论文部分内容阅读
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.
In order to improve the real-time performance of air-fuel ratio control system of gasoline engine and the accuracy of intake air flow measurement, a BP neural network prediction model of intake air flow chaotic time series of gasoline engine is proposed. The phase space reconstruction technique is used to reconstruct the intake air flow time series , Restoring the original chaos of the system, and then using the BP network to train and predict the reconstructed data to achieve the purpose of improving the accuracy of the intake air flow prediction, so as to improve the real-time performance and accuracy of the air-fuel ratio control system of the gasoline engine. The simulation results show that the BP neural network prediction model with chaotic time sequence has higher prediction accuracy and provides a completely new method for accurately and timely predicting the intake flow of the gasoline engine.