Intelligent setup planning in manufacturing by neural networks based approach

Abstract

Setup planning is considered the most significant but also difficult activity in Computer Aided Process Planning (CAPP), and has a strong impact on manufacturability, product quality and production cost. Indeed, setup planning activity deserves much attention in CAPP. The setup planning in manufacturing consists mainly of three steps, namely, setup generation, operation sequence, and setup sequence. In this paper, the Kohonen self-organizing neural networks and Hopfield networks are adopted to solve such problems in setup planning efficiently. Kohonen self-organizing neural networks are utilized, according to the nature of the different steps in setup planning, to generate setups in terms of the constraints of fixtures/jigs, approach directions, feature precedence relationships, and tolerance relationships. The operation sequence problem and the setup sequence problem are mapped onto the traveling salesman problem, and are solved by Hopfield neural networks. This paper actually provides a complete research basis to solve the setup planning problem in CAPP, and also develops the most efficient neural networks based approaches to solve the setup planning problem in manufacturing. Indeed, the results of the proposed approaches work towards the optimal solution to the intelligent setup planning in manufacturing.