Study of Camshaft Grinders Faults Prediction Based on RBF Neural Network


Article Preview

Maintenance schemes in manufacturing systems are devised to reset the machines functionality in an economical fashion and keep it within acceptable levels. Camshaft grinders play the important role for the camshaft production line which is the massive production type. The camshaft grinders working condition is one of the critical sections which affected the production efficiency and profit of the manufactures. Nowadays the maintenance based on condition is carried out in order to meet the requirements of the market. The Time Between Failures (TBF) could be used for arranging the maintenance schedule. The faults prediction model based on RBF neural network, adopted K-means clustering algorithm to select clustering centre of radial basis function neural network (RBFNN), is proposed for the camshaft grinders which are the key equipment of camshaft production line. The TBF of the camshaft grinders are predicted by using this model, where the distribution density is 1, with the accepted network approximation error. An industrial example is used to illustrate the application of this model. The proposed method is effective and can be used for the suggestions for the practical workshop machines maintenance.



Edited by:

Hun Guo, Taiyong Wang, Zeyu Weng, Weidong Jin, Shaoze Yan, Xuda Qin, Guofeng Wang, Qingjian Liu and Zijing Wang




T. Dong et al., "Study of Camshaft Grinders Faults Prediction Based on RBF Neural Network", Applied Mechanics and Materials, Vol. 141, pp. 519-523, 2012

Online since:

November 2011




[1] Ai Hong, Zhou Donghua: Journal of Huazhong University of Science and Technology Vol. 37 (2009) No. 1.

[2] ZHAO Wangda, LIU Yongqiuo and HE Yi: Journal of Translocation Technology Vol. 23 (2004) No. 4.

[3] Zhang Xiuling, Li Haibin, A Digital Recognition Method based on RBF Neural Network, Chinese Journal of Scientific Instrument. 2002, (6).

[4] Fei Sike Technology R & D center, Neural Network Theory and Implementation by MATLAB7. Publishing House of Electronics Industry, Beijing, (2005).

[5] Yan Pingfan, Zhang Changshui, Artificial neural networks and simulated evolutionary computation. Tsinghua University Press, Beijing, (2005).