Describes the latest developments in nonlinear methods and their application in fault diagnosis
Discusses in detail several advances in machine learning theory
Contains numerous case studies with real-world data from industry
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.|
Algorithms for intelligent fault diagnosis of automated operations offer significant benefits to the manufacturing and process industries. Furthermore, machine learning methods enable such monitoring systems to handle nonlinearities and large volumes of data.
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: reviews the application of machine learning to process monitoring and fault diagnosis; 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.
This highly practical and clearly-structured work is an invaluable resource for all researchers and practitioners involved in process control, multivariate statistics and machine learning.
Introduction
Overview of Process Fault Diagnosis
Artificial Neural Networks
Statistical Learning Theory and Kernel-Based Methods
Tree-Based Methods
Fault Diagnosis in Steady State Process Systems
Dynamic Process Monitoring
Process Monitoring Using Multiscale Methods
Algorithms for intelligent fault diagnosis of automated operations offer significant benefits to the manufacturing and process industries. Furthermore, machine learning methods enable such monitoring systems to handle nonlinearities and large volumes of data.
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:
- Reviews the application of machine learning to process monitoring and fault diagnosis
- 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
This highly practical and clearly-structured work is an invaluable resource for all researchers and practitioners involved in process control, multivariate statistics and machine learning.
Dr. Chris Aldrich is a Professor in the Department of Metallurgical and Minerals Engineering at Curtin University, Perth, Australia. Dr. Lidia Auret is a Lecturer in the Department of Process Engineering at Stellenbosch University, South Africa.
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)
This book describes the latest developments in nonlinear methods and their application in fault diagnosis. It details advances in machine learning theory and contains numerous case studies with real-world data from industry.
Introduction.- Overview of Process Fault Diagnosis.- Artificial Neural Networks.- Statistical Learning Theory and Kernel-Based Methods.- Tree-Based Methods.- Fault Diagnosis in Steady State Process Systems.- Dynamic Process Monitoring.- Process Monitoring Using Multiscale Methods.
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)
Inhaltsverzeichnis
Introduction
rn
Overview of Process Fault Diagnosis
rn
Artificial Neural Networks
rn
Statistical Learning Theory and Kernel-Based Methods
rn
Tree-Based Methods
rn
Fault Diagnosis in Steady State Process Systems
rn
Dynamic Process Monitoring
rn
Process Monitoring Using Multiscale Methods
rn
Klappentext
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.
Describes the latest developments in nonlinear methods and their application in fault diagnosis
rn
Discusses in detail several advances in machine learning theory
rn
Contains numerous case studies with real-world data from industry
rn
