A Study of Vehicle Driving Condition Recognition Using Supervised Learning Methods

• Published in: IEEE transactions on transportation electrification Vol. 8; no. 2; pp. 1665 - 1673
• Main Authors: Xu, Bin, Shi, Junzhe, Li, Sixu, Li, Huayi
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.06.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Algorithms; Artificial intelligence; Driving conditions; Driving cycle; Energy efficiency; Fuel consumption; Fuel economy; Hybrid electric vehicles; Machine learning; Neural networks; Pattern recognition; Propulsion; Propulsion systems; Road transportation; Supervised learning; Target recognition; Teaching methods; Temperature sensors; Training data; vehicle propulsion system control
• ISSN: 2332-7782; 2577-4212; 2332-7782
• DOI: 10.1109/TTE.2021.3127194

In vehicle operation, in order to maximize the fuel economy, the propulsion system control can easily adapt to pressure and temperature variations as these variations can be measured by sensors. However, it is challenging to detect driving cycles. With growing progress made in the artificial intelligence field, pattern recognition gains momentum in various applications. This study presents a study on driving cycle pattern recognition based on supervised learning. Training data 2-D visualization is achieved by the t-distributed stochastic neighbor embedding (t-SNE) algorithm. Ten out of 12 supervised learning algorithms predict driving conditions with an accuracy of 88% or higher, and the extra tree (ET) algorithm leads the recognition accuracy at 90.26%. To improve the recognition accuracy, two hierarchical frameworks are proposed by integrating multiple supervised learning methods using weighted average and vote methods. The two hierarchical frameworks boost the driving condition recognition accuracy from 90.26% to 90.43% (weighted average) and 91.76% (vote). The results are further validated in the holdout test. In addition, a plug-in hybrid electric vehicle simulation shows 3.88%-5.82% fuel economy improvement compared to the baseline method. Two hierarchical methods outperform the ET method by 2% fuel economy. In summary, supervised learning shows great potential to detect driving cycles for vehicle energy saving.