基于BP神经网络及遗传算法对热防护服的优化设计

Optimal Design of Thermal Protective Clothing Based on BP Neural Network and Genetic Algorithm

针对高温作业专用服装设计,首先运用了偏微分、非线性规划及有限差分法等理论或方法,构建了“高温环境—服装—空气层—皮肤”为整体的热传递模型并绘制出温度分布图;其次,根据人体灼伤模型初步得到织物层厚度的最优参数;最后,采用遗传算法来优化BP神经网络的权值和阈值,然后将这些优化值赋给网络得到优化的BP神经网络,结合MATLAB对非线性厚度函数进行逼近拟合和极值寻优。

Aiming at the professional clothing design of high-temperature operation,the theories or methods such as partial differential,nonlinear programming and finite difference method are firstly used to construct the heat transfer model of “high-temperature environment-clothing-air layer-skin” as a whole and draw the temperature distribution diagram.Secondly,according to the human body burns the optimal parameters of the model are preliminary fabric thickness.Finally,by using genetic algorithm to optimize the BP neural network weights and thresholds,and then the optimal value is assigned to the network to optimize the BP neural network,combined with the thickness of the MATLAB for nonlinear function approximation fitting and extremal optimization.