Data mining from endmill tool catalog information based on the use of a machine learning method

In recent years, the needs associated with the development of new technologies in the manufacturing industry that utilize big data typified by the Internet-of-Things (IoT) and artificial intelligence (AI) have been increasing. Recent computer-aided manufacturing (CAM) systems have evolved so that unskilled technicians can create tool paths relatively easily with numerically controlled (NC) programs, but tool-cutting conditions used for machining cannot be automatically determined. Therefore, many unskilled technicians often set the cutting conditions based on the recommended conditions described in the tool catalog. However, given that the catalog contains large-scale data on machining technology, setting the proper conditions becomes a time-consuming and inefficient process. In this study, we aimed to construct a system to support unskilled technicians to determine the optimum machining conditions. To this end, we constructed a prediction model using a random forest machine learning method to predict the cutting conditions. It was confirmed that the prediction with the random forest method can be performed with high accuracy based on the cutting conditions recommended by the tool maker. Thus, the effectiveness of this method was verified.