1.
INTRODUCTION
1.1 |
Introduction
to process supervision |
1.2 |
CAD-type tools: modern trends |
1.3 |
SCADA systems and expert
supervision: an overview |
1.4 |
Fault detection: structures
and methodologies |
1.5 |
Knowledge-based fault diagnosis |
1.6 |
IFAC definitions |
2.
FOUNDATIONS OF PROCESS SUPERVISION
2.1 |
Definition,
tasks, and model of process supervision |
2.2 |
Basic configurations |
2.3 |
Pre-processing of numerical
data |
2.4 |
Multiple-level model of
supervision |
2.5 |
Mathematical models and
methods in process supervision |
2.6 |
Typical schemes and applications
of supervisory systems |
3.
ANALYTICAL MODEL-BASED MONITORING, SUPERVISION AND FAULT DETECTION AND
ISOLATION METHODS
4.
FOUNDATIONS OF ARTIFICIAL INTELLIGENCE FOR KNOWLEDGE REPRESENTATION AND
PROCESSING: SELECTED METHODS
4.1 |
Motivation
of the use of AI methods in process supervision |
4.2 |
Types of data |
4.3 |
Symbolic data representation |
4.4 |
Qualitative knowledge representation |
4.5 |
Knowledge representation
with logic |
4.6 |
Decision lists, decision
tables, decision trees |
4.7 |
Knowledge representation
with fuzzy logic |
4.8 |
Rule-based systems |
4.9 |
Fuzzy rule-based systems |
4.10 |
Expert systems |
4.11 |
Graphs and causal graphs |
4.12 |
Representation of knowledge
over time: episodes |
4.13 |
Case-based reasoning |
4.14 |
A note on other forms of
knowledge representation |
4.15 |
Generic problems to be solved
for developing a knowledge-based system |
4.16 |
Artificial Intelligence
in control systems |
4.17 |
Artificial Intelligence
in process monitoring and supervision |
5.
COMPUTER AIDED SUPERVISORY SYSTEM DESIGN: AN OVERVIEW
6.
FROM DATA TO KNOWLEDGE: SIGNAL TO SYMBOL TRANSFORMATION
6.1 |
Steps from
data to knowledge |
6.2 |
States and situations |
6.3 |
Formal foundations of knowledge
formation |
6.4 |
Numeric to symbolic translation |
6.5 |
Signals representation by
means of episodes |
6.6 |
A formalism for episodes-based
representations |
6.7 |
A representation based on
the formalism |
6.8 |
Data and knowledge representation
with object variables |
6.9 |
Data abstraction tools |
7.
KNOWLEDGE-BASED PROCESS MONITORING, SUPERVISION, DECISION SUPPORT AND DIAGNOSIS:
SELECTED METHODOLOGIES
7.1 |
Knowledge-based
supervision: selected issues |
7.2 |
Signal recognition and monitoring
with use of episodes |
7.3 |
Advanced techniques in signal
analysis with episodes |
7.4 |
Qualitative signal analysis:
ALCMEN |
7.5 |
Rule-based systems, decision
tables, and decision trees in state monitoring and situation classification
control and decision support |
7.6 |
Object oriented methodologies
and expert systems: CEES |
7.7 |
An integrated environment
for CASSD |
7.8 |
Model based supervision |
7.9 |
Case-based reasoning in
process supervision and diagnosis – selected issues |
7.10 |
Simple diagnostic models
for fault identification |
7.11 |
Causal logical graphs for
diagnostic reasoning |
7.12 |
Diagnostics |
7.13 |
Fuzzy logic in process supervision |
8.
CASE STUDIES AND EXAMPLE PROBLEMS
8.1 |
Application
of episodes and expert system for supervision and diagnosis of the three
tank model system |
8.2 |
Case study of episode application
to supervision of systems |
8.3 |
The furnace example |
8.4 |
Problems of knowledge based
validation |
8.5 |
Manufacturing process supervision |
8.6 |
A simple diagnostic example |
8.7 |
Other case-studies: references |
9.
TOOLS FOR MONITORING, SUPERVISION AND DIAGNOSIS
9.1 |
SCADA systems |
9.2 |
Rule-based systems and expert
system shells |
9.3 |
Episode generating environments |
9.4 |
CASSD-type environments |
9.5 |
TIGER: an example of complex
system |
9.6 |
9.6 Diagnostic systems |
10.
BENCHMARKS, OPEN PROBLEMS, RESEARCH DIRECTIONS
10.1 |
The three tanks
benchmark |
10.2 |
The Frank/Patton benchmark |
10.3 |
The mono-stable benchmark |
10.4 |
Research directions and
selected open problems |
11.
SOURCE MATERIALS AND REFERENCES. A GUIDE
11.1 |
Glossary |
11.2 |
Recommended readings |
11.3 |
Selected Internet Sites |
11.4 |
References |