5 April 2023 in International Journal of Green Energy
Battery management systems (BMS) are crucial for electric vehicles because effective battery management is essential to their safe and reliable operation. However, BMS experience some problems like high cost, reduced space, low efficiency, and high failure rates. This paper proposes an intelligent digital twin model for the BMS which utilized the historical battery data obtained from real driving scenarios to measure, estimate, predict, and diagnose the battery pack states. The digital twin model consists of two parts, one is the state estimation based on the regression model and the second one is the fault diagnosis. The regression model between the variables of BMS is developed using a back propagation neural network (BPNN). Moreover, a whale optimization algorithm (WOA) is utilized to further optimize the parameters of the regression model. A threshold-based fault detection method is applied to diagnose the faults in the BMS. The dataset gathered from an electric vehicle with one year duration is utilized to evaluate the performance of the proposed method. Experiment results verify that the proposed model achieved over 95% prediction accuracy and can effectively diagnose the faults in the BMS.
12 February 2020 in IEEE Access
Remaining useful life (RUL) estimation is expected to provide appropriate maintenance for components or systems in industry to improve the reliability of the systems. Most data-based methods are limited to a single model, which is susceptible to various factors like environmental variability and diversity of operating conditions. In this paper, we propose an optimal stacking ensemble method combining different learning algorithms as meta-learners to mitigate the impact of multi-operating conditions. The selection of meta-learners follows a multi-objective evolutionary algorithm named non-dominated sorting genetic algorithms-II to balance the two conflicting objectives in terms of accuracy and diversity. Then the eventually evolved meta-learners are integrated by the meta-classifier for RUL estimation. In addition, a long-short-term feature extraction strategy is proposed to capture more degradation information from lifecycle data dynamically. Extensive experiments are performed on aero-engine dataset and battery dataset provided by NASA, which achieves the higher prognostic accuracy compared with the single models and existing methods.
27 July 2023 in IEEE Transactions on Industry Applications
Supercapacitors have been considered as a promising choice for public transportation electrification, e.g., catenary-free trams, as the only power source. Due to the frequent stops and drastic load changes of trams, the DC bus of supercapacitor storage systems exhibits significant voltage fluctuations, which degrades the reliable operation of trams. In this paper, we propose a predictive set point modulation control method for supercapacitors storage systems, where the reference voltage is regulated in real time based on the prediction of DC bus voltage, which can effectively suppress the voltage fluctuations. We first model the supercapacitor storage systems based on the averaging method. Then, a cascade control framework is designed to regulate the DC bus voltage. A predictive set point modulation control method is designed to suppress the voltage fluctuations without changing the closed-loop system structure. We built a laboratory hardware platform to illustrate the performance of the proposed method. Both simulation and experiment results verify that the proposed method can effectively suppress the voltage fluctuations of the DC bus when compared with classical methods.