Lithium-ion battery packs are widely deployed as power sources in transportation electrification solutions. To ensure safe and reliable operation of battery packs, it is of critical importance to monitor operation status and diagnose the running faults in a timely manner. This study investigates a novel fault diagnosis and abnormality detection method for battery packs of electric scooters based on statistical distribution of operation data that are stored in the cloud monitoring platform. According to the battery current and scooter speed, the operation states of electric scooters are clarified, and the diagnosis coefficient is determined based on the Gaussian distribution to highlight the parameter variation in each state. On this basis, the K-means clustering algorithm, the Z-score method and 3σ screening approach are exploited to detect and locate the abnormal cells.By analyzing the abnormalities hidden beneath the external measurement and calculating the fault frequency of each cell in pack, the proposed algorithm can identify the faulty type and locate the faulty cell in a timely manner. Experimental results validate that the proposed method can accurately diagnose faults and monitor the status of battery packs. This theoretical study with practical implications shows the promising research direction of combining data mining technologies with machine learning methods for fault diagnosis and safety management of complex dynamical systems.

No abstract

No abstract

Summary Accurate state of health (SOH) prediction is significant to guarantee operation safety and avoid latent failures of lithium-ion batteries. With the development of communication and artificial intelligence technologies, a body of researches have been performed toward precise and reliable SOH prediction method based on machine learning (ML) techniques. In this paper, the conception of SOH is defined, and the state-of-the-art prediction methods are classified based on their primary implementation procedure. As an essential step in ML-based SOH algorithms, the health feature extraction methods reported in the literature are comprehensively surveyed. Next, an exhausted comparison is conducted to elaborate the development of ML-based SOH prediction techniques. Not only their advantages and disadvantages of the application in SOH prediction are reviewed but also their accuracy and execution process are fully discussed. Finally, pivotal challenges and corresponding research directions are provided for more reliable and high-fidelity SOH prediction.

Accurate estimation of state of charge (SOC) of lithium-ion battery packs remains challenging due to inconsistencies among battery cells. To achieve precise SOC estimation of battery packs, firstly, a long short-term memory (LSTM) recurrent neural network (RNN)-based model is constructed to characterize the battery electrical performance, and a rolling learning method is proposed to update the model parameters for improving the model accuracy. Then, an improved square root-cubature Kalman filter (SRCKF) is designed together with the multi-innovation technique to estimate battery cell's SOC. Next, to cope with inconsistencies among battery cells, the SOC estimation value from the maximum and minimum cells are combined with a smoothing method to estimate the pack SOC. The robustness and accuracy of the proposed battery model and cell SOC estimation method are verified by exerting the experimental validation under time-varying temperature conditions. Finally, real operation data are collected from an electric-scooter (ES) monitoring platform to further validate the generalization of the designed pack SOC estimation algorithm. The experimental results manifest that the SOC estimation error can be limited within 2% after convergence.