The prediction method of tool life on small lot turning process – Development of Digital Twin for production

Saving resources is one of the most significant factors in the manufacturing industry. There are in the factory, several different products under processing at the same time, therefore the handling of production conditions could be hard every now and then. Changing tools during operation might causes interruption and prolong production time. Estimation of a tool life during turning process is one of the key factors to avoid unnecessary unfinished parts and waste of resources. Overall research aiming to develop a machine learning method to predict tool life for any work-piece or tool material in the general turning process. The addressed method is important in modern small lot production when parts and materials changed constantly. The Purpose of this particular paper is to find out suitable machine learning method or several methods to evaluate tool-life in different turning conditions and circumstances. As a hypothesis of this research, we assume machine learning combine mathematical modelling is a proper method to estimate tool life in small-lot production with reasonable cost and operation time.