New Hopfield Neural Network for joint Job Shop Scheduling of production and maintenance

Abstract

Job Shop Scheduling is one of the most difficult problems in industry and it is the main interest of the major researchers in the manufacturing research area. This problem becomes crucial when the production planning and maintenance have to be jointly solved. Several heuristics and intelligent methods have been so far proposed in the literature and applied. This work deals with a Hopfield Neural Network (HNN) method used for solving the JSP taking into account the maintenance tasks. While this method had been already proposed in the literature to solve the JSP alone, our main improvement of this method is to take into account the maintenance periods by extending the Hopfield net to handle the joint problem. Experimental study shows that the proposed HNN algorithm gives efficient results for the resolution of the joint job shop scheduling problem.

Review of job shop scheduling research and its new perspectives under Industry 4.0

“…(2012) [41] applied it to solve joint production and maintenance scheduling problems. However it is difficult to be used in actual JSP because the variables involved are so large that various problems have brought about, i.e., the computational efficiency is low, and it may not converge to good quality solutions.…”

Application of Data Mining in the Field of Human Resource Management: A Review

“…Neural Network Job Shop Scheduling is a difficult issue in the manufacturing sector and an important part of research. [32] proposed a Hopfield Neural Network (HNN) algorithm to solve the shop scheduling problem. [33] studied the rescheduling problem of semiconductor manufacturing systems and proposed a fuzzy neural network model.…”