集美大学学报（自然科学版）2023，Vol.28Issue(5)：467-472,6.DOI:10.19715/j.jmuzr.2023.05.11
GRNN神经网络在汽车发动机性能预测中的应用
Application of GRNN Neural Network in Performance Prediction of Automotive Engine
摘要
Abstract
The prediction models of engine power performance and fuel economy under multi input parame-ters are established.The influence of smoothing factors and input parameters on prediction accuracy has been studied.The influence of engine operating parameters on power performance and fuel consumption rate was stud-ied through the established prediction modes.The results show that the generalized regression neural network(GRNN)can be used to build a more accurate prediction model of engine power performance and fuel economy.The appropriate smoothing factor can not only avoid large fluctuations in the predicted value of GRNN,but also achieve high prediction accuracy.Engine can output higher power and torque under the appropriate throttle opening conditions.The engine fuel consumption rate has a high value at low power or low throttle opening.关键词
汽车发动机/预测模型/广义回归神经网络/动力性能/燃油消耗率Key words
automotive engine/prediction model/generalized regression neural network(GRNN)/power performance/fuel consumption rate分类
能源科技引用本文复制引用
林冬燕..GRNN神经网络在汽车发动机性能预测中的应用[J].集美大学学报（自然科学版）,2023,28(5):467-472,6.基金项目
福建省中青年教师教育科研项目(JAT160271) （JAT160271）
集美大学李尚大基金项目(ZC2016019) （ZC2016019）
