This experiment targets the processing of olive cake (pomace), a by-product of the olive mill, towards a variety of useful products, such as Refined Pomace Olive Oil (edible), Oleins, Soap, Free Fatty Acids (for the pharmaceutical industry), Olive Biomass (renewable fuel). Since the pomace treatment process is very energy consuming it’s not only a huge cost factor for processing companies, mostly SMEs, but also a crucial topic with regard to environmentally damages due to CO2 emissions.
The currently predominantly used Electric Motor‐Driven Systems (EMDS) which are used in pumps, fans, compressors, and material handling and processing, account for around 45% of all global electricity consumption. One way to improve energy efficiency is the replacement of existing motors with eco-efficient ones. Equipment upgrade is usually an important investment, but is not always feasible, especially for SMEs.
The scope of this experiment is to cloudify the energy disaggregation module of Plegma Labs S.A., combine it with the device health monitoring of National Centre of Scientific Research "DEMOKRITOS" and integrate the Decision Support System (DSS) of RISA GmbH to the CloudiFacturing platform. Using advanced CPS / IOT and data analysis technologies and cloud data-analytics, CLARION experiment aims 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 will be deployed and demonstrated in the traditional food processing plants of ELSAP S.A., a leading company in pomace oil extraction and refinement in Greece, and the end-user company in this experiment.
During the CLARION project, the energy monitoring system already deployed to ELSAP for various energy-demanding equipment along the processing chain, will be modified to transmit and analyse the data at the Cloud infrastructure using customized ML/AI algorithms, and the CLARION DSS will incorporate a rule-based expert system to fuse all available data (PLC, SCADA systems) to improve energy and process efficiency.
As a result, this experiment will deliver Decision Support tools for EMDS that assist the plant operators towards reduced energy usage, increased equipment availability and improved process efficiency, by offering a variety of analytics taking place at the edge and the cloud. For example will the combination and analysis of data from different sensors help to identify energy consumption anomalies, which can signify future failure of the equipment. This will in turn (a) allow for the timely scheduling of targeted maintenance actions, and (b) decrease unplanned downtime and increase the process availability. The former reduces maintenance costs by decreasing the costs of storing spare equipment, performing less expensive maintenance actions (of smaller scale) and avoiding equipment failures. The latter increases revenues and decreases loss of profit, by planning maintenance actions during lower production periods. Additional financial benefits of predictive maintenance result from improvement of occupational safety and employee productivity, since sudden equipment failures and unplanned maintenance are factors for occupational accidents. The envisaged solution is expected to have a wide application range, it will be 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.