Unsupervised Process Monitoring and Fault Diagnosis with Machine Learning Methods

1. Front Matter

   Pages i-xix

   PDF

2. Introduction

   • Chris Aldrich, Lidia Auret

   Pages 1-15

3. Overview of Process Fault Diagnosis

   • Chris Aldrich, Lidia Auret

   Pages 17-70

4. Artificial Neural Networks

   • Chris Aldrich, Lidia Auret

   Pages 71-115

5. Statistical Learning Theory and Kernel-Based Methods

   • Chris Aldrich, Lidia Auret

   Pages 117-181

6. Tree-Based Methods

   • Chris Aldrich, Lidia Auret

   Pages 183-220

7. Fault Diagnosis in Steady-State Process Systems

   • Chris Aldrich, Lidia Auret

   Pages 221-279

8. Dynamic Process Monitoring

   • Chris Aldrich, Lidia Auret

   Pages 281-339

9. Process Monitoring Using Multiscale Methods

   • Chris Aldrich, Lidia Auret

   Pages 341-369

10. Back Matter

    Pages 371-374

    PDF

This unique text/reference describes in detail the latest advances in unsupervised process monitoring and fault diagnosis with machine learning methods. Abundant case studies throughout the text demonstrate the efficacy of each method in real-world settings. The broad coverage examines such cutting-edge topics as the use of information theory to enhance unsupervised learning in tree-based methods, the extension of kernel methods to multiple kernel learning for feature extraction from data, and the incremental training of multilayer perceptrons to construct deep architectures for enhanced data projections. Topics and features: discusses machine learning frameworks based on artificial neural networks, statistical learning theory and kernel-based methods, and tree-based methods; examines the application of machine learning to steady state and dynamic operations, with a focus on unsupervised learning; describes the use of spectral methods in process fault diagnosis.

• Classification Trees
• Fault Detection
• Fault Identification
• Kernel-based Methods
• Neural Networks
• Regression Trees

From the reviews:

“The text elaborates a range of classifiers used for supervised and unsupervised machine learning methods, for different types of processes. … The rich examples of various industrial processes and the illustration of subsequent simulation results qualify the work as a reference textbook for graduate studies in machine learning.” (C. K. Raju, Computing Reviews, October, 2013)

• Western Australian School of Mines, Curtin University, Perth, Australia

  Chris Aldrich

• Department of Process Engineering, University of Stellenbosch, Stellenbosch, South Africa

  Lidia Auret

Policies and ethics