PCA fused NN approach for drill wear prediction in drilling mild steel specimen
The present paper describes use of principal components for drill wear prediction. It also makes a comparative analysis in using large sensor based technique in predicting drill wear. In order to reduce the redundancy of the network, principal component has been fused with artificial neural network (ANN) for prediction of drill wear. Large numbers of experiments have been conducted and sensor signals have been acquired using data acquisition system. Cutting force, torque, vibrations along with other process parameters such as spindle speed, feed rate, drill diameter, chip thickness and surface roughness have been used as indicative parameters for characterizing the progressive wear of drill. Principal component of these input parameters has been derived thereafter and has been used to predict the flank wear using BPNN.
component: Neuron sensor integration signal analysis design of ezperiment flank wear BPNN PCA
S.S. Panda S.S. Mahapatra
Department of Mechanical Engineering, Indian Institute of Technology Patna, Bihar-800013, India Department of Mechanical Engineering, National Institute of Technology Rourkela,Orissa-769008, India
国际会议
北京
英文
2642-2646
2009-08-08（万方平台首次上网日期，不代表论文的发表时间）