Optimization of bending sequence in roll forming using neural network and genetic algorithm

Abstract

In the roll forming process, the bending sequence plays a major role in the product quality. The optimal bending sequence results in the smallest number of passes and the flawless process. This paper presents a new optimization procedure of bending sequence in a roll forming process. The multilayer perceptron is used to build the neural network (NN), which models the variation of longitudinal strain in process while the genetic algorithm (GA) is employed to optimize the bending sequence. The data used for training the network is automatically obtained by the integration between CAD and CAE. The values of peak longitudinal strains are maximized while the number of passes is reduced to the smallest and the constraint conditions being set on the maximal longitudinal strain to avoid buckling. The overbending at final pass after spring back is also considered in this paper. Two roll forming processes are optimized in order to prove applicability and efficiency of the optimization procedure. This method maintains the longitudinal strain less than the buckling limit, whereas reducing the number of passes to the smallest. Thus, the advantages of the proposed method show the high applicability in designing and optimizing the bending sequence in the roll forming process.