Optimal Automated Process Fault Analysis

Dr. Richard J. Fickelscherer is currently a licensed Professional Engineer and is a principal owner of FALCONEER Technologies, LLC. He has developed and implemented programs which provide various supervisory control functions for DuPont, Exxon-Mobile, Merck Pharmaceuticals, Koch Industries, the FMC Corporation and many other client companies.

Dr. Daniel L. Chester joined the Department of Computer and Information Sciences at the University of Delaware in 1980, where he soon became one of the principal investigators on the FALCON project. He is currently Associate Chair in the computer science department at the University of Delaware. He has been involved in the creation and development of three companies, one of which is FALCONEER Technologies, LLC. He is also co-inventor in five U.S. patents.

Dedication

Table of Contents

Foreword

Preface

Acknowledgements

Chapter 1. Motivations for Automating Process Fault Analysis

1.1  Introduction

1.2  CPI Trends to Date

1.3  The Changing Role for the Process Operators in Plant Operations

1.4  Methods Currently Used to Perform Process Fault Management

1.5  Limitations of Human Operators in Performing Process Fault Management

1.6  The Role of Automated Process Fault Analysis

1.7  Anticipated Future CPI Trends

1.8  Process Fault Analysis Concept Terminology

Chapter 2. Method of Minimal Evidence: Model-Based Reasoning

2.1 Overview

2.2 Introduction

2.3 Method of Minimal Evidence Overview

2.4 Verifying the Validity and Accuracy of the Various Primary Models

2.5 Summary

Chapter 3. Method of Minimal Evidence: Diagnostic Strategy Details

3.1 Overview

3.2 Introduction

3.3 MOME Diagnostic Strategy

3.4 A General Procedure for Developing and Verifying Competent Model-based

3.5 MOME SV & PFA Diagnostic Logic Compiler Motivations

3.6 MOME Diagnostic Strategy Summary

Chapter 4. Method of Minimal Evidence: Fuzzy Logic Algorithm

4.1 Overview

4.2 Introduction

4.3 Fuzzy Logic Overview

4.4 MOME Fuzzy Logic Algorithm

4.5 Certainty Factor Calculation Review

4.6 MOME Fuzzy Logic Algorithm Summary

Chapter 5. Method of Minimal Evidence: Criteria for Shrewdly Distribution Fault Analyzers and Strategic Process Sensor Placement

5.1 Overview

5.2 Criteria for Shrewdly Distributing Process Fault Analyzers

5.3 Criteria for Strategic Process Sensor Placement

Chapter 6. Virtual SPC Analysis and Its Routine Use in Falconeer™ IV

6.1 Overview

6.2 Introduction

6.3 EWMA Calculations and Specific Virtual SPC Analysis Configurations

6.4 Virtual SPC Alarm Trigger Summary

6.5 Virtual SPC Analysis Conclusions

Chapter 7. Process State Transistion Logic and Its Routine Use in Falconeer™ IV

7.1 Temporal Reasoning Philosophy

7.2 Introduction

7.3 State Identification Analysis Currently Used in Falconeer™ IV

7.4 State Identification Analysis Summary

Chapter 8. Conclusions

8.1 Overview

8.2 Summary of the MOME Diagnostic Strategy

8.3 FALCON, FALCONEER and FALCONEER™ IV Actual KBS Application Performance Results

8.4 FALCONEER™ IV KBS Application Project Procedure

8.5 Optimal Automated Process Fault Analysis Conclusions

Appendix A. Various Diagnostic Strategies for Automating Process Fault Analysis

Appendix B. The Falcon Project

Appendix C. Process State Transition Logic Used by the Original Falconeer KBS

Appendix D. Falconeer™ IV Real-Time Suite Process Performance Solutions Demo Description

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.