A new condition assessment method for distribution transformers based on operation data and record text mining technique

Xie, Cheng; Zou, Guoping; Wang, Huifang; Jin, Yongtao

doi:10.1109/ciced.2016.7576179

Cited by 11 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiment verified the excellent performance of the RNN-LSTM model. Investigating similar deep learning approaches, B. Wei et al [27] proposed a deep BP neural network matching model that could extract target objects from operating instructions with an accuracy of 95%. Furthermore, Jin et al [28] introduced an attention mechanism into the LSTM model, whose corresponding accuracy rate, recall rate and F1-value were 93.71%, 92.46%, 93.08% on Chinese NER.…”

Section: Related Workmentioning

confidence: 99%

Entity Extraction of Electrical Equipment Malfunction Text by a Hybrid Natural Language Processing Algorithm

Kong

Yue²,

Shi

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Many electrical equipment malfunction text messages are collected during power system operation and maintenance procedures. These texts usually contain crucial information for maintenance and condition monitoring. Because these power system malfunction texts are characterized by multidomain vocabularies, complex-syntactic structures, and long sentences, it is challenging to for automated systems to capture their semantic meaning and essential information. To address this issue, we propose a hybrid natural language processing (hybrid-NLP) algorithm to extract entities that represent electrical equipment. This algorithm is composed of a dictionary-based method, a language technology platform (LTP) tool, and the bidirectional encoder representations from a transformers-conditional random field (BERT-CRF) model. Significantly, the softmax output layer of the bidirectional encoder representations from the transformers (BERT) model is replaced by the conditional random field (CRF) algorithm to strengthen the contextual relationships between words and thus solve the local optimization of the preferred word label. The effectiveness of the proposed hybrid-NLP method is verified on a realistic dataset. Moreover, a statistical analysis is conducted to provide a reference for the operation and maintenance of power systems. INDEX TERMS electrical equipment malfunction text, natural language processing, entity extraction, BERT-CRF model.

show abstract

Section: Related Workmentioning

confidence: 99%

Entity Extraction of Electrical Equipment Malfunction Text by a Hybrid Natural Language Processing Algorithm

Kong

Yue²,

Shi

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Xie et al. used HMM‐based (hidden Markov model) text reprocessing to extract the key information from fault and defect elimination record texts to assess the operating condition of distribution transformer, combined with typical power‐off tests and live line detecting results [48]. To identify the causes of transformer failure, Ravi et al.…”

Section: Research Status Of Electric Power Knowledge Miningmentioning

confidence: 99%

“…Particularly, Chinese texts possess the general characteristics of obscure, ambiguous, and hardly segmenting [46]. Text data mining provides new and essential insights for asset management decision makers [47], condition assessment [48], deep analysis of power equipment defect [35,49], and analysis of power customer appeals [50]. Xie et al used HMM-based (hidden Markov model) text reprocessing to extract the key information from fault and defect elimination record texts to assess the operating condition of distribution transformer, combined with typical power-off tests and live line detecting results [48].…”

Section: Power Text Data Miningmentioning

confidence: 99%

A survey on the development status and application prospects of knowledge graph in smart grids

Jian

Wang

et al. 2020

IET Generation Trans & Dist

View full text Add to dashboard Cite

With the advent of the electric power big data era, semantic interoperability and interconnection of power data have received extensive attention. Knowledge graph technology is a new method describing the complex relationships between concepts and entities in the objective world, which is widely concerned because of its robust knowledge inference ability. Especially with the proliferation of measurement devices and exponential growth of electric power data empowers, electric power knowledge graph provides new opportunities to solve the contradictions between the massive power resources and the continuously increasing demands for intelligent applications. In an attempt to fulfil the potential of knowledge graph and deal with the various challenges faced, as well as to obtain insights to achieve business applications of smart grids, this work first presents a holistic study of knowledge-driven intelligent application integration. Specifically, a detailed overview of electric power knowledge mining is provided. Then, the overview of the knowledge graph in smart grids is introduced. Moreover, the architecture of the big knowledge graph platform for smart grids and critical technologies are described. Furthermore, this paper comprehensively elaborates on the application prospects leveraged by knowledge graph oriented to smart grids, power consumer service, decision-making in dispatching, and operation and maintenance of power equipment. Finally, issues and challenges are summarised.

show abstract

“…Based on the operation information of all the subsystems, Islam et al introduced a multivariate general regression neural network (GRNN) into the development of an assessment model for power system transformers, in order to improve the comprehensiveness of the assessment. By exploring text mining technology and utilizing historic records, a state evaluation algorithm for distribution transformers was presented in Xie et al The effectiveness of this method had been validated by the successful prediction of 34 events of the deteriorations of distribution equipment. With the aid of neural network and support vector machine clustering technology, a multi‐evidence‐based internal state diagnosis model of distribution transformers was developed in Chen et al, which effectively improved the evaluation accuracy by fusing the evaluation results of different intelligent algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…[6][7][8][9][10] At present, there are many research results on the state evaluation of electric equipment, while the evaluation approaches for better understanding the real-time state of a distribution equipment are still studied at the fundamental level. In addition to commonly used methods, such as expert scoring and fuzzy comprehensive evaluation, [11][12][13] in recent years, many new evaluation methods have been proposed, such as artificial neural network, 14 text mining technology, 15 support vector machine, 16 gray target theory, 17 cloud models, 18 and so on.…”

mentioning

confidence: 99%

A comprehensive real‐time state evaluation strategy for distribution equipment based on MI‐PSO‐BP algorithm

Yang¹,

Shen²,

Yang³

et al. 2019

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary This paper studies a comprehensive state assessment strategy for distribution equipment with the aim to enhance the reliability and real‐time performance of the state evaluation. In an implementation framework of two‐stage evaluation, a qualitative assessment method is employed to carry out the initial state evaluation, in order to provide sufficient training data samples for the real‐time evaluation in the second stage. To improve the accuracy and timelessness of the distribution equipment state evaluation, we use a mutual information‐based technology to refine the training data set and apply particle swarm optimization approach to optimize the parameters of the neural network‐based prediction model that is crucial to the real‐time evaluation. Numerical simulation results are provided to demonstrate the performance of the developed strategy.

show abstract

A new condition assessment method for distribution transformers based on operation data and record text mining technique

Cited by 11 publications

References 4 publications

Entity Extraction of Electrical Equipment Malfunction Text by a Hybrid Natural Language Processing Algorithm

Entity Extraction of Electrical Equipment Malfunction Text by a Hybrid Natural Language Processing Algorithm

A survey on the development status and application prospects of knowledge graph in smart grids

A comprehensive real‐time state evaluation strategy for distribution equipment based on MI‐PSO‐BP algorithm

Contact Info

Product

Resources

About