Equipment Fault Detection Research Articles

FedCPG: A class prototype guided personalized lightweight federated learning framework for cross-factory fault detection

Industrial equipment condition monitoring and fault detection are crucial to ensure the reliability of industrial production. Recently, data-driven fault detection methods have achieved significant success, but they all face challenges due to data fragmentation and limited fault detection capabilities. Although centralized data collection can improve detection accuracy, the conflicting interests brought by data privacy issues make data sharing between different devices impractical, thus forming the problem of industrial data silos. To address these challenges, this paper proposes a class prototype guided personalized lightweight federated learning framework(FedCPG). This framework decouples the local network, only uploading the backbone model to the server for model aggregation, while employing the head model for local personalized updates, thereby achieving efficient model aggregation. Furthermore, the framework incorporates prototype constraints to steer the local personalized update process, mitigating the effects of data heterogeneity. Finally, a lightweight feature extraction network is designed to reduce communication overhead. Multiple complex industrial data distribution scenarios were simulated on two benchmark industrial datasets. Extensive experiments have demonstrated that FedCPG can achieve an average detection accuracy of 95% in complex industrial scenarios, while simultaneously reducing memory usage and the number of parameters by 82%, surpassing existing methods in most average metrics. These findings offer novel perspectives on the application of personalized federated learning in industrial fault detection.

BibMon: An open source Python package for process monitoring, soft sensing, and fault diagnosis

This paper introduces BibMon, a Python package that provides predictive models for data-driven fault detection and diagnosis, soft sensing, and process condition monitoring. Key features include regression and reconstruction models, preprocessing pipelines, alarms, and visualization through control charts and diagnostic maps. BibMon also includes real and simulated datasets for benchmarking, comparative performance analysis of different models, and hyperparameter tuning. The package is designed to be highly extensible, allowing for easy integration of new models and methodologies through its object-oriented implementation. Currently, BibMon is in production at Petrobras, a major player in the energy industry, monitoring numerous industrial assets and enabling real-time detection and diagnosis of equipment and process faults. The software is open source and available at: https://github.com/petrobras/bibmon.

Drone image recognition and intelligent power distribution network equipment fault detection based on the transformer model and transfer learning

Drone image recognition and intelligent power distribution network equipment fault detection based on the transformer model and transfer learning

Industrial mechanical equipment fault detection and high-performance data analysis technology based on the Internet of Things

In view of the problems of low detection accuracy, long detection time, and inability to monitor fault data in real time in the fault detection of traditional machinery and equipment, this paper studies the identification and fault detection of industrial machinery based on the Internet of Things (IoT) technology. By using Internet of Things technology to build a mechanical equipment fault detection system, Internet of Things technology can better build diagnostic and early warning modules for the system, so as to achieve the goal of improving the accuracy of equipment fault detection, shortening equipment fault detection time, and remotely monitoring equipment. The fault detection system studied in this paper has an accuracy rate of more than 93.4% to detect different types of fault. The use of Internet of Things technology is conducive to improving the accuracy of mechanical equipment fault detection and realizing real-time monitoring of equipment data.

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.

Substation secondary equipment fault detection based on the Llama2 model

Substation secondary equipment fault detection based on the Llama2 model

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 Unsupervised Low-Light Railway Fastener Image Enhancement Method Based on Contrastive Learning GAN

The railway fastener, as a crucial component of railway tracks, directly influences the safety and stability of a railway system. However, in practical operation, fasteners are often in low-light conditions, such as at nighttime or within tunnels, posing significant challenges to defect detection equipment and limiting its effectiveness in real-world scenarios. To address this issue, this study proposes an unsupervised low-light image enhancement algorithm, CES-GAN, which achieves the model’s generalization and adaptability under different environmental conditions. The CES-GAN network architecture adopts a U-Net model with five layers of downsampling and upsampling structures as the generator, incorporating both global and local discriminators to help the generator to preserve image details and textures during the reconstruction process, thus enhancing the realism and intricacy of the enhanced images. The combination of the feature-consistency loss, contrastive learning loss, and illumination loss functions in the generator structure, along with the discriminator loss function in the discriminator structure, collectively promotes the clarity, realism, and illumination consistency of the images, thereby improving the quality and usability of low-light images. Through the CES-GAN algorithm, this study provides reliable visual support for railway construction sites and ensures the stable operation and accurate operation of fastener identification equipment in complex environments.

Transformer equipment fault detection based on multiple machine learning algorithms

Transformer is an indispensable equipment in the power system, and its normal operation plays a vital role in the stable operation of the power system and power quality. However, due to the complexity of the working environment of the transformer, its internal structure is also more complex, so the transformer failure frequency is higher. Therefore, timely detection and early warning of transformer failure is of great importance. In this paper, a machine learning algorithm is introduced to automatically discover the laws and patterns in the data by learning and analysing a large amount of data, and use these laws and patterns to make predictions and decisions. In this paper, the winding temperature indicator, oil temperature indicator alarm, oil temperature indicator trip and magnetic oil level indicator are taken as the target variables, and the current and voltage parameters are taken as the input variables, and the dataset is divided into training set, validation set and test set according to the ratio of 6:2: 2. The dataset is divided into training set, validation set and test set, and 12 kinds of machine learning models are introduced to predict the winding temperature indicator, the oil temperature indicator alarm, the oil temperature indicator trip, and the magnetic oil level indicator, respectively. indicator alarm, oil temperature indicator trip, and magnetic oil level indicator values, respectively, to observe the operating status of the transformer in real time by predicting the transformer state parameters. The results show that the machine learning model has high application value in transformer condition monitoring. Through the input of current and voltage parameters, the machine learning model can accurately predict and monitor the important indicators of the transformer, and discover the abnormal state of the transformer in time, so as to ensure the safe operation of the transformer. In the prediction of winding temperature, oil temperature and oil temperature indicator tripping, the prediction accuracy of the 12 machine learning models reaches more than 85%, and the prediction accuracy of some models even reaches 100%. For magnetic oil level prediction, the prediction accuracy of the 12 machine learning models is more than 90%. These results show that the machine learning models have high accuracy and stability and can provide reliable technical support for transformer fault detection. In summary, machine learning algorithms have high application value in transformer fault detection, which can automatically discover the laws and patterns in the data by learning and analysing a large amount of data, and use these laws and patterns to make predictions and decisions.

A roundtrip probability estimation method for mechanical equipment fault detection under imbalanced samples

Aiming at high misdetection of mechanical faults under imbalanced samples, a roundtrip probability-based method is proposed. By roundtrip mapping between latent variables and real fault data, biased estimation of the probability distribution of real fault data is obtained. Further, virtual fault data are sampled according to such distribution to increase sample amount. For recognition of real and virtual data, loss function based on binary cross-entropy is designed. For reconstruction between fault data and its roundtrip mapped results, objective function based on mean square error is designed. Thus, it preserves boundary data and avoids too many virtual data in central area. Meanwhile, a strategy for eliminating abnormal samples is designed to reduce boundary deviation. For supporting the advantage of roundtrip, in-depth reasons for misdetection are analyzed from empirical risk and structural risk. Experiments on 30 benchmark imbalanced test sets show that fault detection rate increases after amount enhancement. Additionally, it is verified on blade cracking and bearing fault detection. Results show that F1 score increases from 0.485 to 0.51 and 0.725 to 0.775 for such two cases.

Lightweight Defect Detection Equipment for Road Tunnels

Lightweight Defect Detection Equipment for Road Tunnels

Gearbox Condition Monitoring and Diagnosis of Unlabeled Vibration Signals Using a Supervised Learning Classifier

Data-based equipment fault detection and diagnosis is an important research area in the smart factory era, which began with the Fourth Industrial Revolution. Steel manufacturing is a typical processing industry, and efficient equipment operation can improve product quality and cost. Steel production systems require precise control of the equipment, which is a complex process. A gearbox transmits power between shafts and is an essential piece of mechanical equipment. A gearbox malfunction can cause serious problems not only in production, quality, and delivery but in safety. Many researchers are developing methods for monitoring gearbox condition and for diagnosing failures in order to resolve problems. In most data-driven methods, the analysis data set is derived from a distribution of identical data with failure mode labels. Industrial sites, however, often collect data without information on the failure type or failure status due to varying operating conditions and periodic repair. Therefore, the data sets not only include frequent false alarms, but they cannot explain the causes of the alarms. In this paper, a framework called the Reduced Lagrange Method (R-LM) periodically assigns pseudolabels to vibration signals collected without labels and creates an input data set. In order to monitor the status of equipment and to diagnose failures, the input data set is fed into a supervised learning classifier. To verify the proposed method, we build a test rig using motors and gearboxes that are used on production sites in order to artificially simulate defects in the gears and to operate them to collect vibration data. Data features are extracted from the frequency domain and time domain, and pseudolabeling is applied. There were fewer false alarms when applying R-LM, and it was possible to explain which features were responsible for equipment status changes, which improved field applicability. It was possible to detect changes in equipment conditions before a catastrophic failure, thus providing meaningful alarm and warning information, as well as further promising research topics.

Comparative assessment of the production load of specialists in decoding flaw patterns of removable and mobile flaw detection equipment in railway transport

Introduction. In Russian railway transport, flaw detection is one of the reliable methods for assessing the quality of trackbed condition and the most important component of traffic safety. The working conditions of defectogram interpreters in railway transport refer to a complex form of work organization, because professional activities are carried out year-round in various climatic regions, under conditions of exposure to industrial noise and vibration, magnetic fields, etc., contact ultrasound, etc., as well as a number of factors of an unavoidable nature — work in conditions of moving vehicles.
 The study aims to carry out a comparative assessment of the production load of specialists in decoding flaw patterns of removable and mobile flaw detection equipment in railway transport, depending on intra-group differences in working conditions.
 Materials and methods. The authors conducted industrial physiological and hygienic studies with the participation of operators of flaw detectors with different working conditions - decoders of the stationary Center, flaw inspection vehicles and flaw detection wagons. The study was of a complex nature and was carried out at the workplaces of employees, including in the direct performance of official duties. We used timekeeping, professional, and physiological indicators and recorded indicators of functional systems both remotely and through short-term three inspections during the shift.
 Results. Using the example of decoding engineers, scientists have shown a high production load throughout the entire work shift, characteristic of representatives of all three studied objects, with its greatest severity among employees of the stationary defect decoding center. We noted the greatest deviations in accommodation indicators by the end of the work shift, which indicates fatigue of the visual analyzer, requiring the use of rehabilitation measures.
 Conclusion. There is a high production load and the lack of formation of a stable dynamic stereotype of work, which is associated with a high degree of tension in the work process of employees of all groups of flaw detectors in railway transport. The load is most pronounced among the decoding engineers of the flaw detection centers, which requires the organization of a monitoring system for their professional reliability, optimization of work and rest modes.
 Ethics. We have conducted the study in compliance with Ethical principles and the voluntary consent of the participants.

A novel intelligent identification approach based on modified hierarchical diversity entropy and extension theory for diagnosis of rotating machinery faults

Aiming at the troubles of difficult extraction of fault features and low fault recognition rate in rotating equipment fault detection approach, a new technique for intelligent diagnosis based on modified hierarchical diversity entropy (MHDE) and extension theory (ET) is proposed in the thesis. Firstly, MHDE employs to comprehensively describe the fault information of the given signals. Secondly, the MHDE feature sets are regarded as the characteristic parameters of the extension matter element model, and the matter element model in various states is established. Finally, the testing datasets are fed into the matter element model for each operating conditions, and the correlation function is used to compute the comprehensive correlation between the testing datasets and the various conditions of the rotating machinery, so as to realize the qualitative and quantitative identification of the testing datasets. The reliability and superiority of the proposed new approach is validated by real experimental datasets on various rotating machinery types. The analysis results show that the proposed novel technology can effectively excavate the feature information and accurately identify various fault conditions of rotating machinery. In addition, compared with other combined model technology in the paper, the proposed intelligent fault diagnosis technology has better classification performance.

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.

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.

Quick Identification of Open/Closed State of GIS Switch Based on Vibration Detection and Deep Learning

The rapid and accurate identification of the opening and closing state of the knife switch in a gas insulated switchgear (GIS) is very important for the timely detection of equipment faults and for the reduction of related accidents. However, existing technologies, such as image recognition, are vulnerable to weather or light intensity, while microswitch, attitude sensing and other methods are unable to induce equipment power failure with sufficient speed, which brings many new challenges to the operation and maintenance of a GIS. Therefore, this research designs a GIS shell vibration detection system for knife switch state discrimination, introduces a deep learning algorithm for knife switch vibration signal analysis, and proposes a fast convolutional neural network (FCNN) to identify the knife switch state. For the designed FCNN, a normalization layer and a nonlinear activation layer are used after each convolution layer to obviously reduce feature quantity and increase algorithm efficiency. In order to test the recognition performance based on the vibration detection system, this study carried out two kinds of knife switch opening and closing experiments. One group with artificial noise was added, the other group did not include artifical noise, and a corresponding data set was constructed. The experimental results show that the recognition accuracy for both datasets reaches 100%, and the FCNN algorithm is better than the five classical algorithms in terms of prediction efficiency. This study shows that the vibration detection technology based on deep learning can be used to effectively identify the opening and closing state of a GIS knife switch, and is expected to be promoted and applied.

Brain-Inspired Interpretable Network Pruning for Smart Vision-Based Defect Detection Equipment

Detection algorithms play an important role in the life-cycle management of smart vision-based defect detection equipment. This article proposes a brain-inspired interpretable network pruning method for smart detection equipment for online defect detection scenarios. A brain-inspired neuronal circuit decomposition model is constructed from the view of the structure physics of artificial neural networks. To meet the real-time requirements, an interpretable network pruning is proposed in three steps: First, a full-size basic convolutional neural network is constructed. Second, the convolutional neural circuit's extraction method based on a genetic algorithm is designed to evaluate the function of different neural units. Third, a pruning method is proposed to eliminate the redundant convolutional neural circuits and retain key units to balance the accuracy and time efficiency. The experimental results demonstrated the proposed pruning method can improve the frame-pre-second by 116% on the premise of maintaining the detection accuracy of 92%.

Fault Detection and Diagnosis Methods for Sensors Systems: a Scientific Literature Review

Innovation technology in industrial devices allows enhancing process monitoring and control and have a significant impact on communication and interfacing systems within all production contexts, both in the process industries and in the manufacturing sector. Asset status and performances can be monitored by traditional sensors and intelligent devices, wired and wireless, able to collect data and processing them or make them available to specific processing algorithms. Reliability and maintenance researchers and practitioners are focusing on models, tools, and techniques for in field and real-time detection of process anomalies and equipment fault detection. Most analyses start from the assumption that sensors and monitoring systems guarantee reliability and operational availability and that they are always able to provide timely and correct data. Therefore, malfunctions of such devices could affect trust on data-driven analysis and related decision-making process on asset management and workers’ safety. In recent years, different approaches were explored, aimed at recognizing failure mechanisms in industrial measuring devices and sensors systems, both using traditional methodologies or implementing intelligent algorithms, to accurately prevent and predict the anomalies and identify their nature and position before they generate malfunctioning or interruption of plant's operations. This paper proposes a systematic analysis of the scientific literature related to fault/failure detection and diagnosis in sensors and monitoring systems, to obtain an updated state-of-the-art and identify the most promising approaches and research challenges on this topic. A particular focus is dedicated to the usability of soft sensors and artificial intelligence algorithms, in data-driven models.

Research on Network Equipment Fault Detection Based on Fault Tree Analysis

Intelligent fault diagnosis technology has strong robustness and fault tolerance, and has good adaptability to the dynamic changes of the system. Network device fault detection ensures proper running of network devices and ensures network security and reliability. Fault tree analysis method comes from the field of digital electronic technology. Based on fault tree analysis, this paper studies the fault detection of network equipment. Firstly, the fault tree modeling is studied, the mathematical model of the fault tree is constructed, and the fault tree analysis process is designed. Then, the qualitative analysis of the fault tree is studied to find out all the possible factors that cause the fault, and to predict the possible fault of the equipment. Finally, the quantitative analysis of fault tree is studied to obtain the importance of fault tree. According to the importance of different minimum cut sets, it provides a basis for fault detection when network equipment fails.