Fault Detection and Diagnosis in Industrial Systems

Early and accurate fault detection and diagnosis for modern chemical plants can minimize downtime, increase the safety of plant operations, and reduce manufacturing costs. This book presents the theoretical background and practical techniques for data-driven process monitoring. It demonstrates the application of all the data-driven process monitoring techniques to the Tennessee Eastman plant simulator, and looks at the strengths and weaknesses of each approach in detail. A plant simulator and problems allow readers to apply process monitoring techniques.

Early and accurate fault detection and diagnosis for modern manufacturing processes can minimise downtime, increase the safety of plant operations, and reduce costs. Such process monitoring techniques are regularly applied to real industrial systems. Fault Detection and Diagnosis in Industrial Systems presents the theoretical background and practical methods for process monitoring. The coverage of data-driven, analytical and knowledge-based techniques include:

• principal component analysis

• Fisher discriminant analysis

• partial least squares

• canonical variate analysis;

• parameter estimation;

• observer/state estimators

• parity relations;

• artificial neural networks;

• expert systems.

Application of the process monitoring techniques to a number of processes, including to a manufacturing plant, demonstrates the strenghts and weaknesses of each approach in detail. This aids the reader in selecting the right method for a particular application. A plant simulator and homework problems are included in which students apply the process monitoring techniques to a nontrivial simulated process, and can compare their performance with that obtained in the case studies in the text. A number of additional homework problems encourage the reader to implement and obtain a deeper understanding of the techniques.