Equipment Fault Research Articles

Dual-species sensor using time-division multiplexed laser absorption spectroscopy for hydrogen sulfide and carbon monoxide measurement in SF6 insulated equipment fault detection

To address the issues of high detection limits, long response times, and susceptibility to cross-interference in the detection of characteristic gases CO and H2S produced by SF6 electrical equipment failures, a dual-species laser sensor prototype for SF6 decomposition products in electrical equipment was developed based on tunable diode laser absorption spectroscopy (TDLAS). The absorption lines of 2334 nm and 1576 nm were selected for CO and H2S, respectively. The concentration inversion was performed using wavelength modulation spectroscopy (WMS) with first harmonic normalization of the second harmonic. The experimental results demonstrate that a rapid response time of ∼30 s is achieved and the sensor has detection accuracies of 0.59 % for CO and 2.09 % for H2S, with minimum detection limits of 0.46 ppb and 14.00 ppb, respectively. The dual-species laser sensor allows for convenient, rapid, and precise detection of CO and H2S, showing promising application prospects in electrical environment monitoring.

Transfer of learning in convolutional neural networks for thermal image classification in Electrical Transformer Rooms

Overheating of power transformers, low-voltage panels, and medium-voltage components in Electric Transformer Rooms (ETRs) can result from various factors, such as contact issues, irregular loads, and other similar problems. Thermal imaging shows significant potential for detecting faults in power equipment. However, its effectiveness is hindered by the complex thermal patterns of faults and variability in equipment and environmental conditions, making accurate fault detection challenging. This paper aims to study the effectiveness of transfer learning architectures for automating equipment classification in ETRs. This work applies four transfer learning architectures: AlexNet, SqueezeNet, VGG19, and GoogLeNet. The findings of the testing phase demonstrated that the use of transfer learning by fine-tuning pre-trained convolutional neural networks was highly effective in the classification of thermal images captured from ETRs, with the models achieving accuracy rates between 86.98% and 100%, and F1-Scores between 86.79% and 100%.

Semi-supervised adaptive anti-noise meta-learning for few-shot industrial gearbox fault diagnosis

Abstract Real-time and accurate predictive maintenance of industrial equipment is fundamental for ensuring the safety and stability of advanced manufacturing processes. Current fault diagnosis methods based on data mining rely on a large number of labeled samples, and obtaining sufficient labeled data for diagnosing industrial equipment faults is challenging. Meta-learning can achieve the diagnosis of few-shot samples to a certain extent, but the effect is not ideal. Semi-supervision can effectively leverage a large number of unlabeled samples, which is of great practical significance for handling scenarios involving limited labeled samples. However, noise interference can occur when unlabeled samples appear that do not belong to known categories. Therefore, this study proposes adaptive semi-supervised meta-learning networks for noisy few-shot gearbox fault diagnosis. Firstly, a residual network with a Morlet Wavelet layer is used to extract signal features. Next, sample-level attention is defined to select unlabeled samples that are more similar to labeled sample prototypes, thereby reducing the influence of noisy samples. The adaptive metric is used to obtain the relational distance functions of labeled samples and unlabeled samples. Adaptive semi-supervised meta-learning networks uses unlabeled data to refine prototypes for better fault diagnosis. The effectiveness and anti-noise performance of the proposed method are verified by using two gearbox datasets with various few-shot noise scenarios.

Development and application of multi-parameter real-time acquisition system for intelligent secondary equipment

Abstract A multi-parameter real-time collection and analysis system, including intelligent secondary equipment, data collection gateway, and health management backend, has been constructed to solve the problem of current incomplete monitoring data and inability to providential warning of hidden faults of intelligent secondary equipment in substations. The key feature parameters of the device’s functional modules were extracted, and a data collection gateway was developed to achieve IoT access to feature data. A fault identification and warning model for the secondary equipment functional module considering temperature is provided, which realizes the assessment of equipment health status and ensures the stable and reliable operation of the power grid.

Research on rolling bearing fault diagnosis technology based on singular value decomposition

To solve the difficulty of selecting the number of effective singular values in Singular Value Decomposition denoising, a new method to determine the number of effective singular values is proposed. The proposed method to determine the number of effective singular values is based on the non-zero singular value distribution law of the Hankel matrix constructed by the signal. Specifically, the number of effective singular values in the Hankel matrix is twice the number of frequencies contained in the signal, and the difference between the effective singular values of the noisy signal and the non-zero singular values of the pure signal is very small. The proposed method for determining the number of effective singular values is to perform differential processing on the singular values of the signal and normalize the difference obtained. An empirical parameter T is provided, and the number of effective singular values is determined by comparing them with the normalized results. The proposed method is applied to the simulated and measured rolling bearing signals, and the results are compared with the wavelet threshold denoising method. The results show that the proposed method for determining the number of singular values can effectively filter out the noise frequency contained in the signal while maintaining the characteristic frequency of the signal and achieving the purpose of mechanical equipment fault diagnosis.

Substation secondary equipment fault detection based on the Llama2 model

Substation secondary equipment fault detection based on the Llama2 model

A novel transformer-based few-shot learning method for intelligent fault diagnosis with noisy labels under varying working conditions

Recent years have witnessed the success of Few-shot Learning (FSL) methods in equipment reliability enhancement and fault diagnosis, by virtue of learning from limited data and adapting to new operating conditions. However, due to sensor bias, manual collection, and mislabeling, label noise is inevitably introduced into the dataset, which further reduces the quality of supervised information contained in the few-shot dataset, posing significant challenges for accurate fault diagnosis. In this paper, the problem of Few-shot Fault Diagnosis with Noisy Labels (FFDNL) is studied for the first time, and a novel method named Enhanced Transformer with Asymmetric Loss Function (ETALF) is proposed. ETALF leverages the self-attention mechanism of the transformer to dynamically measure the similarity between fault samples in the support set to enhance the model's robustness against label noise, then naturally aggregates the similar samples into corresponding correct prototypes. Furthermore, an asymmetric loss function is designed, which adaptively assigns the model with larger penalties for incorrect category predictions and smaller penalties for correct category predictions, thereby enhancing fault diagnostic performance through inherent asymmetry. Comprehensive experiments are conducted on two benchmark datasets, and the compared results with representative approaches validate the effectiveness of our proposed ETALF in performing intelligent fault diagnosis using limited and noise-labeled data under varying working conditions, which achieves accuracies of 97.77% and 95.78% with 0.2 noisy-level labels during meta-training and meta-testing on the CWRU and KAIST datasets, respectively.

Theoretical investigation of Ag and Au modified CSiN monolayer as a potential gas sensor for air decomposition components detection

Monitoring and detection of air decomposition components (ADCs) is an effective approach for diagnosing the faults in air switchgear devices. Herein, the adsorption behavior of three ADCs (CO, NO, NO2) on pristine CSiN and Ag/Au-doped CSiN (Ag-CSiN and Au-CSiN) monolayers was investigated using first-principles calculations. The electronic properties of different adsorption systems were systematically analyzed. Moreover, the gas-sensing performance of these systems was evaluated by the analyses of conductivity, work function, and recovery time, which aims to explore the potential sensitive materials for monitoring the ADCs. The results reveal that the pristine CSiN exhibits weak adsorption towards CO and NOx. However, the doping of Ag and Au atoms significantly enhances the adsorption effects of CSiN monolayer, resulting in a transformation from physisorption to chemisorption, with the adsorption energy values ranging from − 0.73 eV to − 1.45 eV. The related adsorption mechanism is further elucidated through the analyses of density of states, band structures, charge density difference, and electron localization function. Furthermore, both Ag-CSiN and Au-CSiN exhibit excellent sensitivity towards CO and NO due to the moderate adsorption strength and significant changes in conductivity and work function. Specifically, Ag-CSiN exhibits a sensing response of 5.59 × 103 towards NO at 348 K, with a recovery time of 1.45 s. While Au-CSiN shows sensing responses of 498 and 6.00 × 105 towards CO and NO at 298 K, respectively, with recovery times of 2.20 s and 7.06 s. Therefore, Au-CSiN can be utilized a promising and recyclable gas sensor for detecting CO and NO at room temperature, and its sensing performance is unaffected by moisture in the air. This study offers a theoretical foundation for the design of novel gas sensors that can effectively diagnose the faults in air switchgear equipment.

Safety Design Criteria for the Emergency Discharge of Hazardous Substances in Small and Medium-Sized Polystyrene Polymerization Batch Reactor Processes: Case Study of the South Korean Chemical Industry

In small and medium-sized chemical plants, explosions constantly occur owing to runaway reactions because of equipment defects or human errors and so on. Accordingly, in this study, based on a case study of an explosion accident in a polystyrene reactor in South Korea, the dis-charge capacity of hazardous substances during a runaway reaction is reviewed and a method for safely disposing of hazardous substances is proposed. Using an acceleration rate calorimeter, the maximum temperature rise rate during the polystyrene reaction was determined, and it was determined that 355,643 kg/h can flow during a runaway reaction. A 30-inch header size was then selected to consider maximum flow rate, and two 81.4 m2 heat exchangers were selected to completely condense the hazardous substances. As a result, the facilities at the workplace were configured to condense all hazardous substances and discharge them into the atmosphere. If this method is used, it is believed that the lives of workers can be protected by preventing fires and explosions in small and medium-sized chemical plants in which runaway reactions may occur.

Structure Prompt Augmented Language Model Embedding on Electrical Equipment Defect Knowledge Graph

Knowledge graphs have demonstrated significant impact in the power grid domain, facilitating various applications such as defect diagnosis and grid management. However, their reasoning capabilities have not been fully exploited. In this paper, we explore the utilization of knowledge graphs for power grid defect diagnosis. We construct an electrical equipment defect knowledge graph and predict missing links, which is also known as Knowledge Graph Completion (KGC). However, we notice the long-tail problem in electrical equipment knowledge graph. To tackle this challenge, we propose a novel text-based model named SPALME (Structure Prompt Augmented Language Model Embedding) that incorporates structural information as prompts. Our model leverages the power of pre-trained language models, allowing it to comprehend the semantic information of entities and relationships in the knowledge graph. Additionally, by integrating structural information as prompts during the learning process, our model gains a deeper understanding of the graph’s topological structure efficiently, effectively capturing intricate dependencies between grid equipments. We evaluate our approach on various datasets. The results demonstrate that our model consistently outperforms baseline methods on the majority of the datasets.

A Novel Adversarial Deep Learning Method for Substation Defect Image Generation.

The presence of defects in substation equipment is a major factor affecting the safety of power transmission. Therefore, timely and accurate detection of these defects is crucial. As intelligent inspection robots advance, using mainstream object detection models to diagnose surface defects in substation equipment has become a focal point of current research. However, the lack of defect image data is one of the main factors affecting the accuracy of supervised deep learning-based defect detection models. To address the issue of insufficient training data for defect images with complex backgrounds, such as rust and surface oil leakage in substation equipment, which leads to the poor performance of detection models, this paper proposes a novel adversarial deep learning model for substation defect image generation: the Abnormal Defect Detection Generative Adversarial Network (ADD-GAN). Unlike existing generative adversarial networks, this model generates defect images based on effectively segmented local areas of substation equipment images, avoiding image distortion caused by global style changes. Additionally, the model uses a joint discriminator for both overall images and defect images to address the issue of low attention to local defect areas, thereby reducing the loss of image features. This approach enhances the overall quality of generated images as well as locally generated defect images, ultimately improving image realism. Experimental results demonstrate that the YOLOV7 object detection model trained on the dataset generated using the ADD-GAN method achieves a mean average precision (mAP) of 81.5% on the test dataset, and outperforms other image data augmentation and generation methods. This confirms that the ADD-GAN method can generate a high-fidelity image dataset of substation equipment defects.

Development and Application of IoT Monitoring Systems for Typical Large Amusement Facilities.

The advent of internet of things (IoT) technology has ushered in a new dawn for the digital realm, offering innovative avenues for real-time surveillance and assessment of the operational conditions of intricate mechanical systems. Nowadays, mechanical system monitoring technologies are extensively utilized in various sectors, such as rotating and reciprocating machinery, expansive bridges, and intricate aircraft. Nevertheless, in comparison to standard mechanical frameworks, large amusement facilities, which constitute the primary manned electromechanical installations in amusement parks and scenic locales, showcase a myriad of structural designs and multiple failure patterns. The predominant method for fault diagnosis still relies on offline manual evaluations and intermittent testing of vital elements. This practice heavily depends on the inspectors' expertise and proficiency for effective detection. Moreover, periodic inspections cannot provide immediate feedback on the safety status of crucial components, they lack preemptive warnings for potential malfunctions, and fail to elevate safety measures during equipment operation. Hence, developing an equipment monitoring system grounded in IoT technology and sensor networks is paramount, especially considering the structural nuances and risk profiles of large amusement facilities. This study aims to develop customized operational status monitoring sensors and an IoT platform for large roller coasters, encompassing the design and fabrication of sensors and IoT platforms and data acquisition and processing. The ultimate objective is to enable timely warnings when monitoring signals deviate from normal ranges or violate relevant standards, thereby facilitating the prompt identification of potential safety hazards and equipment faults.

Federated Transfer Fault Diagnosis Method Based on Variational Auto-Encoding with Few-Shot Learning

Achieving accurate equipment fault diagnosis relies heavily on the availability of extensive, high-quality training data, which can be difficult to obtain, particularly for models with new equipment. The challenge is further compounded by the need to protect sensitive data during the training process. This paper introduces a pioneering federated transfer fault diagnosis method that integrates Variational Auto-Encoding (VAE) for robust feature extraction with few-shot learning capabilities. The proposed method adeptly navigates the complexities of data privacy, diverse working conditions, and the cross-equipment transfer of diagnostic models. By harnessing the generative power of VAE, our approach extracts pivotal features from signals, effectively curbing overfitting during training, a common issue when dealing with limited fault samples. We construct a federated learning model comprising an encoder, variational feature generator, decoder, classifier, and discriminator, fortified with an advanced training strategy that refines federated averaging and incorporates regularization when handling non-independent data distributions. This strategy ensures the privacy of data while enhancing the model’s ability to discern subtleties in fault signatures across different equipment and operational settings. Our experiments, conducted across various working conditions and devices, demonstrate that our method significantly outperforms traditional federated learning techniques in terms of fault recognition accuracy. The innovative integration of VAE within a federated learning framework not only bolsters the model’s adaptability and accuracy but also upholds stringent data privacy standards.

Research on Partial Discharge Characteristics of Suspension Defect in GIS under the Action of Voltage and Current

Abstract Gas insulated switchgear (GIS) is a critical component in power system, and the insulation testing is crucial before putting it into operation. Despite passing AC withstand tests, some GIS equipment exhibit insulation faults during operation. Existing AC withstand tests fall short in detecting all insulation faults in GIS equipment. To address this issue, a proposal is made to conduct a comprehensive simulation of actual GIS equipment operating conditions through a combined voltage and current boost test, aiming to address the limitations of existing tests. This study, based on a 330kV GIS test platform, compares the partial discharge characteristics of suspension defects under traditional voltage-boosting mode and the combined voltage and current boost mode. The research investigates the influence of simultaneously applying voltage and current on discharge characteristics. It is observed that the voltage and current boost combined mode significantly increase the partial discharge inception voltage (PDIV) and the corresponding apparent discharge compared to other modes. The apparent discharge quantity after a certain period of current flow during the discharge development process is greater than that observed in other modes. The current notably enhances the ultrasonic amplitude of partial discharge. These findings establish an experimental foundation for conducting voltage and current combined boost tests in the field.

Classification of Multi-Source Partial Discharge in GIS

Abstract Partial discharge (PD) analysis is an important method to identify electrical equipment faults. However, due to the influence of environmental electromagnetic interference and other equipment discharges in the power supply circuit during the on-site PD test, the collected PD signal is the combination of various PD and noise, which makes it challenging to identify the type or source of on-site partial discharge. A multi-source PD classification method based on the multiple threshold and K-means clustering algorithm is pro-posed to solve this problem. First, wavelet transform with an improved threshold is used to initially denoise the original signal. Then the multiple threshold method is used to filter the residual ripple between every two pulses. Finally, spectrum analysis is carried out for each pulse, and the maximum value of the spectrum is extracted as the feature quantity. Then, the K-means algorithm is used to classify the PD pulses, and the PRPD images of PD pulses in different frequency domains are obtained. The results show that the method adopted in this paper can denoise, extract and classify the PD signals collected on the site, and the PRPD diagram of PD pulse after classification is more obvious, which provides a basis for identifying the PD source on the site.

Research on Transformer Fault Diagnosis Based on Voiceprint Signal

Abstract As an important part of the power system, the operating status of the transformer will have a direct impact on the stability and reliability of the power system. In view of the problems of high diagnosis cost and low accuracy of diagnosis results in existing fault diagnosis technology, this paper takes advantage of the obvious difference between the voiceprint signal of the transformer under normal and fault operating conditions and applies it to transformer fault diagnosis, which can effectively reflect its internal working status and fault conditions, helping operation and maintenance personnel promptly discover equipment defects and locate fault causes. In order to accurately realize transformer fault diagnosis, this paper uses the improved hybrid frog leaping algorithm to optimize the fault diagnosis algorithm of support vector machine parameters for fault diagnosis, which further improves the accuracy of fault diagnosis and is of great significance for accurately identifying transformer fault states.

A Novel Electrical Equipment Status Diagnosis Method Based on Super-Resolution Reconstruction and Logical Reasoning.

The accurate detection of electrical equipment states and faults is crucial for the reliable operation of such equipment and for maintaining the health of the overall power system. The state of power equipment can be effectively monitored through deep learning-based visual inspection methods, which provide essential information for diagnosing and predicting equipment failures. However, there are significant challenges: on the one hand, electrical equipment typically operates in complex environments, thus resulting in captured images that contain environmental noise, which significantly reduces the accuracy of state recognition based on visual perception. This, in turn, affects the comprehensiveness of the power system's situational awareness. On the other hand, visual perception is limited to obtaining the appearance characteristics of the equipment. The lack of logical reasoning makes it difficult for purely visual analysis to conduct a deeper analysis and diagnosis of the complex equipment state. Therefore, to address these two issues, we first designed an image super-resolution reconstruction method based on the Generative Adversarial Network (GAN) to filter environmental noise. Then, the pixel information is analyzed using a deep learning-based method to obtain the spatial feature of the equipment. Finally, by constructing the logic diagram for electrical equipment clusters, we propose an interpretable fault diagnosis method that integrates the spatial features and temporal states of the electrical equipment. To verify the effectiveness of the proposed algorithm, extensive experiments are conducted on six datasets. The results demonstrate that the proposed method can achieve high accuracy in diagnosing electrical equipment faults.

Research on Equipment Fault Identification Method and System based on Big Data Correlation Analysis

With the rapid progress in the industrial field, equipment fault identification plays a crucial role in improving production efficiency and reducing operating costs. This article proposes a specialized and efficient equipment fault identification method and system based on big data correlation analysis. This system achieves precise identification of equipment faults by finely collecting and preprocessing equipment operation data, deeply exploring potential association rules between data. The method proposed in this article not only improves the accuracy of fault recognition, but also significantly enhances recognition efficiency, providing strong support for intelligent and refined management in the industrial field.

Rotating machinery weak fault features enhancement via line-defect phononic crystal sensing

The fault features of rotating machinery at the early degradation stage are always weak as a result of interference from strong noise and irrelevant harmonics. Although traditional acoustic diagnosis techniques have attracted much attention with the merits of rich information and non-contact, extracting meaningful features related to faults in extremely low signal-to-noise ratios (SNRs) has always been a challenging problem. Considering the extraordinary physical properties of phononic crystals (PnCs) and acoustic metamaterials, this study proposes a structural enhancement method for rotating machinery fault diagnosis via line-defect PnC sensing. In contrast to conventional acoustic filtering and enhancement methods, this method can directly filter out noise and enhance fault features in the pre-processing stage of acoustic perception without the need for complex post-processing algorithms. Consequently, the original information of the fault features is preserved intact, thus further increasing the detection limit of current acoustic sensing. Specially, the designed line-defect PnC is parametrically tunable. Combined with the prior knowledge of rotating machinery fault features, such as gears and bearings, it is possible to design structures suitable for enhancing their fault features, which has great potential for practical engineering applications. The enhancement mechanism of line-defect PnC is theoretically described, and numerical simulations are also conducted to verify its ability to detect weak faults in rotating machinery. The experimental results show that by comparison with the variational modal decomposition (VMD)-based method, the proposed method exhibits superior fault feature enhancement performance under low SNR conditions. By systematically combining fault detection methods and acoustic metamaterial sensing, it can be foreseen that the proposed method shows great potential in mechanical equipment fault diagnosis.

Periodic group-sparse method via generalized minimax-concave penalty for machinery fault diagnosis

Abstract Diagnosing faults in large mechanical equipment poses challenges due to strong background noise interference, wherein extracting weak fault features with periodic group-sparse property is the most critical step for machinery intelligent maintenance. To address this problem, a periodic group-sparse method based on a generalized minimax-concave penalty function is proposed in this paper. This method uses periodic group sparse techniques to capture the periodic clustering trends of fault impact signals. To further enhance the sparsity of the results and preserve the high amplitude of the impact signals, non-convex optimization techniques are integrated. The overall convexity of the optimization problem is maintained through the introduction of a non-convex controllable parameter, and an appropriate optimization algorithm is derived. The effectiveness of this method has been demonstrated through experiments with simulated signals and mechanical fault signals.