The abnormality detection of lithium-ion battery pack is crucial to ensure the safety of electric vehicles (EVs). However, the dynamic and complex operating conditions of EVs making it challenging for algorithms. ••The proposed method is based on unsupervised learning, avoiding the. EVs Electric vehiclesANN Artificial neural networkAE. Transportation electrification has been considered as a promising solution to environmental problems and has experienced rapid growth in recent years, leading to a glob. In practice, data acquisition during a thermal runaway is almost impossible, meaning that only few samples can be collected for algorithm design. Consequently, tr. 3.1. Data acquisitionTo incorporate real-world EV charging profiles, in this work, datasets from the National Bigdata Alliance Open Laboratory of NEVs (NBAOL.
[PDF Version]
Can a faulty battery system be detected and diagnosed accurately?
The above analysis proves that even the slight voltage abnormities of battery system during vehicular operation can be detected and diagnosed accurately by the method proposed in this work. Moreover, this method can achieve voltage fault diagnosis in advance when the voltage of the faulty cell still within the normal range.
How to diagnose a battery overvoltage & undervoltage fault?
Threshold-based fault diagnosis methods The battery overvoltage or undervoltage fault can be diagnosed using the threshold-based method. The voltage information collected by the voltage sensor is compared with the preset threshold. When the battery voltage exceeds the threshold, the fault occurrence state and fault occurrence time are defined .
Can a battery model be used to detect voltage anomalies?
Future studies can investigate extensions of the model to diagnose specific types of voltage anomalies, enhancing fault detection capabilities. Additionally, exploring the model's adaptability for voltage prediction in other battery systems can also be considered.
Is there a fault diagnosis method for electric vehicle power batteries?
Wang et al. proposed a fault diagnosis method for electric vehicle power batteries based on improved radial basis function (RBF) neural networks.
How to detect battery voltage abnormities during vehicular operation?
Based on the properly thresholds, the battery voltage abnormities during vehicular operation can be detected and diagnosed through accurate voltage prediction. During driving, acceleration, deceleration, braking and stopping occur alternately, and accordingly, the battery energy output and energy recovery switch frequently.
Unchecked faults would have great impacts on battery, or even lead to battery thermal runaway under extreme conditions . It has been shown that voltage abnormity always implies one or more faults in battery, such as internal short circuit (ISC), electrode structure fault, and so forth .