendes
-->
A Novel Robust Control Scheme for LTV Systems Using Output Integral Discrete-Time Synergetic Control Theory
Saeid Rastegar, Rui Araújo, Jalil Sadati and Jérôme Mendes
Journal
About The Publication

The paper presents a new robust control strategy based on a synergetic control theory (SCT) approach for discrete-time linear time varying (LTV) systems in the presence of unknown disturbance. The proposed control scheme is featured by an integral type of SCT macro-variable manifold based on the output error. Stability analysis shows that in LTV systems, and for any unmeasured bounded disturbance, the proposed controller accomplishes the goal of stabilizing the system by asymptotically driving the error of the controlled variable to a bounded SCT macro-variable set containing the origin and then maintaining it there. The effectiveness of the proposed method and the implications of the controller design on feasibility and closed-loop performance are demonstrated through an example of reactor temperature control of Continuous Stirred Tank Reactor (CSTR) plant, and the control of a real coupled DC motors plant.

Mar 2016

Review of soft sensors methods for regression applications

Chemometrics and Intelligent Laboratory Systems


Journal Francisco A. A. Souza, Rui Araújo, and Jérôme Mendes
-->
Review of soft sensors methods for regression applications
Francisco A. A. Souza, Rui Araújo, and Jérôme Mendes
Journal
About The Publication

Soft sensors for regression applications (SSR) are inferential models that use online available sensors (e.g. temperature, pressure, flow rate, etc.) to predict quality variables which cannot be automatically measured at all, or can only be measured at high cost, sporadically, or with high delays (e.g. laboratory analysis). SSR are built using historical data of the process, usually provided from the supervisory control and data acquisition (SCADA) system or obtained from laboratory annotations/measurements. In the SSR development, there are many issues to deal with. The main issues are the treatment of missing data, outlier detection, selection of input variables, model training, validation, and SSR maintenance. In this work, a literature review on each of these topics will be performed, reviewing the most important works in these areas. Emphasis will be given to the methods and not to the applications.

Jan 2016

A new approach for online t-s fuzzy identification and model predictive control of nonlinear systems

Journal of Vibration and Control


Journal Saeid Rastegar, Rui Araújo, and Jérôme Mendes
-->
A new approach for online t-s fuzzy identification and model predictive control of nonlinear systems
Saeid Rastegar, Rui Araújo, and Jérôme Mendes
Journal
About The Publication

This paper proposes a new unsupervised fuzzy clustering algorithm (NUFCA) to construct a novel online evolving Takagi–Sugeno (T-S) fuzzy model identification method and an adaptive predictive process control methodology. The proposed system identification approach consists of two main steps: antecedent T-S fuzzy model parameters identification and consequent parameters identification. The NUFCA combines the K-nearest neighbour and fuzzy C-means methods into a fuzzy modelling method for partitioning of the input–output data and identifying the antecedent parameters of the fuzzy system; then the recursive least squares method is exploited to obtain initialization type consequent parameters and to construct a method for on-line fuzzy model identification. The integration of the proposed adaptive identification method with the generalized predictive control results in an effective adaptive predictive fuzzy control methodology. For better demonstration of the robustness and efficiency of the proposed methodology, it is applied to the identification of a model for the estimation of the flour concentration in the effluent of a real-world wastewater treatment plant (WWTP); and to control a simulated continuous stirred tank reactor (CSTR), and a real experimental setup composed of two coupled DC motors. The results show that the developed evolving T-S fuzzy model methodology can identify nonlinear systems satisfactorily and can be successfully used for a prediction model of the process for the generalized predictive controller. It is also shown that the algorithm is robust to changes in the initial parameters, and to unexpected disturbances.

Mar 2014

Automatic Extraction of the Fuzzy Control System by a Hierarchical Genetic Algorithm

Engineering Applications of Artificial Intelligence


Journal Jérôme Mendes, Rui Araújo, Tiago Matias, Ricardo Seco, Carlos Belchior
-->
Automatic Extraction of the Fuzzy Control System by a Hierarchical Genetic Algorithm
Jérôme Mendes, Rui Araújo, Tiago Matias, Ricardo Seco, Carlos Belchior
Journal
About The Publication

The paper proposes a new method to automatically extract all fuzzy parameters of a Fuzzy Logic Controller (FLC) in order to control nonlinear industrial processes. The main objective of this paper is the extraction of a FLC from data extracted from a given process while it is being manually controlled. The learning of the FLC is performed by a hierarchical genetic algorithm (HGA), from a set of process-controlled input/output data. The algorithm is composed by a five level structure, being the first level responsible for the selection of an adequate set of input variables. The second level considers the encoding of the membership functions. The individual rules are defined on the third level. The set of rules are obtained on the fourth level, and finally, the fifth level selects the elements of the previous levels, as well as, the t-norm operator, inference engine and defuzzifier methods which constitute the FLC. To optimize the proposed method, the HGA’s initial populations are obtained by an initialization algorithm. This algorithm has the main goal of providing a good initial solution for membership functions and rule based populations, enhancing the GA’s tuning. Moreover, the HGA is applied to control the dissolved oxygen in an activated sludge reactor within a wastewater treatment plant. The results are presented, showing that the proposed method extracted all the parameters of the fuzzy controller, successfully controlling a nonlinear plant.

Dec 2013

Adaptive fuzzy identification and predictive control for industrial processes

Expert Systems with Applications


Journal Jérôme Mendes, Rui Araújo, Francisco Souza
-->
Adaptive fuzzy identification and predictive control for industrial processes
Jérôme Mendes, Rui Araújo, Francisco Souza
Journal
About The Publication

This paper proposes a method for adaptive identification and control for industrial applications. The learning of a T–S fuzzy model is performed from input/output data to approximate unknown nonlinear processes by a hierarchical genetic algorithm (HGA). The HGA approach is composed by five hierarchical levels where the following parameters of the T–S fuzzy system are learned: input variables and their respective time delays, antecedent fuzzy sets, consequent parameters, and fuzzy rules. In order to reduce the computational cost and increase the algorithm’s performance an initialization method is applied on HGA. To deal with nonlinear plants and time-varying processes, the T–S fuzzy model is adapted online to maintain the quality of the identification/control. The identification methodology is proposed for two application problems: (1) the design of data-driven soft sensors, and (2) the learning of a model for the Generalized predictive control (GPC) algorithm. The integration of the proposed adaptive identification method with the GPC results in an effective adaptive predictive fuzzy control methodology. To validate and demonstrate the performance and effectiveness of the proposed methodologies, they are applied on identification of a model for the estimation of the flour concentration in the effluent of a real-world wastewater treatment system; and on control of a simulated continuous stirred tank reactor (CSTR) and on a real experimental setup composed of two coupled DC motors. The results are presented, showing that the developed evolving T–S fuzzy model can identify the nonlinear systems satisfactorily and it can be used successfully as a prediction model of the process for the GPC controller.

Nov 2013

A Multilayer-Perceptron Based Method for Variable Selection in Soft Sensor Design

Journal of Process Control


Journal Francisco Souza, Rui Araújo, Tiago Matias, Jérôme Mendes
-->
A Multilayer-Perceptron Based Method for Variable Selection in Soft Sensor Design
Francisco Souza, Rui Araújo, Tiago Matias, Jérôme Mendes
Journal
About The Publication

The paper proposes a new method for variable selection for prediction settings and soft sensors applications. The new variable selection method is based on the multi-layer perceptron (MLP) neural network model, where the network is trained a single time, maintaining low computational cost. The proposed method was successfully applied, and compared with four state-of-the-art methods in one artificial dataset and three real-world datasets, two publicly available datasets (Box–Jenkins gas furnace and gas mileage), and a dataset of a problem where the objective is to estimate the fluoride concentration in the effluent of a real urban water treatment plant (WTP). The proposed method presents similar or better approximation performance when compared to the other four methods. In the experiments, among all the five methods, the proposed method selects the lowest number of variables and variables-delays pairs to achieve the best solution. In soft sensors applications having a lower number of variables is a positive factor for decreasing implementation costs, or even making the soft sensor feasible at all.

Oct 2012

Genetic fuzzy system for data-driven soft sensors design

Applied Soft Computing


Journal Jérôme Mendes, Francisco Souza, Rui Araújo, Nuno Gonçalves
-->
Genetic fuzzy system for data-driven soft sensors design
Jérôme Mendes, Francisco Souza, Rui Araújo, Nuno Gonçalves
Journal
About The Publication

This paper proposes a new method for soft sensors (SS) design for industrial applications based on a Takagi–Sugeno (T–S) fuzzy model. The learning of the T–S model is performed from input/output data to approximate unknown nonlinear processes by a coevolationary genetic algorithm (GA). The proposed method is an automatic tool for SS design since it does not require any prior knowledge concerning the structure (e.g. the number of rules) and the database (e.g. antecedent fuzzy sets) of the T–S fuzzy model, and concerning the selection of the adequate input variables and their respective time delays for the prediction setting. The GA approach is composed by five hierarchical levels and has the global goal of maximizing the prediction accuracy. The first level consists in the selection of the set of input variables and respective delays for the T–S fuzzy model. The second level considers the encoding of the membership functions. The individual rules are defined at the third level, the population of the set of rules is treated in fourth level, and a population of fuzzy systems is handled at the fifth level. To validate and demonstrate the performance and effectiveness of the proposed algorithm, it is applied on two prediction problems. The first is the Box–Jenkins benchmark problem, and the second is the estimation of the flour concentration in the effluent of a real-world wastewater treatment system. Simulation results are presented showing that the developed evolving T–S fuzzy model can identify the nonlinear systems satisfactorily with appropriate input variables and delay selection and a reasonable number of rules. The proposed methodology is able to design all the parts of the T–S fuzzy prediction model. Moreover, presented comparison results indicate that the proposed method outperforms other previously proposed methods for the design of prediction models, including methods previously proposed for the design of T–S models.

Apr 2011

An architecture for adaptive fuzzy control in industrial environments

Computers in Industry


Journal Jérôme Mendes, Rui Araújo, Pedro Sousa, Filipe Apóstolo, and Luís Alves
-->
An architecture for adaptive fuzzy control in industrial environments
Jérôme Mendes, Rui Araújo, Pedro Sousa, Filipe Apóstolo, and Luís Alves
Journal
About The Publication

The paper presents an architecture for adaptive fuzzy control of industrial systems. Both conventional and adaptive fuzzy control can be designed. The control methodology can integrate a priori knowledge about the control and/or about the plant, with on-line control adaptation mechanisms to cope with time-varying and/or uncertain plant parameters. The paper presents the fuzzy control software architecture that can be integrated in industrial processing and communication structures. It includes four distinct modules: a mathematical fuzzy library, a graphical user interface (GUI), fuzzy controller, and industrial communication. Three types of adaptive fuzzy control methods have been studied, and compared: (1) direct adaptive, (2) indirect adaptive, and (3) combined direct/indirect adaptive. An experimental benchmark composed of two mechanically coupled electrical DC motors has been employed to study the performance of the presented control architectures. The first motor acts as an actuator, while the second motor is used to generate nonlinearities and/or time-varying load. Results indicate that all tested controllers have good performance in overcoming changes of DC motor load.

Jun 2018

Iterative Design of a Mamdani Fuzzy Controller

13th APCA International Conference on Control and Soft Computing


Conference Jérôme Mendes, António Craveiro, and Rui Araújo
-->
Iterative Design of a Mamdani Fuzzy Controller
Jérôme Mendes, António Craveiro, and Rui Araújo
Conference
About The Publication

This paper proposes an iterative approach to automatically design a Mamdani fuzzy logic controller.

Jul 2017

Online Evolving Fuzzy Control Design: An Application to a CSTR Plant

IEEE 15th International Conference on Industrial Informatics (INDIN 2017)


Conference Jérôme Mendes, Francisco Souza and Rui Araújo
-->
Online Evolving Fuzzy Control Design: An Application to a CSTR Plant
Jérôme Mendes, Francisco Souza and Rui Araújo
Conference
About The Publication

The paper proposes a methodology to self-evolve an online fuzzy logic controller (FLC). The proposed methodology does not require any initialization at all, it can start with an empty set of fuzzy control rules or with a simple collection of fuzzy control rules obtained from an expert operator. The FLC design is online, using only the input/output data obtained during the normal operation of the system while it is being controlled. The FLC is composed of a simple structure, where each input variable has its own set of fuzzy control rules, and is evaluated individually by the proposed methodology avoiding the high increase in the number of fuzzy control rules. The FLC structure and their antecedent and consequent parameters are both online modified by the proposed methodology. Only simple information about the system and controller is need, specifically the universe of discourse of the input and output variables, an information that is mandatory to control any process. The performance of the proposed methodology is tested on a simulated continuous-stirred tank reactor (CSTR) system where the results show that the proposed methodology has the capability of designing the FLC in order to successfully controlling the CSTR system by evolving/modifying the FLC structure when unknown regions of operation are reached (unknown for the controller).

Oct 2014

Evolutionary learning of a fuzzy controller for industrial processes

The 40th Annual Conference of the IEEE Industrial Electronics Society (IECON 2014)


Conference Jérôme Mendes, Rui Araújo, Tiago Matias, Ricardo Seco, and Carlos Belchior
-->
Evolutionary learning of a fuzzy controller for industrial processes
Jérôme Mendes, Rui Araújo, Tiago Matias, Ricardo Seco, and Carlos Belchior
Conference
About The Publication

The paper proposes a new framework to learn a Fuzzy Logic Controller (FLC), from data extracted from a process while it is being manually controlled, in order to control nonlinear industrial processes. The learning of the FLC is performed by a hierarchical genetic algorithm (HGA). First, the fuzzy c-means (FCM) clustering algorithm is applied to initialize the HGA population, in order to reduce the computational cost and increase the performance of the HGA. The HGA is composed by five hierarchical levels and it is an automatic tool since it does not require any prior knowledge concerning the structure (e.g. the number of rules) and the database (e.g. antecedent and consequent fuzzy sets) of the FLC, and concerning the selection of the adequate input variables and their respective time delays. After the extraction of the FLC by the proposed method, in order to obtain a better control results, if necessary, the learned FLC can be improved manually by using the information transmitted by a human operator, and/or the learned FLC could be easily applied to initialize the required fuzzy knowledge-base of adaptive controllers. In order to improve the results of the learned FLC, a direct adaptive fuzzy controller is applied. Moreover, the proposed method is applied on control of the dissolved oxygen in an activated sludge reactor within a simulated wastewater treatment plant. The results are presented, showing that the proposed method successfully extracted the parameters of the FLC.

Oct 2014

Adaptive identification and predictive control using an improved on-line sequential extreme learning machine

The 40th Annual Conference of the IEEE Industrial Electronics Society (IECON 2014)


Conference Tiago Matias, Francisco Souza, Rui Araújo, Saeid Rastegar, and Jérôme Mendes
-->
Adaptive identification and predictive control using an improved on-line sequential extreme learning machine
Tiago Matias, Francisco Souza, Rui Araújo, Saeid Rastegar, and Jérôme Mendes
Conference
About The Publication

This paper proposes a method for adaptive identification and predictive control using an online sequential extreme learning machine based on the recursive partial least-squares method (OS-ELM-RPLS). OL-ELM-RPLS is an improvement to the online sequential extreme learning machine based on recursive least-squares (OS-ELM-RLS) introduced in [1]. Like in the batch extreme learning machine (ELM), in OS-ELM-RLS the input weights of a single-hidden layer feedforward neural network (SLFN) are randomly generated, however the output weights are obtained by a recursive least-squares (RLS) solution. However, due to multicollinearities in the columns of the hidden-layer output matrix caused by the presence of redundant input variables or by a large number of hidden-layer neurons, the problem of estimation the output weights can become ill-conditioned. In order to circumvent or mitigate such ill-conditioning problem, it is proposed to replace the RLS method by the recursive partial least-squares (RPLS) method. The identification methodology is proposed for two application problems: (1) construction of a inferential model, and (2) the learning of a model for the Generalized predictive control (GPC) algorithm. The integration of the proposed adaptive identification method with the GPC results in an adaptive predictive control methodology. To validate and demonstrate the performance and effectiveness of the proposed methodologies, they are applied on modeling of two public regression data sets and on control of the flow through a simulated valve.

Oct 2014

Self-adaptive takagi-sugeno model identification methodology for industrial control processes

The 40th Annual Conference of the IEEE Industrial Electronics Society (IECON 2014)


Conference Saeid Rastegar, Rui Araújo, Jérôme Mendes, Tiago Matias, and Alireza Emami
-->
Self-adaptive takagi-sugeno model identification methodology for industrial control processes
Saeid Rastegar, Rui Araújo, Jérôme Mendes, Tiago Matias, and Alireza Emami
Conference
About The Publication

A novel adaptive evolving Takagi-Sugeno (T-S) model identification method is investigated and integrated in a control architecture to control of nonlinear processes is investigated. The proposed system identification approach consists of two main steps: antecedent T-S fuzzy model parameters identification and consequent parameters identification. First, a new unsupervised fuzzy clustering algorithm (NUFCA) is introduced to combine the K-nearest neighbor and fuzzy C-means methods into a fuzzy modeling method for partitioning of the input-output data and identifying the antecedent parameters of the fuzzy system. Then, a recursive procedure using a particle swarm optimization (PSO) algorithm is exploited to construct an online fuzzy model identification and adaptive control methodology. For better demonstration of the robustness and efficiency of the proposed methodology, it is applied to the identification of a model for the estimation of the flour concentration in the effluent of a real-world wastewater treatment plant (WWTP), and identification and control, using a generalized predictive controller (GPC), of a real experimental setup composed of two coupled DC motors. The results show that the developed evolving T-S fuzzy model methodology can identify nonlinear systems satisfactorily and can be successfully used for a prediction model of the process for the GPC.

Sep 2012

Fuzzy model predictive control for nonlinear processes

17th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2012)


Conference Jérôme Mendes and Rui Araújo
-->
Fuzzy model predictive control for nonlinear processes
Jérôme Mendes and Rui Araújo
Conference
About The Publication

The paper proposes an adaptive fuzzy predictive control method for industrial processes, which is based on the Generalized predictive control (GPC) algorithm. To provide good accuracy in the identification of unknown nonlinear plants, an online adaptive law is proposed to adapt a T-S fuzzy model. It is demonstrated that the tracking error remains bounded. The stability of closed-loop control system is studied and proved via the Lyapunov stability theory. To validate the theoretical developments and to demonstrate the performance of the proposed control, the controller is applied on a simulated laboratory-scale liquid-level process. The simulation results show that the proposed method has good performance and disturbance rejection capacity in industrial processes.

Sep 2012

Evolutionary fuzzy models for nonlinear identification

17th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2012)


Conference Jérôme Mendes, Samuel Pinto, Rui Araújo, Francisco Souza
-->
Evolutionary fuzzy models for nonlinear identification
Jérôme Mendes, Samuel Pinto, Rui Araújo, Francisco Souza
Conference
About The Publication

This paper proposes a new method for identification problems for industrial applications based on a Takagi-Sugeno (T-S) fuzzy model. The learning of the T-S model is performed from input/output data to approximate unknown nonlinear processes by a coevolationary genetic algorithm (GA). The proposed method is an automatic tool since it does not require any prior knowledge concerning the structure (e.g. the number of rules) and the database (e.g. antecedent fuzzy sets) of the T-S fuzzy model, and concerning the selection of the adequate input variables and their respective time delays. The proposed methodology is able to design all the parts of the T-S fuzzy prediction model and it is composed by five hierarchical levels. To validate and demonstrate the performance and effectiveness of the proposed algorithm, it is applied on Box-Jenkins benchmark problem.

Sep 2011

Adaptive predictive control with recurrent fuzzy neural network for industrial processes

16th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2011)


Conference Jérôme Mendes, Nuno Sousa, and Rui Araújo
-->
Adaptive predictive control with recurrent fuzzy neural network for industrial processes
Jérôme Mendes, Nuno Sousa, and Rui Araújo
Conference
About The Publication

The paper proposes an adaptive fuzzy predictive control method. The proposed controller is based on the Generalized predictive control (GPC) algorithm, and a recurrent fuzzy neural network (RFNN) is used to approximate the unknown nonlinear plant. To provide good accuracy in identification of unknown model parameters, an online adaptive law is proposed to adapt the consequent part of the RFNN, and its antecedent part is adapted by back-propagation method. The stability of closed-loop control system is studied and proved via the Lyapunov stability theory. A nonlinear lab oratory-scale liquid-level process is used to validate and demonstrate the performance of the proposed control. The simulation results show that the proposed method has good performance and disturbance rejection capacity in industrial processes and outperforms the PID and the classical GPC controllers.

Sep 2011

Automatic extraction of the fuzzy control system for industrial processes

16th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2011)


Conference Jérôme Mendes, Ricardo Seco, and Rui Araújo
-->
Automatic extraction of the fuzzy control system for industrial processes
Jérôme Mendes, Ricardo Seco, and Rui Araújo
Conference
About The Publication

The paper proposes a new method to automatically extract all fuzzy parameters of a Fuzzy Logic Controller (FLC) in order to control nonlinear industrial processes. The learning of the FLC is performed from controller input/output data and by a hierarchical genetic algorithm (HGA). The algorithm is composed by a five level structure, where the first level is responsible for the selection of an adequate set of input variables. The second level considers the encoding of the membership functions. The individual rules are defined on the third level. The set of rules are obtained on the fourth level, and finally, the fifth level, selects the elements of the previous levels, as well as, the t-norm operator, inference engine and defuzzifier methods which constitute the FLC. To demonstrate and validate the effectiveness of the proposed algorithm, it is applied to control a simulated water tank level process.

Sep 2011

Stable indirect adaptive predictive fuzzy control for industrial processes

16th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2011)


Conference Jérôme Mendes and Rui Araújo
-->
Stable indirect adaptive predictive fuzzy control for industrial processes
Jérôme Mendes and Rui Araújo
Conference
About The Publication

The paper proposes a stable indirect adaptive fuzzy predictive control, which is based on a discrete-time Takagi-Sugeno (T-S) fuzzy model and on the Generalized predictive control (GPC) algorithm. The T-S fuzzy model is used to approximate the unknown nonlinear plant, that to provide good accuracy in identification of unknown model parameters, three online adaptive laws are proposed. It is demonstrated that the tracking error remains bounded. The stability of closed-loop control system is studied and proved via the Lyapunov stability theory. To validate the theoretical developments and to demonstrate the performance of the proposed control, the controller is applied on a nonlinear simulated laboratory-scale liquid-level process. The simulation results show that the proposed method has a good performance and disturbance rejection capacity in industrial processes.

Sep 2012

A comparison of adaptive PID methodologies controlling a DC motor with a varying load

18th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2013)


Conference Luís Osório, Jérôme Mendes, Rui Araújo, and Tiago Matias
-->
A comparison of adaptive PID methodologies controlling a DC motor with a varying load
Luís Osório, Jérôme Mendes, Rui Araújo, and Tiago Matias
Conference
About The Publication

This work addresses the problem of controlling unknown and time varying plants for industrial applications. To deal with such problem several Self-Tuning Controllers with a Proportional Integral and Derivative (PID) structure have been chosen. The selected controllers are based on different methodologies, and some use implicit identification techniques (Single Neuron and Support Vector Machine) while the others use explicit identification (Dahlin, Pole placement, Deadbeat and Ziegler-Nichols) based in the Least Squares Method. The controllers were tested on a real DC motor with a varying load. The results have shown that all the tested methods were able to properly control an unknown plant with varying dynamics.

Sep 2010

Adaptive Fuzzy Generalized Predictive Control Based on Discrete-Time T-S Fuzzy Model

15th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2010)


Conference Jérôme Mendes, Rui Araújo, Francisco Souza
-->
Adaptive Fuzzy Generalized Predictive Control Based on Discrete-Time T-S Fuzzy Model
Jérôme Mendes, Rui Araújo, Francisco Souza
Conference
About The Publication

The paper presents an adaptive fuzzy predictive control based on discrete-time Takagi-Sugeno (T-S) fuzzy model. The proposed controller is based on Generalized predictive control (GPC) algorithm, and a discrete-time T-S fuzzy model is employed to approximate the unknown nonlinear process. To provide a better accuracy in identification of unknown parameters of the model, it is proposed an on-line adaptive law which ensures that the tracking error remains bounded. The stability of closed-loop control system is proved/studied via the Lyapunov stability theory. To validate the theoretical developments and to demonstrate the performance of the proposed control is simulated as nonlinear system a laboratory-scale liquid-level process. The simulation results show that the proposed method has a good performance and disturbance rejection capacity in industrial process.

Sep 2010

Adaptive fuzzy model-based predictive control: a lyapunov approach

9th Portuguese Conference on Automatic Control (CONTROLO 2010)


Conference Jérôme Mendes, and Rui Araújo
-->
Adaptive fuzzy model-based predictive control: a lyapunov approach
Jérôme Mendes, and Rui Araújo
Conference
Sep 2010

Fuzzy control architecture for industrial systems

9th Portuguese Conference on Automatic Control (CONTROLO 2010)


Conference Jérôme Mendes, Rui Araújo, Pedro Sousa, Filipe Apóstolo, and Luís Alves
-->
Fuzzy control architecture for industrial systems
Jérôme Mendes, Rui Araújo, Pedro Sousa, Filipe Apóstolo, and Luís Alves
Conference
Nov 2010

Adaptive fuzzy generalized predictive control based on discrete-time t-s fuzzy model for industrial processes

National Science and Technology Week, University of Coimbra


Poster Jérôme Mendes and Rui Araújo
-->
Adaptive fuzzy generalized predictive control based on discrete-time t-s fuzzy model for industrial processes
Jérôme Mendes and Rui Araújo
Poster
Sep 2010

Variable Selection Based on Mutual Information for Soft Sensors Applications

9th Portuguese Conference on Automatic Control (CONTROLO 2010)


Conference Francisco Souza, Rui Araújo, Symone Soares, Jérôme Mendes
-->
Variable Selection Based on Mutual Information for Soft Sensors Applications
Francisco Souza, Rui Araújo, Symone Soares, Jérôme Mendes
Conference
Jun 2014

VRFT and MPC Control Methodologies

Technical Report SCIAD-04


Technical Reports Luı́s Osório, Alireza Emami, Jérôme Mendes, Rui Araújo, Tiago Matias, and Pedro Sousa
-->
VRFT and MPC Control Methodologies
Luı́s Osório, Alireza Emami, Jérôme Mendes, Rui Araújo, Tiago Matias, and Pedro Sousa
Technical Reports
About The Publication

From SCIAD project.

Sep 2013

Algorithm to Obtain Linguistic Values (Fuzzy Sets) of Fuzzy Linguistic Variables by Learning

Technical Report SCIAD-03


Technical Reports Tiago Matias, Jérôme Mendes, Rui Araújo, and Pedro Sousa
-->
Algorithm to Obtain Linguistic Values (Fuzzy Sets) of Fuzzy Linguistic Variables by Learning
Tiago Matias, Jérôme Mendes, Rui Araújo, and Pedro Sousa
Technical Reports
About The Publication

From SCIAD project.

Sep 2013

Adaptive Techniques on Linear Controllers, and Methods for Identification of Process Models for Control Applications

Technical Report SCIAD-02


Technical Reports Luı́s Osório, Saeid Rastegar, Jérôme Mendes, Rui Araújo, Tiago Matias, and Pedro Sousa
-->
Adaptive Techniques on Linear Controllers, and Methods for Identification of Process Models for Control Applications
Luı́s Osório, Saeid Rastegar, Jérôme Mendes, Rui Araújo, Tiago Matias, and Pedro Sousa
Technical Reports
About The Publication

From SCIAD project.

Sep 2012

Obtaining Fuzzy Rules by Genetic Programming and Linear Control Techniques

Technical Report SCIAD-01


Technical Reports Tiago Matias, Luı́s Osório, Jérôme Mendes, Rui Araújo, and Pedro Sousa
-->
Obtaining Fuzzy Rules by Genetic Programming and Linear Control Techniques
Tiago Matias, Luı́s Osório, Jérôme Mendes, Rui Araújo, and Pedro Sousa
Technical Reports
About The Publication

From SCIAD project.

Sep 2009

Intelligent systems and applications

Technical Report SInCACI-01


Technical Reports Jérôme Mendes and Rui Araújo
-->
Intelligent systems and applications
Jérôme Mendes and Rui Araújo
Technical Reports
About The Publication

From SInCACI project.

.05

Contact

Let's make innovation together

Get in touch to get Innovation

[ My Email: jermendes@gmail.com ]