Computational Intelligence Based Systems

Code:

EEC0083

Acronym:

SBIC

Keywords
Classification	Keyword
OFICIAL	Automation, Control & Manufacturing Syst.

Instance: 2014/2015 - 2S

Active?	Yes
Responsible unit:	Department of Electrical and Computer Engineering
Course/CS Responsible:	Master in Electrical and Computers Engineering

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
MIEEC	105	Syllabus	4	-	6	56	162

Teaching language

Suitable for English-speaking students

Objectives

The main goal of the discipline is to provide knowledge, methods and technologies in order: - to design fuzzy logic and neuro-fuzzy based control systems to be applied in nonlinear and uncertain industrial processes - to discuss and design supervision, fault detection and diagnostics systems based on neuro-fuzzy concepts; - to evaluate the applicability of control and data analysis systems based on computational intelligence methods in engineering systems.

Learning outcomes and competences

At the end of the course the student should be capable to: 1. critically analyze the operation of engineering systems containing subsystems based on fuzzy logic and/or neural networks, 2. Modelling and simulate a process using the simulation tool Matlab/Simulink; 3. Designing a control system based on fuzzy logic; 4. - Implement in HW and SW, subsystems based on fuzzy logic and neural networks; 5. Explain and apply the concepts of fault detection or diagnosis systems .

Working method

Presencial

Program

Introduction to intelligent systems and intelligent control. Principles of fuzzy sets and fuzzy logic. Fuzzy models and fuzzy systems. Fuzzy logic based control. Uncertainty and non linearity. Design of simple (direct) fuzzy controllers. Adaptive fuzzy controllers. Introduction to neural networks and neuro-fuzzy systems.  Topologies and learning methods. Sliding Mode control. Application to control systems. Fault detection and diagnosis systems. Fuzzy logic and neuro-fuzzy based . Applications of fuzzy logic based systems and neural networks based systems. Analysis of some examples.

Mandatory literature

Dimiter Driankov, Hans Hellendoorn, Michael Reinfrank; An introduction to fuzzy control. ISBN: 3-540-60691-2
Jyh-Shing Roger Jang, CXhuen-Tsai Sun, Eiji Mizutani; Neuro-fuzzy and soft computing. ISBN: 0-13-261066-3
R. Isermann; Fault-diagnosis systems, Springer, 2006. ISBN: 3-540-24112-4

Teaching methods and learning activities

The theoretical classes are tutorials (2/3) and discussion of applied examples (1/3). There are also presentation of design tools in various fields of CU. The practical classes are for accompanying the execution of the simulation and experimental works.

Software

Matlab
Simulink
Fuzzy Logic Tlbx
Neural Network Tlbx

keywords

Technological sciences > Engineering > Control engineering > Automation
Technological sciences > Engineering > Simulation engineering
Technological sciences > Engineering > Process engineering > Process control
Technological sciences > Engineering > Systems engineering

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Exame	50,00
Participação presencial	10,00
Trabalho escrito	10,00
Trabalho laboratorial	30,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Elaboração de projeto	40,00
Elaboração de relatório/dissertação/tese	12,00
Estudo autónomo	38,00
Frequência das aulas	48,00
Trabalho laboratorial	24,00
Total:	162,00

Eligibility for exams

Have a minimum number of presences in the practical classes and obtain a minimum of 40% in the practical work.

Calculation formula of final grade

The Final Classification is based on three components: 1. Resolution of problem (PR), simulation based; Homework and Class participation (HW+PC); 2. Practical work (PW), simulation or experimental based 3. Final exam (EX), without notes, with a duration of 2 hours The Final Classification is given by: FC=0.2*(PR+WH+PC)+0.3*PW+0.5*EX Note. It is required a minimum of 40% in the final exam to obtain approval.

Examinations or Special Assignments

None.

Special assessment (TE, DA, ...)

The same of the ordinary students.

Classification improvement

Only the final exam evaluation component can be increased in the appropriate dates.