基于RBF神经网络的船用柴油机NOx排放的预测  

Prediction of NOx Emissions from Marine Diesel Engine Based on RBF Neural Network

作　　者：李孟杰[1] 黄加亮[1,2] 

机构地区：[1]集美大学轮机工程学院,福建厦门361021 [2]福建省船舶与海洋工程重点实验室,福建厦门361021

出　　处：《集美大学学报（自然科学版）》2016年第2期136-139,共4页Journal of Jimei University：Natural Science

基　　金：福建省自然科学基金资助项目(2012J01230);福建省科技厅资助省属高校专项(JK2013025)

摘　　要：依据4190Z_LC-2型船用四冲程增压柴油机实际试验测得的数据,利用MATLAB中的神经网络工具箱,建立了基于径向基函数神经网络(RBF)的柴油机氮氧化物(NOx)排放浓度的预测模型。在预测模型建立过程中选取柴油机油耗率(SFOC)、功率、转速等参数数值作为输入矩阵,柴油机的氮氧化物排放浓度作为输出矩阵。仿真结果表明:该方法预测精度高,可为控制氮氧化物的排放提供依据。Based on the actual experimental data of type 4190ZLC-2 supercharged four-stroke marine diesel engine, the prediction model is established by using neural network toolbox of MATLAB, which is a- bout the concentration of nitrogen oxides （NOx） emissions of radial basis function neural network （RBF）. In the experimental data, the fuel consumption rate （SFOC） , power, speed are chosen as the input matrix and NOx emission concentration of diesel engine is used as the output matrix. Simulation results show that RBF neural network has high prediction accuracy and it can be a very good model for prediction NOx emission con- centration of marine diesel engine. The most important is that it can provide a basis for controlling the emis- sion of nitrogen oxide.

关 键 词：4190ZLC-2型船用柴油机 径向基函数神经网络 氮氧化物排放 预测模型 

分 类 号：U664.121[交通运输工程—船舶及航道工程] TK421[交通运输工程—船舶与海洋工程]