LAUSR

Driving cycles construction, which aims to generate various vehicle driving profiles corresponding to typical traffic conditions, plays an important role in the evaluation of vehicle emissions, economy and mileage. Existing methods usually represent the speed-time distributions of driving data in the space spanned by hand-crafted features, and select typical sequences to combine driving cycle curves. However, since the driving data is treated as static, the inherent dynamic characteristics and temporal dependency tend to be ignored, resulting in low accuracy and insufficient robustness. To address this issue, this paper proposes a dynamic driving cycle construction framework, in which feature extraction and sequence clusters are achieved in an unsupervised joint learning manner. Specifically, the driving data are firstly encoded by a Bi-directional Long Short-Term Memory (BiLSTM) branch to capture the temporal correlation property of driving sequences. Then, a temporal clustering branch is presented to achieve soft distribution clustering of feature sequences by introducing a relative-entropy-based regularization term into the coding unit. The two branches are iteratively updated until stable feature learning and clustering results are obtained. Consequently, each branch benefits from the additional improvement over the previous branch during the iteration process. Finally, typical driving sequences are selected according to the intra-class/extra-class distance and class proportion, and then assembled to generate driving cycles profiles. To verify the performance of our proposed method, evaluations are performed on the on-road driving data of light vehicles in Fuzhou, in which the constructed driving cycle from our methods is substituted into COPERT model to estimate and visualize the road emissions, and the experimental results demonstrate that our proposed methods can greatly improve the accuracy and robustness of the constructed driving cycle.