Towards a Novel Maintenance Support System Based On mini-terms: Mini-term 4.0
This paper presents how to design a novel Maintenance Support System (MSS) to prognostic breakdowns in production lines based on mini-terms, well known as a Mini-term 4.0. The system is based on the real time sub-cycle time (mini-term) monitorization and how the mini-term variability can be used as a fault detection indicator. Mini-terms and micro-terms were introduced in our previous work as a machine subdivision. A mini-term subdivision can be selected by the expert team for several reasons, the replacement of a machine part or simply to analyze the machine more adequately. (A micro-term is a component from a mini-term and it can be as small as the user wishes. Mini-terms are able to detect the same physical deterioration phenomenon than common sensor but with an important advantage, it is easy and cheap to install. It is cheap because do not require any additional hardware installation to measure the sub-cycle time, just use the PLC and sensors installed for the automated production process, and easy because only requires to code extra timers into the PLC. Mini-terms are nowadays implanted at Ford factories around the world where a learning process is established to enrich the knowledge of the system. The system detects change points and sends an e-mail to the maintenance workers. They repair the machine and report the pathology detected to the system. Real cases are shown at the end of the paper.
KeywordsKnowledge-driven support system Maintenance prognosis mini-term Change point Mini-term 4.0
The authors wish to thank Ford España S.L and in particular Almussafes Factory for the support in the present research.
- 2.Li L, Djurdjanovic D, Ni J (2007) Maintenance task priorization using data driven bottleneck detection and maintenance opportunity windows. In: ASME 2007 international conference on manufacturing science and engineering, pp 517–523. https://doi.org/10.1115/MSEC2007-31150
- 5.Chang Q (2005) Supervisory factory control based on real-time production feedback. PhDGoogle Scholar
- 8.López CE (2014) Unbalanced workload allocation in large assembly lines. PhDGoogle Scholar
- 9.Garcia E (2016) Análisis de los sub-tiempos de ciclo técnico para la mejora del rendimiento de las líneas de fabricación. PhDGoogle Scholar
- 10.Negnevitsky M (2005) Artificial intelligence: a guide to intelligent systems. Pearson EducationGoogle Scholar
- 12.Chakir A, Chergui M, Elhasnaou S, Medromi H, Sayouti A (2016) A decision approach to select the best framework to treat an it problem by using multi-agent systems and expert systems. In: Advances in ubiquitous networking, pp 499–511. https://doi.org/10.1007/978-981-287-990-540
- 13.Felsberger A, Bernhard O, Gerald R (2016) A review of decision support systems for manufacturing systems. In: The international conference on knowledge technologies and data-driven business 2016 - i-KNOW 2016, pp 499–511Google Scholar
- 14.Murthadha M, Banaz A (2013) Knowledge-driven decision support system based on knowledge warehouse and data mining for market management. J Manag Bus Res 13(10):2249–2288Google Scholar
- 17.Garcia E, Montes N (2017) A Tensor Model for Automated Production Lines based on Probabilistic Sub-Cycle Times. Nova Science Publishers 18(1):221–234Google Scholar
- 22.Garcia E, Montes N, Alacreu M (2018) Towards a knowledge-driven maintenance support system for manufacturing lines. In Proceedings of the 15th international conference on informatics in control, automation and robotics (ICINCO 2018), vol 1, pp 43–54. https://doi.org/10.5220/0006834800430054