Abstract: Lithium-ion batteries are being extensively used as the energy storage element to store and transform the electric energy. Nevertheless, its state of charge (SOC) and state of health (SOH) can not be directly measured. To address this problem, the correlation between SOC and SOH was analyzed and a SOC and SOH joint estimation method based on deep learning was proposed. In detail, the SOC and SOH can be estimated simultaneously in the whole life cycle of lithium-ion batteries by voltages, currents and temperatures of lithium-ion batteries based on recurrent neural network with gated recurrent unit (GRU-RNN) and convolutional neural network (CNN). Considering the estimated SOH during SOC estimation, the proposed method can eliminate the effects of aging to the SOC estimation, which can improve the accuracy of estimated SOC. The experimental results on two lithium-ion battery test datasets show that the proposed joint estimation method can realize the SOC and SOH joint estimation with high accuracy in the whole life cycle of lithium-ion batteries at different temperatures and working conditions.