Prediction of Cutting Forces for Machine Tools by Neural Networks

• Published in: ADVANCES IN MANUFACTURING IV, VOL 1, MANUFACTURING 2024
• Main Authors: Kataraki, Pramodkumar S.; Ishak, Aulia; Mazlan, M.; Qasem, Isam; Hussien, Ahmed A.; Zubair, Ahmad Faiz; Janvekar, Ayub Ahmed
• Format: Proceedings Paper
• Language: English
• Published: SPRINGER INTERNATIONAL PUBLISHING AG 2024
• Subjects: Engineering
• Online Access: https://www-webofscience-com.uitm.idm.oclc.org/wos/woscc/full-record/WOS:001267307500005

The research objective is focused on developing artificial neural network (ANN) based approach to estimate optimal cutting forces based on various input parameters during machining processes for the enhancement of tool life and machining efficiency. The literature review explores the existing techniques and methodologies adopted for cutting force prediction. In this paper, experimental data are gathered from a lathe machine, incorporating diverse cutting parameters (such as depth of cut, feed rate, and cutting speed) that have significant impact on cutting forces. The collected data is then pre-processed to remove any inconsistencies or outliers, ensuring the quality and integrity of the dataset. The ANN model is constructed using a feedforward architecture, comprising multiple hidden layers with different activation functions. The model is trained using a backpropagation algorithm, optimizing the weights and biases to minimize the difference between predicted and actual cutting forces. Performance metrics such as mean squared error and mean absolute error are employed to evaluate the accuracy of the model. Extensive experiments and simulations are conducted to validate the developed model. The results demonstrate that the ANN-based approach exhibits high accuracy in predicting cutting forces. The model effectively captures the complex relationships between input parameters and cutting forces, enabling optimization of machining processes and tool selection. The developed predictive models provide valuable insights for process planning, control, and optimization. In conclusion, this project highlights the potential of ANNs in predicting cutting forces. The developed models offer a promising solution for optimizing machining processes, leading to improved manufacturing efficiency.