The self-excited DC air circuit breaker (SE-DCCB) has been widely used in urban rail transit due to its excellent stability. It can realize forward and reverse interruption, but has difficulty interrupting small currents due to the phenomenon of arc root sticking at the entrance of the arc chamber in the splitting process, which is known as arc root stagnation. A coupling model of the self-excited magnetic field and magnetohydrodynamics is established for the SE-DCCB with the traditional structure. The magnetic field, temperature and airflow distribution in the arc chamber are investigated with an interrupting current of 150 A. The simulation results show that the direction and magnitude of the magnetic blowout force are the dominant factors in the arc root stagnation. The local high temperature of the arc chamber due to arc root stagnation increases the obstruction effect of the airflow vortex on the arc root movement, which significantly increases the arc duration time of small current interruption. Based on the research, the structure of the magnetic conductance plate of the actual product is improved, which can improve the direction and magnitude of the magnetic blowout force at the arc root so as to restrain the development of the airflow vortex effectively and solve the problem of arc root stagnation when the small current is interrupted. The simulation results show that the circuit breaker with improved structure has a better performance for a small current interruption range from 100 A to 350 A.

To tackle the challenges of low prediction accuracy caused by single-feature modeling, and the hidden state of the neural network easily loses some information of the long time series, a method for predicting the remaining electrical life of AC contactor using a convolutional autoencoder-bidirectional gated recurrent unit-attention (CAE-BiGRU-Attention) was proposed in this work. Firstly, the feature parameters were extracted from the AC contactor full-life test, and an optimal feature subset was selected using neighborhood component analysis and Spearman rank correlation coefficient to characterize the degradation state of electrical life effectively. Then, the deep information of the optimal feature subset was extracted using CAE. Finally, the remaining electrical life of the AC contactor was treated as a long time series problem and predicted in time series by BiGRU-Attention accurately. The case analysis demonstrates that the model has better prediction accuracy than recurrent neural network (RNN), long short-term memory (LSTM), GRU, BiGRU and CAE-BiGRU models, with an average effective accuracy of 97.12%. This effectively demonstrates the model’s feasibility to accurately predict temporal sequences in the remaining electrical life prediction of electrical equipment.

AC contactors are used frequently in various low-voltage control lines, so remaining-life prediction for them can significantly improve the operational reliability of power control systems. To address the problem that the existing AC contactor remaining-life prediction methods do not make full use of the correlation between previous and later states in the degradation process, a CNN-GRU (convolutional neural network-gated recurrent unit) method for AC-contactor remaining-life prediction is proposed. Firstly, the entire cycle of an AC contactor’s degradation data is obtained through a whole-life test, from which the characteristic parameters that effectively reflect the operating states of the contactor are extracted; secondly, neighborhood component analysis (NCA) and maximal information coefficient (MIC) are used to eliminate the redundant information of multidimensional parameters in order to select the optimal feature subset; and then, CNN is used to compress the feature dimension and mine the regular information between the features, so as to extract the effective feature vectors; finally, taking the AC contactor remaining electrical life as a long time sequence issue, time-series accurate prediction is performed using GRU. It is verified that this model is better than RNN (recurrent neural network), LSTM (long short-term memory) and GRU models in prediction, with an effective accuracy of 96.63%, which effectively supports the feasibility of time-series prediction in the field of the remaining-life prediction of electrical devices.

Aiming at the problem that it is difficult to extract useful information from the contactor characteristic parameter data due to a large amount of noise interference, and it is difficult to determine the weight allocation of different characteristic parameters in the process of contactor degradation state characterisation, this paper proposes a contactor degradation state characterisation method based on the improved variational modal decomposition and the optimisation of similarity metrics with combined weights. Firstly, the CJX2-5011 model contactor is taken as the experimental object, and the full-life test is carried out to extract the contactor characteristic parameter data; Then, the sparrow search algorithm (SSA) is used to optimise the parameter settings of the variational modal decomposition, and the optimal component selection and noise reduction are completed based on the correlation determination and wavelet threshold noise reduction, which effectively extracts the useful information of the feature parameters; Secondly, The combined weights of feature parameters are constructed by Analytic Hierarchy Process (AHP) and CRITIC weighting method, which solves the problem of weight allocation of feature parameters in the process of characterising the degraded state of the contactor; Finally, the combination of weights is used to optimise the similarity measurement process and achieve a more accurate characterisation of the contactor degradation state. In the multi-characteristic parameter noise reduction process, the Noise Rejection Rate ( NRR ) and Correlation (ρ) are at least improved by 0.0592 and 0.0006. In the degraded state characterisation, the Goodness of Fit ( R ) is improved by at least 0.06723, and the Root Mean Square Error ( RMSE ) is reduced by at least 0.34689. Therefore, it can be seen that the method in this paper is able to better complete the noise reduction of the contactor characteristic parameter data, and to achieve a more accurate characterisation of the degraded state of the contactor.

The cathode sheath (CS) formation of the direct current air circuit breaker is simulated by a fluid model, and the influence of metal vapor concentration between the contacts after liquid metal bridge rupture is considered. The CS conductivity increases with the increasing concentration of copper vapor. The copper vapor concentration increases from 5% to 95%, and the thickness of the positive space charge layer and ionization layer increases from 22.3 and 49.1 μm to 51.8 and 81.7 μm, respectively. Increasing the CS conductivity is beneficial for the motion of arc roots in a certain range.