Chapter 4 Fuzzy Cognitive Maps for Identifying Fault Activation Patterns in Automation Systems

1. Introduction

2. Situational awareness — State of the art

3. Graph-theoretic based approach

3.1. Basic idea

3.2. Challenges with FCM

4. Proposed methodology

4.1. Overview

4.2. Assumptions

4.3. Algorithm

4.3.1. Step 0 — Initializing the FCM

4.3.2. Step 1 — Local weight initialization

4.3.3. Step 2 —Weight update based on graph structure

4.3.4. Step 3 — Weight update based on relation to critical vertices

4.4. Discussion

5. Case study

5.1. Case study 1: Impact of failures on major functions

5.2. Case study 2: Range of impact of a failure

6. Practical considerations

6.1. Scalability

6.2. Reliability and accuracy of the results

7. FCM adaptation

7.1. Structural changes to the FCM

7.2. Training the FCM

7.2.1. Supervised learning

7.2.2. Unsupervised learning

8. Concluding remarks

Author details

References