With the widespread use of electric vehicles today, limited driving range is noted as one of the main technical factors affecting the acceptance of electric vehicles. Real-time and accurate driving range predictions help drivers plan their journeys and ease their mileage anxiety, thereby increasing their acceptance and confidence in using electric vehicles. Therefore, it is important to improve the prediction accuracy of driving range to provide reliable information for users of pure electric vehicles. Unfortunately, driving range is difficult to predict due to many uncertainties. Driving style, road conditions or traffic conditions are some of them. Moreover, most of the current methods for predicting driving range have the problem of requiring many preconditions and poor accuracy. Based on an electric bus data, this paper proposes a method to predict the driving range from data related to the battery itself using Digital Twin technology. The method digs deeply into the relationship between variables such as SOC, battery unit voltage and driving range, and combines KNN algorithm and Sliding Window algorithm to achieve the prediction of electric vehicle driving range from the pure data perspective. The accuracy of this method is already adequate for the actual working conditions and is complementary to the current status quo.
Digital-Twin-Driven Driving Range Prediction of Electric Vehicles
Lect. Notes Electrical Eng.
International Conference on Image, Vision and Intelligent Systems ; 2022 ; Jinan, China August 15, 2022 - August 17, 2022
Proceedings of International Conference on Image, Vision and Intelligent Systems 2022 (ICIVIS 2022) ; Kapitel : 79 ; 793-801
29.03.2023
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Digital Twin-Based Remaining Driving Range Prediction for Connected Electric Vehicles
SAE Technical Papers | 2023
|Dynamic driving range prediction for electric vehicles
Europäisches Patentamt | 2021
|Energy-Optimal Driving Range Prediction for Electric Vehicles
British Library Conference Proceedings | 2017
|