Aging precursor identification is crucial to achieving online condition monitoring and estimating the remaining lifetime of an insulated gate bipolar transistor (IGBT). However, existing failure precursors are limited with respect to in situ monitoring. In this paper, the duration of Miller plateau during the IGBT turn-on transition is proposed as an online precursor indicating two dominant types of failures. Based on the theoretical closed-form expressions, the adverse effects of package-related bond wire fatigue and chip-related gate oxide degradation on the Miller plateau duration are explained in detail. By a dedicated online measurement system implemented on the gate driver side, the proposed precursor is extracted during operation. Discrete IGBTs of two gate structures are employed during the accelerated aging tests. Negative and positive degradation trends of the Miller plateau duration under power cycling and high electric field stress, respectively, are revealed, thus illustrating the validity of the proposed method. Finally, the main differences in physics-of-failure between two types of aged devices are investigated using post-failure analysis. The innovation of applying the Miller plateau duration as a failure precursor involves its ability to accomplish real-time field monitoring and its sensitivity to multiple failure mechanisms.

Intelligent fault diagnosis methods, especially convolutional neural network (CNN), have made significant progress in gas-insulated switchgear (GIS) partial discharge (PD) diagnosis, which are attributable to two reasons: 1) the training and testing samples come from the identical distribution; 2) there are massive labeled data with PD information. However, owing to the specific operating conditions of GIS, collecting massive samples from the same distribution is difficult in field conditions. With the purpose of resolving the data dilemma of conventional diagnosis methods in the field, we propose a domain adaptive deep transfer learning (DADTL) CNN for small samples GIS PD diagnosis. First, we adopted a CNN to automatically extract transferable features from PD samples. Then, a multilayer DADTL is developed to reduce the marginal and conditional distribution of learned transferable features, and Sliced Wasserstein distance (SWD) is employed as a penalty to reduce the negative migration. The experimental verification was performed on experimental and on-site GIS PD datasets. The results show that DADTL CNN can effectively achieve a high-accuracy diagnosis of GIS PD for small samples. Compared with other methods, the DADTL CNN can achieve more accurate and robust GIS PD diagnosis for on-site small samples.

Data-driven artificial intelligence methods, especially convolutional neural networks (CNNs), have achieved excellent performance in high-voltage circuit breaker (HVCB) fault diagnosis. However, CNN relies heavily on massive data. When the amount of data decreases, the fault diagnosis performance drops severely. To settle these problems, a few-shot transfer learning (FSTL) with attention mechanism (AM) to realize the mechanical fault diagnosis of HVCBs is proposed. First, a one-dimensional CNN with AM is used to extract the fault features of HVCBs. The introduction of the AM makes CNN pay more attention to the interesting part of the fault signal to extract discriminative features. Then, domain adaptive transfer learning is used to realize a reliable diagnosis of HVCBs in small samples.The subdomain adaptation is adopted to adjust the distribution of related subdomains under the same category. The proposed subdomain adaptation can not only align the global distribution well but also effectively align the distribution of the same category of subdomains. Experimental results show that the FSTL proposed can achieve highly accurate and robust fault diagnosis of HVCBs with few-shot on-site. Compared with the traditional methods, the FSTL is obvious and provides a reliable reference for the diagnosis of HVCBs.

Condition assessment for gas-insulated switchgear (GIS), which are crucial component of power systems, involves three interrelated aspects, i.e., partial discharge (PD) diagnosis, localization, and severity assessment. However, existing methods for GIS PD condition assessment perform these aspects as separate tasks, ignoring the mutual influence among them and leading to inferior performance. To settle the abovementioned issue, we propose a multitask learning network (MTLN) for GIS PD condition assessment. First, a multitask network was developed, taking severity assessment as the main task and diagnosis and localization as parallel auxiliary tasks. This model not only facilitates the extraction of the coupling relationship between diagnosis and localization but also furnishes pertinent feature information for severity assessment. Second, to deploy the developed model to label-free scenarios on-site, a novel subdomain adaptation is established. The process of subdomain adaptation considers the alignment of both intraclass and interclass information, incorporating a secondary filtering mechanism to mitigate the issue of feature mismatch caused by incorrect pseudo labels. Experimental results show that the proposed MTLN not only offers diagnosis and location information for severity assessment but also facilitates the exploration of the coupling relationship between diagnosis and localization, thereby enhancing the performance of GIS PD condition assessment.

The coordination of resistive-type superconducting fault current limiters (R-SFCLs) and DC circuit breakers (DCCBs) have been investigated. However, the use of R-SFCLs with mechanical DCCBs (M-DCCBs) in hybrid transmission systems has not been studied. The objective of this paper is to investigate the parameter requirements of R-SFCLs and M-DCCBs for a detailed system protection strategy in a hybrid AC/DC system considering the influence of AC faults and three types of DC faults. When the AC fault is far from all MMCs, its impact on the DC system is weak. If the AC fault is close to one MMC, it will produce a strong transient response in the DC part. Therefore, a bypass switch in parallel with an R-SFCL is used to remove the R-SFCL from the system if it quenches during the AC fault. Then, the parameters of the protection devices are designed based on pole-to-pole DC fault. System restoration can be achieved within 200 ms after the fault. For pole-to-neutral and pole-to-ground faults, except for the R-SFCLs at the faulty pole, the R-SFCLs at the healthy pole will also quench, but the resistances are very low. The system may be restored within 250 ms after the DC fault.

Researchers have investigated the interruption properties of CO2 gas, including CO2 and O2 mixed gas. However, there has been no research on the passive resonance DC interrupting characteristics of CO2/O2 mixed gas. The objective of this paper is to learn the passive resonance DC interrupting properties of CO2/O2 mixed gas with superconducting fault current-limiting technology. A proposed passive resonance DCCB that includes a superconducting current-limiting module (SCLM) and a DC interrupting module (DCIM) connected in series was tested for DC voltages of 1.3, 3 and 10 kV and DC currents from 50 A to 10 kA. The experimental results show that the DCCB could successfully interrupt a 10 kA current in a 10 kV DC system. The response time of the DCCB was only 0.3 ms. After interruption, there was no overvoltage. The arcing time and the arc voltage of the SF6 gas and the CO2/O2 mixed gas were also compared experimentally. Experimental results show that CO2/O2 mixed gas may be a good substitute for the SF6 gas in passive resonance interruption. The CO2/O2 mixed gas passive resonance DCCB combined with the SCLM is an effective way to interrupt high short-circuit fault currents in medium-voltage and high-voltage DC systems.