End-to-end industrial IoT platform for Quality 4.0 applications

Predictive maintenance, quality management, and zero-defect manufacturing are among the most prominent smart manufacturing use cases in the Industry4.0 era. Nevertheless, the development of such systems is still challenging because of the need to integrate multiple fragmented data sources, to apply advanced machine learning techniques for multi-objective optimizations, and to implement configurable digital twins that can flexibly adapt to changing industrial configurations. This paper presents the architecture, design, practical implementation, and evaluation of an end-to-end platform that addresses these challenges. The platform provides the means for collecting, managing, and routing data streams from heterogeneous cyber physical production systems, in configurable and interoperable ways. Moreover, it supports advanced data analytics by means of a novel machine learning framework that leverages quantitative rule mining. The presented platform has been successfully deployed in various industrial settings and has been positively evaluated in terms of its ability to accelerate application development, reduce unscheduled downtimes, provide increased Overall Equipment Efficiency (OEE), compute production process parameter configurations that lower the percentage of product defects, and predict product defects before they occur.