Fault Detection and Diagnosis in Industrial Systems

€ 60,49
Sofort lieferbar
Dezember 2000



Early and accurate fault detection and diagnosis for modern chemical plants can minimise downtime, increase the safety of plant operations, and reduce manufacturing costs. The process monitoring techniques that have been most effective in practice are based on models constructed almost entirely from process data.The goal of the book is to present the theoretical background and practical techniques for data-driven process monitoring. Process monitoring techniques presented include: Data-driven methods - principal component analysis, Fisher discriminant analysis, partial least squares and canonical variate analysis; Analytical Methods - parameter estimation, observer-based methods and parity relations; Knowledge-based methods - causal analysis, expert systems and pattern recognition.The text demonstrates the application of all of the data-driven process monitoring techniques to the Tennessee Eastman plant simulator - demonstrating the strengths and weaknesses of each approach in detail. This aids the reader in selecting the right method for his process application. Plant simulator and homework problems in which students apply the process monitoring techniques to a non-trivial simulated process, and can compare their performance with that obtained in the case studies in the text are included. A number of additional homework problems encourage the reader to implement and obtain a deeper understanding of the techniques. The reader will obtain a background in data-driven techniques for fault detection and diagnosis, including the ability to implement the techniques and to know how to select the right technique for a particular application.


I. Introduction.
- 1. Introduction.- Process Monitoring Procedures.- Process Monitoring Measures.- Process Monitoring Methods.- Book Organization.-
II. Background.
- 2. Multivariate Statistics.- Data Pretreatment.- Univariate Statistical Monitoring.- T2 Statistic.- Thresholds for the T2 Statistic.- Data Requirements.- Homework Problems.
- 3. Pattern Classification.- Discriminant Analysis.- Feature Extraction.- Homework Problems.-
III. Data-driven Methods.
- 4. Principal Component Analysis.- Principal Component Analysis.- Reduction Order.- Fault Detection.- Fault Identification.- Fault Diagnosis.- Dynamic PCA.- Other PCA-based Methods.- Homework Problems.
- 5. Fisher Discriminant Analysis.- Fisher Discriminant Analysis.- Reduction Order.- Fault Detection and Diagnosis.- Comparison of PCA and FDA.- Dynamic FDA.- Homework Problems.
- 6. Partial Least Squares.- PLS Algorithms.- Reduction Order and PLS Prediction.- Fault Detection, Identification, and Diagnosis.- Comparison of PCA and PLS.- Other PLS Methods.- Homework Problems.
- 7. Canonical Variate Analysis.- CVA Theorem.- CVA Algorithm.- State Space Model and System Identifiability.- Lag Order Selection and Computation.- State Order Selection and Akaike's Information Criterion.- Subspace Algorithm Interpretations.- Process Monitoring Statistics.- Homework Problems.-
IV. Application.
- 8. Tennessee Eastman Process.- Process Flowsheet.- Process Variables.- Process Faults.- Simulation Program.- Control Structure.- Homework Problems.
- 9. Application Description.- Data Sets.- Sampling Interval.- Sample Size.- Lag and Order Selection.- Fault Detection.- Fault Identification.- Fault Diagnosis.
- 10. Results and Discussion.- Case Study on Fault.- Case Study on Fault 4.- Case Study on Fault 5.- Case Study on Fault 11.- Fault Detection.- Fault Identification.- Fault Diagnosis.- Homework Problems.-
V. Analytical and Knowledge-based Methods.
- 11. Analytical Methods.- Fault Descriptions.- Parameter Estimation.- Observer-based Method.- Full-order State Estimator.- Reduced-order Unknown Input Observer.- Parity Relations.- Residual Generation.- Detection Properties of the Residual.- Specification of the Residuals.- Implementation of the Residuals.- Connection Between the Observer and Parity Relations.- Isolation Properties of the Residual.- Residual Evaluation.- Homework Problems.
- 12. Knowledge-based Methods.- Causal Analysis.- Signed Directed Graph.- Symptom Tree Model.- Expert Systems.- Shallow-Knowledge Expert System.- Deep-Knowledge Expert Systems.- Combination of Shallow-Knowledge and Deep-Knowledge Expert Systems.- Machine Learning Techniques.- Knowledge Representation.- Inference Engine.- Pattern Recognition.- Artificial Neural Networks.- Self-Organizing Map.- Combinations of Various Techniques.- Neural Networks and Expert Systems.- Fuzzy Logic.- Fuzzy Expert Systems.- Fuzzy Neural Networks.- Fuzzy Signed Directed Graph.- Fuzzy Logic and the Analytical Approach.- Neural Networks and the Analytical Approach.- Data-driven, Analytical, and Knowledge-based Ap- proaches.- Homework Problems.- References.
EAN: 9781852333270
ISBN: 1852333278
Untertitel: Softcover reprint of the original 1st ed. 2001. Book. Sprache: Englisch.
Verlag: Springer
Erscheinungsdatum: Dezember 2000
Seitenanzahl: 296 Seiten
Format: kartoniert
Es gibt zu diesem Artikel noch keine Bewertungen.Kundenbewertung schreiben