Prediction of tool wear based cutting forces during end milling of Inconel 718 using artificial neural networks

During the research, correlation between the input parameters (cutting parameters and cutting forces measure like peak to peak, root mean square and root mean square of ripple) and the variables were searched for, and the sensitivity of the network to input parameters was determined. In this paper artificial neural networks (ANNs) to prediction of tool wear based on cutting forces were used. Multilayer perceptron (MLP) networks with backward error propagation were used. The research shows that for the tested material and in the tested range, the cutting parameters are not diagnostically significant for the prediction of VBC (band width of the corner wear). The authors of this article focus on simplifying the model and analyzing the influence of variables on the prediction error. Neural networks show a correlation of about 95% for test sets.

---

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).