This work uses advanced CPS / IOT technologies and edge/cloud data-analytics, to develop a data-driven approach for equipment fault detection, and test its application for the improvement of Energy Efficiency and Predictive Maintenance. The proposed solution is expected to have wide application, it will be inexpensive and easy to deploy, and is particularly addressed to SMEs seeking cost effective industry 4.0- retrofitting-based solutions, to assist the transition to the Smart Factory era. The focus of the experiment is on Electric Motor‐Driven Systems (EMDS), used in pumps, fans, compressors, and material handling and processing. They consume around 2/3 of the electrical energy used in industry, their environmental footprint is, therefore, significant; and they have energy efficiency potential estimated as 10% of the global electricity demand.
The industrial pilot plant is a food-processing SME for which we have multiannual data on energy consumption and other process attributes, as well as the equipment maintenance log files. At present, everything depends on the individual expertise of the personnel, to identify and address any major or minor issues. During the experiment, we deploy custom non-intrusive devices to obtain high frequency (64kHz) electric load data of various critical energydemanding EMDS along the processing chain. The obtained results will identify underperforming equipment, overconsumption of energy, departures from normal operation etc. using edge / cloud analytics.