乘用车燃料消耗量的神经网络预测  

Prediction on Fuel Consumption of Passenger Cars Based on BP Neural Network

作　　者：苏卉[1] 任焕焕[1] 

机构地区：[1]中国汽车技术研究中心

出　　处：《汽车工程师》2016年第11期20-22,共3页Automotive Engineer

摘　　要：随着油耗标准法规的日益严苛,整车企业需要从企业整体层面进行产品规划,以满足合规性要求。整车企业在针对企业平均燃料消耗量合规进行规划时,对于未来车型单车油耗的预测是必不可少的环节。剖析了影响乘用车燃料消耗量的影响因素,在此基础上建立了基于BP神经网络的乘用车燃料消耗量预测模型,对单车油耗进行模拟预测。测试结果表明,模型算例的相对误差率最大值为3.06%,预测精确度较高,该模型为单车油耗的模拟预测提供了一种新的方法。In response to increasingly stringent fuel economy slandards and regulations, auto makers take more attention to fuel consumption in overall product planning to meet the requirements. The prediction on the fuel consumplion of a single vehicle is focused on setting the average fuel consumption of a single vehicle. In this paper, the influence factors of fuel consumption of passenger ears are analyzed, and the prediction model of fuel eonsumption of passenger cars based on the BP neural network is established and simulated. The test results show that the maximum relative error rate of the model is 3.06%, and the prediction accuracy is very high. The model povides a new method for the simulation of a single vehicle fuel consumption.

关 键 词：燃料消耗量法规 神经网络 油耗预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] U467.498[自动化与计算机技术—控制科学与工程]