【摘要】 装配是产品制造过程中耗费大量时间和精力的重要环节，影响着产品整个生命周期。针对产品装配效率低的问题，提出遗传算法优化BP神经网络的装配质量预测方法。以DC零件的质心后端、质量、长度这三个质量特性为基础，划分数据，确定BP神经网络结构，以均方误差作为遗传算法的适应度函数，寻找最优的初始权值和阈值，建立了遗传算法优化BP神经网络模型，并结合平均绝对误差MAE、均方误差MSE、均方根误差RMSE对预测结果进行了对比。实验结果表明：相比于传统的BP神经网络，经过遗传算法优化的BP神经网络在质量预测方面具有更好的精度和准确性。更多还原

【Abstract】 Assembly is an important part of the product manufacturing process that consumes a lot of time and energy,affecting the entire life cycle of the product.In order to solve the problem of low product assembly efficiency,a quality prediction method of BP neural network optimized by genetic algorithm was proposed.Based on the three mass characteristics of the back-end of the center of mass,mass and length of the bomb bay physical quantity(referred to as DC physical quantity),the data were divided,the structure of the BP neural network was determined,the mean square error was used as the fitness function of the genetic algorithm,the optimal initial weight and threshold were found,the genetic algorithm was established to optimize the BP neural network model,and the prediction results were compared by combining the mean absolute percentage error MAE,mean square error(MSE) and root mean square error(RMSE).Experimental results show that compared with the traditional BP neural network,the BP neural network optimized by genetic algorithm has better precision and accuracy in quality prediction.更多还原