A on-Line Fault Diagnosis Method of Transmission Line Using Adaptive Neural Network and Wavelet

Li, Yun Feng; Li, Xian Li; Zhu, Qing Sheng; Cao, Yu; Zhang, Jiawei

doi:10.1142/9789812701695_0091

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the significance of studying heart sound signals is that waveform changes in heart sounds can often occur before ECG abnormalities and cardiac pain, reflecting early pathological changes in the heart 2 . Owing to the physical characteristics of heart sounds and the limitations of human hearing ability 3 , medical personnel often have considerable clinical experience and time to fully master heart sound auscultation techniques. Therefore, many researchers are committed to finding efficient and accurate methods for automatically diagnosing heart sounds.…”

Section: Introductionmentioning

confidence: 99%

A Cardiac Audio Classification Method Based on Multidimensional Feature Expression

Hu,

Lv,

Jie

et al. 2024

Preprint

View full text Add to dashboard Cite

Heart sound auscultation plays a crucial role in the early diagnosis of cardiovascular diseases. In recent years, great achievements have been made in automatic heart sound classification; however, most methods are based on segmentation features and traditional classifiers, and do not fully use existing deep networks. This paper proposes a cardiac audio classification method based on image expression of multidimensional features (CACIEMDF). First, a 102-dimensional feature vector is designed by combining the characteristics of heart sound data in the time, frequency and statistical domains. Based on the feature vector, a two-dimensional feature projection space is constructed by PCA dimensionality reduction and the convex hull algorithm, and 102 pairs of coordinate representations of the feature vector in the two-dimensional plane are calculated. Each one-dimensional component of the feature vector corresponds to a pair of 2-d coordinate representations. Finally, the one-dimensional feature component value and its divergence from the two categories are used to fill the three channels of a color image, and a Gaussian model is used to dye the image to enrich its content. The color image is subsequently sent to a deep network such as ResNet50 for classification tasks. In this paper, three public heart sound datasets are fused, and experiments are conducted using the above methods. The results show that the proposed method can achieve a classification accuracy of 95.72% for the two-classification task of heart sounds when combined with the current deep network.

show abstract

Section: Introductionmentioning

confidence: 99%

A Cardiac Audio Classification Method Based on Multidimensional Feature Expression

Hu,

Lv,

Jie

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The literature (Li LF, Rao D, Fan R, Zhang H, Wang J, Luo HY, Liu Z & Xu GH, 2022) takes the pre-processed traveling wave data and trains the data using Long-Short term Memory (LSTM) networks. In the literature (Liu F, Li YK, Gao F, et al, 2021), wavelet scattering feature extraction is performed on the fault zero sequence current signal to obtain the fault feature vector, which is then input to the Bi-LSTM network for training. The literature (R. Resmi, V. Vanitha, E. Aravind, B. R. Sundaram, C. R. Aswin & S. Harithaa, 2019) provides all the collected three-phase voltages and currents to the Artificial Neural Network (ANN) algorithm for detecting the fault type.…”

Section: Introductionmentioning

confidence: 99%

Transmission Line Fault Classification Based on Higher-Order Spectrum and ResNet

Wang

Shan-hua

2023

IST

View full text Add to dashboard Cite

The accurate classification of transmission line faults has been a key issue in the development of smart grids. At present, fault classification is based on recurrent neural network (RNN) for temporal signals, and the development of RNN is not so mature compared with convolutional neural network (CNN). Therefore, this paper proposes a transmission line fault classification algorithm based on higher-order spectral analysis and CNN, aiming at converting the time-series signals into images and using CNN for fault classification. After establishing the fault model on Matlab/Simulink, the current signals of different faults are obtained. After processing the current signals to extract their zero-mode currents, the fault image signals are obtained using higher-order spectral analysis as the input to the CNN. Simulation results show that the proposed method can accurately identify faults with high accuracy when faults occur in transmission lines, thus reducing the economic losses caused by faults.

show abstract

A on-Line Fault Diagnosis Method of Transmission Line Using Adaptive Neural Network and Wavelet

Cited by 2 publications

References 0 publications

A Cardiac Audio Classification Method Based on Multidimensional Feature Expression

A Cardiac Audio Classification Method Based on Multidimensional Feature Expression

Transmission Line Fault Classification Based on Higher-Order Spectrum and ResNet

Contact Info

Product

Resources

About