A Multimodal Machine Learning Framework for Optimizing Coated Cutting Tool Performance in CNC Turning Operations

The present study introduces a comprehensive machine-learning framework for modeling, interpretation and optimization of the CNC turning procedure employing coated cutting inserts. The primary novelty of this work lies in the integrated pipeline that leverages a multimodal experimental dataset in order to simultaneously model surface roughness and residual stresses, as well as to interpret these predictions within a unified optimization scheme. Particularly, a deep learning model was developed incorporating a convolutional encoder for analyzing time-series signals and a static encoder for the investigated machining parameters. This fused representation enabled accurate multi-task predictions, capturing the thermo-mechanical interactions that govern surface integrity. Additionally, to ensure interpretability, a surrogate meta-model based on the deep model’s predictions was established and evaluated via Shapley Additive Explanations. This analysis quantified the relative influence of each cutting parameter, linking data-driven insights to contact-mechanical principles. Furthermore, a multi-objective optimization scheme was implemented to derive Pareto optimal trade-offs among the examined parameters that could enhance the machining efficiency. Overall, the integration of deep learning, interpretable modeling and optimization established a coherent framework for data-driven decision making in turning, highlighting the importance of model transparency in advancing intelligent manufacturing systems.