Hybrid feature selection–artificial intelligence–gravitational search algorithm technique for automated transformer fault determination based on dissolved gas analysis

Fang

IET Generation Trans & Dist

et al. 2021

The information of dissolved gas in transformer oil can reflect the potential fault in oil immersed power transformer. In order to improve the accuracy of transformer fault diagnosis, a transformer fault diagnosis model based on IFA-LPboost-CART is proposed here. First, a LPboost-CART model is established. The classification and regression tree (CART) are used as the weak classifiers, and the linear programming boosting (LPboost) ensemble learning method is used to adjust the weight of each weak classifier to construct a strong classifier. Then the improved firefly algorithm (IFA) is adopted to optimize the number of CART and the maximum number of splits of CART in LPboost-CART to obtain the IFA-LPboost-CART model. The experimental results show that, compared with the existing methods, such as CART and support vector machine (SVM), the proposed IFA-LPboost-CART model has higher fault diagnosis accuracy, which can provide technical support for transformer fault diagnosis.

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on transformer fault diagnosis: Based on improved firefly algorithm optimized LPboost–classification and regression tree

Fang

IET Generation Trans & Dist

et al. 2021

Applied Mathematics and Nonlinear Sciences

“…We first expand the feature map by column to get the feature q t ∈ R H×C and sequence q 1 , q 2 , • • • , q w of each column. Then, we send these features one by one into the BLSTM layers for encoding [8]. An LSTM has 512 hidden neurons, and two LSTMs are combined forward and backward, respectively.…”

Section: The Trn Approachmentioning

confidence: 99%

Least-squares method and deep learning in the identification and analysis of name-plates of power equipment

Zhong

Ruan

Abozinadah

et al. 2021

This article proposes a nameplate recognition method based on the least-squares method and deep learning algorithm character feature fusion. This method extracts the histogram of the edge direction of the character and constructs the histogram feature vector based on the wavelet transform deep learning algorithm. We use classifier training for the text recognition of the nameplate to segment the text into individual characters. Then, we extract the character features to build a template. Experiments prove that the algorithm meets the practical application needs of nameplate identification of power equipment and achieves the design goals.

“…For multimodal problems, a niching GSA with neighbors is a promising design [74]. For real-world problems such as power engineering [75], [76], feature selection [77], [78], energy [79], [80] and cloud computing [81], GSA has also exerted the strong optimization ability.…”

Section: Introductionmentioning

confidence: 99%

A Novel Distributed Gravitational Search Algorithm With Multi-Layered Information Interaction

Yang

et al. 2021

IEEE Access

Population structures play a crucial role in individuals' evolution. Gravitational search algorithm (GSA) inspired by physical laws is a population-based algorithm. Its population structure is able to influence the individuals' search behavior. In this paper, we propose a distributed GSA with multi-layered information interaction, termed as MGSA, to offer a good balance between exploitation and exploration. A historical information layer and an elite top layer are designed to improve individuals' interaction. A distributed structure maintains the population diversity. Experimental results on CEC2017 benchmark functions and a real-world static economic dispatch problem confirm the effectiveness of MGSA in comparison with several state-of-the-art algorithms. In addition, landscape search trajectory and population diversity analyses verify the excellent convergence of MGSA.