Fractional-Order GRU Networks With Memory Units Based on Hausdorff Difference for SOC Estimations of Lithium-Ion Batteries

The gated recurrent unit (GRU) networks are widely used in engineering applications due to the excellent performance. But, the flexibility of the proportion of update information to reset information is weak in GRU networks. To tackle this issue, this article proposes a fractional-order GRU (FOGRU) with a memory unit for the state of charge (SOC) estimation of lithium-ion batteries (LIBs). First, the Hausdorff difference is introduced into the GRU network to gain the fractional-order memory unit. Then, the range of the order is rigorously analyzed to ensure the convergence of the improved structure in the FOGRU network, and the adjustment rule of orders in the FOGRU network is to adaptively tune the FOGRU network. Finally, the experiment results show that the FOGRU network achieves a satisfactory effect in the SOC estimation of LIBs.