ID:
142957
Tipo Insegnamento:
Opzionale
Durata (ore):
64
CFU:
8
SSD:
AUTOMATICA
Url:
INGEGNERIA INFORMATICA E DELL’AUTOMAZIONE/Automazione e robotica Anno: 1
Anno:
2024
Dati Generali
Periodo di attività
Primo Semestre (19/09/2024 - 17/12/2024)
Syllabus
Obiettivi Formativi
Engineers working in Robotics and Automation may expect to learn about data-driven approaches and adaptive control in this course. Given that it examines complicated adaptive and control systems from a dynamic perspective, it also serves as an advanced course in nonlinear and adaptive control for complex systems. The primary objective of this course is to provide students with the knowledge and skills necessary to analyse and manage complex dynamic systems via learning and adaptation.
The primary information gathered is:
- a firm grasp of the fundamentals of nonlinear dynamic system software simulation tools;
- an understanding of nonlinear blocks and system identification techniques;
- a familiarity with nonlinear mathematical tools for the control of nonlinear dynamic systems;
- a solid grounding in basic nonlinear control and identification techniques for complex processes from a dynamical perspective, taking into account information from input to output variables;
- a solid grounding in the analysis of nonlinear dynamic systems in steady and transient states, as well as their advanced simulation tools; - a solid grasp of nonlinear blocks and system identification techniques;
- a solid grasp of nonlinear mathematical tools for the control of nonlinear dynamic systems;
- a solid grounding in the fundamentals of system identification, neural networks and fuzzy logic for control, nonlinear methods for control, adaptive and learning algorithms, optimisation methods and tools, nonlinear prediction and filtering tools.
What we mean by "basic acquired skills," here meaning the ability to put what we've learned into practice, are:
- analysing the behaviour of nonlinear control systems in both static and dynamic settings;
- creating adaptive and nonlinear dynamic controllers for specific nonlinear dynamic systems;
- determining the optimal system identification algorithm for intelligent control solution design using fuzzy logic, neural networks, adaptive schemes, nonlinear filters, and purely nonlinear prototypes;
- analysing nonlinear systems using numerical simulation programmes.
The primary information gathered is:
- a firm grasp of the fundamentals of nonlinear dynamic system software simulation tools;
- an understanding of nonlinear blocks and system identification techniques;
- a familiarity with nonlinear mathematical tools for the control of nonlinear dynamic systems;
- a solid grounding in basic nonlinear control and identification techniques for complex processes from a dynamical perspective, taking into account information from input to output variables;
- a solid grounding in the analysis of nonlinear dynamic systems in steady and transient states, as well as their advanced simulation tools; - a solid grasp of nonlinear blocks and system identification techniques;
- a solid grasp of nonlinear mathematical tools for the control of nonlinear dynamic systems;
- a solid grounding in the fundamentals of system identification, neural networks and fuzzy logic for control, nonlinear methods for control, adaptive and learning algorithms, optimisation methods and tools, nonlinear prediction and filtering tools.
What we mean by "basic acquired skills," here meaning the ability to put what we've learned into practice, are:
- analysing the behaviour of nonlinear control systems in both static and dynamic settings;
- creating adaptive and nonlinear dynamic controllers for specific nonlinear dynamic systems;
- determining the optimal system identification algorithm for intelligent control solution design using fuzzy logic, neural networks, adaptive schemes, nonlinear filters, and purely nonlinear prototypes;
- analysing nonlinear systems using numerical simulation programmes.
Prerequisiti
The following concepts and the knowledge provided by the course of “Fundamentals of Automatic Control” or “Automatic Control” are mandatory:
- basic concepts of mathematics, differential and integral computation;
- knowledge of the basic concepts of Physics;
- knowledge of dynamic systems, their behaviour, and their practical application; methods to analyse dynamic systems in steady and transient states;
- knowledge of the frequency tools for the analysis of dynamic systems;
- ability to analyse and design digital systems.
- basic concepts of mathematics, differential and integral computation;
- knowledge of the basic concepts of Physics;
- knowledge of dynamic systems, their behaviour, and their practical application; methods to analyse dynamic systems in steady and transient states;
- knowledge of the frequency tools for the analysis of dynamic systems;
- ability to analyse and design digital systems.
Metodi didattici
The course is organised as follow:
- 47 hours of lectures on all the course’s topics;
- 17 hours of practical exercises in the Informatics Laboratory concerning the analysis and the simulation of nonlinear dynamic systems.
After the guided tutorials the students will have free access to the computer laboratories for additional individual tests and hands-on.
- 47 hours of lectures on all the course’s topics;
- 17 hours of practical exercises in the Informatics Laboratory concerning the analysis and the simulation of nonlinear dynamic systems.
After the guided tutorials the students will have free access to the computer laboratories for additional individual tests and hands-on.
Verifica Apprendimento
The aim of the exam is to verify at which level the learning objectives previously described have been acquired.
The examination is divided in 2 sections that will take place in the same day.
- A project regarding the simulation and the control design for a nonlinear system by using the Matlab and Simulink environments, which aims at understanding if the student has the skills in the analysis and the synthesis of a complex process. To pass this test it is required to get at least 18 points out of 22. The time allowed for this test is 1.5 hours. It is allowed consulting the Matlab and Simulink programme manual only;
- One test (30 multiple choice questions) based on all the topics tackled in the class or on the basic concepts of the course, with the aim of evaluating how deeply the student has studied the subject and how he is able to understand the topics analysed. To pass this test it is required to get at least 18 points out of 30. The time allowed for this test is 0.5 hour. It is not allowed consulting any textbook or using any PC, smart phone, calculator..
The final mark is the sum of the 2 marks. To pass the exam it is necessary to get at least 18 points out of 31. If the first test fails or if the final mark is below 18, it is necessary to repeat all the exam’s sections.
Passing the exam is proof of having acquired the ability to apply knowledge and the required skills defined in the course training objectives.
Note finally that also the examination is held in English.
The examination is divided in 2 sections that will take place in the same day.
- A project regarding the simulation and the control design for a nonlinear system by using the Matlab and Simulink environments, which aims at understanding if the student has the skills in the analysis and the synthesis of a complex process. To pass this test it is required to get at least 18 points out of 22. The time allowed for this test is 1.5 hours. It is allowed consulting the Matlab and Simulink programme manual only;
- One test (30 multiple choice questions) based on all the topics tackled in the class or on the basic concepts of the course, with the aim of evaluating how deeply the student has studied the subject and how he is able to understand the topics analysed. To pass this test it is required to get at least 18 points out of 30. The time allowed for this test is 0.5 hour. It is not allowed consulting any textbook or using any PC, smart phone, calculator..
The final mark is the sum of the 2 marks. To pass the exam it is necessary to get at least 18 points out of 31. If the first test fails or if the final mark is below 18, it is necessary to repeat all the exam’s sections.
Passing the exam is proof of having acquired the ability to apply knowledge and the required skills defined in the course training objectives.
Note finally that also the examination is held in English.
Testi
Teacher’s handouts and slides are only required for the exam and the course preparation. They are available from the personal web page of the teacher: www.silviosimani.it/lessons.html
Specific topics can be further developed in the following textbooks, which are not fundamental for the exam nor the course preparation:
- "Applied nonlinear control", J.J. Slotine, W. Li. - Prentice Hall, 1991.
- "A course in fuzzy systems and control", L.-X. Wang - Prentice Hall, 1997.
- "Neural Networks for Identification, Prediction, and Control", D.T. Pham and X. Liu - Springer Verlag, 1995.
- "Model-based Fault Diagnosis in Dynamic Systems Using Identification Techniques", S. Simani, C. Fantuzzi, R. J. Patton - Springer, 2003.
Note finally that course lectures, its lecture notes, and handouts are provided in English.
Specific topics can be further developed in the following textbooks, which are not fundamental for the exam nor the course preparation:
- "Applied nonlinear control", J.J. Slotine, W. Li. - Prentice Hall, 1991.
- "A course in fuzzy systems and control", L.-X. Wang - Prentice Hall, 1997.
- "Neural Networks for Identification, Prediction, and Control", D.T. Pham and X. Liu - Springer Verlag, 1995.
- "Model-based Fault Diagnosis in Dynamic Systems Using Identification Techniques", S. Simani, C. Fantuzzi, R. J. Patton - Springer, 2003.
Note finally that course lectures, its lecture notes, and handouts are provided in English.
Contenuti
There are a total of 64 hours of instruction for the course, with 47 hours devoted to classroom instruction and 17 hours to computer lab tutorials.
We will examine and evaluate the following subjects in further depth:
- Overview. Adaptive and intelligent control. Essential resources and interdisciplinary methods for understanding, analysing, representing, and synthesising complicated physical processes. A primer on the theory and practice of adaptive systems.
- Identifying Dynamic Systems. Identification methods (parametric and nonparametric), linear system identification using recursive algorithms, identification of nonlinear dynamic systems using online models and mathematical tools, adaptive identification and control methods, adaptive PID and classical controllers, and so on.
"Fuzzy Logic for Control" Fuzzy logic: its definition, characteristics, and applications in model identification and control, as well as in adaptive fuzzy control, automated learning and adaptation for fuzzy models, and the Adaptive Neuro Fuzzy Inference System (ANFIS) tool.
—Networks of Neurons. Fundamentals and properties. Adaptive neural controller design using the Model Reference Adaptive Control (MRAC) principle; algorithms for supervised and unsupervised learning with applications to dynamic system identification and control; stochastic search algorithms; recurrent neural networks; adaptive neural networks; convolutional neural networks for identification and control.
- Computer-aided software for making physical objects (CAD). Direct experience in the areas of adaptive control scheme design, neural network analysis, fuzzy logic for control, and nonlinear dynamic system identification.
We will examine and evaluate the following subjects in further depth:
- Overview. Adaptive and intelligent control. Essential resources and interdisciplinary methods for understanding, analysing, representing, and synthesising complicated physical processes. A primer on the theory and practice of adaptive systems.
- Identifying Dynamic Systems. Identification methods (parametric and nonparametric), linear system identification using recursive algorithms, identification of nonlinear dynamic systems using online models and mathematical tools, adaptive identification and control methods, adaptive PID and classical controllers, and so on.
"Fuzzy Logic for Control" Fuzzy logic: its definition, characteristics, and applications in model identification and control, as well as in adaptive fuzzy control, automated learning and adaptation for fuzzy models, and the Adaptive Neuro Fuzzy Inference System (ANFIS) tool.
—Networks of Neurons. Fundamentals and properties. Adaptive neural controller design using the Model Reference Adaptive Control (MRAC) principle; algorithms for supervised and unsupervised learning with applications to dynamic system identification and control; stochastic search algorithms; recurrent neural networks; adaptive neural networks; convolutional neural networks for identification and control.
- Computer-aided software for making physical objects (CAD). Direct experience in the areas of adaptive control scheme design, neural network analysis, fuzzy logic for control, and nonlinear dynamic system identification.
Lingua Insegnamento
INGLESE
Altre informazioni
To contact the professor, students can use their email addresses included in this document.
The professor will publish the teaching materials (slides, assignments, etc.) they use throughout the course in the
personal website of the subject.
http://www.silviosimani.it/lessons.html
Additionally, the professor will use the emailing list of the subject to announce key events
and provide relevant information on the subject.
The Google Classrooom code is available from the instructor's personal course webpage:
http://www.silviosimani.it/lessons.html
The professor will publish the teaching materials (slides, assignments, etc.) they use throughout the course in the
personal website of the subject.
http://www.silviosimani.it/lessons.html
Additionally, the professor will use the emailing list of the subject to announce key events
and provide relevant information on the subject.
The Google Classrooom code is available from the instructor's personal course webpage:
http://www.silviosimani.it/lessons.html
Corsi
Corsi
INGEGNERIA INFORMATICA E DELL’AUTOMAZIONE
Laurea Magistrale
2 anni
No Results Found
Persone
Persone
No Results Found