A Framework for Big Data Driven On-Line Monitoring of Tool Wear

Abstract

The state of the tool wear is an important factor that affects the processing quality and production efficiency. With the development of a large number of automation equipment in the workshop, the on-line monitoring of tool wear is increasingly important for manufacturing industries. However, there are several challenges, such as the real-time storage and efficient processing of large amounts of signal data, in the process of on-line monitoring of tool wear. In this paper, a framework for big data driven on-line monitoring of tool wear was proposed to address these challenges. Then, two key technologies of the proposed framework including self-driving data acquisition and storage, processing of real-time and non-real time data were developed for the big data analytics for tool wear. Finally, a study of experiment was presented to demonstrate the proof-of-concept of the proposed framework. The results show that the proposed framework was feasible to be adopted in on-line monitoring of tool wear and can be used to make decisions on the time to change tool.