Fault Classification with Data-Driven Methods

This chapter addressees the fault classification task with data-driven methods. Once a fault has been detected and the operating mode is identified, pattern recognition methods can be used to determine the cause of the fault. This is possible as long as there exists a data set representative of the fault to be classified. Four different classifiers are considered: neural networks (NN), support vector machines (SVD), maximum a posterior probability (MAP) and decision trees (DT). The procedure to solve the fault classification task is analyzed by using the three benchmarks used along this book.

[1]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[2]  Yoshua Bengio,et al.  Algorithms for Hyper-Parameter Optimization , 2011, NIPS.

[3]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[4]  Adrián Rodríguez Ramos,et al.  An approach to fault diagnosis with online detection of novel faults using fuzzy clustering tools , 2018, Expert Syst. Appl..

[5]  Nitesh V. Chawla,et al.  Data Mining for Imbalanced Datasets: An Overview , 2005, The Data Mining and Knowledge Discovery Handbook.

[6]  A. Offermans,et al.  Socially Robust River Management: Role of Perspective Dependent Acceptability Thresholds , 2016 .

[7]  Zheng Yi Wu,et al.  Leakage Zone Identification in Large-Scale Water Distribution Systems Using Multiclass Support Vector Machines , 2016 .

[8]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[9]  Ang Li,et al.  A Generalized Framework for Population Based Training , 2019, KDD.

[10]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[11]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[12]  Yurong Liu,et al.  A survey of deep neural network architectures and their applications , 2017, Neurocomputing.

[13]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[14]  Krzysztof Patan,et al.  Artificial Neural Networks for the Modelling and Fault Diagnosis of Technical Processes , 2008 .

[15]  Orestes Llanes-Santiago,et al.  Optimizing kernel methods to reduce dimensionality in fault diagnosis of industrial systems , 2015, Comput. Ind. Eng..

[16]  B. A. Shenoi,et al.  Introduction to Digital Signal Processing and Filter Design , 2005 .

[17]  Robert P. W. Duin,et al.  State Estimation in Practice , 2005 .

[18]  Vicenç Puig,et al.  Leak localization in water distribution networks using Bayesian classifiers , 2017 .

[19]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[20]  Geoff Dougherty,et al.  Pattern Recognition and Classification , 2013, Springer New York.

[21]  Orestes Llanes-Santiago,et al.  A New Approach for Fault Diagnosis of Industrial Processes During Transitions , 2018, IWAIPR.

[22]  Elliot Meyerson,et al.  Evolving Deep Neural Networks , 2017, Artificial Intelligence in the Age of Neural Networks and Brain Computing.

[23]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.