Abstract:

As an important stage of the automotive design process， conceptual design requires rapid conceptual design and evaluation. The current methods generally use a combination of parametric design and CAE to achieve analysis based conceptual design of car body structures. With the development and maturity of machine learning and deep learning algorithms， intelligent design methods will become the main innovative technology for body structure design. In this article， a combination of data-driven and optimization design method is used to independently develop the vehicle structure intelligent design software tool （S-iVCD）. Firstly， based on residual networks and thermal map regression algorithms， feature points of the vehicle body structure are extracted to achieve automated modeling of the conceptual model of the vehicle body structure. Secondly， based on Gaussian process sampling， a body structure dataset is collected and a fully connected neural network model is used to construct the body structure network model. The parameters of various components of the vehicle body can be input into the trained network model to obtain the overall performance results of the vehicle body. Finally， by combining data-driven computing with the moving asymptote algorithm， a multi-objective optimization design of the vehicle body structure that considers mass， bending stiffness， and torsional stiffness is quickly achieved. By comparing with finite element examples， the error of the calculation results is within the allowable range， with the optimization calculation time greatly shortened， and the lightweight rate reaching 7.4%. This indicates that the data-driven body structure optimization design method is effective in improving efficiency in the conceptual design stage of automobiles.

Key words: body structure design, lightweighting, data-driven analysis, fully connected neural networks