Prediction of full-path operating conditions based on the characteristics of the driving environment

ABSTRACT

The prediction of driving conditions is an important basis for the energy management systems of new energy vehicles. Accurate predictions of driving conditions can help reduce the use of on-board energies such as gasoline and electricity, and improve the efficiency of energy use. Aiming at the limitations of existing driving condition prediction, this paper proposes a full-path driving condition prediction based on driving environment characteristics. BP neural network optimized by GA algorithm is used to establish a prediction model of driving condition characteristic parameters based on driving environment characteristics, and use road traffic environment information to predict driving condition characteristic parameters. And use the predicted characteristic parameters to perform fuzzy matching to predict the type of driving conditions of the vehicle for a period of time in the future. In this paper, some roads in Nanjing are used as an example to verify the prediction model. The results show that the prediction accuracy has reached 94.18%. When it is applied to energy consumption prediction, the prediction error is only 5.82%. This method provides a more accurate and reliable driving condition prediction method for new energy vehicles, which is conducive to the design of more reliable and efficient energy management strategies.

KEYWORDS:

• Driving condition characteristics
• driving characteristics
• person-vehicle-road data
• GA-BP algorithm
• pre-construction of vehicle driving conditions

Highlights

• Fully consider the influence of the driving environment on driving conditions, and quantify the influence.

• The BP algorithm optimized by GA is applied to the prediction of the characteristic parameters of the driving conditions.

• Fuzzy pattern recognition is applied to driving condition type matching.

• Apply the predicted driving conditions to the prediction of vehicle driving energy consumption

Acknowledgments

This work was supported by Natural Science Foundation of Jiangsu Province (Grant No. BK20181295).

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the Natural Science Foundation of Jiangsu Province [BK20181295].

Notes on contributors

Yufang Li

Yufang Li was born in Shandong, China, in 1976. She received the Ph.D. degree in vehicle engineering from the Beijing Institute of Technol ogy, China, in 2007. Since 2013, she has been an Associate Professor with the Nanjing University of Aeronautics and Astronautics. From 2015 to 2016, she was a Visiting Research Scientist with University of Michigan, Ann Arbor, MI, USA. Her research interests include intelligent energy man agement, hybrid vehicles, and vehicle dynamics.

Kai Lu

Kai Lu was born in Jiangsu, China, in 1995. He received the B.S. degree in automobile service engineering from the Nanjing Institute of Technology, in 2019. He is currently pursuing the master’s degree in vehicle engineering with the Nanjing University of Aeronautics and Astro nautics. His research interest includes the prediction of vehicle driving conditions based on big data and artificial intelligence algorithm.

Xuefeng Dong

Xuefeng Dong was born in Chongqing, China, in 1997. He received the B.S. degree in vehicle engineering from the Nanjing University of Aeronautics and Astronautics, in 2016, where he is currently pursuing the master’s degree in vehicle engineering. His research interest includes the prediction-based optimization of multi-level intelligent energy management for PHEVs.