Modeling of tool wear in drilling by statistical analysis and artificial neural network

摘要: Abstract The useful life of a cutting tool and its operating conditions largely control the economics machining operations. Hence, it is imperative that condition tool, particularly some indication as to when requires changing, be monitored. drilling operation frequently used preliminary step for many operations like boring, reaming tapping, however, itself complex demanding. Back propagation neural networks were detection drill wear. network consisted three layers input, hidden output. Drill size, feed, spindle speed, torque, time thrust force are given inputs ANN flank wear was estimated. Drilling experiments with 8 mm size performed by changing speed feed at two different levels. number neurons in layer selected from 1, 2, 3, …, 20. learning rate 0.01 no smoothing factor used. estimated values obtained statistical analysis various structures. Comparative has been done between analysis, structures actual experimentation.