Technique for Optimum Design of Truss Structures by Neural Network.

This paper describes an application of a mutual combination-type neural network to the optimum design problems of truss structures. The optimum design problems of truss structures are changed to some combinatorial optimization problems. The Hopfield model and the quadratic energy function are used to solve the design problems. The method is able to obtain feasible solutions for several optimum design problems. The effectiveness of this method is demonstrated by two examples of the minimum weight and maximum stiffness design problems of truss structures.