A proper and effective maintenance and replacement schedule help to restore power equipment health condition, increase cost efficiency, and reduce the failure risk of the power grid. Imperfect maintenances cannot restore the equipment to a “as good as new” state as replacement did, but the financial cost of maintenance is much lower than that of replacement. The optimal balance and coordination between imperfect maintenances and replacements leads to the optimal substation operational cost. In this paper, a risk-based optimization model for power substation equipment maintenance and replacement scheduling is proposed in the presence of imperfect maintenances for the aging power equipment. The degradation process is firstly established based on historical trending analysis of failure data. Afterwards, a virtual age model is proposed for each equipment and the imperfect maintenance effectiveness is represented by the rejuvenation of this virtual age. Eventually, equipment failure risk, maintenance risk, and replacement risk are obtained, which are then incorporated into a MILP problem to obtain the optimal scheduling results. Case studies are performed on substations with three different bus-bar layout schemes. Results shows that the proposed method achieves a 34% lower total risk and 12.1% higher cost efficiency, compared to the traditional maintenance strategies.

The state of transformer equipment is usually manifested through a variety of information. The characteristic information will change with different types of equipment defects/faults, location, severity, and other factors. For transformer operating state prediction and fault warning, the key influencing factors of the transformer panorama information are analyzed. The degree of relative deterioration is used to characterize the deterioration of the transformer state. The membership relationship between the relative deterioration degree of each indicator and the transformer state is obtained through fuzzy processing. Through the long short-term memory (LSTM) network, the evolution of the transformer status is extracted, and a data-driven state prediction model is constructed to realize preliminary warning of a potential fault of the equipment. Through the LSTM network, the quantitative index and qualitative index are organically combined in order to perceive the corresponding relationship between the characteristic parameters and the operating state of the transformer. The results of different time-scale prediction cases show that the proposed method can effectively predict the operation status of power transformers and accurately reflect their status.

Recognition of partial discharge (PD) patterns in gas insulated switchgear (GIS), as a basis of fault diagnosis, provides essential information for the condition assessment of GIS. However, traditional recognition methods are limited to handcrafted feature extraction or are extremely sensitive to the quantity and quality of datasets. Therefore, this article proposes a knowledge-driven algorithm, composed of the feature space and the knowledge space, to automatically extract PD features and improve the performance on noised, insufficient, and imbalanced datasets. First, the deep residual network (ResNet) in feature space extracts features from raw signals. Second, in knowledge space, the graph convolutional network (GCN) extracts additional information from the knowledge graph, which compensates for the missing information of original datasets. Finally, the algorithm recognizes patterns by ranking similarities between feature vectors and knowledge vectors. Verified by the comparison experiment, the proposed algorithm outperforms traditional methods with the accuracy of 99.58% on the experimental dataset and 95.67% on the online-detected dataset. Moreover, the accuracy of the proposed algorithm achieves 88.79% and 70.37% on noised and insufficient datasets, respectively, while the F-measure is higher than those of the comparison methods by 12.95% $\sim$ 18.69% on imbalanced datasets.

It is of great significance to accurately get the running state of power transformers and timely detect the existence of potential transformer faults. This paper presents a prediction method of transformer running state based on LSTM_DBN network. Firstly, based on the trend of gas concentration in transformer oil, a long short-term memory (LSTM) model is established to predict the future characteristic gas concentration. Then, the accuracy and influencing factors of the LSTM model are analyzed with examples. The deep belief network (DBN) model is used to establish the transformer operation using the information in the transformer fault case library. The accuracy of state classification is higher than the support vector machine (SVM) and back-propagation neural network (BPNN). Finally, combined with the actual transformer data collected from the State Grid Corporation of China, the LSTM_DBN model is used to predict the transformer state. The results show that the method has higher prediction accuracy and can analyze potential faults.

Gas insulated switchgear (GIS) in service may tolerate large temperature changes, which leads to uncertainty in the evaluation of the partial discharge (PD) signal. To clarify the influence of temperature on the discharge signals of GIS insulation void defects, this paper proposes a multiscale fusion simulation method and used experiments to verify it. This method combines the streamer simulation at the micro level and the circuit simulation model at the macro level, and a more accurate simulation signal of GIS insulation void PDs under the influence of temperature can be obtained. Experiments have also been carried out, and a PDs detection experiment platform that can be set in different temperature environments was built. The discharge signals at different temperatures were obtained follow IEC60270. Finally, by combining analyses of simulation and experimental data, the law of the influence of temperature on the PD signal of GIS insulation voids was summarized, and the mechanism of the influence was analyzed. The results showed that the multiscale fusion simulation method of GIS insulation void PD signals proposed in this paper is consistent with the experimental results, which can provide a reference for the digital twin model of power equipment status.