A generalized generation and evaluation method for cutting process parameter knowledge based on CTGAN

The machining process knowledge base is a crucial tool in the decision-making process for cutting process parameters, as the diversity and accuracy of its stored process knowledge directly affect the decision effectiveness. To address the complex demands in actual production, it is necessary to adopt effective expansion methods to enrich the process knowledge base content and improve its generalizability. However, current expansion methods face limitations such as insufficient process knowledge coverage and the lack of an effective evaluation mechanism. In response to these issues, this paper proposes a generalized generation and evaluation method for cutting process parameter knowledge based on CTGAN. Firstly, a cutting process data acquisition platform is developed to serve as the basic data source. Then, Conditional Tabular Generative Adversarial Network (CTGAN) is used to construct a generalized generation model to learn the joint distribution law of real process parameter data and enable the intelligent generation of cutting process parameter cases. Finally, the accuracy and applicability of the generated cutting process parameter cases are evaluated through statistical indicator analysis and machine learning performance analysis. The proposed framework is validated using the external cylindrical turning process of a sleeve part as a test case. Results indicate that the generated process parameter data samples not only cover a broader range of machining scenarios but also maintain high quality, which can effectively support the autonomous expansion of machining process knowledge base, and enhance its generalization capability.