基于HPO-LSTM的柴油机NOx拟预测技术研究

潘恒斌; 官维; 潘明章; 梁科; 文涛; 姜淑君

车用发动机 ›› 2024, Vol. 0 ›› Issue (1) : 67-75.

栏目

基于HPO-LSTM的柴油机NO_x拟预测技术研究

潘恒斌¹，官维¹，潘明章¹，梁科¹，文涛¹，姜淑君²

作者信息 +

NO_x Virtual Prediction Technology of Diesel Engine Based on HPO-LSTM

PAN Hengbin¹,GUAN Wei¹,PAN Mingzhang¹,LIANG Ke¹,WEN Tao¹,JIANG Shujun²

Author information +

文章历史 +

摘要

在严格的排放法规面前，柴油机后处理系统发挥了不可估量的作用，而获取NO_x排放是后处理系统中SCR装置得以正常工作的前提之一。建立一种使用猎人猎物优化（HPO）算法优化长短期记忆（LSTM）网络的虚拟预测模型，实现对柴油机NO_x排放准确预测，以代替现有物理传感器或作为并行装置监控其运行。试验在柴油机测功机上进行，在高度瞬态的柴油机运行周期内，输入了若干种便于获取且与NO_x形成密切相关的参数至模型中，结果表明：该优化后的网络应用于测试集和全新的未知瞬态工况时，与未优化网络的预测结果相比，RMSE分别提高了29.1%和23.4%，R²分别大于和接近0.95，预测结果与传感器测量值呈现高度相同的变化趋势，满足了车载运用和准确性的需求，验证了该方法的可行性。

Abstract

In the face of strict emission regulations, the diesel engine posttreatment system plays an immeasurable role, and the acquisition of NOx emissions is one of the prerequisites for the normal operation of SCR device in the posttreatment system. A virtual prediction model that used hunterprey optimization(HPO) algorithm to optimize long short term memory(LSTM) network was established to accurately predict NO_x emissions of diesel engine in place of existing physical sensors or as a parallel device to monitor their operation. The test was carried out on a dynamometer of diesel engine. During the highly transient operation cycle of diesel engine, several parameters that were easy to obtain and closely related to NO_x formation were input into the model. The results show that, compared with the prediction results of nonoptimized network, RMSE increases by 29.1% and 23.4%， and R² is greater than and close to 0.95 respectively when the optimized network is applied to the test set or to a new unknown transient condition. The prediction results show a highly identical trend with the measured values of sensor, which meets the requirements of onboard application and accuracy and hence verifies the feasibility of this method.

导出引用

潘恒斌，官维，潘明章，梁科，文涛，姜淑君. 基于HPO-LSTM的柴油机NO_x拟预测技术研究[J]. 车用发动机. 2024, 0(1): 67-75

PAN Hengbin,GUAN Wei,PAN Mingzhang,LIANG Ke,WEN Tao,JIANG Shujun. NO_x Virtual Prediction Technology of Diesel Engine Based on HPO-LSTM[J]. Vehicle Engine. 2024, 0(1): 67-75