Search

The transformer plays a critical role in maintaining the stability and smooth operation of the entire power system, particularly in power transmission and distribution. The paper begins by providing an overview of traditional fault diagnosis methods for transformers, including dissolved gas analysis and vibration analysis techniques, elucidating their developmental trajectory. Building upon these traditional methods, numerous researchers have aimed to enhance and optimize them through intelligent technologies such as neural networks, machine learning, and support vector machines. These researchers have addressed common issues in traditional fault diagnosis methods, such as the low correlation between characteristic parameters and faults, ambiguous fault descriptions, and the complexity of feature analysis. However, due to the complexity of transformer structures and the uncertainties in operating environments, the collection and analysis of characteristic parameters becomes highly intricate. Researchers have further refined algorithms and feature values based on intelligent diagnostic algorithms for transformers. The goal is to improve diagnostic speed, mitigate the impact of measurement noise, and further advance the adaptability of artificial intelligence technology in the field of transformers. On the other hand, the excellent multi-parameter analysis capability of artificial intelligence technology is more suitable for transformer diagnostic techniques that involve the fusion of multiple information sources. Through the powerful data acquisition, processing, and decision-making capabilities provided by intelligent algorithms, it can comprehensively analyze non-electrical parameters such as oil and gas characteristics, vibration signals, temperature, along with electrical parameters like short-circuit reactance and load ratio. Moreover, it can automatically analyze the inherent relationship between faults and characteristic quantities and provide decision-making suggestions. This technique plays a pivotal role in ensuring transformer safety and power network security, emerging as a prominent direction in transformer fault diagnosis research. [ABSTRACT FROM AUTHOR]

Addressing the issues that single-source information cannot comprehensively reflect the operational status of equipment, redundant features fail to diagnose effectively, and information fusion is challenging, this study explores a novel method of feature extraction, selection, and fusion for wind turbine rolling bearing from the perspective of multi-viewpoint and multi-source heterogeneous information fusion, aimed at diagnosing inner ring crack faults of rolling bearings. Initially, based on the failure mechanism of rolling bearings, a multi-source and multi-domain feature set is constructed from both signal processing and data-driven perspectives. By investigating the latent relationships among feature variables, a random forest model is utilized to optimize and reduce the dimensionality of the multi-source feature set. Subsequently, an improved PCR6 method is employed for decision-level fusion of the random forest classification results, thereby facilitating fault extraction, dimensionality reduction, and fault classification of wind turbine bearings from multi-source and multi-viewpoint perspectives. The results indicate that the constructed multi-source and multi-viewpoint feature set enhances the model's recognition performance (with a 5% increase in accuracy), and the fusion of features and decision layers further improves the accuracy of fault diagnosis. In cases where single-feature set classification is erroneous, the proposed decision-layer fusion model's classification probability can provide accurate fault classification. [ABSTRACT FROM AUTHOR]

The current industrial knowledge graph often faces the challenge of data sparsity, which can significantly impact its effectiveness and reliability in daily operational processes. To address this challenge and ensure the integrity of the knowledge graph, we propose a novel method for link prediction that leverages both entity descriptions and neighborhood structure information. Specifically, our method uses BERT pre-training to obtain meaningful embeddings from entity descriptions and the R-GCN model to capture the structural patterns within neighborhoods. Additionally, a CNN is employed to fuse and decode these two types of representations, ensuring high accuracy in predicting missing links. We have evaluated our method on publicly available datasets, and the experimental results show its superiority over baseline models. Furthermore, when tested on the SEFD dataset for steel fault diagnosis, our method effectively completes the knowledge graph for this industrial domain. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has been widely used to promote the development of intelligent fault diagnosis, bringing significant performance improvement. However, most of the existing methods cannot capture the temporal information and global features of mechanical equipment to collect sufficient fault information, resulting in performance collapse. Meanwhile, due to the complex and harsh operating environment, it is difficult to extract fault features stably and extensively using single-source fault diagnosis methods. Therefore, a novel hierarchical vision transformer (NHVT) and wavelet time–frequency architecture combined with a multi-source information fusion (MSIF) strategy has been suggested in this paper to boost stable performance by extracting and integrating rich features. The goal is to improve the end-to-end fault diagnosis performance of mechanical components. First, multi-source signals are transformed into two-dimensional time and frequency diagrams. Then, a novel hierarchical vision transformer is introduced to improve the nonlinear representation of feature maps to enrich fault features. Next, multi-source information diagrams are fused into the proposed NHVT to produce more comprehensive presentations. Finally, we employed two different multi-source datasets to verify the superiority of the proposed NHVT. Then, NHVT outperformed the state-of-the-art approach (SOTA) on the multi-source dataset of mechanical components, and the experimental results show that it is able to extract useful features from multisource information. [ABSTRACT FROM AUTHOR]

Effective fault diagnosis for diaphragm pumps is crucial. This paper proposes a diaphragm pump fault diagnosis method based on deep learning and multi-source information fusion (DMF). The time-domain features, frequency-domain features, and modulation features are extracted from the vibration signals from eight different positions. After feature enhancement and data preprocessing, the features are input into auto encoders (AE), convolutional neural networks (CNN), and support vector machines (SVM) to obtain the diagnostic results. The results indicate that the DMF method achieves a fault diagnosis accuracy of 99.98%, which is on average 9.09% higher than using a single diagnostic model. The demodulation method is more suitable for vibration signal feature extraction of the diaphragm pump, while the CNN is more suitable for identification of diaphragm pump faults. Specifically, it outperformed the sampling point 1-DPCA-AE model by 13.98% and the sampling point 4-DPCA-SVM model by 8.98%. [ABSTRACT FROM AUTHOR]

Applications in industrial production have indicated that the challenges of sparse fault samples and singular monitoring data will diminish the performance of deep learning-based diagnostic models to varying degrees. To alleviate the above issues, a multi-source information fusion meta-learning network with convolutional block attention module (CBAM) is proposed in this study for bearing fault diagnosis under limited dataset. This method can fully extract and exploit the complementary and enriched fault-related features in the multi-source monitoring data through the designed multi-branch fusion structure and incorporate metric-based meta-learning to enhance the fault diagnosis performance of the model under limited data samples. Furthermore, the introduction of CBAM can further assist the model to trade-off and focus on more discriminative information in both spatial and channel dimensions. Extensive experiments conducted on two bearing datasets that cover multi-source monitoring data fully demonstrate the validity and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

The transformer plays a critical role in maintaining the stability and smooth operation of the entire power system, particularly in power transmission and distribution. The paper begins by providing an overview of traditional fault diagnosis methods for transformers, including dissolved gas analysis and vibration analysis techniques, elucidating their developmental trajectory. Building upon these traditional methods, numerous researchers have aimed to enhance and optimize them through intelligent technologies such as neural networks, machine learning, and support vector machines. These researchers have addressed common issues in traditional fault diagnosis methods, such as the low correlation between characteristic parameters and faults, ambiguous fault descriptions, and the complexity of feature analysis. However, due to the complexity of transformer structures and the uncertainties in operating environments, the collection and analysis of characteristic parameters becomes highly intricate. Researchers have further refined algorithms and feature values based on intelligent diagnostic algorithms for transformers. The goal is to improve diagnostic speed, mitigate the impact of measurement noise, and further advance the adaptability of artificial intelligence technology in the field of transformers. On the other hand, the excellent multi-parameter analysis capability of artificial intelligence technology is more suitable for transformer diagnostic techniques that involve the fusion of multiple information sources. Through the powerful data acquisition, processing, and decision-making capabilities provided by intelligent algorithms, it can comprehensively analyze non-electrical parameters such as oil and gas characteristics, vibration signals, temperature, along with electrical parameters like short-circuit reactance and load ratio. Moreover, it can automatically analyze the inherent relationship between faults and characteristic quantities and provide decision-making suggestions. This technique plays a pivotal role in ensuring transformer safety and power network security, emerging as a prominent direction in transformer fault diagnosis research.

Dempster-Shafer theory (DST), as a generalization of Bayesian probability theory, is a useful technique for achieving multi-source information fusion under uncertain environments. Nevertheless, when a high degree of conflict exists between pieces of evidence, unreasonable results are often generated using Dempster's combination rule. How to fuse highly conflicting information is still an open problem. In this study, we first propose an improved belief Hellinger divergence measure, which can fully consider the uncertainty in basic probability assignments, to quantify the conflict level between evidence. Second, some properties (i.e., nonnegativity, nondegeneracy, symmetry, and trigonometric inequality) of the proposed divergence measure are discussed. Then, we present a novel multi-source information fusion strategy, in which the credibility of the evidence is determined based on external discrepancy and internal ambiguity. Additionally, we consider the decay of credibility when fusing evidence across different times. Finally, applications in fault diagnosis and Iris dataset classification are presented to demonstrate the effectiveness of our method. The results indicate that our approach is more reasonable and can identify the target with a higher belief degree. [ABSTRACT FROM AUTHOR]

A radar is an important part of an air defense and combat system. It is of great significance to military defense to improve the effectiveness of radar state monitoring and the accuracy of fault diagnosis during operation. However, the complexity of radar equipment's structure and the uncertainty of the operating environment greatly increase the difficulty of fault diagnosis in real life situations. Therefore, a Bayesian network diagnosis method based on multi-source information fusion technology is proposed to solve the fault diagnosis problems caused by uncertain factors such as the high integration and complexity of the system during the process of fault diagnosis. Taking a fault of a radar receiver as an example, we study 2 typical fault phenomena and 21 fault points. After acquiring and processing multi-source information, establishing a Bayesian network model, determining conditional probability tables (CPTs), and finally outputting the diagnosis results. The results are convincing and consistent with reality, which verifies the effectiveness of this method for fault diagnosis in radar receivers. It realizes device-level fault diagnosis, which shortens the maintenance time for radars and improves the reliability and maintainability of radars. Our results have significance as a guide for judging the fault location of radars and predicting the vulnerable components of radars. [ABSTRACT FROM AUTHOR]

• Innovative Fault Diagnosis: 3D feature maps capture distinct PV array fault conditions. • Multi-Module Fusion: MSIFN integrates TDFM, MSECM, and MMPCM for accurate diagnosis. • Optimized Algorithm: MSFWOA refines WOA for precise hyper-parameter tuning, achieving 99.92 % diagnostic accuracy. Photovoltaic (PV) arrays' random and intermittent output characteristics impact power system safety. To improve the performance of the PV array fault diagnosis model, a novel online fault monitoring technique is introduced. (1) Fault diagnostic model construction: Significant differences in PV arrays' I-V and P-V curves under various fault conditions led to constructing a 3D channel feature map based on I, V, and P features. (2) Multi-source information fusion network (MSIFN): this multi-module fusion model includes a time–frequency domain fusion module (TDFM), a multi-feature shuffle expansion convolution module (MSECM), a parameter-free parallel hybrid attention enhancement module, and a multi-scale mixed pooling fusion classification module (MMPCM). (3) Multi-strategy fusion whale optimization algorithm (MSFWOA): addressing the original WOA's deficiencies, we designed time control, parameter modification, and greedy control strategies based on lens imaging to optimize MSIFN's hyper-parameters. Experimental results show that the MSFWOA-MSIFN model excels in PV array fault diagnosis (P accuracy = P precision = P recall = 99.92 %). In three types of noise experiments with 15 dB, 25 dB, and 30 dB, the average performance index remained above 99 %. In practical experiments, the average performance indices were P accuracy = 97.53 %, P precision = 97.32 %, and P recall = 97.41 %, further demonstrating its excellent diagnostic performance. This model effectively diagnoses various faults in PV arrays, providing scientific and theoretical support for PV system operations. [ABSTRACT FROM AUTHOR]

Effective condition monitoring and fault diagnosis of rolling bearings, integral components of rotating machinery, are crucial for ensuring equipment reliability. However, existing diagnostic methods based on single signals perform poorly due to the detrimental effects of strong noise. Traditional deep learning approaches often neglect the interdependence between data samples when dealing with rolling bearing faults, thus constraining the accuracy and reliability of fault diagnosis. To tackle these challenges, this study introduces an intelligent diagnostic framework that integrates multi-source information at multiple levels, using acoustic and vibration signals (AVS) data and graph neural networks. Firstly, a data-level fusion method called Correlation Variance Contribution is proposed to effectively integrate vibration signals, addressing the issue of multi-source information integration. An Adaptive Convergent Viewable Graph (AcvGraph) is introduced to optimize the representation of original AVS data and fused vibration signals, improving the capturing of correlation relationships within the data and enhancing classification accuracy. Furthermore, an enhanced DiffPool method is utilized to downsample the graph-structured data, reducing feature dimensions while preserving crucial information. Finally, the framework combines and integrates feature vectors from diverse inputs to form global feature vectors, enabling the accurate classification of rolling bearing faults. Exhaustive experiments validate the effectiveness of the proposed framework in utilizing AVS data for detecting different types of faults. Additionally, rigorous comparisons with alternative intelligent diagnosis techniques substantiate the superiority and advancements of the proposed method. • Developed an intelligent diagnostic framework with interpretability using graph neural networks. • Proposed CVC method for integrating vibration signals, improving fault classification accuracy. • Introduced AcvGraph algorithm for capturing correlations in time series data, improving recognition performance. [ABSTRACT FROM AUTHOR]

As faults in the solar water heaters are structurally complicated and highly correlated, an approach of fault diagnosis on the basis of support vector machine and D-S evidence theory has been proposed in this study, attempting to enhance the system's thermal efficiency and ensure its safety. In the approach presented, information of audio conditions, temperature at the outlet of solar thermal collectors, hourly flow and hourly heat transfer rate are accessible, which facilitate the feature evidence and are diagnosed by using "one-against-one" multi-class support vector machine. Experiments are conducted to diagnose fault information fusion and the results show that the diagnosis approach proposed in this study is of high reliability with fewer uncertainties, indicating that the approach is capable to recognize and diagnose solar water heater faults accurately. [ABSTRACT FROM AUTHOR]

Aviation hydraulic pump is one of the key components in aircraft hydraulic system, therefore, high-precision fault diagnosis is essential to improve the reliability and performance of hydraulic pump. A novel multi-source information fusion fault diagnosis method is proposed based on the Dempster–Shafer (D–S) evidence theory, which utilizes the three-level signals from pump level, hydraulic power system level and hydraulic actuation system level. The feature vectors of these three levels are extracted as three bodies of evidences (BOEs) and the fuzzy membership function is employed to construct the basic probability assignments (BPAs) of three BOEs. In order to solve the issue of combining the conflicting evidences, the D–S evidence theory based on the new evidence similarity distance is developed to combine the obtained BPAs. Finally, the making-decision rules are given to diagnose the faults. The diagnosis results validate that the proposed method not only can increase significantly the belief level of supporting the diagnosis target, but also has the ability to diagnose fault of pump correctly even if a sensor is faulty. [ABSTRACT FROM AUTHOR]

Vibration, current, and acoustic signals have different advantages and characteristics in fault diagnosis. Although a few researches have explored their fusion methods and applied them to fault diagnosis fields in recent years, it remains a knotty problem whether the classification results are trustworthy or not. Therefore, in order to facilitate trusted multi-source information fusion learning and deep sensitive fault feature mining, a modified graph convolution network-trusted multi-source information fusion (MGCN-TMIF) framework is designed. First, the modified graph convolution network is used to deeply mine the relationship between samples through the original signals to obtain the nonlinear evidence. Second, the nonlinear evidence is combined with the Dirichlet distribution to obtain the classification probability distribution. Finally, the evidence is integrated by the reduced D-S evidence theory (DST) to obtain the trusted fusion results. The effectiveness of MGCN-TMIF is verified by experimental-level and industrial-level electromechanical coupling equipment datasets, and the results demonstrate the classification accuracy of the proposed method up to 100 %. The proposed fusion diagnosis method is also verified to have high noise robustness performance through anti-noise experiments. [ABSTRACT FROM AUTHOR]

The relationship between the multi-source information fusion and the fault diagnosis is briefly presented, and the general approach of multi-source information fusion based fault diagnosis is introduced. From the viewpoint of fusion structure and algorithms, the classified presentation is given about the multi-source information fusion based fault diagnosis method, and the diagnosis principle and the research status are also described, respectively. It is pointed out that the information fusion fault diagnosis method can be divided into hierarchy, multi-level and combination of neural network information fusion fault diagnosis from the aspect of fusion architecture. From the fusion algorithms, it can be divided into the Bayesian theory, DS evidence theory, fuzzy sets theory, rough sets theory and artificial neural network fault diagnosis methods of multi-source information fusion. Finally, some future development trends of information fusion based fault diagnosis methods are given. [ABSTRACT FROM AUTHOR]

Highlights: [•] A multi-source information fusion based fault diagnosis methodology is proposed. [•] The diagnosis model is obtained by combining two proposed Bayesian networks. [•] The proposed model can increase the fault diagnostic accuracy for single fault. [•] The model can correct the wrong results for multiple-simultaneous faults. [Copyright &y& Elsevier]

• Remote monitoring system for combine harvester developed based on multi-source information fusion and edge computing theory. • The system implements monitoring, fault diagnosis and maintenance information query functions for key components of the combine harvester. • An adaptive fault diagnosis method was proposed to achieve 97.46% fault diagnosis accuracy for combine harvesters. Combine harvesters are prone to blockage, belt burnout and maintenance problems due to their complex transmission structure and variable operating environment. Therefore, a remote monitoring system of combine harvesters based on multi-source information fusion was designed, which could not only realize effective monitoring of combine harvesters, but also realize the functions of fault diagnosis and remote dispatching guidance. By analyzing the working principle and fault mechanism of combine harvester, a fault diagnosis algorithm based on speed fusion index, component slip rate and adaptive threshold discrimination was proposed. Users could obtain the real-time operation status and fault records of the combine harvester anytime and anywhere through the browser. The performance of the combine harvester remote monitoring system was verified through simulation tests and indoor tests. The test results showed that the system met the requirements of combine harvester remote monitoring, and the accurate recognition rate of combine harvester working condition is 97.46%, which has the advantages of high judgment accuracy, fast recognition speed and robustness. [ABSTRACT FROM AUTHOR]