论文部分内容阅读
从设计参数特征入手分析影响汽车油耗的因素,利用灰关联分析方法,解析了各设计参数对汽车油耗的影响程度,选择其中灰关联度较大的设计参数作为输入数据,综合工况油耗作为输出数据,构建6-5-1层结构的BP神经网络预测模型,并利用遗传算法获得优化后的BP神经网络的权值和阈值,然后训练BP神经网络得到最优值,最后以国内市场340款汽车作为研究样本,进行有效性验证.研究结果表明,模型利用灰关联分析获得影响汽车油耗的主要因素,简化了网络结构;与优化前的BP神经网络相比,具有更高的预测精度和可靠性.
Starting from the characteristics of the design parameters, the paper analyzes the factors that affect the fuel consumption of the automobile, and uses the gray relational analysis method to analyze the influence of each design parameter on the fuel consumption of the automobile. The design parameter with larger gray correlation degree is selected as the input data and the fuel consumption as the output Data to build 6-5-1 layer structure of BP neural network prediction model, and use genetic algorithm to get the weight and threshold of the optimized BP neural network, and then train the BP neural network to get the optimal value, and finally to the domestic market 340 models Vehicle as the research sample to verify the validity.The results show that the model can get the main factors that affect the fuel consumption of automobile by using the gray relational analysis and simplify the network structure.Compared with the BP neural network before optimization, the model has higher prediction accuracy and reliability Sex.