A multi-objective optimization method for the thickness of automobile composite bumper anti-collision beam

Abstract

The invention discloses a multi-objective optimization method for the thickness of an automobile composite material bumper anti-collision beam, comprising: step 1, respectively determining the layer thicknesses of the upper plate, the lower plate, the front plate, the rear plate and the rib plate of the anti-collision beam The value range, and the ply sequence corresponding to each ply thickness; Step 2, generate an initial sample data set, and determine the objective function f(x) and constraint function g(x) for the optimization of the ply thickness of the anti-collision beam; Step 3 , according to the objective function and the constraint function, the initial parameters of the Gaussian random process kernel function are set, and the GPR model is obtained through training; Step 4, the Pareto front solution set is obtained by the GPR model, and a new solution is screened out from the Pareto front solution set The sample is added to the initial sample data set; loop step two to step four, until the number of iterations is satisfied, the optimized Pareto front solution set is obtained, and the upper and lower panels of the anti-collision beam are obtained according to the optimized Pareto front solution set Optimized ply thickness for slabs, fronts, backs and ribs.

Description

technical field [0001] The invention belongs to the technical field of automobile passive safety research, and particularly relates to a multi-objective optimization method for the thickness of an automobile composite material bumper anti-collision beam. Background technique [0002] At present, most of the multi-objective optimization is based on the optimization method of the surrogate model. Before optimization, a surrogate model with sufficient accuracy needs to be established. Usually, the accuracy of the surrogate model is only above 0.9, and the optimization results are accurate and credible. However, for high-dimensional and highly nonlinear mathematical models, such as car crashes, hundreds or even thousands of Design of Experiments (DOEs) need to be used for simulation and simulation. The price is unbearable. In addition, most traditional surrogate models do not directly reflect the uncertainty of the model, resulting in large deviations in the optimization result...

AI Technical Summary

Problems solved by technology

the price is unbearable

In addition, most traditional proxy models do not directly reflect the uncertainty of the model, resulting in large deviations in the optimization results. When faced with higher-dimensional optimization, the optimization cannot be carried out smoothly.

In addition, for one-step optimization design, the modeling is one-time, and there is no process of approximate model improvement. If the model has a large approximation error, the optimization based on the model must be inaccurate

At present, there is no optimization method that combines sequential optimization and Gaussian process regression model to achieve multi-objective optimization

Images