Intelligent setup planning in manufacturing by neural networks based approach

Setup planning is considered the most significant but also difficult activi ty in Computer Aided Process Planning (CAPP), and has a strong impact on ma nufacturability, product quality and production cost. Indeed, setup plannin g activity deserves much attention in CAPP. The setup planning in manufactu ring consists mainly of three steps, namely, setup generation, operation se quence, and setup sequence. In this paper, the Kohonen self-organizing neur al networks and Hopfield networks are adopted to solve such problems in set up planning efficiently. Kohonen self-organizing neural networks are utiliz ed, according to the nature of the different steps in setup planning, to ge nerate setups in terms of the constraints of fixtures/jigs, approach direct ions, feature precedence relationships, and tolerance relationships. The op eration sequence problem and the setup sequence problem are mapped onto the traveling salesman problem, and are solved by Hopfield neural networks. Th is paper actually provides a complete research basis to solve the setup pla nning problem in CAPP, and also develops the most efficient neural networks based approaches to solve the setup planning problem in manufacturing. Ind eed, the results of the proposed approaches work towards the optimal soluti on to the intelligent setup planning in manufacturing.