Equipment Fault Research Articles

Feature selection algorithm for substation main equipment defect text mining based on natural language processing

AbstractThe dimension of relevant text feature space and feature weight of substation main equipment defect information is high, so it is difficult to accurately select mining features. The Natural Language Processing (NLP) medium and short‐term neural network model is used to realise the defect information text feature word segmentation in the log. After extracting the text features of defect information of main substation equipment with high categories to form the feature space; the TF‐IDF algorithm is designed to calculate the importance weight of text keywords, judge the criticality of defect information text feature vocabulary, accurately locate defect information text features, and realise defect information text feature mining. Experiments show that the algorithm has high precision for specific word segmentation of massive substation main equipment log information.

A Knowledge-Graph-Driven Method for Intelligent Decision Making on Power Communication Equipment Faults

The grid terminal deploys numerous types of communication equipment for the digital construction of the smart grid. Once communication equipment failure occurs, it might jeopardize the safety of the power grid. The massive amount of communication equipment leads to a dramatic increase in fault research and judgment data, making it difficult to locate fault information in equipment maintenance. Therefore, this paper designs a knowledge-graph-driven method for intelligent decision making on power communication equipment faults. The method consists of two parts: power knowledge extraction and user intent multi-feature learning recommendation. The power knowledge extraction model utilizes a multi-layer bidirectional encoder to capture the global features of the sentence and then characterizes the deep local semantics of the sentence through a convolutional pooling layer, which achieves the joint extraction and visual display of the fault entity relations. The user intent multi-feature learning recommendation model uses a graph convolutional neural network to aggregate the higher-order neighborhood information of faulty entities and then the cross-compression matrix to solve the feature interaction degree of the user and graph, which achieves accurate prediction of fault retrieval. The experimental results show that the method is optimal in knowledge extraction compared to classical models such as BERT-CRF, in which the F1 value reaches 81.7%, which can effectively extract fault knowledge. User intent multi-feature learning recommendation works best, with an F1 value of 87%. Compared with the classical models such as CKAN and KGCN, it is improved by 5%~11%, which can effectively solve the problem of insufficient mining of user retrieval intent. This method realizes accurate retrieval and personalized recommendation of fault information of electric power communication equipment.

Analytical method of identifying the type of defect of oil-filled equipment according to the results of analysis of gases dissolved in oil

Purpose. Development of a method for recognizing the type of defect of oil-filled equipment based on the results of the analysis of gases dissolved in oil. Methodology. Analysis of gas ratio values in oil-filled equipment with various types of defects, synthesis of a method for recognizing the type of defects. Findings. A description of the analytical method for recognising the type of defects in oil-filled equipment based on the results of the dissolved gases analysis is given. To recognise the type of defect, the values of three ratios are used: CH4/H2, C2H4/C2H6, and C2H2/C2H4. Using these ratios, 40 different types of defects and their combinations can be recognised. These defects correspond to 25 different ranges of gas ratios obtained as a result of gas content studies for 3715 units of oil-filled equipment The type of defect is determined by analysing the obtained gas ratio values and classifying them according to the ranges of gas ratios for each fault. In the case when the obtained ratio values correspond to several types of faults in the same range, characteristic nomograms of defects and recommendations according to the key gas method are used to clarify the type of fault. A comparative analysis of the reliability of fault type recognition using the developed method and some well-known methods for interpreting the results of dissolved in oil gases analysis was performed. Originality. An analytical method for recognising the type of faults in oil-filled equipment of electrical networks based on the results of the dissolved gases analysis is proposed. This method differs from the existing ones in that, when using three known gas ratios, it allows recognising a larger number of defects of different types (40), including those for which the known methods do not allow establishing a diagnosis. This result is ensured by the use of 25 ranges of gas ratios obtained from the results of gas content studies for 3715 units of oil-filled equipment. Practical value. The use of the developed method for recognising the type of faults in oil-filled equipment of electrical networks allows increasing the reliability of defect recognition based on the results of dissolved gases analysis. This, in turn, makes it possible to increase the operational reliability of electric power equipment and extend the service life of this equipment.

Fault diagnosis method for hydro-power plants with Bi-LSTM knowledge graph aided by attention scheme

In hydro-power systems, the fault of equipment is an important potential threat for the safe production of electricity. Therefore, the automation and intelligence of fault diagnosis becomes the popular issue in the research on hydro-power system. In this paper, a knowledge graph-based method is put forth to diagnose faults occurred in hydro-power systems, since the knowledge graph can store structured and unstructured data for better fault diagnosis and intelligently search the reasons of the faults. First, we model the knowledge graph for hydro-power plants, where the rational path for the fault reason is formulated. Then, the bi-directional long short-term memory (Bi-LSTM) with conditional random field (CRF) is used to extract the entities and relations to the given documents, which record the phenomenon and reasons for the occurred faults. Moreover, the attention scheme is employed in the Bi-LSTM to weigh the closer relationships to improve the diagnosis accuracy. An automatic diagnosis algorithm is developed to improve the diagnosing efficiency by constructing rational paths, with which directive and in-directive factors for occurring faults can be traced. Simulation results reveal that the intelligent search method with a knowledge graph can effectively find the reason, locate the position, and provide useful suggestions for the occurred faults.

Fault diagnosis model of main equipment in substation based on multi-mode time-frequency combination

The conventional fault diagnosis method of the main equipment in substations has strong limitations and the fault diagnosis accuracy is low, so this paper introduces the multi-mode time-frequency combination method and designs the fault diagnosis model of the main equipment in substations. First, the transmission mode of fault information of main transformer equipment is analyzed and the fault source is diagnosed. Secondly, the UHF partial discharge method is used to detect the partial discharge signal of the main substation equipment. On this basis, the main equipment fault diagnosis model of the substation is established based on the multi-mode time-frequency combination, and the equipment fault degree is obtained to complete the fault diagnosis. According to the experimental results, the proposed fault diagnosis model is highly feasible, and the accuracy of an insulation fault, overheating fault and discharge fault diagnosis is more than 98%.

Analysis of Partial Discharge Fault Diagnosis Technology for High Voltage Switch Cabinet

In order to enhance the security and reliability of high-voltage switch cabinet operation, the diagnosis of internal discharge defects in high-voltage switch cabinet equipment is analyzed in this paper. Firstly, a variety of partial discharge live detection technologies such as three-dimensional voiceprint monitoring technology and three-dimensional ultraviolet technology for partial discharge are studied. Then, a variety of partial discharge live detection technologies are constructed. Finally, the data fusion of the relevant detection data is carried out, and the monitoring results of the equipment’s running state are analyzed. The analysis results show that the data sensitivity and specificity of creepage, non-breakdown discharge, and breakdown discharge at different output values in the application of various partial discharge detection technologies have obvious effects. It is believed that the technology constructed in this study can improve detection accuracy and equipment safety. It provides important parameters and a basis for the maintenance of high-voltage switch cabinets. It is of extremely good importance to take partial live detection measures for the operating switch cabinet and provides a reference for field application.

Analysis of the main problems arising during the recognition of the defect type based on the results of the dissolved gases analysis

The article presents the results of the analysis of the main problems that arise when recognising the defect type in oil-filled equipment of electric power networks based on the results of the dissolved gases analysis. On the example of interpreting the actual results of the dissolved gases analysis, the main problems arising in the recognition of partial discharges, spark discharges, discharges with low and high energy density, local overheating and combined defects are analysed using the graphical method from the IEC 60599 standard, the ETRA square and the Duval triangle. The analysis revealed significant discrepancies in the norms and criteria regulated by different standards and methods for interpreting the results of the dissolved gases analysis to recognise the same defect. The research results showed that for almost all the analysed defects, the non-recognition is caused by the absence of normalised values of diagnostic criteria (values of gas ratios, percentage of gases and ratios of gas concentrations to the gas with the maximum content) for some defects or combinations of several defects. False diagnoses are made when identifying the type of defects in oil-filled equipment based on the results of the dissolved gases analysis because the values of individual gas ratios or percentage content of individual gases are not taken into account. The analysis revealed contradictions in the diagnoses made when different diagnostic criteria (ratios of characteristic gases and percentage of gases) are used for the same results of the analysis of gases dissolved in oil. Ensuring reliable recognition of the type of defect in oil-filled equipment based on the results of dissolved gas analysis is possible thanks to an integrated approach that includes not only the analysis of gas ratios, but also the analysis of the percentage of gases and defect nomograms. In addition, it is crucial to take into account the physicochemical laws of gas formation in oil, in particular, the dependence of gas content on the temperature or energy of defects.

Research on Fault Prevention and Maintenance System of Automatic Substation Primary Equipment Based on Decision Tree Algorithm

Abstract Electric power enterprises are developing rapidly in the era of big data information digitization. At this stage, the total number of substations is gradually increasing, the structure of the power engineering system is slowly becoming complicated, and the video monitoring system instantly collects a lot and contains a lot of noisy data information, which affects the power supply system’s access to effective data information and fault detection. To prevent the above phenomenon. This paper selects a decision tree algorithm to obtain and analyze meaningful operation-confirming information from a large amount of data information, and then can quickly and confirm the diagnosis of common fault machines and equipment in substations, reduce the running time of common fault machines, and improve the safety and reliability of primary equipment in substations with automation technology. The paper describes the basic concept of big data mining common algorithm and its data mining algorithm in the automation technology substation primary equipment fault detection, selected the typical alarm signal to start the analysis, and categorization and collocation solution. A decision tree algorithm entity model is built, several classical decision tree algorithms are described, and their data analysis is carried out for each attribute, and then the decision tree algorithm is improved. According to build the decision tree algorithm according to improve the decision tree algorithm under the fuzzy set base theory, mainly by expertise in the four on cannot identify the association, rough set and up close and down close, similar and membership relationship, expertise concise to optimize the calculation method. And the common ID3, C4.5, and CRAT algorithm of each property is compared and analyzed, and the results show that: compared with C4.5 and ID3, the boosted optimization algorithm has higher classification accuracy and can model rate more quickly. The research in this paper can quickly diagnose the automation technology substation primary equipment and fault phenomena, and its establishment of the whole process is easy, the scope of application is relatively high, and it has wide applicability.

Advanced Diagnostic Approach for High-Voltage Insulators: Analyzing Partial Discharges through Zero-Crossing Rate and Fundamental Frequency Estimation of Acoustic Raw Data

Acoustic inspection is a valuable technique that can detect early stage defects in equipment, thereby facilitating predictive maintenance. In recent times, ultrasonic sensors have made detecting partial discharges through acoustic sensing increasingly feasible. However, interpreting the acoustic signals can pose challenges, as it requires extensive expertise and knowledge of equipment configuration. To address this issue, a technique based on zero-crossing rate and fundamental frequency estimation has been proposed to standardize insulator diagnosis. In an experiment involving a database of 72 raw acoustic signals with frequencies ranging from 0 to 128 kHz, various types of pollution and defects were introduced to a chain of insulators. By employing the proposed technique, the occurrence of partial discharges can be detected and classified according to type, such as corona or surface discharges. This advanced approach to diagnosis simplifies the process while providing valuable insights into the severity of observed phenomena in the field.

MHlinker: Research on a Joint Extraction Method of Fault Entity Relationship for Mine Hoist

Triplet extraction is the key technology to automatically construct knowledge graphs. Extracting the triplet of mechanical equipment fault relationships is of great significance in constructing the fault diagnosis of a mine hoist. The pipeline triple extraction method will bring problems such as error accumulation and information redundancy. The existing joint learning methods cannot be applied to fault texts with more overlapping relationships, ignoring the particularity of professional knowledge in the field of complex mechanical equipment faults. Therefore, based on the Chinese pre-trained language model BERT Whole Word Masking (BERT-wwm), this paper proposes a joint entity and relation extraction model MHlinker (Mine Hoist linker, MHlinker) for the mine hoist fault field. This method uses BERT-wwm as the underlying encoder. In the entity recognition stage, the classification matrix is constructed using the multi-head extraction paradigm, which effectively solves the problem of entity nesting. The results show that this method enhances the model’s ability to extract fault relationships as a whole. When the small-scale manually labeled mine hoist fault text data set is tested, the extraction effect of entities and relationships is significantly improved compared with several baseline models.

CaFANet: Causal-Factors-Aware Attention Networks for Equipment Fault Prediction in the Internet of Things.

Existing fault prediction algorithms based on deep learning have achieved good prediction performance. These algorithms treat all features fairly and assume that the progression of the equipment faults is stationary throughout the entire lifecycle. In fact, each feature has a different contribution to the accuracy of fault prediction, and the progress of equipment faults is non-stationary. More specifically, capturing the time point at which a fault first appears is more important for improving the accuracy of fault prediction. Moreover, the progress of the different faults of equipment varies significantly. Therefore, taking feature differences and time information into consideration, we propose a Causal-Factors-Aware Attention Network, CaFANet, for equipment fault prediction in the Internet of Things. Experimental results and performance analysis confirm the superiority of the proposed algorithm over traditional machine learning methods with prediction accuracy improved by up to 15.3%.

Research on Mechanical Equipment Fault Diagnosis Method Based on Deep Learning and Information Fusion.

Solving the problem of the transmission of mechanical equipment is complicated, and the interconnection between equipment components in a complex industrial environment can easily lead to faults. A multi-scale-sensor information fusion method is proposed, overcoming the shortcomings of fault diagnosis methods based on the analysis of one signal, in terms of diagnosis accuracy and efficiency. First, different sizes of convolution kernels are applied to extract multi-scale features from original signals using a multi-scale one-dimensional convolutional neural network (1DCNN); this not only improves the learning ability of the features but also enables the fine characterization of the features. Then, using Dempster-Shafer (DS) evidence theory, improved by multi-sensor information fusion strategy, the feature signals extracted by the multi-scale 1DCNN are fused to realize the fault detection and location. Finally, the experimental results of fault detection on a flash furnace show that the accuracy of the proposed method is more than 99.65% and has better fault diagnosis, which proves the feasibility and effectiveness of the proposed method.

Reactive molecular dynamics simulations on the pyrolysis of SF6

There are occasionally partial over-thermal faults in gas-insulated equipment inducing SF6 insulating medium to dissociate. It remains unclear at the atomic scale how this chemically stable gas pyrolyzes at high temperatures. To date, there is a lack of micro-level investigations on the molecular behavior of SF6 at high temperatures. In particular, it requires an effective force field to characterize the evolution of the reactions involving SF6 and low-fluorine sulfides. The paper aims to fill the gap in this field by performing reactive molecular dynamics (MD) simulations. In this work, MD simulations were carried out on a system consisting of more than 100 SF6 molecules using a new developed reactive force field The dissociation of SF6 and the subsequent reactions involving low-fluorine sulfides at high temperatures were simulated. The variation of all species in the system were recorded to investigate the effects of the temperature and pressure on the pyrolysis process. The obtained data was then used to establish the relationship between the reaction rate and temperature, thereby formulating Arrhenius law. Furthermore, the trajectories of SF6 and other species were observed at the atomic level. Snapshots of key frames during the reaction helped us to explore the interaction mechanism of free F atoms with SF6 molecules and SF5 fragments. It was found that the early dissociation of SF6 mainly comes from the thermal vibrations of the molecule itself, while the later decomposition of SF6, SF5 and others is related to high-speed collisions by F atoms. This work contributes to the understanding of the mechanism of SF6 pyrolysis and lays a foundation for more MD investigations.

Bearing Fault Diagnosis of WDCNN-LSTM in Siamese Network

In this paper, a Siamese network-based WDCNN + LSTM model was used to diagnose bearing faults using a few shot learning algorithm. Recently, deep learning-based fault diagnosis methods have achieved good results in equipment fault diagnosis. However, there are still limitations in the existing research. The biggest problem is that a large number of training samples are required to train a deep learning model. However, manufacturing sites are complex, and it is not easy to intentionally create equipment defects. Furthermore, it is impossible to obtain enough training samples for all failure types under all working conditions. Therefore, in this study, we propose a few-shot learning algorithm that can effectively learn with limited data. A Few shot learning algorithm and Siamese network based WDCNN + LSTM model bearing fault diagnosis, which can effectively learn with limited data, is proposed in this study.

Revolutionizing condition monitoring techniques with integration of artificial intelligence and machine learning

The field of condition monitoring has made great strides in the development of innovative techniques that facilitate early detection and diagnosis of faults in equipment. Present article provides a comprehensive overview of condition-monitoring technologies, namely, ultrasound technique and radiography. By providing detailed insight into the strengths and weaknesses of mentioned techniques, present work highlights their suitability for various industrial applications and how artificial intelligence and machine learning can be integrated to form multimodal systems that improve overall performance. Additionally, it evaluates developments in artificial intelligence and machine learning that enable accurate and reliable condition monitoring systems.

Partial Discharge Wideband Full-Band High-Gain Resonant Cavity UHF Sensor Research.

To meet the real demand for broadband full-band high-gain antenna sensors in the process of partial discharge (PD) Ultra-High frequency (UHF) detection test and online monitoring of power equipment, this paper builds a resonant cavity monopole UHF antenna sensor based on Fabry-Perot resonant cavity antenna technology, conducts the sensor Voltage Standing Wave Ratio (VSWR) optimization study using curved flow technology, conducts the sensor gain optimization study using slot dual resonant structure, and, finally, tests the sensor performance using the built PD detection test platform. The resonant cavity monopole antenna exhibits outstanding VSWR performance in the frequency range of 0.37 GHz-3 GHz, according to simulation and test data: the average gain in the frequency range of 0.3 GHz-3 GHz is 4.92 dBi, and the highest gain at the primary resonant frequency of 1.0 GHz is 7.16 dBi, with good radiation performance over the whole frequency spectrum. The electromagnetic pulse signal sensed by the UHF sensor developed in this paper can demonstrate the energy spectrum distribution characteristics of PD radiation electromagnetic wave signal more comprehensively, laying a firm technical foundation for thoroughly understanding the electromagnetic wave radiation characteristics of various types of PD insulation defects of various power equipment and the selection of a specific direction for its supporting optimization.

A Hierarchical Maintenance Method for Power System Transmission and Substation Multi-Equipment Operation Status Considering Equipment Service Age

The current conventional maintenance methods for transmission and substation operation equipment are mainly used to extract fault data features by combining micro-network algorithms to process equipment operation data. The lack of effective analysis of equipment fault characteristics leads to poor maintenance results. In this regard, a power system transmission and substation multi-device operation status hierarchical maintenance method considering the age of equipment service is proposed. By accessing the configuration network and interacting with the grid intelligent collection of data, network storage and parallel processing of data are realized. The characteristics of transmission and substation equipment operation data are analyzed and processed to build the maintenance system. In the experiments, the proposed method is validated for the effect of condition assessment. The experimental results show that when the proposed method is used to process the transmission and substation equipment, the condition assessment accuracy is high and it has a more desirable equipment maintenance performance.

Research on equipment safety fault diagnosis method based on multi‐sensor fusion deep network in mechatronics equipment environment

AbstractThe safety performance and stability of mechatronics equipment play an important role in modern industrial production. However, using a single‐sensor signal cannot effectively ensure robustness in complex scenarios. Moreover, the efficient collection and real‐time transmission of information can improve the real‐time performance of fault detection. To this end, this article proposes a novel deep network based on multi‐sensor information fusion for mechatronics equipment fault detection. Firstly, three sensors are used to collect status information. We use the CC2420 model to transmit the collected signals to the server for storage and analysis. Secondly, we designed a multi‐sensor information fusion deep network. To better model local and global features, we introduced convolutional operations and the multi‐head attention mechanism to form the backbone of the network. The results on the self‐built dataset indicate that the proposed model fully utilizes the advantages of multimodal information and deep networks to achieve the optimal fault detection results.

Open-set federated adversarial domain adaptation based cross-domain fault diagnosis

Abstract Data-driven fault diagnosis techniques utilizing deep learning have achieved widespread success. However, their diagnostic capability and application possibility are significantly reduced in real-world scenarios where fault modes are not fully covered and labels are lacking. Owing to potential conflicts of interest and legal risks, industrial equipment fault data usually exist in the form of isolated islands, making it difficult to carry out large-scale centralized model training. This paper proposes open-set federated adversarial domain adaptation (OS-FADA) to achieve collaborative evolution of fault diagnosis capabilities among cross-domain data owners while protecting privacy. The OS-FADA is a general fault diagnosis framework that employs two-phase adversarial learning. First, faced with the data distribution shift caused by variable working conditions, a generative adversarial feature extractor training strategy is designed to achieve domain-invariant fault feature extraction by approximating the feature distributions of clients to a unified generated distribution. Second, considering the label distribution shift of unknown faults occurring in the target client, an adversarial learning method is proposed to establish decision boundaries between known and unknown faults. Ultimately, the co-evolution of fault diagnosis models between clients is achieved by combining two-phase adversarial learning and federated aggregation. Results from an industrial gearbox case demonstrate that our proposed method achieves over 20% diagnostic accuracy improvement and has excellent potential for cross-domain fault diagnosis tasks with unknown faults when the data silos problem cannot be ignored.

Adsorption and Sensing of SF6 Decomposition Products by a Pd-Doped MoTe2 Monolayer: A First-Principles Study.

The detection of sulfur hexafluoride (SF6) decomposition components has become one of the best ways to diagnose early latent insulation faults in gas-insulated equipment, which can effectively prevent sudden accidents by identifying such faults. In this paper, we by first-principles theory investigated the adsorption and sensing behaviors of four typical SF6 decomposition components (H2S, SO2, SOF2, and SO2F2) on the pristine Pd-doped MoTe2 monolayer. The adsorption energy, work function, recovery time, charge density difference, density of state, and band structure of the adsorption structures are obtained as well as analyzed. The results indicate that the Pd dopant prefers to be trapped at the TMo site, with a binding energy of -2.25 eV. The Pd-MoTe2 chemisorbs the remaining gases except SO2xF2, with the adsorption capacity ranking as SOF2 > SO2 > H2S. The adsorption of gas molecules reduces the bandgap of Pd-MoTe2, thereby increasing conductivity. On the other hand, the recovery time of the Pd-MoTe2 monolayer material at a temperature of 398 K demonstrates its excellent gas desorption performance toward four decomposition gases. The research results provide a theoretical basis for Pd-MoTe2 to detect SF6 decomposition components, thus, promoting the stable operation of the power system.