Study of automatic designing of line heating technique parameters

Abstract

Based on experimental data of line heating, the methods of vector mapping, plane projection, and coordinate converting are presented to establish the spectra for line heating distortion discipline which shows the relationship between process parameters and distortion parameters of line heating. Back-propagation network (BP-net) is used to modify the spectra. Mathematical models for optimizing line heating techniques parameters, which include two-objective functions, are constructed. To convert the multi-objective optimization into a single-objective one, the method of changing weight coefficient is used, and then the individual fitness function is built up. Taking the number of heating lines, distance between the heating lines' border (line space), and shrink quantity of lines as three restrictive conditions, a hierarchy genetic algorithm (HGA) code is established by making use of information provided by the spectra, in which inner coding and outer coding adopt different heredity arithmetic operators in inherent operating. The numerical example shows that the spectra for line heating distortion discipline presented here can provide accurate information required by techniques parameter prediction of line heating process and the technique parameter optimization method based on HGA provided here can obtain good results for hull plate.