Publication Type:

Journal Article


International Journal of Computer Integrated Manufacturing, Taylor and Francis Ltd., Volume 32, Number 2, p.174-182 (2019)



Adaptive neuro-fuzzy inference system, Artificial intelligence techniques, Condition monitoring, Cutting, Cutting forces, Cutting tools, Expert systems, Feedforward backpropagation neural networks, Fuzzy inference, Fuzzy neural networks, Fuzzy systems, Mean square error, Mean squared error, Milling (machining), Neural networks, Regression coefficient, Sound pressures, Tool condition monitoring, Wear of materials


An efficient tool condition monitoring system was designed for keyway milling of 7075-T6 hybrid aluminium alloy composite with resultant machining force and sound acquired while the milling process. During the milling process, sound pressure and machining force were measured using a microphone and milling tool dynamometer with NI USB 6221 DAQ card and monitored using LabVIEW. The resultant cutting force for fresh and dull tool varies up to 1 kN and 1.8 kN respectively. The sound pressure for fresh, working and dull tool varies up to 1.9 Pa, 2 Pa and 2.5 Pa respectively. The tool condition was estimated from the Artificial Intelligence techniques based on the acquired signals. The acquired signals were given as an input signal to the expert system. The predictor output varies from 0 to 3 to indicate the progression of flank wear and it was utilised to evaluate the tool condition. When the output exceeds the value of 3, it indicates that the tool has to be replaced for the machining process. The Mean Squared Error (MSE) for a feedforward backpropagation neural network and ANFIS model were 2.06517e-9 mm and 0.487505e-3 mm respectively. The neural network had the regression coefficient of 0.99 which shows the accuracy of the model. © 2018, © 2018 Informa UK Limited, trading as Taylor & Francis Group.


cited By 0

Cite this Research Publication

S. Shankar, T. Mohanraj, and Rajasekar, R., “Prediction of Cutting Tool Wear during Milling Process using Artificial Intelligence Techniques”, International Journal of Computer Integrated Manufacturing, vol. 32, pp. 174-182, 2019.