Identification and health-aware economic control of production systems: A fuzzy logic max plus algebraic approach. (April 2023)

• Record Type: Journal Article
• Authors: Mrugalski, Marcin
• Is Part Of: Engineering applications of artificial intelligence. Volume 120(2023)
• Publication Date: 2023-04
• Subjects: Health aware control -- Manufacturing system -- IoT -- Fuzzy logic -- Max plus algebra; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2022.105802
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: The first objective of this paper is to settle the practical problem pertaining to the modelling and identification of the production system performance, which is defined a discrete event one. For that purpose the Internet of Things tools are employed, which are located at each manufacturing machine. As a result, a set of time-driven data is obtained, which measure the metal processing time of the shot blasting machines. These result constitute the base for the development of the state-space model designed with fuzzy logic and max-plus algebraic paradigms. The appealing property of the processing time model is that it is designed with the experimental design strategy, and hence, a minimum number of metal plates is required for its design. It should be noted that the system considered contains concurrent machines, which are redundant, and hence, cause the need for appropriate scheduling and control. Apart from that the system has an associated economic and health-aware indicators, which express the cost of possible degradation of using them over a specified time horizon. Thus, the proposed strategy allows finding a trade-off between general performance of the entire system and these indicators. The proposed strategy is illustrated with a practical proof-of-concept production system, which clearly exhibits the benefits concerning the application of the proposed approach. Graphical abstract: Highlights: Development and deployment of IoT structure. Development of a metal processing machine model for manufacturing prediction. Improvement of the Takagi–Sugeno model quality with an optimal experimental design. Development of health-aware economic control strategy for the entire metal processing system.