Approximate model establishment method for vehicle body structure parameterization design

Abstract

The invention relates to an approximate model establishment method for structure parameterization design. The method comprises the following steps: step 1, forming an initial training sample set according to an optimization design issue; step 2, establishing a plurality of approximate models to form a unit model library; step 3, performing unit model decision making, and constructing an ideal unit model set suitable for current training samples; step 4, calculating a weight coefficient of each unit model and establishing an integrated approximation model; step 5, correcting the current integrated approximation model; step 6, judging whether a convergence criterion is met or not, if yes, completing the design, and if not, executing the step 7; step 7, adding new training samples to the training sample set generated in the step 1 by using an incremental learning technology, and sequentially executing the steps 2 to 6. According to the method, the dependence of the approximation model on response characteristics is eliminated, the technical universality is ensured, the prediction robustness is improved, the prediction reliability is improved, and the prediction precision of the integrated approximation model is improved.

Description

technical field [0001] The invention relates to the field of vehicle structure design, in particular to an approximate model establishment method for parametric design of vehicle body structure. Background technique [0002] Parametric design is an important means of forward design of body structure. By establishing an implicit parametric body model, the optimal design of the body structure is carried out based on full-scale parameter transformation and efficient optimization algorithms, which can meet the needs of multidisciplinary design, reduce repeated trial and error work, and shorten the design and development cycle. [0003] Whether it is based on the gradient algorithm or the optimization design method using the evolutionary algorithm, a large amount of structural performance response evaluation is required, and the performance response evaluation based on finite element simulation is expensive, resulting in excessive calculation and slow convergence. For example, a...

AI Technical Summary

Problems solved by technology

[0004] Although the optimization method based on the approximate model is considered to be one of the most effective ways to realize the parametric design of the body structure, there are still some deficiencies, mainly in the following aspects: 1. Subject optimization design method, there are many kinds of approximate models at present, but there is no general approximate modeling technology that has outstanding advantages for different types of responses; 2. Crashworthiness is one of the important properties that must be considered in the process of body structure design , and the crashworthiness response is a typical strong nonlinear structural response, the current approximate modeling technology has poor prediction accuracy for the crashworthiness response; 3. Since the approximate modeling is a mathematical approximation to a complex physical system, the Unavoidable prediction uncertainty in any approximate model

The establishment and application of the approximate model is one of the important influencing factors to achieve structural optimization. As far as the current public technology is concerned, there is no approximate modeling that meets the requirements of accuracy, reliability and robust performance in the crashworthiness design of the body structure. method

Images