This book presents a detailed and up-to-date exposition of fault monitoring methods in industrial processes and structures. The following approaches are explained in considerable detail: Model-based methods (simple tests, analytical redundancy, parameter estimation); knowledge-based methods; artificial neural network methods; and nondestructive testing, etc. Each approach is complemented by specific case studies from various industrial sectors (aerospace, chemical, nuclear, etc.), thus bridging theory and practice. This volume will be a valuable tool in the hands of professional and academic engineers. It can also be recommended as a supplementary postgraduate textbook. For scientists whose work involves automatic process control and supervision, statistical process control, applied statistics, quality control, computer-assisted predictive maintenance and plant monitoring, and structural reliability and safety.
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.
This book reviews current design paths for soft sensors, and guides readers in evaluating different choices. The book presents case studies resulting from collaborations between the authors and industrial partners. The solutions presented, some of which are implemented on-line in industrial plants, are designed to cope with a wide range of applications from measuring system backup and what-if analysis through real-time prediction for plant control to sensor diagnosis and validation.
The introduction of the microprocessor in computer and system engineering has motivated the development of many new concepts and has simplified the design of many modern industrial systems. During the first decade of their life. microprocessors have shown a tremendous evolution in all possible directions (technology. power. functionality. I/O handling. etc). Of course putting the microprocessors and their environmental devices into properly operating systems is a complex and difficult task requiring high skills for melding and integrating hardware. and systemic components. software This book was motivated by the editors' feeling that a cohesive reference is needed providing a good coverage of modern industrial applications of microprocessor-based real time control, together with latest advanced methodological issues. Unavoidably a single volume cannot be exhaustive. but the present book contains a sufficient number of important real-time applications. The book is divided in two sections. Section I deals with general hardware. software and systemic topics. and involves six chapters. Chapter 1. by Gupta and Toong. presents an overview of the development of microprocessors during their first twelve years of existence. Chapter 2. by Dasgupta. deals with a number of system software concepts for real time microprocessor-based systems (task scheduling. memory management. input-output aspects. programming language reqUirements.
This Proceedings contains the papers presented at the 14th International Conference on Condition Monitoring and Diagnostic Engineering Management (COMADEM 2001), held in Manchester, UK, on 4-6 September 2001. COMADEM 2001 builds on the excellent reputation of previous conferences in this series, and is essential for anyone working in the field of condition monitoring and maintenance management.The scope of the conference is truly interdisciplinary. The Proceedings contains papers from six continents, written by experts in industry and academia the world over, bringing together the latest thoughts on topics including: Condition-based maintenance Reliability centred maintenance Asset management Industrial case studies Fault detection and diagnosis Prognostics Non-destructive evaluation Integrated diagnostics Vibration Oil and debris analysis Tribology Thermal techniques Risk assessment Structural health monitoring Sensor technology Advanced signal processing Neural networks Multivariate statistics Data compression and fusion This Proceedings also contains a wealth of industrial case studies, and the latest developments in education, training and certification. For more information on COMADEM's aims and scope, please visit http://www.comadem.com
Featuring a model-based approach to fault detection and diagnosis in engineering systems, this book contains up-to-date, practical information on preventing product deterioration, performance degradation and major machinery damage.;College or university bookstores may order five or more copies at a special student price. Price is available upon request.
The book documents 25 papers collected from the Special Issue “Advances in Condition Monitoring, Optimization and Control for Complex Industrial Processes”, highlighting recent research trends in complex industrial processes. The book aims to stimulate the research field and be of benefit to readers from both academic institutes and industrial sectors.
A three-volume work bringing together papers presented at 'SAFEPROCESS 2003', including four plenary papers on statistical, physical-model-based and logical-model-based approaches to fault detection and diagnosis, as well as 178 regular papers.
This book provides a ‘one-stop source’ for all readers who are interested in a new, empirical approach to machine learning that, unlike traditional methods, successfully addresses the demands of today’s data-driven world. After an introduction to the fundamentals, the book discusses in depth anomaly detection, data partitioning and clustering, as well as classification and predictors. It describes classifiers of zero and first order, and the new, highly efficient and transparent deep rule-based classifiers, particularly highlighting their applications to image processing. Local optimality and stability conditions for the methods presented are formally derived and stated, while the software is also provided as supplemental, open-source material. The book will greatly benefit postgraduate students, researchers and practitioners dealing with advanced data processing, applied mathematicians, software developers of agent-oriented systems, and developers of embedded and real-time systems. It can also be used as a textbook for postgraduate coursework; for this purpose, a standalone set of lecture notes and corresponding lab session notes are available on the same website as the code. Dimitar Filev, Henry Ford Technical Fellow, Ford Motor Company, USA, and Member of the National Academy of Engineering, USA: “The book Empirical Approach to Machine Learning opens new horizons to automated and efficient data processing.” Paul J. Werbos, Inventor of the back-propagation method, USA: “I owe great thanks to Professor Plamen Angelov for making this important material available to the community just as I see great practical needs for it, in the new area of making real sense of high-speed data from the brain.” Chin-Teng Lin, Distinguished Professor at University of Technology Sydney, Australia: “This new book will set up a milestone for the modern intelligent systems.” Edward Tunstel, President of IEEE Systems, Man, Cybernetics Society, USA: “Empirical Approach to Machine Learning provides an insightful and visionary boost of progress in the evolution of computational learning capabilities yielding interpretable and transparent implementations.”
With increasing demands for efficiency and product quality plus progress in the integration of automatic control systems in high-cost mechatronic and safety-critical processes, the field of supervision (or monitoring), fault detection and fault diagnosis plays an important role. The book gives an introduction into advanced methods of fault detection and diagnosis (FDD). After definitions of important terms, it considers the reliability, availability, safety and systems integrity of technical processes. Then fault-detection methods for single signals without models such as limit and trend checking and with harmonic and stochastic models, such as Fourier analysis, correlation and wavelets are treated. This is followed by fault detection with process models using the relationships between signals such as parameter estimation, parity equations, observers and principal component analysis. The treated fault-diagnosis methods include classification methods from Bayes classification to neural networks with decision trees and inference methods from approximate reasoning with fuzzy logic to hybrid fuzzy-neuro systems. Several practical examples for fault detection and diagnosis of DC motor drives, a centrifugal pump, automotive suspension and tire demonstrate applications.
