Power Equipment Fault Research Articles

Research on Blind Super-Resolution Technology for Infrared Images of Power Equipment Based on Compressed Sensing Theory.

Infrared images of power equipment play an important role in power equipment status monitoring and fault identification. Aiming to resolve the problems of low resolution and insufficient clarity in the application of infrared images, we propose a blind super-resolution algorithm based on the theory of compressed sensing. It includes an improved blur kernel estimation method combined with compressed sensing theory and an improved infrared image super-resolution reconstruction algorithm based on block compressed sensing theory. In the blur kernel estimation method, we propose a blur kernel estimation algorithm under the compressed sensing framework to realize the estimation of the blur kernel from low-resolution images. In the estimation process, we define a new norm to constrain the gradient image in the iterative process by analyzing the significant edge intensity changes before and after the image is blurred. With the norm, the salient edges can be selected and enhanced, the intermediate latent image generated by the iteration can move closer to the clear image, and the accuracy of the blur kernel estimation can be improved. For the super-resolution reconstruction algorithm, we introduce a blur matrix and a regular total variation term into the traditional compressed sensing model and design a two-step total variation sparse iteration (TwTVSI) algorithm. Therefore, while ensuring the computational efficiency, the boundary effect caused by the block processing inside the image is removed. In addition, the design of the TwTVSI algorithm can effectively process the super-resolution model of compressed sensing with a sparse dictionary, thereby breaking through the reconstruction performance limitation of the traditional regularized super-resolution method of compressed sensing due to the lack of sparseness in the signal transform domain. The final experimental results also verify the effectiveness of our blind super-resolution algorithm.

Research on Power Equipment Fault Diagnosis Technology Based on Acoustic Signal

In recent years, with the continuous growth of China’s electricity load, the power industry has developed rapidly. Power transformer is the most important and expensive in transmission and distribution system of large-scale power equipment, which undertakes the important task of power transmission. With the development of power system towards ultra-high voltage, large power grid and intelligence, it is particularly important to improve the safe operation level of transformers. Once the power transformer accident occurs, the repair time is longer and the influence is more serious. To solve this problem, a new power equipment fault diagnosis technology based on acoustic signals is studied in this paper, which is used to accurately diagnose and analyse the running state of the transformer. The simulation results show that the fault diagnosis based on acoustic signal is more accurate and can effectively diagnose the fault of power equipment.

Power equipment fault information acquisition system based on Internet of things

With the advent of the Internet of things era, power equipment is gradually connected to the network, and its intelligent fault detection function provides greater help for the power industry. The purpose of this study is to design the power equipment fault information acquisition system of the Internet of things. This research is based on the equipment fault information collection system of the Internet of things and mainly studies the fault information collection method based on the Internet of things technology. Equipment fault data are generally time series data. In the analysis of equipment failure, the data before and after fault and before and after fault are analyzed. The abnormal state of equipment is associated with the data before and after the fault. Therefore, by analyzing the characteristics of the fault data and the equipment before and after the fault, a bidirectional recurrent neural network model based on LSTM is constructed. The method designed in this paper can not only improve the efficiency and speed of collection, but also can compare and collect fault information. The overall operation state of the power unit is improved accurately. The research results show that the company's low-voltage user acquisition success rate has reached more than 99%. With the increase of time, the fault information collection efficiency can approach 99%. It shows that the function of this research system is better, the economic loss of the company is reduced, and the management is optimized.

GIS partial discharge defect diagnosis system and method based on Extreme Learning Machine

Partial discharge type identification is of great significance to the diagnosis of insulation faults in high-voltage power equipment. The partial discharge type recognition method based on deep learning map diagnosis has the disadvantages of large memory space and high hardware environment requirements. This paper presents a GIS discharge defect diagnosis system and method based on Extreme Learning Machine (ELM), which can be deployed on the edge layer equipment. The principal component analysis method is used to obtain the principal parameters that characterize the defects and form a sample feature data set. The sample feature data set is used to train the neural network model and continuously optimize it. Finally, the trained neural network model is used to identify the types of partial discharge defects. This method can effectively solve the problems that the partial discharge type identification method based on atlas diagnosis occupies large memory space and requires high hardware environment, which is convenient for the wide application of engineering.

Intelligent learning approach for UHF partial discharge localisation in air‐insulated substations

To achieve comprehensive insulation deterioration motoring of power equipment and early fault warning in air-insulated substations, a data-driven partial discharge (PD) source localisation method employing noisy ultra-high frequency (UHF) received signal strength indicator (RSSI) and particle filter is proposed in this study. Compared with the existing UHF time-difference-based techniques, UHF wireless sensor arrays and RSSI-based methods provide an economical and high-adaptability solution. However, owing to the multi-pathing and shadowing effects, UHF signal attenuation cannot be modelled. Therefore, a Kalman filter was employed to smoothen the RSSI signal. Furthermore, a semi-parametric regression model is proposed to achieve a more accurate relationship between the RSSI and the transmission distance. Finally, in contrast to traditional localisation algorithms directly based on the RSSI ranging model, a particle filter was used to achieve higher accuracy. It predicted the best distribution of the position of PD by learning and considering all the system states of the previous moment. The laboratory test was performed within an area of 6 m × 6 m, and the results demonstrate that the mean PD source localisation error was 1.16 m, which gives a potential application for the identification of power equipment with insulation deterioration in a substation, while the accuracy is still needed to be verified further by field tests.

Knowledge Extraction Method for Power Grid Fault Text Based on Ontology

The power industry usually records equipment failures, defects and other information in the form of text, which contains lots of regular patterns. Knowledge extraction in fault text is of great significance to improve efficiency and reduce the labor cost in the power industry. However, the research for knowledge extraction of text information in this field is rare, it is even more difficult to use machine learning algorithms to mine the deep patterns. To solve this problem, a method of knowledge extraction is proposed in this field. We use power equipment fault texts and relevant guidance as raw materials. Firstly, the knowledge base of this field is designed and constructed based on the ontology concepts, including ontology concept base, description base and regular expression base. Then, the knowledge extraction algorithm is designed according to the knowledge base. After that we conduct the knowledge merge operation to make the extraction results more accurate. Experiments on the real fault texts shows the feasibility and the high accuracy of our method when compared with artificial extraction.

Application and Research of Machine Learning Simulation Technology in Equipment Fault Monitoring under Smart Grid

Smart grid is increasingly becoming the development trend of grid technology. Smart grid is an important part of smart grid. Power equipment is the core part of smart grid, and the normal or not of power equipment directly affects the safety and stability of the entire power system. Smart smart grid usually has relatively complete fault diagnosis and self-healing functions to improve the stability and reliability of the grid. The application and development of a practical fault monitoring and early warning system for power equipment is to carry out predictive maintenance of power equipment so that the equipment can operate more safely and reliably. Due to the time-varying nonlinearity, stochastic uncertainty and local observability of smart grid, it is difficult for traditional power system modeling and analysis methods to fully reflect the steady- state and transient characteristics of power system in the new form. In this paper, based on machine learning simulation technology, through the research of power equipment fault monitoring system in smart grid, provide early warning information and solutions for equipment management personnel maintenance.

Anomaly detection for condition monitoring data using auxiliary feature vector and density‐based clustering

High-quality condition monitoring data can provide vital information on power equipment condition assessment and fault diagnosis. However, data quality is difficult to guarantee because valid and invalid anomalies, and different normal data patterns inevitably occur in datasets. This study presents a method for anomaly detection based on auxiliary feature vector and density-based spatial clustering of applications with noise (DBSCAN). The auxiliary feature vectors of each condition variable are constructed for clustering to recognise normal data patterns and different types of anomalies. Furthermore, a heuristic method based on the ‘number of clusters–Eps’ curve is proposed for the parameter selection of DBSCAN in an unsupervised setting. Different application examples are implemented on data of dissolved gas content in transformer oil. Compared with state-of-the-art anomaly detection techniques, the proposed method shows an ability to identify and distinguish normal data patterns and valid and invalid anomalies accurately, provided that the condition monitoring data satisfy the assumption of stationarity.

Condition monitoring and fault diagnosis of power equipment

With the rapid progress of modernization, power equipment can smooth and safe operation, relates to the enterprise’s production level, production safety, product quality assurance and other aspects of the smooth development of the electric power equipment fault are often referred to in a specific time and condition, the equipment does not have the specified function, touch the occurrence of this situation is mostly due to a component. The fault diagnosis of power equipment is actually the analysis of the specific location and nature of the fault. This paper is to detect the state of electric power equipment and to find fault, and gives some suggestions for the power equipment fault diagnosis.

A Comparison of Numerical Methods for Modeling Overpressure Effects from Low Impedance Faults in Power Transformers

Low-impedance faults in power equipment may lead to catastrophic tank ruptures, resulting in fires, oil spills and projection of parts, as well as economic losses. Up to recently, the tank for a large power transformer or a shunt reactor was typically designed to withstand vacuum filling, transportation and sometimes earthquakes. Since 2008, Hydro-Quebec has implemented arc-containment requirements in its power transformer and shunt reactor specifications. Tank rupture is a very complex phenomenon to investigate - arc testing is cost-prohibitive and, moreover, random in nature. Therefore, mechanical design of tanks to withstand such events, as well as investigation of such phenomena, must rely primarily on numerical methodologies. In this paper, Hydro-Quebec and SIEMENS present and compare two main classes of numerical methods, as well as some of their possible variations, that may be used to obtain an optimized and safer tank design to withstand overpressure effects from low impedance faults.

Numerical Method for the Investigation of Fault Containment and Tank Rupture of Power Transformers

This paper presents an analysis method based on explicit dynamic analysis, enabling detailed and representative investigations of the mechanical effects of low-impedance faults in power equipment. To illustrate the effectiveness of the proposed method, a given transformer design having caused the projection of a heavy chimney/bushing assembly over a significant distance is used as a case study. A comparison about the observed projection distance of this assembly shows that the method provides representative results, thus offering the significant advantage of replacing costly and unpractical tests. The method is then used to study the retrofit measure proposed in this case to retain the chimney, further exemplifying its power to effectively study different design and retrofitting options.