Research on intelligent fault diagnosis of mechanical equipment based on sparse deep neural networks

Journal of Vibroengineering - Tập 19 Số 4 - Trang 2439-2455 - 2017
Feiwei Qin, Bai Jing1, Wenqiang Yuan2
1School of Computer Science and Engineering, Beifang University of Nationalities, Yinchuan, China
2School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China

Tóm tắt

In the big data background, the accuracy of fault diagnosis and recognition has been difficult to be improved. The deep neural network was used to recognize the diagnosis rate of the bearing with four kinds of conditions and compared with traditional BP neural network, genetic neural network and particle swarm neural network. Results showed that the diagnosis accuracy and convergence rate of the deep neural network were obviously higher than those of other models. Fault diagnosis rates with different sample sizes and training sample proportions were then studied to compare with the latest reported methods. Results showed that fault diagnosis had a good stability using deep neural networks. Vibration accelerations of the bearing with different fault diameters and excitation loads were extracted. The deep neural network was used to recognize these faults. Diagnosis accuracy was very high. In particular, the fault diagnosis rate was 98 % when signal features of vibration accelerations were very obvious, which indicated that using deep neural network was effective in diagnosing and recognizing different types of faults. Finally, the deep neural network was used to conduct fault diagnosis for the gearbox of wind turbines and compared with the other models to present that it would work well in the industrial environment.

Từ khóa


Tài liệu tham khảo

<b>Randall R. B., Antoni J. </b>Rolling element bearing diagnostics – a tutorial. Mechanical Systems and Signal Processing, Vol. 25, Issue 2, 2011, p. 485-520.

<b>Harris T. A., Kotzalas M. N. </b>Rolling Bearing Analysis Essential Concepts of Bearing Technology. CRC Press Inc., New York, 2007.

<b>Chen K. J. </b>Study on Ball Bearing Fault Diagnosis Based on Vibration Signals. Xidian University, Xi’an, 2011.

<b>Mahanty R. N., Gupta P. B. D. </b>Application of RBF neural network to fault classification and location in transmission lines. IEE Proceedings of Generation, Transmission and Distribution, Vol. 151, Issue 2, 2004, p. 201-212.

<b>Kankar P. K., Sharma S. C., Harsha S. P. </b>Vibration-based fault diagnosis of a rotor bearing system using artificial neural network and support vector machine. International Journal of Modelling, Identification and Control, Vol. 15, Issue 3, 2012, p. 185-198.

<b>Ahmed R., El Sayed M., Gadsden S. A., et al. </b>Automotive internal-combustion-engine fault detection and classification using artificial neural network techniques. IEEE Transactions on Vehicular Technology, Vol. 64, Issue 1, 2015, p. 21-33.

<b>Baklacioglu T., Turan O., Aydin H. </b>Dynamic modeling of exergy efficiency of turboprop engine components using hybrid genetic algorithm-artificial neural networks. Energy, Vol. 86, 2015, p. 709-721.

<b>Wei X. T., Pan H. X., Ma Q. F. </b>Application of particle swarm optimization based on neural network to fault diagnosis. Journal of Vibration, Measurement and Diagnosis, Vol. 26, Issue 2, 2006, p. 133-137.

<b>Yang X. S. </b>Firefly algorithm for multimodal optimization. Lecture Notes in Computer Science, Vol. 5972, 2009, p. 169-178.

<b>Samanta B., Al Balushi K.-R. </b>Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mechanical systems and signal processing, Vol. 17, Issue 2, 2003, p. 317-328.

<b>Martins J. F., Pires V. F., Pires A. J. </b>Unsupervised neural-network-based algorithm for an on-line diagnosis of three-phase induction motor stator fault. IEEE Transactions on Industrial Electronics, Vol. 54, Issue 1, 2007, p. 259-264.

<b>Cheriyadat A. M. </b>Unsupervised feature learning for aerial scene classification. IEEE Transactions on Geoscience and Remote Sensing, Vol. 52, Issue 1, 2014, p. 439-451.

<b>Erhan D., Bengio Y., Courville A., et al. </b>Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research, Vol. 11, 2010, p. 625-660.

<b>Lee H., Pham P., Largman Y., et al. </b>Unsupervised feature learning for audio classification using convolutional deep belief networks. Advances in Neural Information Processing Systems, 2009, p. 1096-1104.

<b>Hinton G. E., Salakhutdinov R. R. </b>Reducing the dimensionality of data with neural networks. Science, Vol. 313, Issue 5786, 2006, p. 504-507.

<b>Ciregan D., Meier U., Schmidhuber J.</b> Multi-column deep neural networks for image classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012, p. 3642-3649.

<b>Simonyan K., Zisserman A. </b>Very deep convolutional networks for large-scale image recognition. Computer Vision and Pattern Recognition, 2015.

<b>Tang J., Deng C., Huang G. B., et al. </b>Compressed-domain ship detection on spaceborne optical image using deep neural network and extreme learning machine. IEEE Transactions on Geoscience and Remote Sensing, Vol. 53, Issue 3, 2015, p. 1174-1185.

<b>Hinton G., Deng L., Yu D., et al. </b>Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, Vol. 29, Issue 6, 2012, p. 82-97.

<b>Dahl G. E., Yu D., Deng L., et al. </b>Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, Vol. 20, Issue 1, 2012, p. 30-42.

<b>Xu Y., Du J., Dai L. R. </b>An experimental study on speech enhancement based on deep neural networks. IEEE Signal Processing Letters, Vol. 21, Issue 1, 2014, p. 65-68.

<b>Coates A., Ng A. Y. </b>The importance of encoding versus training with sparse coding and vector quantization. Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2011, p. 921-928.

<b>Lyons J., Dehzangi A., Heffernan R., et al. </b>Predicting backbone Cα angles and dihedrals from protein sequences by stacked sparse auto-encoder deep neural network. Journal of Computational Chemistry, Vol. 35, Issue 28, 2014, p. 2040-2046.

<b>Su S. Z., Liu Z. H., Xu S. P., et al. </b>Sparse auto-encoder based feature learning for human body detection in depth image. Signal Processing, Vol. 112, 2015, p. 43-52.

<b>Bengio Y., Lambin P., Popovici D. </b>Greedy layer wise training of deep networks. Advances in Neural Information Processing Systems 19, Vancouver, Canada, 2007, p. 153-160.

Case Western reserve university Bearing Data Center. Bearing Data Center Fault Test Data, http://www.eecs.case.edu/laboratory/bearing.

<b>Lei Y. G., Jia F., Xing S. B., Ding S. X. </b>An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data. IEEE Transactions on Industrial Electronics, Vol. 63, Issue 5, 2016, p. 3137-3147.

<b>Lin Y. H. </b>Study on Wind Turbine Fault Diagnosis Decision System Based on Wavelet Analysis and Neural Network Method. Xi’an University of Technology, Xi’an, 2014.

Thông tin
Thông tin xuất bản

Journal of Vibroengineering

Tập 19 Số 4

2439-2455

Thông tin tác giả