MoBiSea: A Binary Search Algorithm for Product Clustering in Industry 4.0

• Published in: Electronics (Basel) Vol. 12; no. 15; p. 3262
• Main Authors: Herrero, Angel C., Sanguesa, Julio A., Garrido, Piedad, Martinez, Francisco J., Calafate, Carlos T.
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2023
• Subjects: Algorithms; Automation; Clustering; Clustering (Computers); Control; Data collection; Design; Efficiency; Electromagnetic interference; Electromechanical devices; Error analysis; Industrial applications; Industrial management; Industry 4.0; Internet of Things; Low cost; Machinery; Manufacturing; Modernization; Production lines; Productivity; Real time; Sealing; Search algorithms; Technology application; Spain
• ISSN: 2079-9292; 2079-9292
• DOI: 10.3390/electronics12153262

Proprietary systems used to modernize Industry 4.0 usually involve high financial costs. Consequently, using low-cost devices with the same functionalities, capable of replacing these proprietary systems but at a lower cost, has become an incipient trend. However, these low-cost devices usually come with electromagnetic interference problems as they are encapsulated in electrical panels, sitting alongside electromechanical devices. In this article, we present Mode Binary Search, an algorithm specifically designed for use in a low-cost automated-industrial-productivity-data-collection system. Specifically, productivity data are obtained from the availability and sealing signals of the thermoplastic sealing machines in production lines belonging to the agri-food industry. Mode Binary Search was designed to cluster sealing signals, thus enabling us to identify which products have been made. Furthermore, the algorithm determines when the manufacturing of each product starts and ends, in other words, the exact moment a product change occurs and all this without the need for operator supervision or intervention. Finally, we compared our algorithm, based on binary search, with three clustering mechanisms: k-means, k-rms and x-means. Out of all the cases we analyzed, the maximum error committed by Mode Binary Search is limited to 2.69%, thereby outperforming all others.