Recently, numerous data‐driven fault diagnosis methods have been developed, and the tasks involving the same distribution of training and test data have been well solved. However, considering the particularity of gas‐insulated switchgear (GIS), collecting massive data, especially with the same distribution, is difficult. Therefore, existing fault diagnosis methods hardly achieve satisfactory insulation defect diagnosis with small datasets. Aiming at solving this problem, a novel domain adversarial transfer convolutional neural network (DATCNN) is proposed, realising the diagnosis of GIS insulation defects on small samples. First, a residual CNN is built to learn feature representations from the source and target domains. Second, the domain adversarial training strategy is used for feature transfer, where a conditional adversarial mechanism is introduced, and the joint distribution of features and labels is improved to a random linear combination, which realises the simultaneous adaptation of features and labels. Finally, the Nesterov accelerated gradient descent optimisation algorithm is used to speed up the gradient convergence. DATCNN has 99.15% and ≥89.5% diagnosis accuracy for GIS insulation defects in the laboratory and on‐site, respectively. Comprehensive experiment results show the effectiveness and superiority of the proposed method in diagnosing GIS insulation defects with small samples.

One of the crucial challenges of the distribution network is the unintentionally isolated section of electricity from the power network, called unintentional islanding. Unintentional islanding detection is severed when the local generation is equal to or closely matches the load requirement. In this paper, both ensemble learning and canonical methods are implemented for the islanding detection technique of synchronous machine‐based distributed generation. The ensemble learning models for this study are random forest (RF) and Ada boost, while the canonical methods are multi‐layer perceptron (MLP), decision tree (DT), and support vector machine (SVM). The training and testing parameters for this technique are the total harmonic distortion (THD) of both current and voltage signals. THD is the most important parameter of power quality monitoring under islanding scenarios. The parameter and data extraction from the test system is executed in a MATLAB/Simulink environment, whereas the training and testing of the presented techniques are implemented in Python. Performance indices such as accuracy, precision, recall, and F 1 score are used for evaluation, and both ensemble learning models and canonical models demonstrate good performance. Ada‐boost shows the highest accuracy among all the five models with original data, while RF is robust and gives the best results with noisy data (20 and 30 dB) because of its ensemble nature.

Fault analysis is an essential prerequisite for fault detection, location andisolation. A detailed fault analysis method on the steady state of the pole‐to‐pole fault forvoltage source converter (VSC) based DC systems is presented in this paper. According to faultcharacteristics under different transition resistances (TRs), the steady‐state response is dividedinto three scenarios: low transition resistance with blocked converter (LTRBC), medium transitionresistance with blocked converter (MTRBC) and high transition resistance with unblocked converter(HTRUC). When TR is relatively low, fault currents through insulated gate bipolar transistors(IGBTs) are large and the converter is blocked. After an in‐depth study of freewheel diodes’conduction states, the iterative method is utilized to solve the steady state under blockedconverter. When TR is relatively high, fault currents through IGBTs are not large enough to blockthe converter. With the unblocked converter, control strategy and pulse width modulation (PWM) areinvestigated to obtain steady‐state fault currents. Finally, a reasonable simulation model was builtin PSCAD/EMTDC software. The simulation results verified the fault analysis accuracy, with much lesscalculation error than that of the conventional method. Besides, the proposed analysis method wasproved applicable to fault scenarios under different TRs.

Online experimental systems that include remote and virtual experiments based on the Internet has become a new form of experiment in engineering education. This paper proposes a virtual experiment for the complex process control system. It is based on the networked control system laboratory (NCSLab), which provides a reliable framework for virtual thermal experiment. Taking the combustion system of 1000 MW ultra‐supercritical coal‐fired once‐through boiler‐turbine units as an example, the framework and the implementation process of the online system are given in this paper. A new presentation form for complex processes control experiment is provided, which could be a solution for simulating physical experimental equipment in virtual environments. The potential danger in practical experiments could be avoided. Additionally, the real‐time operation for complex control systems could be presented in a 3D scene. Meanwhile, the flexibility and efficiency could be increased in engineering experimental education. Moreover, using the experiment evaluation method, the references and feedback for teaching and assessment are provided in this paper.

Demand response (DR) is an effective load management method. To attract customers to participate, DR policies need to both satisfy customers' individual DR habits and be economically profitable. However, customers’ individual DR habits are hard to be formulated with few hypotheses when other objectives are simultaneously considered. To tackle this challenge, a novel DR behavioural learning method is proposed. We learn customers’ DR habits by an inverse reinforcement learning (IRL) method to reduce the subjectivity in DR model formulation. Meanwhile, in contrast to traditional learning‐based methods, the proposed method can adapt to multiple DR objectives more than just following customers’ DR habits, like obtaining higher economic revenues. Additionally, we consider the diversity and changes of customer DR behaviour patterns and offer an enhancement for the proposed DR behavioural learning method via building a DR pattern clustering and inference module. The proposed method can work with customer‐side energy storage systems to diversify the DR policies and make the DR behaviours more flexible. Case studies show the proposed method can reduce about 10–20% behavioural learning deviations than the compared model‐based methods, while daily charges of the proposed method can be further reduced by over 4% than the compared supervised‐learning‐based methods.