Search Results

Approximately 50% energy is consumed during the acceleration of a city bus. Fuel consumption during acceleration is significantly affected by driving behavior. In this study, 13 characteristic parameters were selected to describe driving style based on analysis of how driving influences fuel consumption during acceleration. The 100,000 km real-world vehicle running data of six drivers on three city buses in a particular bus line in Tianjin, China were sampled using a vehicle-on-line data logger. Based on the selected characteristic parameters and collected driving data, an evaluation model of the fuel consumption level of a driver was established by adopting the method of decision tree C4.5. For two-level classification, the model has over 85% prediction accuracy. The model also has the advantages of having a few training samples and strong generalization. As an example of the model application, the fuel-saving potential of a driver under optimal operations was analyzed.

Although excellent progress has been made recently in powertrain fault diagnosis based on vibration signals, most of them are based on the assumption that the fault features of the training and test data are drawn from the same probability distribution. Due to the limitation of the domain shift phenomenon, the performance of the current intelligent fault diagnosis methods is significantly reduced. Even many existing transfer learning methods have the problem of low generalization ability. Inspired by sparse representation theory, a novel cross-domain fault diagnosis method based on K-means singular value decomposition (K-SVD) and long short-term memory network (LSTM) is proposed in this study. First, K-SVD can convert source domain data into a sparse dictionary and sparse coefficient. The domain-invariant features are explored in the sparse dictionary, which contains redundant features. The sparse coefficients are input into the LSTM to obtain a primary classifier.

P2 hybrid electric vehicle is the single-motor parallel configuration integrating with an engine disconnect clutch (EDC) between the engine and the motor. The key point with P2 hybrid electric vehicle is to start the engine utilizing the single driving motor while still propelling the vehicle, which requires an appropriate engine-start control strategy and a high mechanical performance of EDC. Since the space for EDC is limited, EDC torque response is difficult to follow the torque command, which complicates the issue of precisely controlling the clutch. Consequently, methods proposed in massive papers are inappropriate for current EDC of target vehicle. Considering that slip control of shifting clutch also contributes to reducing impact of engine start assisted by EDC, a detailed engine-start control strategy was proposed to simplify the control of EDC for being applied to actual target vehicle.