High−precision and robust localization is critical for intelligent vehicle and transportation systems, while the sensor signal loss or variance could dramatically affect the localization performance. The vehicle localization problem in an environment with Global Navigation Satellite System (GNSS) signal errors is investigated in this study. The error state Kalman filtering (ESKF) and Rauch–Tung–Striebel (RTS) smoother are integrated using the data from Inertial Measurement Unit (IMU) and GNSS sensors. A segmented RTS smoothing algorithm is proposed in order to estimate the error state, which is typically close to zero and mostly linear, which allows more accurate linearization and improved state estimation accuracy. The proposed algorithm is evaluated using simulated GNSS signals with and without signal errors. The simulation results demonstrate its superior accuracy and stability for state estimation. The designed ESKF algorithm yielded an approximate 3% improvement in long straight line and turning scenarios compared to classical EKF algorithm. Additionally, the ESKF−RTS algorithm exhibited a 10% increase in the localization accuracy compared to the ESKF algorithm. In the double turning scenarios, the ESKF algorithm resulted in an improvement of about 50% in comparison to the EKF algorithm, while the ESKF−RTS algorithm improved by about 50% compared to the ESKF algorithm. These results indicated that the proposed ESKF−RTS algorithm is more robust and provides more accurate localization.

Hydro-pneumatic suspension (HPS) systems are increasingly being implemented in commercial vehicles and various industrial equipment, which is mainly attributed to the integration of adaptable nonlinear pneumatic stiffness and hydraulic damping properties. The integrated HPS design with a shared gas-oil chamber, however, leads to gas-oil emulsion flow within the suspension chambers, which intricately affects the internal and external properties of the HPS, especially under variations in temperature and excitation frequency. This study experimentally and analytically investigated the temperature- and frequency-dependent properties of the hydro-pneumatic suspension with the gas-oil emulsion. Laboratory experiments were performed under three different near-constant temperatures (30, 40, and 50 °C) in the 0.5–8 Hz frequency range. An analytical model of the HPS was formulated considering the effects of temperature on internal fluid properties, gas-oil emulsion flow between the coupled chambers, the dynamic seal friction, and polytropic change in the gas state. The internal parameters, including the gas volume fraction, the discharge coefficient of the emulsion, and the dynamic friction components, as well as the external stiffness and damping characteristics, were determined. The relationships between these properties and the system temperature, velocity, and excitation frequency were further investigated. The simulated responses obtained under different excitations showed reasonably good agreement with the experimental results of the HPS. The results suggested that increased temperature yielded greater equivalent stiffness and comparable damping properties of the system. The gas volume fraction, discharge coefficient, and magnitude of seal friction generally tended to increase with increasing temperature. Increased excitation frequency led to greater hysteresis in hydraulic damping force and seal friction, and reduced seal friction magnitude and Stribeck effect.

A frequently large variation in load conditions is of great impact on the service life of fuel cells during the operation of fuel cell vehicles and further increases the maintenance cost of the system. This study proposed a method of power demand prediction of the proton exchange membrane fuel cell (PEMFC) on vehicles in the actual traffic environment. The hybrid power system topology of fuel cells and power battery on commercial vehicles is selected to build a fuel cell model, and the accuracy of the fuel cell model is verified. An improved multiple grey prediction method is then proposed to predict the power demand during the sampling period of the fuel cell while considering a dynamic time window in the prediction period. Comparisons were made between this proposed model and the other two prediction models as a single-step prediction and multi-step prediction. Data of CHTC-HT and field testing working conditions were used to evaluate these three prediction models in fuel cell power demand. Results showed that the multiple grey method showed a better prediction performance than the other models, indicated by the lowest error value of 16.944% under the CHTC-HT condition, the lowest error value of 2.169% under stable conditions with less variable load and 1.930% under dynamic conditions with frequent load changes in field testing. This study of the demand power prediction can be devoted to pre-tuning the fuel cell system to avoid performance degradation caused by unanticipated power fluctuation.

Predicting the remaining useful life (RUL) of proton exchange membrane fuel cells (PEMFCs) is central to their prognostics and health management. Accurate and reliable RUL prediction facilitates improvement in the durability of PEMFCs. To fully leverage the advantages of both mechanismbased models and data-driven methods while mitigating the impact of measurement noise on RUL prediction, this paper proposes a hybrid adaptive RUL prediction method based on mechanismguided feature selection and inverted Transformer (iTransformer) network. Firstly, by analyzingthe polarization processes within the stack, the polarization model is reconstructed and refined. Selecting feature data from the improved polarization model enhances the interpretability of feature selection. Subsequently, by incorporating the variable embedding strategy and structurally modified Transformer, the capability to capture multivariate correlations is enhanced, enabling multi-step prediction of voltage degradation. Finally, the sliding-window pointwise adaptive algorithm (SWPAA) is designed to perform adaptive filtering and extend the signal boundary based on the volatility ofpredicted decay voltage, which reduces the impact of severe fluctuations in the measured voltage on RUL prediction and achieves robust interval prediction of RUL. Compared with the bidirectional long short-term memory, echo state network, unscented Kalman filter, and Transformer prediction models, iTransformer demonstrated the highest accuracy in both time-series voltage prediction and RUL prediction. Furthermore, the robust RUL interval obtained via SWPAA further enhances theprecision and reliability of RUL prediction.