Remote NO_x emission prediction model based on LSTM neural network

¹ School of mechanical and electrical engineering and vehicle engineering, East China Jiaotong University, Nanchang 330100, China
² School of automotive engineering, Wuhan University of technology, Wuhan 430070, China
³ Power transmission development department, Jiangling Automobile Co., Ltd., Nanchang 330100, China

^* Corresponding author: wtt31@126.com

Abstract

Test results from many researchers show that NO_x emission from many on-broad heavy-duty diesel vehicles is higher than which been registered. Therefore, CN_VI emission regulations clearly proposes that the heavy-duty diesel vehicles should be supervised by a T-BOX which can transmit CAN message from vehicle OBD interface to the remote monitoring platform. Based on the formation mechanism of NO_x emission and the variety of OBD data flow, the LSTM (Long Short-Term Memory) neural network model inputs such as engine speed, torque, atmospheric pressure, coolant temperature, fuel consumption rate and intake air mass flow are selected by using partial least square method (PLS). 19877 groups of data from engine test results were used for model training and verification, the root mean square error of training and test are R_TR = 29.7 × 10^-6 and R_TE = 19.9 × 10^-6,with a high prediction accuracy which can fully meet the requirements of the SCR system DeNO_x performance diagnosis module in the OBD remote monitoring system.