Grid Fault Diagnosis Research Articles

ESG guidance and artificial intelligence support for power systems analytics in the energy industry.

In order to increase the precision and effectiveness of power system analysis and fault diagnosis, this study aims to assess the power systems in the energy sector while utilizing artificial intelligence (AI) and environmental social governance (ESG). First, the ESG framework is presented in this study to fully account for the effects of the power system on the environment, society, and governance. Second, to coordinate the operation of various components and guarantee the balance and security of the power system, the CNN-BiLSTM power load demand forecasting model is built by merging convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM). Lastly, the particle swarm optimization (PSO) algorithm is used to introduce and optimize the deep belief network (DBN), and a power grid fault diagnostic model is implemented using the PSO technique and DBN. The model's performance is assessed through experimentation. The outcomes demonstrate how the CNN-BiLSTM algorithm significantly increases forecasting accuracy while overcoming the drawback of just having one dimension of power load data. The values of 0.054, 0.076, and 0.102, respectively, are the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Effective processing of large-scale nonlinear data is achieved in the area of power grid fault diagnosis, resulting in prediction accuracy of 96.22% and prediction time of only 129.94s. This is clearly better than other algorithms and increases fault prediction efficiency and accuracy. Consequently, the model presented in this study not only produces impressive results in fault diagnosis and load demand forecasting, but also advances the field of power system analysis in the energy industry and offers a significant amount of support for the sustainable and intelligent growth of the energy industry.

An enhanced semi-supervised learning method with self-supervised and adaptive threshold for fault detection and classification in urban power grids

With the rapid development of urban power grids and the large-scale integration of renewable energy, traditional power grid fault diagnosis techniques struggle to address the complexities of diagnosing faults in intricate power grid systems. Although artificial intelligence technologies offer new solutions for power grid fault diagnosis, the difficulty in acquiring labeled grid data limits the development of AI technologies in this area. In response to these challenges, this study proposes a semi-supervised learning framework with self-supervised and adaptive threshold (SAT-SSL) for fault detection and classification in power grids. Compared to other methods, our method reduces the dependence on labeling data while maintaining high recognition accuracy. First, we utilize frequency domain analysis on power grid data to filter abnormal events, then classify and label these events based on visual features, to creating a power grid dataset. Subsequently, we employ the Yule–Walker algorithm extract features from the power grid data. Then we construct a semi-supervised learning framework, incorporating self-supervised loss and dynamic threshold to enhance information extraction capabilities and adaptability across different scenarios of the model. Finally, the power grid dataset along with two benchmark datasets are used to validate the model’s functionality. The results indicate that our model achieves a low error rate across various scenarios and different amounts of labels. In power grid dataset, When retaining just 5% of the labels, the error rate is only 6.15%, which proves that this method can achieve accurate grid fault detection and classification with a limited amount of labeled data.

A grid fault diagnosis framework based on adaptive integrated decomposition and cross-modal attention fusion

In large-scale power systems, accurately detecting and diagnosing the type of faults when they occur in the grid is a challenging problem. The classification performance of most existing grid fault diagnosis methods depends on the richness and reliability of the data, in addition, it is difficult to obtain sufficient feature information from unimodal circuit signals. To address these issues, we propose a deep residual convolutional neural network (DRCNN)-based framework for grid fault diagnosis. First, we design a comprehensive information entropy value (CIEV) evaluation metric that combines fuzzy entropy (FuzEn) and mutual approximation entropy (MutEn) to integrate multiple decomposition subsequences. Then, DRCNN and heterogeneous graph transformer (HGT) are constructed for extracting multimodal features and considering modal variability. In addition, to obtain the implicit information of multimodal features and control the degree of their performance, we propose to incorporate the cross-modal attention fusion (CMAF) mechanism in the synthesis framework. We validate the proposed method on the three-phase transmission line dataset and VSB power line dataset with accuracies of 99.4 % and 99.0 %, respectively. The proposed method also achieves superior performance compared to classical and state-of-the-art methods.

Enhancing Resilience: Smart Grid Cybersecurity and Fault Diagnosis Strategies

The increasing integration of advanced technologies within the power grid infrastructure has led to significant advancements in efficiency, reliability, and sustainability. However, this integration also introduces new vulnerabilities, particularly in the realm of cybersecurity. This paper presents an overview of smart grid cybersecurity challenges and proposes strategies for enhancing resilience through fault diagnosis techniques. Firstly, the paper examines the evolving threat landscape facing smart grids, encompassing cyber-attacks, insider threats, and natural disasters. It highlights the critical need for robust cybersecurity measures to safeguard grid operations and prevent potentially catastrophic disruptions. Next, the paper delves into various cybersecurity frameworks and standards tailored specifically for smart grids, emphasizing the importance of comprehensive risk assessment, intrusion detection systems, and secure communication protocols. Additionally, it discusses the role of machine learning and artificial intelligence in augmenting cyber defense capabilities, enabling proactive threat detection and rapid response. Furthermore, the paper explores fault diagnosis strategies aimed at maintaining grid resilience in the face of cyber incidents or physical faults. It discusses the integration of data analytics, predictive modeling, and real-time monitoring to identify and mitigate potential grid disturbances swiftly.

Research on data-driven model for power grid fault diagnosis fusing topological quantification information

In increasingly complex power grid operation scenarios and fault modes, rapid and accurate fault identification is highly important for improving the reliability of power systems. Faced with the massive amount of available power grid data, the rapid development of artificial intelligence technology provides a powerful tool for power grid fault diagnosis. However, existing data-driven diagnosis methods lack quantitative power grid topology change representations, cannot integrate power grid fault topology with alarm information, and have limited effectiveness in terms of diagnosing complex faults. To address these issues, a data-driven power grid fault diagnosis model that integrates topological quantitative features is proposed. By studying the changes in the topological connection relationships of equipment before and after a power grid fault and the topological connectivity in a power failure zone, based on the basic topological network indicators in graph theory, a representation of the quantitative features of the power grid fault topology is achieved, and these quantitative features and the alarm information are integrated to construct a data-driven power grid fault diagnosis model. The model uses the light gradient boosting machine algorithm to determine the types of complex faults and accurately identify faulty equipment, addressing the lack of model diagnosis effects considered in previous studies. Finally, the accuracy and effectiveness of the model are verified by using simulated fault cases.

Research on Hazard Analysis and Control Strategy of Power System Dispatching Operation Based on Information Fusion Technology

Abstract In this paper, a decision model for grid fault diagnosis based on multi-source information fusion is established, and the probability of component fault is obtained by using the change of switching quantity characteristic information and electrical quantity characteristic information during grid fault, and the static fault degree obtained by switching quantity information and the voltage and current energy distortion degree and fault degree obtained by electrical quantity information is used as independent evidence bodies, which are fused by improved D-S evidence fusion technique, and the fused The results are decided by improved fuzzy C-mean decision model to finally determine the fault components. Then, the optimal control of the grid is studied, and the corresponding self-healing control model is established according to the different operating conditions of the system so as to propose a self-healing control strategy of the microgrid based on the improved particle swarm algorithm. After analysis and verification, the accuracy of the grid fault diagnosis method proposed in this paper reaches 0.9681, and the diagnosis results are consistent with the pre-defined fault elements compared with FCM. The system network loss decreases from 0.146 kW to 0.031 kW, and the maximum power supply capacity increases from 1.574 to 2.468 after using the improved particle swarm algorithm-based microgrid self-healing control strategy. Therefore, the method in this paper can improve the reliability of grid operation and resist the risk of accidents.

Research on Power Grid Fault Diagnosis Based on a Quantitative Representation of Alarm Information

Power grid operation is trending toward digitalization and intelligence, and data-driven power grid fault diagnosis has become a realistic demand for smart grid dispatching. At present, power grid fault diagnosis is based on text content analysis and alarm information feature extraction. With a lack of models and methods for alarm information quantitative representation, current models cannot adapt to complex and changeable engineering field practices. Based on quantity and time series distribution characteristics of alarm information during faults, this paper proposes a quantitative representation method for alarm information and uses the quantified alarm information as classification features. The classification algorithm is used to obtain the classification results based on a power grid fault diagnosis framework. A fault diagnosis strategy is designed to integrate fault classification and faulty device discrimination model results, and fault types and faulty devices are determined. Finally, the simulation system-generated fault cases and actual fault cases collected by a power grid are used to verify the calculation example. The experiments and model comparisons show that the method, with advantages of simple modeling, stronger practicability and better diagnosis accuracy than previous methods, can handle different forms of alarm information and perform power grid fault diagnosis based on the data.

Power Transformer Fault Diagnosis Based on Improved BP Neural Network

Power transformers are complex and extremely important piece of electrical equipment in a power system, playing an important role in changing voltage and transmitting electricity. Its operational status directly affects the stability and safety of power grids, and once a fault occurs, it may lead to significant economic losses and social impacts. The traditional detection methods rely on the technical level of power system operation and maintenance personnel, and are based on Dissolved Gas Analysis (DGA) technology, which analyzes the components of dissolved gases in transformer oil for preliminary fault diagnosis. However, with the increasing accuracy and intelligence requirements for transformer fault diagnosis in power grids, the DGA analysis method is no longer able to meet the requirements. Therefore, this article proposes an improved transformer fault diagnosis method based on a residual BP neural network. This method deepens the BP neural network by stacking multiple residual network modules, and fuses and expands gas feature information through an improved BP neural network. In the improved residual BP neural network, SVM is introduced to judge the extracted feature vectors at each layer, screen out feature vectors with high accuracy, and increase their weights. The feature vector with the highest cumulative weight is selected as an input for transformer fault diagnosis. This method utilizes multi-layer neural network mapping to extract gas feature information with more significant feature differences after fusion expansion, thereby effectively improving diagnostic accuracy. The experimental results show that, compared with traditional BP neural network methods, the proposed algorithm has higher accuracy in transformer fault diagnosis, with an accuracy rate of 92%, which can ensure the sustainable, normal, and safe operation of power grids.

Power Grid Fault Diagnosis Method Based on Inception Network

With the continuous evolution of grid intelligence, the traditional grid fault diagnosis model can not satisfied the development needs of smart grid in terms of accuracy and diagnosis speed, and how to apply the fault information provided by the supervisory control and data acquisition (SCADA) system to achieve fast and accurate grid fault diagnosis is the main problem at present. In this paper, we propose an Inception network-based fault diagnosis method, in which the alarm information of different fault types is filtered and transformed into a grayscale map as model input to avoid the interference of redundant alarm information to the fault diagnosis, and the Inception network with excellent image feature extraction capability is employed to obtain the grayscale map of the alarm information to achieve fast fault diagnosis. This method has been proven to have excellent fault-type discriminatory capability and is effective in achieving fast and accurate fault diagnosis based on deep learning algorithms.

Research on online monitoring of grid current transformer based on transformers and BiGRU

Transformers play a crucial role in ensuring the safety of power grids. It is of great value to diagnose faults using the large amount of power data generated by the grid. It is possible to detect internal latent faults in transformers in advance of their occurrence if the normal operating condition of the transformer is detected in a timely manner. To perform online fault diagnosis of grid current transformers, we combine the Transformer and BiGRU methods. There is a temporal component to the fault input sample sequences. By using Transformer’s multi-headed attention mechanism to extract deep features from fault input sample sequences, the temporal association between latent variables can be fully exploited. As a result of the extraction of features, BiGRU is used to generate fault category coding as an output. The experimental results indicate that using the proposed algorithm achieves better results than using a single model, which is useful for the study and application of fault diagnosis in power grids for current transformers.

A Power Grid Fault Diagnosis Method Considering Online Dynamic Alarm Information

With the continuous development of the smart grid and the gradual improvement of the demand for grid reliability and power grid self-healing capability, a large number of artificial intelligence technologies have been applied to the power grid. In order to improve the automation of the power grid, realize automatic fault identification and diagnosis after a power grid failure, and improve the efficiency of fault handling by the dispatching department, it is of great practical significance to use alarm information to achieve accurate fault judgment. However, the difference between the dynamic reading of alarm information flow and static samples in engineering applications is often ignored in the research of fault diagnosis using alarm information, which makes it difficult to apply fault diagnosis methods in engineering practice. Based on the characteristics of the LSTM algorithm, such as deep knowledge extraction ability, data mining ability and time series knowledge processing ability, this paper studies the power grid fault diagnosis method based on LSTM to adapt to the data of each sampling time window in the process of online fault diagnosis, solves the problems faced by the application of traditional diagnosis methods in engineering practice, and effectively improves the reliability of fault diagnosis.

Research on the distribution mechanism of fault alarm information for power grid fault diagnosis

Power grid fault diagnosis aims to locate faulty components quickly and accurately. The alarm information generated by the SCADA system of the grid is the data basis for power grid fault diagnosis. The existing research lacks mechanical analysis of the alarm information, so the models and algorithms are difficult to be used in engineering applications. The established power grid fault diagnosis models are somewhat different from the actual grid, and the alarm information timing characteristics are difficult to express. In this paper, we analyze the correlation and characteristics of the data related to the number of voltages, number of stations, and duration of faults for each period, and analyze the spatial and temporal distribution mechanism of the alarm messages in conjunction with the characteristics of the equipment that issued the alarm messages during the fault events. It also compares the differences in the distribution patterns of the alarm information when the data sources are different. The research can lay the foundation for establishing fault diagnosis models and provide theoretical support for model design and algorithm research.

Power Grid Fault Diagnosis Method Based on LightGBM

With access to distributed power generation and interconnection between regions, China’s power system structure is becoming increasingly complex, and the requirements for power grid dispatching capacity are getting higher and higher. When the power grid fails, a large amount of alarm information appears in the monitoring window, which needs to be processed and classified first to speed up the fault diagnosis and processing. Therefore, this paper proposes a power grid fault diagnosis method based on LightGBM. First, after pre-processing the power grid alarm information, Word2vec is used to vectorize the text, and then the LightGBM model is used to process the text, extract the information features and continue to train. Finally, realizing the three classifications of such simple faults as the transformer fault, bus fault, and line fault. Finally, through the test and verification of the actual power grid case data, it is verified that the method can effectively classify simple faults and meet the needs of the actual power grid online diagnosis.

A Grid Fault Diagnosis Method Based on Stacking Algorithm

Power grid dispatching is developing towards digitalization and intellectualization. Using the data generated in power grid operations to diagnose faults through artificial intelligence technology directly has become the development trend of the power grid. However, traditional machine learning algorithms often need help to achieve good diagnostic results in practical applications. Therefore, a fusion model based on the Stacking integration algorithm is proposed, and four commonly used machine learning algorithms are selected for fusion. Furthermore, the model is trained using the fault alarm information features extracted from the SCADA system. Then, by comparing and analyzing the diagnostic effect of four single algorithms and the Stacking model for various fault types, the conclusion that the Stacking model has a better overall effect than other algorithms in the diagnosis of various fault types is obtained, and the advantage of the stacking fusion algorithm is proved.

Improvement of power transformer fault diagnosis by using sequential Kalman filter sensor fusion

Power transformers are one of the most important and costly equipment for the reliability and continuity of electrical power systems. For this reason, continuous monitoring of power transformers during normal operating conditions of the power grid and early fault diagnosis from existing parameters before a fault occurs is an important task. One of the most common analysis is the Dissolved Gas Analysis (DGA) method. In the DGA analysis, the concentrations of gases formed in the transformer insulating fluid are measured, classified and used to predict failures. It is observed that the classification and diagnosis are performed by classical and artificial intelligence-based methods in the relevant literature and applications. In this study, gas data classified by machine learning method is combined with sensor fusion methods to increase the diagnosis accuracy. It has been determined that the Sequential Kalman filter, which is first used differently from the literature, increases the estimation accuracy over 90% according to the results obtained by the Majority Voting and Dempster Shafer Evidence Theory fusion methods and the other results with IEC-TC-10 dataset mentioned in the literature.

Distribution grid fault diagnosis based on fault indicator and random matrix

The analysis and utilization of massive recording data of distribution grid fault indicator is beneficial to improve the effect of distribution grid fault diagnosis. In this paper, the distribution grid monitoring are realized by the random matrix theory (RMT) of high dimensional statistical analysis. The fault diagnosis method based on RMT has the advantages of no need for detailed distribution grid topology, comprehensive utilization of wide-area spatiotemporal data, and observation from a muti-dimensional view. By explaining the application principle of limit spectrum distribution function, the linear eigenvalue statistics (LES) is proposed as the state monitoring index. Distribution grid fault diagnosis based on fault indicator and RMT provides a new data-driven method for distribution grid fault diagnosis while efficiently utilizing massive fault indicator data.

A novel fault diagnosis method for power grid based on graph Fourier transform

The fast and robust identification of fault elements is essential for the security and continuous operation of the power grid. The existing methods might be maloperation for bad data disturbance and require strict and exact synchronization. To address the challenge, this paper uses the conflict graph to propose a new sensitivity graph signal model for the power grid fault diagnosis. Next, a novel graph Fourier transform (GFT)-based method is proposed to diagnose the fault branch. Firstly, the measurement sensitivity graph signals are constructed by the conflict graph model, where the data is from activated recorders and protection devices. Next, the eigenvalue and GFT coefficient are used to extract the frequency characteristics of the signals. The fault branches provide the maximum contribution rate to the high-frequency coefficient of GFT. Then, for each node, the importance degree of the measurement sensitivity conflict graph signal is defined. The high-frequency importance degree-based method is proposed to discriminate the fault branch. Finally, simulations and practical cases verify the correctness and effectiveness of the proposed method. The proposed method owns fast faults diagnosis and good practicability. Additionally, the identification accuracy is high and the method is robust to bad data interference, due to considering measured data from whole activated fault recorders and protection devices.

Application of knowledge graph in smart grid fault diagnosis

Abstract The stability and high quality of electricity are the basic factors which ensure that the residents and enterprises lead a happy and productive life. Therefore, in order to meet the requirements of residents’ life and enterprise production, it is necessary to improve the efficiency and accuracy of power grid fault diagnosis. In this paper, the knowledge graph is integrated into the power grid fault diagnosis, and the fault diagnosis system of the knowledge graph is constructed to realise the fault diagnosis of the power grid. The article first completes the knowledge graph construction through knowledge extraction, knowledge fusion and knowledge processing; then, it completes the construction of the fault scheduling knowledge graph through power grid equipment fault records, entity attribute extraction, coreference resolution, relation extraction, relation screening and data integration; finally, combined with the fault information knowledge analysis technology, it builds a power grid fault diagnosis system using a knowledge graph. Experiments show that using the system to diagnose the fault quantity, fault location and fault analysis information of the pilot power grid not only has ideal efficiency but also has high accuracy.

Power grid fault diagnosis model based on the time series density distribution of warning information

Fast and intelligent power grid fault diagnosis is a key means of improving the intelligence level of power grid dispatching. Currently, data-driven power grid fault diagnosis lacks a method to quantify the time series characteristics of alarm information, and it is difficult to build a deep learning model. This paper proposes a power grid fault diagnosis method based on the time series density distribution of alarm information. First, the alarm information is classified; quantized time sequence feature extraction is performed for the device, and the obtained quantized time sequence features are superimposed. After graphical coding, a time series density distribution map of the alarm information of each device and a mosaic map reflecting the overall fault event are generated, providing a unified data representation for the deep learning model. Then, a faulty equipment type classification model and equipment state judgment model are constructed based on a residual network. The faulty equipment and fault type are determined using a sequential evaluation strategy that first determines the type of faulty equipment and then determines the state of the equipment. The proposed method can meet the requirements of on-line fault diagnosis of a power grid and provide emergency decision support for dispatchers.

Power System Fault Diagnosis Method Based on Deep Reinforcement Learning

Intelligent power grid fault diagnosis is of great significance for speeding up fault processing and improving fault diagnosis efficiency. However, most of the current fault diagnosis methods focus on rule diagnosis, relying on expert experience and logical rules to build a diagnosis model, and lack the ability to automatically extract fault knowledge. For switch refusal events, it is difficult to determine a refusal switch without network topology. In order to realize the non-operating switch identification without network topology, this paper proposes a power grid fault diagnosis method based on deep reinforcement learning for alarm information text. Taking the single alarm information of the non-switch refusal sample as the research object, through the self-learning ability of deep reinforcement learning, it learns the topology connection relationship and action logic relationship between equipment, protection and circuit breakers contained in the alarm information, and realizes the detection of fault events. The correct prediction of the fault removal process after the occurrence, based on this, determines the refusal switch when the switch refuses to operate during the fault removal process. The calculation example results show that the proposed method can effectively diagnose the refusal switch of the switch refusal event, which is feasible and effective.