Prediction of machining accuracy and surface quality for CNC machine tools using data driven approach

CNC machine tool is universal machinery in industry, and each product has the different quality requirements during machining process. Therefore, the performance of machine tool is very important for machining capabilities. The milling accuracy and surface quality are usually regarded as the indicators of product quality, and these indicators are affected by CAD/CAM, machining parameters of CNC controller, servo loop, and feed drive system, etc. In this paper, we propose a data driven method to predict machining quality of product by ANFIS model, which the inputs are CNC machining parameters and the outputs are two performance indexes (milling accuracy and surface quality). The corresponding fuzzy rules can be extracted from the ANFIS for user to understand the relationship between CNC parameters and performance indexes. Finally, simulation and experimental results illustrate that the two indexes can be predicted effectively for different machining parameters. Therefore, this predicted system can help user to achieve the required product quality and machining productivity.