论文信息 - Study on machining prediction in plane grinding based on artificial neural network

Study on machining prediction in plane grinding based on artificial neural network

A new approach based on an artificial neural network (ANN) is presented for the forecasting of machining precision of plane grinding. The ANN model is based on GCAOBP (Globally Convergent Adaptive Quick Back Propagation) algorithm. A genetic algorithm (GA) was then applied to the trained ANN model to predict the machining precision. The integrated GCAOBP-GA algorithm was successful in predicting the value of PV (Peak to Valley) of machined workpiece using the machining environment parameters. The results of verification experiments have shown that the PV of workpiece profile in plane grinding process can be predicted effectively through this approach.

Jue Jin | Qingqing Yang

[1] Peter Willett,et al. Neural network detection of grinding burn from acoustic emission , 2001 .

[2] Sounak Kumar Choudhury,et al. Prediction of wear and surface roughness in electro-discharge diamond grinding , 2007 .

[3] Kuang-Hua Fuh,et al. Force modeling and forecasting in creep feed grinding using improved bp neural network , 1997 .

[4] Li Jian-zhen. A learning algorithm of artificial neural network based on genetic algorithm , 2002 .

[5] Yongsheng Gao,et al. A discrete system model for form error control in surface grinding , 2010 .

[6] Qiu Wei. Globally convert adaptive quick back propagation algorithm based on neural network , 2004 .