摘要
为提高汽油机空燃比控制系统的实时性及进气流量计量的精确度,提出了一种汽油机进气流量混沌时序BP神经网络预测模型.利用相空间重构技术对进气流量时间序列进行重构,恢复系统原有的混沌性,再利用BP网络对重构后的数据进行训练及预测,达到提高进气流量预测精确度的目的,进而提高汽油机空燃比控制系统的实时性及精确度.试验仿真结果表明,混沌时序BP神经网络预测模型具有更高的预测精度,为精确及时地预测汽油机进气流量提供了一种全新的方法.
A BP neural network prediction model for chaotic time series of gasoline engine intake flow is proposed to improve the accuracy of the air fuel ratio control system of gasoline engine and the real- time air inlet flow. First,phase space reconstruction technique is adopted to reconstruct inlet flow time series and to recover the chaotic characteristics of the original intake system. BP neural network is then employed in training and predicting the reconstructed data to achieve accuracy of the measurement of the inlet flow rate,which in turn realizes real- time and accurate air fuel ratio control. The simulation results show that chaotic time series BP neural network forecasting model has higher prediction accuracy,which provides a new method for measuring the intake flow of gasoline engine in a timely manner.
出处
《昆明理工大学学报（自然科学版）》
CAS
2016年第5期46-50,共5页
Journal of Kunming University of Science and Technology(Natural Science)
基金
国家自然科学基金项目(51406017
51176014)
高等学校博士学科点专项科研基金项目(20104316110002)
江西省科技支撑计划项目(20151BBE50108)
河南省交通厅科研项目(2012PII10)
长沙理工大学工程车辆轻量化与可靠性技术湖南省高校重点实验室开放基金资助项目(2013kfjj02)
湖南省自然科学基金项目(13JJ4063)
湖南省教育厅高校创新平台基金项目(13K053)
