90761 - ELEMENTI DI AUTOMAZIONE INDUSTRIALE LM

Learning outcomes

The course aims to provide the conceptual, methodological, and practical bases that allow to analyze and design automatic control systems of industrial plants and processes. The course, therefore, includes the deepening of the techniques of modelling, analysis and control of dynamic systems with discrete events, essential for the study of industrial automation problems. In addition, some significant cases of industrial processes and plants will be analyzed. Finally, the most advanced techniques based on Machine Learning and Neural Networks, characterizing Industry 4.0, of Condition Monitoring and Predictive Maintenance are illustrated, as well as the discrete-time techniques of Digital Control for the (auto)tuning of Industrial DIGITAL PID regulators

Course contents

NTRODUCTION TO INDUSTRIAL AUTOMATION

 

• From Industrial Revolution to Industry 4.0
• Classification of plants, processes and control systems
• Types and main components of production lines
• Supervision, control, monitoring
• Production plants and their automation problems
• Computer Integrated Manufactoring (CIM)
• Pyramidal Model of a CIM system: field, control, supervision, planning and Management 
• Field, procedural and coordination control

 

 

MACHINE LEARNING INDUSTRIAL AUTOMATION

 

MACHINE LEARNING FAULT DIAGNOSIS and PREDICTIVE MAINTENANCE of Industrial Plants and Machinery

Fundamentals of Machine Learning

•  Bagging, Boosting and Blended learning.
• Main algorithms such as Support Vector Machine, Random Forest, Naive Bayes and their application to learning procedure

 

Application of Machine Learning to Industrial Automation

• Condition Monitoring (CM) and Predictive Maintenance (MP) within the Smart Factory
  

• Sensorization to obtain Big Data of systems for the CM and MP: real-time measurement of mechanical, electronic, and electrical data, data on wear, overheating and consumption

• Fault Detection and Isolation, Remaining Useful Life (RUL) prediction, Fault-tolerant Control: mitigation of fault effects

• Matlab/Simulink Predictive Maintenance package illustration: programming, examples and synergistic use of the Matlab Machine Learning Toolbox

• Application of Machine Learning techniques to the diagnosis of failures in ball bearings through the use of accelerometers (real data): vibration analysis, spectrum and envelope spectrum of vibrations increase of the signal-to-noise ratio by Kurtogram, Support Vector Machine based classification of the fault (inner and/or outer race fault). Programming in Matlab/Simulink

• Application of Machine Learning Techniques to the diagnosis of faults and to the prediction of the remaining useful life of a Hydraulic Pump by means of pressure measurements (data from digital twin). Programming in Matlab/Simulink

NEURAL NETWORK INTELLIGENT CONTROL

Neuro Adaptive Control

1. Fundamentals of Neural Networks: Radial Basis Function Neural Networks
2. Fundamentals of Error Learning Control Feedback
3. Fundamentals of Sliding Mode Against

Machine Vision Applications to Industrial Systems

1. "Machine Vision" and "Imaging Transformations"
2. "Multi Cameras-Based Visual Servoing for Industrial Robots"
3. "Distributed Filtering for Sensorless Control"

INDUSTRIAL AUTOMATION OF PRODUCTION LINES

Modelling of discrete event dynamical systems using Petri nets

• Discrete event dynamical systems: definitions and properties
• Petri net modeling of discrete event systems: places, transitions, flow relationship between places and transitions, Petri Graph, marking function
• Evolution of Dynamic Petri nets: enabling and firing transitions, incidence matrix, occurrence vector, reachability analysis, graphical analysis of Petri nets
• Petri net simulators: WoPeD and PIPE 2.0 software
• Petri net modeling of industrial production systems: physical approach and functional approach

 

Examples of Models, Simulation and Control of production lines:

• Model of the producer/consumer system
• Client/server system model with unit capacity or unlimited capacity request buffer

• Model of a production line with 3 warehouses, three robots, one conveyor belt, two machine tools

• Implementation and simulation in WoPeD and PIPE 2.0 of the systems referred to in points 1,2,3

Analysis and Control of Petri Graph and Application to Industrial Process Control

• Analysis of industrial processes described with Petri nets: Liveliness, Limitedness, Reversibility, Shaft and graph of reachability and coverage, Reduction techniques, P-Invariants, T-Invariants, Siphons, Traps, Deadlock.
• Control and supervision of an production lines using Petri nets: control by invariants

• Action Planner based on Petri Nets

Examples of DESIGN OF PRODUCTION LINE CONTROLLERS: Petri Net Control

• Example: Handling system with self-driving vehicles

• Notes on the translation of Petri nets in code

Readings/Bibliography

• Notes of the Teacher

• KLS Sharma, Overview of Industrial Process Automation, second edition. Elsevier LtD, 2017

• John O. Moody, Panos J. Antsaklis, Supervisory Control of Discrete Event Systems using Petri Nets, Editore: Kluwer Academic Publishers, ISBN: 0-7923-8199-8

• Pedro Larrañaga et al, Industrial Applications of Machine Learning. Editore: Chapman & Hall/CRC Data Mining and Knowledge Series

Teaching methods

Frontal Lessons, laboratory, industry didactic visits.

Assessment methods

Oral Colloquium. Optional project on a topic agreed with the student.

The oral colloquiom could be taken also on-line by TEAMS or ZOOM platform.

Teaching tools

Computer, laboratory, didactic visit to local industry

Office hours

See the website of Paolo Castaldi