Search

Rapid and accurate battery fault diagnosis and distinction is of great importance in electrical vehicles and electrochemical energy storage system. However, misdiagnosis and missed diagnosis happened occasionally. In this paper, a statistical analysis-based multi-fault diagnosis method is proposed to detect and localize short circuit faults, electrical connection faults and voltage sensor faults in LFP battery packs. This method uses non-redundant interleaved voltage measurement topology to detect battery voltages, where every voltage sensor measures the sum of two neighboring batteries and one connection resistor between them. The statistical analysis method sets detection thresholds based on the battery operating data, and captures fault characteristics by analyzing abnormal changes in battery voltage unrelated to current. Theoretical analysis and tests verified that this method can diagnose these three kinds of faults. Sensor faults of excessive error and data sticking can also be distinguished. • The proposed method can diagnose short circuit faults, electrical connection faults and sensor faults. • The non-redundant interleaved voltage measurement topology does not require additional voltage sensors, which saves costs. • The introduction of time window avoids blocking the fault diagnosis process when a fault occurs. • Sensor faults of excessive error and data sticking can be distinguished. [ABSTRACT FROM AUTHOR]

A Convolution Neural Network and a Bidirectional Long Short-Term Memory network connected architecture with a Multi-Head Attention mechanism (CNN-BiLSTM-MHA) is studied for predicting state of charge (SOC) of lithium-ion batteries (LIBs). Firstly, an adaptive noise based complete ensemble empirical mode decomposition (AN-CEEMD) algorithm is adopted to catch the intrinsic features of measured battery signals by adding white noises. Secondly, a CNN-BiLSTM model with the MHA mechanism is developed to learn the mapping between processed input signals and battery SOC, it has three parts: 1) the CNN extracts features of the processed data, mine the relation among input signals, and promote estimation precision; 2) the BiLSTM has memory ability to catch battery dynamics, and the Swish activation function in the BiLSTM ensures unsaturated and reduces over-fitting due to its upper unbound and lower bound; 3) The multi-head attention mechanism uses several independent self-attention layers to associate input information and variables, extracts more associate information by adding weights; it reduces the overfitting risk of a single attention head, and improves the model generalization performance through joint learning of multiple heads. Finally, experiments and simulations are implemented under four operating conditions at five different temperatures, and the presented method is verified effective. • A CNN-BiLSTM network with multi-head attention (MHA) is explored to identify SOC. • The CNN extracts features of input data, and mine the relation among input signals. • The BiLSTM with feedback structure has memory ability to catch battery dynamics. • The MHA mechanism improves model performance through joint learning of multiple heads. [ABSTRACT FROM AUTHOR]