Tool wear prediction in hard turning of EN8 steel using cutting force and surface roughness with artificial neural network

Abstract

In this work, the flank wear of the cutting tool is predicted using artificial neural network based on the responses of cutting force and surface roughness. EN8 steel is chosen as a work piece material and turning test is conducted with various levels of speed, feed and depth of cut. Cutting force and surface roughness are measured for both the fresh and dull tool under dry cutting conditions. The tool insert used is CNMG 120408 grade, TiN coated cemented carbide tool. The experiments are conducted based on the response surface methodology face central composite design of experiments. The feed rate (14.52%), depth of cut (27.72%) and the interaction of feed rate and depth of cut (50.39%) influence the cutting force. The feed rate (21.33%) and the interaction of cutting speed and depth of cut (26.67%) influence the flank wear. The feed rate (61.63%) has the significant influence on surface roughness. The feed forward back propagation neural network of 5-n-1 architecture is trained using the algorithms like Levenberg Marquardt, BFGS quasi-Newton, and Gradient Descent with Momentum and Gradient descent with adaptive learning rate. The network performance has been assessed based on their mean square error and computation time. From this analysis, the BFGS quasi-Newton back propagation algorithm produced the least mean squared error value with minimum computation time.

Parametric study and multi-criteria optimization during turning of X210Cr12 steel using the desirability function and hybrid Taguchi-WASPAS method

“…For this, the modeling and optimization of cutting parameters is indispensable for any adopted manufacturing process. [5][6] For that, several researches have been carried out on the machining of X210Cr12 steel (AISI D3) in terms of tool wear evolution, surface quality, cutting forces, power consumption, modeling, and optimization of cutting conditions. Yallese et al 7 have conducted a comparative study that investigated the cutting performance variations between CC650 and CBN7020 inserts when machining X200Cr12 steel in terms of wear and surface roughness evolutions.…”

Machining characteristics investigations of duplex stainless steel by considering dual effect of chip breaker and cooling conditions

“…21–23 There are some adverse effects such as rapid tool wear because of high temperature, reducing tool life, deteriorating surface quality, and changing metallurgical features of workpiece in dry machining. 24,25 The improvement in tool materials, coating qualities and tool geometries, and the application of optimal cutting parameters have enabled dry machining of some materials and contributed to sustainable manufacturing without using cutting fluids. 26–28 The different air types such as chilled, mist, cold, and cryogenic are used as a cryogenic condition in machining.…”

Tool Wear Conditions Monitoring Based on Kernel Smoothing Density and Deep Learning

“…Recently, data-driven approach has proven successful in relation to different machine learning techniques developed allowing learning features, among these, Support Vector Machine, Hidden Markov and Neural Network, etc. [14][15][16], the latter creates more and more competitive architectures in the different fields, medicine, maintenance, and Aerospace, etc. among these architectures are Probabilistic Neural Network [17], Multi-Layer Perceptron, Convolutional Neural Network and Recurrent Neural Network (RNN) [18,19], the advantage of the latter is remarkable especially with datasets of sequential nature, to capture the temporal relation between the different sequences, unfortunately, despite these advantages, it presented a major disadvantage, is a gradient vanishment, which can cause losses of long-term information, and to remedy this problem, an architecture has been proposed which is LSTM, allowing to ensure long and short term dependency [20].…”