Power grid fault diagnosis technology based on improved deep Q-network model

With the increase of energy demand, the scale of power grid is expanding, and the difficulty of power grid fault diagnosis is increasing. Aiming at the problem of large power grid fault diagnosis, a method of partition fault diagnosis based on improved Probabilistic neural network (PNN) and gray relational analysis (GRA) integral is proposed. Firstly, the large power grid divided into small areas for fault diagnosis through power grid partition, which reduces the difficulty of fault diagnosis. Then the PNN diagnosis module is established by the PNN optimized by GA‐CPSO for diagnosing the power grid fault. Finally, the faults in the overlapping area are reanalyzed by the GRA method, in order to realize the accurate fault diagnosis of the whole power grid. The feasibility and effectiveness of the method are analyzed by two cases. The diagnosis results show that the method can effectively identify the faults in the nonoverlapping area and the overlapping area, and has strong fault tolerance and high diagnosis accuracy. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

With the rapid development of smart grid technology, more and more attention has been paid to the stability of the power grid. When the power grid fails, the dispatch center will receive various types of data, including the PMU data collected by the PMU (Power Management Unit) device used by the Wide Area Monitoring System (WAMS) and the data collected by the Supervisory Control System for Data Acquisition and Control (SCADA). Alarm information data, they describe the same grid fault from different dimensions. At present, the power grid fault diagnosis based on PMU data and alarm information texts has been fully studied, but the information source is single, and it is difficult to ensure the accuracy of the diagnosis results when complex faults and multiple faults occur in the power grid. This paper starts with the information source of power grid fault diagnosis and develops a power grid fault diagnosis method that integrates the dual data sources of PMU and alarm information: 1. effectively connect alarm message text and PMU based on fault events. 2. complete the fusion of PMU and alarm information to improve the scope and accuracy of power grid fault diagnosis. Finally, the simulation fault data is used to test. The experimental results show that the accuracy of fault diagnosis of dual data source fusion is higher than that of single data.

The increasing demand on electrical power consumption all over the world makes the need for stable and reliable electrical power grids is indispensable. Meanwhile, power grid fault diagnosis based on fault recording data is an important technology to ensure the normal operation of the power grid. Despite the fact that dozens of studies have been put forward to detect electrical faults, these studies still suffer from several downsides, such as fuzzy characteristics of complex fault samples with small inter-class differences and large intra-class differences in different topology structures of distribution networks. To tackle the above issues, this work proposes a power grid fault diagnosis method based on an improved Synchrosqueezing Wavelet Transform (SWT) and ConvNeXt-v2 network (named PGFDSC). Firstly, PGFDSC extracts fault features from the fault recording data with an improved SWT method, and outputs the vector signal to enhance the instantaneous frequency. Then, PGFDSC inputs the extracted feature vectors into the improved ConvNeXt-v2 network for power grid faults recognition. The improved ConvNeXt-v2 network is a self-supervised learning model with the advantages of fast speed and high accuracy, which can effectively solve the problem of inaccurate judgment caused by the high dimensionality of data samples. Finally, extensive experiments were conducted and the experimental results show that PGFDSC improves the accuracy of fault diagnosis by two percentage points compared to other baseline models.

According to the fault alarm information, the power grid faults are classified into three categories: simple fault, complex single fault and complex multiple fault, and the corresponding diagnosis models will be established to reduce the redundant operation in diagnosis. For the complex multiple faults, the existing probabilistic Petri nets are improved as follows: (1) Introduced the "non-logic" relation in the probabilistic Petri net; (2) the transition ignition function of the probabilistic Petri net is improved; (3) The input arc weights are analyzed to find more suitable for improving the probability Petri net. Three typical fault examples of Siping power grid in Jilin province are used to simulate and test the diagnosis method in this paper. The simulation results show that this method reduces the unnecessary modeling process and diagnosis time for simple fault diagnosis, gives correct diagnosis results under incomplete information, and improves the diagnosis efficiency and accuracy of complex multiple faults.

This paper proposes a method to improve the weight of Particle swarm optimization (PSO) by using similarity, so as to realize the fast and accurate diagnosis of power grid fault. First, a mathematical model of power grid fault diagnosis is established by analyzing the circuit breaker, equipment protection and action information in the power grid. Next, the model is transformed into a 0-1 integer programming problem. Last, the traditional PSO algorithm is improved, so that the inertia weight in the algorithm can be adjusted dynamically according to the concept of similarity. Simulation results show that the improved PSO greatly increases the convergence speed and efficiency of power grid fault diagnosis.

With the development of artificial intelligence (AI) and digital technology, power grid fault diagnosis methods have been significantly improved in new power systems. This article conducts in-depth research on the application of AI in power grid fault diagnosis, and adopts a comprehensive approach of multiple intelligent diagnostic technologies to improve the intelligence level of analysis and diagnosis. The new digital technology system of the power system provides a continuous “digital body”, and AI injects an “intelligent soul” that can learn, analyze, and make decisions. The deep integration of the two has led to the construction of a power grid fault diagnosis model and a continuous “data-driven” digital mainline, which fundamentally transforms the operation and maintenance mode of power grid faults from “passive response” to “active warning” and “intelligent decision-making”. This transformation will enable the recording of data throughout the entire lifecycle, achieving carbon footprint tracking and transparency.

In recent years, due to shifts in the global climate and environment, a variety of extreme weather events have become more frequent, resulting in numerous accidents. The increased occurrence of extreme weather not only poses risks to the functioning of the power grid but also impacts the accuracy of power grid fault diagnosis outcomes. By integrating research on power grid fault risks during extreme weather events, this study introduces weather data and self-check information to develop a fault diagnosis approach for the power grid based on a random self-regulating algorithm. The fault diagnosis method comprises two main components: Firstly, an analytical model for fault diagnosis is constructed using alarm data, weather information, and self-check data from the affected power outage area. Three types of self-adjusting trust factors are incorporated into the model to enhance its fault diagnosis capabilities in the context of extreme weather events. Subsequently, a random self-regulating algorithm is applied to optimize the model and generate a hypothesis regarding the fault. Through a simulation test on a sample calculation, the results demonstrate that the fault diagnosis method exhibits robust fault tolerance towards abnormal operation of protective devices and inaccuracies in alarm data.

Asymmetrical faults in the grid can lead to voltage drops at the grid-connected points, and in serious cases, there is also a risk of cutting the machine. The traditional voltage support strategy is easily affected by the output of the units and cannot support the voltage flexibly. To address the above problems, an optimized strategy for boosting voltage performance is proposed under asymmetrical faults in the power grid. Firstly, the voltage support principle under asymmetrical fault is analyzed, and the voltage support equation is derived. Then, based on the above equations, an optimal voltage support strategy under asymmetrical faults is proposed by taking the operation requirements of grid-connected standard voltage as the objective and considering the peak current and active power fluctuation amplitude as the constraints. Finally, the effectiveness and flexibility of the above strategy are validated by simulation.

With the development of big data, artificial intelligence and other technologies, data-driven aviation equipment fault diagnosis and prediction technology has gradually become a research hotspot in the aviation field. Many typical intelligent algorithm models have been applied to this field. However, limited by the airborne embedded computing environment, there are still some problems in the deployment of intelligent prediction models represented by deep neural networks on aircraft. This paper summarizes and analyzes the research and application of typical deep neural networks such as convolutional neural networks in the field of aircraft fault diagnosis and prediction. Facing the airborne embedded environment, the current difficulties in deploying the deep neural network algorithm model in the airborne environment are analyzed. The development direction of the application of fault prediction and diagnosis algorithms represented by neural networks in the future is discussed.

A power system fault diagnosis framework based on multi-agent system (MAS) is proposed to realize the parallelization and intelligence of grid fault diagnosis system. In the form of encapsulating multiple sub-modules of power grid fault diagnosis function, the multi-agent system model of power grid fault diagnosis with perception, reasoning and interaction is formed. Under the co-operation of agents, the fault diagnosis system is designed and the complex fault analysis of power grid is realized. Finally, taking the 3/2 wiring fault analysis as example, the MAS cooperation architecture is analyzed.

With the rapid advancement of industrial technology and the continuous expansion of production scale, electromechanical special equipment (ESE), such as cranes, has become increasingly essential in industrial operations. The demands for safety, reliability, and operational efficiency of this equipment have grown significantly. Extensive research has been conducted on fault diagnosis (FD) technologies for ESE to enhance their operational lifespan and ensure personnel safety. However, despite the considerable body of research, a comprehensive and systematic review in this field remains conspicuously absent. Therefore, this paper summarizes and analyzes the FD technologies associated with ESE, detailing the principal processes and the current status of technology applications. The typical failure modes that can compromise the performance are analyzed by thoroughly examining the core components of such equipment. Moreover, an in-depth discussion on FD methodologies is provided from the perspectives of traditional methods, signal processing methods, and machine learning methods. By examining these methods side by side, their strengths, limitations, and suitability for different types of ESE are highlighted. Finally, this paper offers a forward-looking assessment of the future development trajectory for FD technologies for ESE. This paper provides a comprehensive review and outlines a future development path on FD techniques in ESE, which will contribute to the continued development of these techniques.

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 129.94 s. 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.

The traditional fault diagnosis method only uses the protection and circuit breaker alarm messages to determine the fault sections. This paper put forward a new power grid fault track method based on big data platform. It extends the data source to transformer substation and deal with the fault date by the technology of Spark. This method can solve the problem of mass data processing. This paper analyses fault information by data mining and track the malfunction of protection or circuit breaker by decision tree. It can give the reason of fault and optimize the function of fault diagnosis system.

With the rapid development and increasing energy production capacity of high-power wind turbines, a corresponding increase in maintenance requirements has been observed. Reducing the failure rate of wind turbines is a critical objective, alongside decreasing affiliated operation and maintenance costs. This review focuses on the status monitoring, fault diagnosis, fault prediction, and status evaluation of wind turbines. The early fault diagnosis of wind turbines is explored with regard to existing condition monitoring technology. Moreover, the current mathematics-based fault diagnosis and smart fault diagnosis technologies are further explored. Through comprehensive investigation, this paper summarizes the research status of wind turbine fault prediction and complete machine status evaluation, conclusively presenting relevant research points and trends in the fault diagnosis, fault prediction, and status assessment of high-power wind turbines.

Deep learning models for solar irradiance forecasting: A comprehensive review