基于TCN-GRU-GAT的数字孪生锂离子电池SOH估计方法OA

To achieve accurate and dynamic estimation of the state of health(SOH)of lithium-ion batteries throughout their entire life cycle and ensure their safe and stable operation,a digital twin-based SOH estimation method for lithium-ion batteries using TCN-GRU-GAT was proposed.Firstly,a digital twin estimation structure system coupling five layers of physics,perception,trans-mission,analysis,and service was designed,and a data analysis layer integrating TCN-GRU-GAT network and digital twin technology was constructed.Then,health feature parameters were ex-tracted from battery charge and discharge data,with highly correlated feature values set as graph nodes and feature value connections as edges to build a graph structure.Time-domain convolu-tional network(TCN)and recurrent neural network(GRU)were used to extract temporal features,and graph attention network(GAT)was used to extract spatial features,to estimate the SOH of lithium-ion batteries considering spatial-temporal correlations.Finally,the proposed lithium-ion battery SOH estimation method was simulated and analyzed using measured data.The results show that the proposed method can effectively improve the estimation accuracy of SOH.