A design of an intelligent maintenance integrated system into manufacturing systems

Abstract

The allocation of maintenance action timing highly affects the useful life length of the maintained equipments, direct costs of maintenance and consequently production costs. A reliable maintenance system is critical for any corporation to keep acceptable level of profit and competition. This paper describes a design of an intelligent maintenance which can help maximising the availability of the system at minimum cost. It combines maintenance methods applied at present to fuse the advantages of different approaches of state of the art. It is the first phase of a scheme based on Neural Management Maintenance System (NMMS), which would permanently monitor the system and suggest the most appropriate maintenance actions. This integrated system for manufacturing systems is based on the concept of Neural Management Maintenance which is based on artificial intelligence algorithms. The scheme has been designed, simulated, and then the basic level unit of the scheme is applied on a subsystem of hydraulic drive. The application demonstrated the efficiency of the method.

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

“…Many techniques of resolution of JSSP have been applied to find good solutions. Among them are heuristic methods [3]; genetic algorithms [5], [6]; Taboo search [7] intelligent methods [8], [9]; neural networks [10], [11] etc. Recently, neural networks have been used to solve JSSP.…”