Machine learning framework for predictive maintenance in milling

In the Industry 4.0 era, artificial intelligence is transforming the manufacturing industry. With the advent of Internet of Things (IoT) and machine learning methods, manufacturing systems are able to monitor physical processes and make smart decisions through realtime communication and cooperation with humans, machines, sensors, and so forth. Artificial intelligence enables manufacturers to reduce equipment downtime, spot production defects, improve the supply chain, and shorten design times by using machine learning technologies which learn from experiences. One of the last application of these technologies is the development of Predictive Maintenance systems. Predictive maintenance combines Industrial IoT technologies with machine learning to forecast the exact time in which manufacturing equipment will need maintenance, allowing problems to be solved and adaptive decisions to be made in a timely fashion. This study will discuss the implementation of a milling Cutting-tool Predictive Maintenance solution (including Wear Monitoring), applied to a real milling data set as validation of the framework. More generally, this work provides a basic framework for creating a tool to monitor the wear level, preventing the breakdown, of a generic manufacturing tool, in order to improve human-machine interaction and optimize the production process.