An evolving approach to unsupervised and Real-Time fault detection in industrial processes

A new approach to fault detection in industrial processes is presented.This approach uses TEDA algorithm and has autonomous learning.A practical application of TEDA algorithm to fault detection problems is presented.TEDA is applied to two different real world industrial fault detection problems. Fault detection in industrial processes is a field of application that has gaining considerable attention in the past few years, resulting in a large variety of techniques and methodologies designed to solve that problem. However, many of the approaches presented in literature require relevant amounts of prior knowledge about the process, such as mathematical models, data distribution and pre-defined parameters. In this paper, we propose the application of TEDA - Typicality and Eccentricity Data Analytics - , a fully autonomous algorithm, to the problem of fault detection in industrial processes. In order to perform fault detection, TEDA analyzes the density of each read data sample, which is calculated based on the distance between that sample and all the others read so far. TEDA is an online algorithm that learns autonomously and does not require any previous knowledge about the process nor any user-defined parameters. Moreover, it requires minimum computational effort, enabling its use for real-time applications. The efficiency of the proposed approach is demonstrated with two different real world industrial plant data streams that provide "normal" and "faulty" data. The results shown in this paper are very encouraging when compared with traditional fault detection approaches.

[1]  T. Liukkonen,et al.  A case study of SPC in circuit board assembly: statistical mounting process control , 2004, 2004 24th International Conference on Microelectronics (IEEE Cat. No.04TH8716).

[2]  J. G. Saw,et al.  Chebyshev Inequality With Estimated Mean and Variance , 1984 .

[3]  Jingjing Liu,et al.  Estimation of an incipient fault using an adaptive neurofuzzy sliding-mode observer , 2014 .

[4]  Junhong Li,et al.  Improved kernel principal component analysis for fault detection , 2008, Expert Syst. Appl..

[5]  Shuchita Upadhyaya,et al.  Outlier Detection: Applications And Techniques , 2012 .

[6]  Edwin Lughofer,et al.  Fault detection in multi-sensor networks based on multivariate time-series models and orthogonal transformations , 2014, Inf. Fusion.

[7]  Guanghong Yang,et al.  Dynamic observer-based robust control and fault detection for linear systems , 2012 .

[8]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[9]  Chen Lu,et al.  Neural network-based fault detection method for aileron actuator , 2015 .

[10]  VARUN CHANDOLA,et al.  Outlier Detection : A Survey , 2007 .

[11]  Plamen Angelov,et al.  Autonomous Learning Systems: From Data Streams to Knowledge in Real-time , 2013 .

[12]  Józef Korbicz,et al.  Application of the MLP Neural Network to the Robust Fault Detection , 2007 .

[13]  Yuan Yao,et al.  Robust Multivariate Statistical Process Monitoring via Stable Principal Component Pursuit , 2016 .

[14]  Plamen P. Angelov,et al.  Fully unsupervised fault detection and identification based on recursive density estimation and self-evolving cloud-based classifier , 2015, Neurocomputing.

[15]  J. Poshtan,et al.  Observer-based fault detection and isolation of three-tank benchmark system , 2011, The 2nd International Conference on Control, Instrumentation and Automation.

[16]  Li Xu,et al.  Robust Model-Based Fault Detection for a Roll Stability Control System , 2007, IEEE Transactions on Control Systems Technology.

[17]  Edwin Lughofer,et al.  Residual-based fault detection using soft computing techniques for condition monitoring at rolling mills , 2014, Inf. Sci..

[18]  Lei Chen,et al.  An Analytical Redundancy-Based Fault Detection and Isolation Algorithm for a Road-Wheel Control Subsystem in a Steer-By-Wire System , 2007, IEEE Transactions on Vehicular Technology.

[19]  Plamen Angelov,et al.  Anomaly detection based on eccentricity analysis , 2014, 2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS).

[20]  F. Gomide,et al.  Real-time fault diagnosis of nonlinear systems , 2009 .

[21]  João Miguel da Costa Sousa,et al.  An architecture for fault detection and isolation based on fuzzy methods , 2009, Expert Syst. Appl..

[22]  Walmir M. Caminhas,et al.  Design of an artificial immune system based on Danger Model for fault detection , 2010, Expert Syst. Appl..

[23]  Takehisa Yairi,et al.  An approach to spacecraft anomaly detection problem using kernel feature space , 2005, KDD '05.

[24]  Joseba Quevedo,et al.  Introduction to the DAMADICS actuator FDI benchmark study , 2006 .

[25]  Igor Skrjanc,et al.  A new fault-detection system for nonlinear systems based on an interval fuzzy model , 2007, 2007 European Control Conference (ECC).

[26]  Plamen P. Angelov,et al.  A comparative study of autonomous learning outlier detection methods applied to fault detection , 2015, 2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[27]  Alvin M. Strauss,et al.  Statistical process control application to weld process , 1997 .

[28]  Michael J. Pont,et al.  Improving the performance of radial basis function classifiers in condition monitoring and fault diagnosis applications where 'unknown' faults may occur , 2002, Pattern Recognit. Lett..

[29]  Yi Hu,et al.  Fault Detection and Identification Based on the Neighborhood Standardized Local Outlier Factor Method , 2013, Industrial & Engineering Chemistry Research.

[30]  Sirkka-Liisa Jämsä-Jounela,et al.  Fault detection and diagnosis approach based on nonlinear parity equations and its application to leakages and blockages in the drying section of a board machine , 2013 .

[31]  Karl-Erwin Großpietsch,et al.  Fault tolerance , 1994, IEEE Micro.

[32]  Lionel Tarassenko,et al.  The use of novelty detection techniques for monitoring high-integrity plant , 2002, Proceedings of the International Conference on Control Applications.

[33]  Nilanjan Sarkar,et al.  Robust Fault Detection and Isolation in Mobile Robot , 2007 .

[34]  Walmir M. Caminhas,et al.  Design of an Artificial Immune System for fault detection: A Negative Selection Approach , 2010, Expert Syst. Appl..

[35]  Wen Chen,et al.  Observer-based strategies for actuator fault detection, isolation and estimation for certain class of uncertain nonlinear systems , 2007 .

[36]  Ramezani Saeed,et al.  A FUZZY RULE BASED SYSTEM FOR FAULT DIAGNOSIS, USING OIL ANALYSIS RESULTS , 2011 .

[37]  Victoria J. Hodge,et al.  A Survey of Outlier Detection Methodologies , 2004, Artificial Intelligence Review.

[38]  Huajing Fang,et al.  Fault Detection for Nonlinear Systems with Unknown Input , 2013 .

[39]  Yue Zhao,et al.  Wind turbine fault detection and isolation using support vector machine and a residual-based method , 2013, 2013 American Control Conference.

[40]  Rolf Isermann,et al.  Supervision, fault-detection and fault-diagnosis methods — An introduction , 1997 .

[41]  Andrea Bernieri,et al.  On-line fault detection and diagnosis obtained by implementing neural algorithms on a digital signal processor , 1996 .

[42]  Rolf Isermann,et al.  Fault-diagnosis systems : an introduction from fault detection to fault tolerance , 2006 .

[43]  Srinivas Katipamula,et al.  Review Article: Methods for Fault Detection, Diagnostics, and Prognostics for Building Systems—A Review, Part I , 2005 .

[44]  V. Venkatasubramanian,et al.  Systemic risks management in complex process plants: Challenges, opportunities, and emerging trends , 2010, 2010 Conference on Control and Fault-Tolerant Systems (SysTol).

[45]  Plamen Angelov,et al.  Evolving clustering, classification and regression with TEDA , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[46]  Plamen Angelov,et al.  Real-Time Fault Detection Using Recursive Density Estimation , 2014, Journal of Control, Automation and Electrical Systems.

[47]  Frank L. Lewis,et al.  Dominant Feature Identification for Industrial Fault Detection and Isolation Applications , 2011, Expert Syst. Appl..

[48]  Plamen P. Angelov,et al.  Online fault detection based on Typicality and Eccentricity Data Analytics , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[49]  Steven X. Ding,et al.  Model-based Fault Diagnosis Techniques: Design Schemes, Algorithms, and Tools , 2008 .

[50]  Yuanqing Xia,et al.  Fault Detection for T–S Fuzzy Discrete Systems in Finite-Frequency Domain , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[51]  Radu-Emil Precup,et al.  An overview on fault diagnosis and nature-inspired optimal control of industrial process applications , 2015, Comput. Ind..

[52]  Kai Dong,et al.  Detection and repair faults of sensors in sampled control system , 2015, 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).