摘要
传统的基于MAP图查表方式得到柴油机NOx排放的方法需要做大量标定实验,本文采用BP神经网络构建柴油机NOx排放预测模型.论文选取进气压力、进气温度、排气温度和发动机转速这4个量作为预测模型的输入量.考虑到柴油机NOx生成与其工作参数之间有时间迟滞,模型的输入量包含当前值和历史值.对输入数据做了归一化处理,在模型后处理模块对输出数据做反归一化处理.所提出的模型具有较高的预测精度.
The traditional method based on MAP which gets diesel engine NOx emission needs a lot of calibration experiments, this paper adopts BP neural network to build the predictive model of diesel engine NOx emission. Four parameters including intake pressure, intake temperature, exhaust temperature and engine speed are selected as inputs of the predictive model. Considering diesel engine NOx emission to have lag between the working parameters, the history and current value of those parameters put into the model. Dealing with the inputting parameters by normalization and the output data by reversing normalization in the post-processing module of model have been done. The result of calibration shows the model has satisfying prediction accuracy.
出处
《天津理工大学学报》
2009年第3期5-9,共5页
Journal of Tianjin University of Technology
基金
国家863项目(2006AA060304)