An Industry 4.0-Enabled Low Cost Predictive Maintenance Approach for SMEs

This paper outlines the base concepts, materials and methods used to develop an Industry 4.0 architecture focused on predictive maintenance, while relying on low-cost principles to be affordable by Small Manufacturing Enterprises. The result of this research work was a low-cost, easy-to-develop cyber-physical system architecture that measures the temperature and vibration variables of a machining process in a Haas CNC turning centre, while storing such data in the cloud where Recursive Partitioning and Regression Tree model technique is run for predicting the rejection of machined parts based on a quality threshold. Machining quality is predicted based on temperature and/or vibration machining data and evaluated against average surface roughness of each machined part, demonstrating promising predictive accuracy.