Prediction of cold start emissions for hybrid electric vehicles based on genetic algorithms and neural networks

• Published in: Journal of cleaner production Vol. 420; p. 138403
• Main Authors: Tang, Dong, Zhang, Zhen, Hua, Lun, Pan, Jinchong, Xiao, Yang
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 25.09.2023
• Subjects: algorithms; carbon dioxide; carbon monoxide; cold; Cold start; cost effectiveness; Emission; energy; Genetic algorithm; Hybrid electric vehicle; Neural networks; nitrogen; particulates; pollutants; prediction; statistics; temperature; vehicles (equipment); Emission; Hybrid electric vehicle; Neural networks; Genetic algorithm; Cold start
• ISSN: 0959-6526; 1879-1786
• DOI: 10.1016/j.jclepro.2023.138403

The emission of hybrid electric vehicles deteriorates during cold start, and it is a cost-effective method to reduce pollutant emissions during cold start of hybrid electric vehicles through energy management strategies. The development of energy management strategies for hybrid electric vehicle requires an accurate cold-start emissions model. However, traditional cold-start emission models based on statistics and experience are difficult to achieve satisfactory prediction accuracy, and require a lot of experimental cost and time. The use of neural networks for cold start emission prediction of hybrid electric vehicles has been widely used because of its low cost and high prediction accuracy. In this paper, the genetic algorithm is used to optimize the weights and thresholds of the neural network, and a neural network cold-start emission prediction model for hybrid electric vehicles is built. We trained the neural network using the high temperature (40 °C), normal temperature (23 °C) and low temperature (−20 °C) cold start data of hybrid vehicles obtained in the World Light Vehicle Test Code (WLTC), studied the cold start prediction results under the different cold start temperature, studied the cold start prediction results under the different input parameters, studied the cold start prediction results of the neural network optimized by the genetic algorithm. Under different input parameters and cold start temperature, the GA-BP algorithm can accurately predict the emissions of carbon monoxide (CO), carbon dioxide (CO2), hydrocarbons (THC), nitrogen oxides (NOx) and particulate matter number (PN) under hybrid electric vehicles.