Online monitoring of the slip ring was important to ensure the normal operation of the wind turbine equipment. The current-carrying friction experiment was carried out to simulate the degradation process of the slip ring. The chaotic parameter enclosing radius and statistical parameter root mean square were used to characterize the multi-sensor signals comprehensively. A new health indicator was proposed to evaluate the degradation state of slip ring based on the long and short-term memory (LSTM) neural network. It was fused by the signals of friction vibration, friction torque, voltage and electric current. The health indicator shows a better prediction effect by the prediction model. At the severe stage of the slip ring, the evaluation criteria MAE, RMSE, and MAPE of the health indicator are 0.0055,0.0043 and 4.5470%, which are much better than the RMS of the vibration signal. The results verify that the method can effectively determine the real-time degradation state of the slip ring.