Abstract
Fault diagnosis is crucial to improve reliability and performance of machinery. Effective feature extraction and clustering analysis can mine useful information from large amounts of raw data and facilitate fault diagnosis. This paper presents a novel intelligent fault diagnosis method based on ant colony clustering analysis. Vibration signals acquired from equipment are decomposed by wavelet packet transform, after which sub-bands of signals are clustered by ant colony algorithm, and each cluster as a set of data is analyzed from pattern of frequency band perspective for selecting intrinsic features reflecting operation condition of equipment, and thus fault diagnosis model is established to combine the extracted major features with given fault prototypes from historical data. The classification process for fault diagnosis is carried out using Euclidean nearness degree based on the established model. Furthermore, an improved ant colony clustering algorithm is proposed to adjust comparison probability dynamically and detect outliers. When compared with other clustering algorithms, the algorithm has higher convergence speed to meet requirements of real-time analysis as well as further improvement of accuracy. Finally, effectiveness and feasibility of the proposed method is verified by vibration signals acquired from a rotor test bed.
Similar content being viewed by others
References
Liu B (2003) Adaptive harmonic wavelet transform with applications in vibration analysis. J Sound Vib 262(1):45–64
Belotti V, Crenna F, Michelini RC, Rossi GB (2006) Wheel-flat diagnostic tool via wavelet transform. Mech Syst Signal Process 20(8):1953–1966
Nikolaou NG, Antoniadis IA (2002) Rolling element bearing fault diagnosis using wavelet packets. Independent Nondestructive Test Eval 35(3):197–205
Wu JD, Liu CH (2008) An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network. Expert Syst Appl 36(3):4278–4286
Sophian A, Tian GY, Taylor D, Rudlin J (2003) A feature extraction technique based on principal component analysis for pulsed Eddy current NDT. Independent Nondestructive Test Eval 36(1):37–41
Yuan Y, Ma XJ (2007) Feature extraction from vibration signals of diesel based on PCA. Chinese Mech Eng 18(8):971–975
Cord A, Ambroise C, Cocquerez JP (2006) Feature selection in robust clustering based on Laplace mixture. Pattern Recognit Lett 27(6):627–635
Park HS, Jun CH (2009) A simple and fast algorithm for K-medoids clustering. Expert Syst Appl 6(2):3336–3341
Ahmad A, Dey L (2007) A k-mean clustering algorithm for mixed numeric and categorical data. Data Knowl Eng 63(2):503–527
De Carvalho FAT (2007) Fuzzy c-means clustering methods for symbolic interval data. Pattern Recognit Lett 28(4):423–437
Wu S, Chow TWS (2004) Clustering of the self-organizing map using a clustering validity index based on inter-cluster and intra-cluster density. Pattern Recognit 37(2):175–188
Deneubourg JL, Goss S, Franks N, Sendova-Franks A, Detrain C, Chretien L (1991) The dynamics of collective sorting: Robot-like ants and ant-like robots. In: Proceedings of the first international conference on simulation of adaptive behavior: from animal to animats. MIT Press, Cambridge, pp 356–363
Lumer ED, Faieta B (1994) Diversity and adaptation in populations of clustering ants. In: Proceedings of the third international conference on simulation of adaptive behavior: from animals to animats. MIT Press, Cambridge, pp 501–508
Yang Y, Kamel M (2003) Clustering ensemble using swarm intelligence. In: Proceedings of the IEEE swarm intelligence symposium (SIS), Indiana, pp 65–71
Boryczka U (2009) Finding groups in data: cluster analysis with ants. Appl Soft Comput 9(1):61–70
Qin Y, Qin SR, Mao YF (2008) Research on iterated Hilbert transform and its application in mechanical fault diagnosis. Mech Syst Signal Process 22(8):1967–1980
Jack LB, Nandi AK (2002) Fault detection using support vector machines and artificial neural network, augmented by genetic algorithms. Mech System Signal Process 16(2–3):373–390
Samanta B (2004) Gear fault detection using artificial neural networks and support vector machines with genetic algorithms. Mech Syst Signal Process 18(3):625–644
Samanta B, Al-Balushi KR (2003) Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mech Syst Signal Process 17(2):317–328
Chen D, Wang WJ (2002) Classification of wavelet map patterns using multi-layer neural networks for gear fault detection. Mech Syst Signal Process 16(4):695–704
Widodo A, Yang BS, Han T (2007) Combination of independent component analysis and support vector machines for intelligent faults diagnosis of induction motors. Expert Syst Appl 32:299–312
Abbasion S, Rafsanjani A, Farshidianfar A, Irani N (2007) Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine. Mech Syst Signal Process 21(7):2933–2945
Chen L, Xu XH, Chen YX, He P (2004) A novel ant clustering algorithm based on cellular automata. In: Proceedings of the IEEE/WIC/ACM international conference on intelligent agent technology (IAT). Washington, DC, pp 148–154
Qu JH, Liu XY (2007) A quick ant clustering algorithm. In: Proceedings of the Fourth International Conference on—vol 01, IEEE Computer Society, Washington, DC, pp 722–725
Xu XH, Chen L, Chen YX (2004) A4C: an adaptive artificial ants clustering algorithm. In: Proceedings of the IEEE symposium on computational intelligence in bioinformatics and computational biology (CIBCB), California, pp 268–275
Barnett V, Lewis T (1994) Outliers in statistical data, 3rd edn. Wiley, New York
UCI Repository for Machine Learning Databases retrieved from the World Wide Web: http://www.ics.uci.edu/~mlearn/MLRepository.html
Larsen B, Aone C (1999) Fast and effective text mining using linear-time document clustering. In: Proceedings of the fifth ACM SIGKDD international conference on knowledge discovery and data mining, San Diego, CA, pp 16–22
Zhang P, Bui TD, Suen CY (2004) Feature dimensionality reduction for the verification of handwritten numerals. Pattern Anal Appl 7(3):296–307
Zeng H, Cheung YM (2009) A new feature selection method for Gaussian mixture clustering. Pattern Recognit 42:243–250
Hu Q, He ZJ, Zhang ZS, Zi YY (2007) Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble. Mech Syst Signal Process 21(2):688–705
Uyar M, Yildirim S, Gencoglu MT (2008) An effective wavelet-based feature extraction method for classification of power quality disturbance signals. Electr Power Syst Res 78(10):1747–1755
Acknowledgments
This research is supported by the National Natural Science Foundation of China (Grant No. 70701012 and No. 70971030).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhao, D., Yan, J. Ant colony clustering analysis based intelligent fault diagnosis method and its application to rotating machinery. Pattern Anal Applic 16, 19–29 (2013). https://doi.org/10.1007/s10044-012-0289-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-012-0289-3