Accurately detecting and classifying faults are essential for fault clearance and recovery of the system. One of the biggest challenges in fault diagnosis is dealing with fault class imbalances, where some fault types occur less frequently than others. The class imbalance makes the classifier prefer the majority class, which will cause the deterioration of classification performance. To solve the problem of serious class imbalances in fault natures, fault causes, and fault phases for the actual power system, this article presents a transmission line fault classification method based on the squeeze and excitation (SE)-Inception-residual network (ResNet) model with focal loss (FL). In this method, the FL is introduced to focus more on hard-to-classify faults by reducing the weight of easy-to-classify faults automatically. Also, the proposed model integrates the SE-Inception module and the SE-ResNet module, which can exploit the advantages of each to achieve better classification accuracy along with good computational efficiency due to the lighter network structure. To verify the effectiveness of the proposed method, various types of faults with unequal numbers are generated based on the 735-kV three-phase transmission line model, and three-phase signals are converted into 2-D time–frequency maps using continuous wavelet transform (CWT) for extraction of the deeper and higher level features. Experimental results show that the proposed method achieves 98.5% classification accuracy and above 92% F1-score, which indicates the improvement of classification performance in the case of serious class imbalance. Also, the effectiveness of this proposed method is verified by the real recording fault data. In addition, the comparisons with other convolutional neural networks (CNNs) and the cross-entropy (CE) demonstrate its superiority. The interpretability of the proposed networks for fault recognition is provided based on the gradient-weighted class activation mapping (Grad-CAM) visualization, and it reveals the inherent mechanism of its good classification performance from time–frequency features.

The bipolar dc microgrid is attracting attention for its high efficiency and reliability, but the bipolar dc bus is susceptible to unbalanced power. This article proposes a bipolar current-fed dc–dc converter with automatic voltage balance under phase-shift plus pulsewidth control. Combined with the current-fed dual active bridge converter and voltage balancer, the circuit structure is streamlined and fewer devices are required. The proper magnetizing inductance allows the converter to achieve automatic bipolar voltage balancing even under extreme load imbalance, and achieve full-range zero-voltage switching (ZVS) over a wide voltage range. In addition, the coupled inductor is utilized to further reduce the number of magnetic components. Finally, based on the accurate ZVS analysis considering parasitic capacitance, the parameters of the converter are designed, and an experimental prototype is constructed to verify the feasibility of the proposed scheme.

Insulated overhead conductor (IOC) faults cannot be detected by the ordinary protection devices due to the existence of the insulation layer. The failure of insulated overhead conductors is regularly accompanied by partial discharge (PD); thus, IOC faults are often judged by the PDs of insulated overhead conductors. In this paper, an intelligent PD detection model based on bidirectional long short-term memory with attention mechanism (AM-Bi-LSTM) is proposed for judging IOC faults. First, the original signals are processed using discrete wavelet transform (DWT) for de-noising, and then the signal statistical-feature and entropy-feature vectors are fused to characterize the PD signals. Finally, an AM-Bi-LSTM network is proposed for PD detection, in which the AM is able to assign the inputs different weights and highlight their effective characteristics; thus, the identification accuracy and computational complexity have been greatly improved. The validity and accuracy of the proposed model were evaluated with an ENET common dataset. The experiment results demonstrate that the AM-Bi-LSTM model exhibits a higher performance than the existing models, such as LSTM, Bi-LSTM, and AM-LSTM.

The varying-coefficient state-dependent autoregressive with exogenous inputs (SD-ARX) models are very useful in nonlinear system modeling and control. Considering that state feedback control strategy with a series of variable feedback gains provides more freedom than a constant feedback gain for the robust predictive controller design, this paper proposes a robust model predictive control (RPC) algorithm with variable feedback gains for output tracking. In the proposed method, by defining input and output increment sequences of the system, two polytopic state space models, in which the dynamic behavior of the system is wrapped, are constructed. Then, based on the polytopic state space models, an RPC with variable feedback gains for output tracking is designed. To further reduce the conservatism, the parameter-dependent Lyapunov functions are constructed for the design of the variable feedback gains in the control strategy. The proposed RPC can expand the feasible region of the robust controller and improve the control performance. The simulation on a continuous stirred tank reactor verified the feasibility and efficacy of the proposed method.

Interturn short-circuit (ITSC) is one of the most common faults in permanent magnet synchronous machines (PMSMs), but most ITSC diagnosis methods are only validated under steady operating conditions. In practice, the commanded speed or commanded torque of PMSM drive system need to be changed frequently to meet some special demands. When PMSMs run under variable operating conditions (especially transient operating conditions), the abrupt changes of speed or torque introduce extra harmonics in machine currents and voltages, which may lead to unexpected fault alarms and financial losses. This article establishes the dynamic response models of the current and voltage of closed-loop PMSM drive based on the system transfer functions, and the dynamic responses of the current and voltage under variable operating conditions can be obtained. Based on these models, an ITSC diagnosis method is proposed to compensate for the harmonic transient spikes in the current and voltage due to the abrupt changes in machine speed and load torque, thereby reducing the possibility of ITSC misdiagnosis. Experimental tests are carried out on a PMSM with ITSC to verify the proposed method, and the results show that the method can accurately detect ITSC faults and avoid fault misdiagnosis.