The machine abnormal degree detection method based on SVDD and negative selection mechanism

As is well-known, fault samples are essential for the fault diagnosis and anomaly detection, but in most cases, it is difficult to obtain them. The negative selection mechanism of immune system, which can distinguish almost all nonself cells or molecules with only the self cells, gives us an inspiration to solve the problem of anomaly detection with only the normal samples. In this paper, we introduced the Support Vector Data Description (SVDD) and negative selection mechanism to separate the state space of machines into self, non-self and fault space. To estimate the abnormal level of machines, a function that could calculate the abnormal degree was constructed and its sensitivity change according to the change of abnormal degree was also discussed. At last, Iris-Fisher and ball bearing fault data set were used to verify the effectiveness of this method.

[1]  Joseph Mathew,et al.  Bearing fault prognosis based on health state probability estimation , 2012, Expert Syst. Appl..

[2]  J. Kamruzzaman,et al.  An Adaptive Self-Configuration Scheme for Severity Invariant Machine Fault Diagnosis , 2013, IEEE Transactions on Reliability.

[3]  Fabio A. González,et al.  An Evolutionary Approach to Generate Fuzzy Anomaly Signatures , 2003, IAW.

[4]  Keheng Zhu,et al.  Incipient fault diagnosis of roller bearings using empirical mode decomposition and correlation coefficient , 2013 .

[5]  Lei Guo,et al.  Robust bearing performance degradation assessment method based on improved wavelet packet–support vector data description , 2009 .

[6]  H. Selcuk NOGAY,et al.  A proposal for visually handicapped students to use electrical control laboratory , 2011 .

[7]  Dawei Wang,et al.  Anomaly Detection Using Neighborhood Negative Selection , 2011, Intell. Autom. Soft Comput..

[8]  Masoud Mohammadi,et al.  Discrete wavelet transform and artificial neural network for gearbox fault detection based on acoustic signals , 2013 .

[9]  Pascal Bouvry,et al.  Immune anomaly detection enhanced with evolutionary paradigms , 2006, GECCO.

[10]  Zhan Yong-zhao,et al.  Support vector data description discriminant analysis , 2011 .

[11]  Feng Zhao.  An Optimizing Kernel Algorithm for Improving the Performance of Support Vector Domain Description: An Optimizing Kernel Algorithm for Improving the Performance of Support Vector Domain Description , 2009 .

[12]  Zhou Ji,et al.  Real-Valued Negative Selection Algorithm with Variable-Sized Detectors , 2004, GECCO.

[13]  Yuhong Zhao,et al.  A new fault detection method based on artificial immune systems , 2008 .

[14]  Zhou Ji,et al.  V-detector: An efficient negative selection algorithm with "probably adequate" detector coverage , 2009, Inf. Sci..

[15]  Heng-You Wang,et al.  Generalized Mercer theorem and its application to feature space related to indefinite kernels , 2008, 2008 International Conference on Machine Learning and Cybernetics.

[16]  Jonathan Timmis,et al.  Artificial Immune Recognition System (AIRS): An Immune-Inspired Supervised Learning Algorithm , 2004, Genetic Programming and Evolvable Machines.

[17]  V. Sugumaran,et al.  Fault diagnosis of antifriction bearings through sound signals using support vector machine , 2012 .

[18]  Gilbert L. Peterson,et al.  An evolutionary algorithm to generate hyper-ellipsoid detectors for negative selection , 2005, GECCO '05.

[19]  Alan S. Perelson,et al.  Self-nonself discrimination in a computer , 1994, Proceedings of 1994 IEEE Computer Society Symposium on Research in Security and Privacy.

[20]  Wenjian Luo,et al.  A Heuristic Detector Generation Algorithm for Negative Selection Algorithm with Hamming Distance Partial Matching Rule , 2006, ICARIS.

[21]  Xin Wang,et al.  A Novel Negative Selection Algorithm with an Array of Partial Matching Lengths for Each Detector , 2006, PPSN.

[22]  Pascal Bouvry,et al.  Coevolutionary-based Mechanisms for Network Anomaly Detection , 2007, J. Math. Model. Algorithms.

[23]  Yanxue Wang,et al.  Application of extended time-frequency domain average in ultrasonic detecting , 2011 .

[24]  Shulin Liu,et al.  FAULT DETECTION APPROACH BASED ON IMMUNE MECHANISM FOR GAS VALVES OF RECIPROCATING COMPRESSORS , 2004 .

[25]  Wu Zhaohui,et al.  Support vector domain description for speaker recognition , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

[26]  Fernando Niño,et al.  Recent Advances in Artificial Immune Systems: Models and Applications , 2011, Appl. Soft Comput..

[27]  David J. Brown,et al.  Combining multiple classifiers to quantitatively rank the impact of abnormalities in flight data , 2012, Appl. Soft Comput..

[28]  Wanli Ma,et al.  Negative Selection with Antigen Feedback in Intrusion Detection , 2008, ICARIS.

[29]  Mo-Yuen Chow,et al.  Multi-Level Optimization Of Negative Selection Algorithm Detectors With Application In Motor Fault Detection , 2010, Intell. Autom. Soft Comput..

[30]  Guilherme Costa Silva,et al.  Immune inspired Fault Detection and Diagnosis: A fuzzy-based approach of the negative selection algorithm and participatory clustering , 2012, Expert Syst. Appl..

[31]  Ashkan Moosavian,et al.  814. Fault diagnosis of main engine journal bearing based on vibration analysis using Fisher linear discriminant, K-nearest neighbor and support vector machine , 2012 .

[32]  Claudia Eckert,et al.  Is negative selection appropriate for anomaly detection? , 2005, GECCO '05.

[33]  Masoud Masoumi,et al.  Using continuous wavelet transform of generalized flexibility matrix in damage identification , 2013 .

[34]  R. Srinivasan,et al.  Immune-System-Inspired Approach to Process Monitoring and Fault Diagnosis , 2011 .

[35]  Guanghua Xu,et al.  Automatic detection of epileptic slow-waves in EEG based on empirical mode decomposition and wavelet transform , 2013 .