Structural optimisation of transportation equipment using an adaptive approximation model

Abstract

Considering the high computational cost of the optimisation process of complex transportation equipment, an efficient structural optimisation method for transportation equipment based on the multi-criteria sample updating and management strategy of the approximation model is proposed. First, the approximation models of the objective function and constraints are established based on the radial basis function, and the intergeneration projection genetic algorithm is applied to find the optimal solution. According to error evaluation of the optimal solution, second, the function fluctuation index is used to adopt the local sample points. Meanwhile, the global sample points are solved by the inherited Latin hypercube design to ensure the distribution uniformity of samples in the whole design space. Furthermore, the weighted Euclidean distance criterion is applied to evaluate the rationality between the samples. Then, the qualified samples are added to the sample space to update the approximation models of the transportation equipment. Based on the above multi-criteria sample updating and management strategy, more accurate optimisation results could be obtained. Finally, the effectiveness of the method and its applicability in practical application of transportation equipment are investigated by one numerical test and one engineering example.