Research on transformer fault diagnosis method and calculation model by using fuzzy data fusion in multi-sensor detection system

Zhang, Xuewei; Li, Hanshan

doi:10.1016/j.ijleo.2018.09.017

Cited by 23 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Repeat step 3 until the number of samples in A m reach a certain threshold ε, which can be computed using Eq. (5).…”

Section: Proposed Approachmentioning

confidence: 99%

“…At present, many data mining techniques have presented promising performance to analyze the power transformer operation data. In the literature [4], [5], the fuzzy set methods are applied to monitor the transformer condition based on IEC/IEEE standards. The fuzzy method improves the identification accuracy of transformers and gives remarkable effects, whereas it needs to determine the input/output membership functions, diagnostic rules, and defuzzification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Economic Operation Analysis Method of Transformer Based on Clustering

2019

View full text Add to dashboard Cite

The economic operation of power transformers is analyzed in the present paper, which is performed by the clustering analysis method. In order to overcome the disadvantages of the conventional k-means algorithm lacking the stability and accuracy, we propose a novel boost k-means algorithm by optimizing the choice of initial cluster centers, and no additional parameters are required. The proposed approach outperforms the conventional approach in most experiments, for the best one, the accuracy of the proposed approach is 20.37% higher than that of the traditional approach. More importantly, empirical research is conducted in the paper. The index system reflecting the load characteristics of power transformers is established, and using the boost k-means algorithm, the economic operation analysis of power transformers is conducted. The clustering results of different transformers are obtained and the relevant suggestions are given as well. The empirical analysis results prove the validity of the proposed approach, and it can be efficiently applied for the economic operation analysis of transformers.

show abstract

“…Repeat step 3 until the number of samples in A m reach a certain threshold ε, which can be computed using Eq. (5).…”

Section: Proposed Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Economic Operation Analysis Method of Transformer Based on Clustering

2019

View full text Add to dashboard Cite

show abstract

“…To fuse the monitoring data from multiple sensors efficiently, a variety of fusion models have been proposed [5]. Conventional data fusion methods in fault diagnosis for multisource sensor data include some simple processing algorithms, fuzzy logic algorithms [6], probability-based algorithms, and artificial intelligence algorithms [7][8][9], etc. For example, one of the simple processing algorithms is the weighted average method.…”

Section: Introductionmentioning

confidence: 99%

On-Site Fault Diagnosis for Mechanical Equipment Based on Compressed Sensing of Multisource Data

2023

IJOMAM

View full text Add to dashboard Cite

With the development of the Internet of Things (IoT), on-site fault diagnosis of multisource sensor data is becoming more and more important. Thus, for on-site fault diagnosis implemented on edge computing platform, efficient multisource data fusion and low-cost computation is essential for fault diagnosis. In this study, a fault diagnosis scheme based on multisource sensor data com-pression is proposed, and its advantages include high data compression & fusion efficiency, low computational cost, and fast online training. The method includes reference matrix construction, compression and fusion, sparse vectors calculation, testing sample reconstruction & quality evaluation. First, a reference matrix is constructed with labelled multisource sensor data. Then, the reference matrix is compressed using a measurement matrix, meanwhile, the multisource data samples are fused. Later, the testing sample is sparsely represented based on batch matching pursuit algorithm, and outputs a sparse vector. Finally, based on reconstruction quality evaluation, the pattern of the testing sample is determined. Two cases are employed to validate the effective-ness of the proposed approach, including landfill gas power generator maintenance pattern recognition and multiple redundancy aileron actuator fault diagnosis, and the accuracy is 96.13% and 97.50%, respectively.

show abstract

“…To fuse the collected data from multiple sensors efficiently, a variety of fusion models have been proposed [5]. Conventional data fusion-based fault diagnosis methods for multisource sensor data include some simple processing algorithms, fuzzy logic algorithms [6], probability-based algorithms, and artificial intelligence algorithms [7][8][9], etc. For example, one of the simple processing algorithms is the weighted average method.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis Based on Compressed Sensing of Multisource Data

You

Deng

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

With the development of the internet of things (IoT) and the application of 5G communication, fault diagnosis of massive multisource sensor data becomes more and more important. In this study, a compressed multisource sensor data-based fault diagnosis scheme is proposed, and its advantages include high data compression and fusion efficiency, low computational cost, and a fast online training sample updating rate. The method includes reference matrix construction, reference matrix compression and fusion, sparse vectors calculation, testing sample reconstruction, and quality evaluation. First, a reference matrix is constructed with labeled multisource sensor data, and each column in the matrix is composed of data samples collected from different sources. Then, the reference matrix is compressed using a measurement matrix, meanwhile, the multisource data samples are fused based on weighted summation during the compression. Later, sparse representation based on batch matching pursuit algorithm is conducted, in this step, the compressed testing sample is represented by the compressed reference matrix, and the output of the sparse representation is a sparse vector. After that, elements in the sparse vector corresponding to different patterns are retained exclusively while other elements are set to zero, respectively, and estimated testing samples are reconstructed with the compressed reference matrix and the processed sparse vector. Finally, based on reconstruction quality evaluation, the pattern of the testing sample is determined. Two cases are employed to validate the effectiveness of the proposed approach, including landfill gas power generator maintenance pattern recognition and multiple redundancy aileron actuator fault diagnosis, and the detection accuracy is 96.13% and 96.67%, respectively.

show abstract

Research on transformer fault diagnosis method and calculation model by using fuzzy data fusion in multi-sensor detection system

Cited by 23 publications

References 1 publication

An Economic Operation Analysis Method of Transformer Based on Clustering

An Economic Operation Analysis Method of Transformer Based on Clustering

On-Site Fault Diagnosis for Mechanical Equipment Based on Compressed Sensing of Multisource Data

Fault Diagnosis Based on Compressed Sensing of Multisource Data

Contact Info

Product

Resources

About