Application and Comparative Analysis of Traditional Machine Learning and Deep Learning in Transmission Line Fault Classification

Qian, He; Chen, Li; Tang, Wei; He, Guoqing; Tan, Shan; Shu, Yongqian; Jiang, Lijuan

doi:10.1109/imcec55388.2022.10020121

Cited by 3 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Confusion matrix is a visual tool that provides a clear illustration of classification accuracy by comparing classification results with actual measured values. The confusion matrix, also known as the probability matrix or error matrix, grows into an X‐by‐X matrix with rows and columns denoting the many classes in issues involving X‐classification [49]. In this work, a confusion matrix with a structure made up of four elements has been used, which is shown in Figure 3.…”

Section: Methodologiesmentioning

confidence: 99%

“…The ratio of correctly predicted labels to the total number of samples in the testing set is used to measure the model's accuracy [49]. In fault detection and classification tasks, accuracy plays a multifaceted role.…”

Section: Methodologiesmentioning

confidence: 99%

“…The detect dataset was utilized for fault detection, containing two distinct labels such as normal and fault. On the other hand, six different labels, including normal state, two‐phase short circuit fault (LL), three‐phase short circuit fault (LLL), single‐phase ground fault (LG), two‐phase ground short circuit fault (LLG), and three‐phase ground short circuit fault (LLLG), have been used in the class dataset for fault classification purposes [49].…”

Section: Methodsmentioning

confidence: 99%

“…AdaBoost is an ensemble learning algorithm known for its simple structure and parameter-free nature while having the resistance to overfitting and the ability to combine multiple weak classifiers into a strong classifier [49]. This algorithm is popular for classification tasks.…”

Section: Adaboostmentioning

confidence: 99%

“…Open datasets have been used to facilitate TLs fault diagnosis and evaluate their performance under cyber-attacks. The details about the data collection process are discussed in [49], where both the dataset for detection and the dataset for classification have been used for independent investigations on the detectors and classifiers. The detect dataset was utilized for fault detection, containing two distinct labels such as normal and fault.…”

Section: Data Collection and Processingmentioning

confidence: 99%

See 4 more Smart Citations

A comparative analysis of different transmission line fault detectors and classifiers during normal conditions and cyber‐attacks

Tusher,

Rahman,

Islam

et al. 2024

The Journal of Engineering

View full text Add to dashboard Cite

Transmission lines, the core part of the transmission and distribution system in the smart grid, require effective, efficient, and reliable protective measures against faults to avoid severe damage to physical infrastructure and financial losses. Due to their growing popularity, machine learning models are used in fault detection and classification, whose performances can be severely affected by cyber‐attacks due to their data dependency, posing a critical concern. Hence, this paper introduces false data injection attacks to address the vulnerability of machine learning‐based fault detectors and classifiers. A comparative study of 9 detection models and 6 classification models under normal conditions and during a combination of two models of false data injection attacks is presented to evaluate the severity of cyber‐attacks. Experimental results show that highly accurate models in normal conditions are more susceptible to cyber‐attacks, with up to 69% and 28% degradations in accuracy for fault detectors and classifiers, respectively. Furthermore, the detection models are found to be more vulnerable to cyber‐attacks than the classification models. With no robust detectors and classifiers being found, this work addresses the importance of developing attack‐resilient fault detection and classification schemes considering their academic and industrial significance.

show abstract

Section: Methodologiesmentioning

confidence: 99%

Section: Methodologiesmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Adaboostmentioning

confidence: 99%

Section: Data Collection and Processingmentioning

confidence: 99%

See 3 more Smart Citations

A comparative analysis of different transmission line fault detectors and classifiers during normal conditions and cyber‐attacks

Tusher,

Rahman,

Islam

et al. 2024

The Journal of Engineering

View full text Add to dashboard Cite

show abstract

A Fast Response Fault Detection Technique for HVAC Transmission Line Using Machine Learning

Muntasir,

Al Wazed Wasi,

Nafis

et al. 2023

2023 10th IEEE International Conference on Power Systems (ICPS)

View full text Add to dashboard Cite

Automated Manufacturing Robot Fault Diagnosis in Real Time Using Convolutional Neural Networks

Mahdi,

Shelke

et al. 2024

JMC

View full text Add to dashboard Cite

This study introduced a novel real-time Fault Diagnosis Model (FDM) in manufacturing robots by integrating Depthwise Convolutional Neural Networks (CNNs) with Bidirectional Long Short-Term Memory (BiLSTM) networks. The objective is to design a model that can handle the complex high-dimensional sensor data that arrives out of complex, non-linear systems for effective FDM. The work introduced a Feature Extraction (FE) model based on Monte Carlo Filtering (MCF). The work integrates a Depthwise CNN with BiLSTM (DC-BiLSTM) for diagnosis. The integration helps to reduce the computational need and, at the same time, preserve the feature representation. The model was experimented against other models, such as CNN, Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Feed-Forward Neural Networks (FFNN), using a fault dataset sourced from a simulated environment. The results have shown that the proposed model fared well in terms of accuracy, precision, recall, and F1 score against all compared models. The results have judged the proposed model’s applicability in the field of fault diagnosis, which could effectively predict mishaps in advance, thereby helping with efficient maintenance and ensuring continuous productivity.

show abstract

Application and Comparative Analysis of Traditional Machine Learning and Deep Learning in Transmission Line Fault Classification

Cited by 3 publications

References 10 publications

A comparative analysis of different transmission line fault detectors and classifiers during normal conditions and cyber‐attacks

A comparative analysis of different transmission line fault detectors and classifiers during normal conditions and cyber‐attacks

A Fast Response Fault Detection Technique for HVAC Transmission Line Using Machine Learning

Automated Manufacturing Robot Fault Diagnosis in Real Time Using Convolutional Neural Networks

Contact Info

Product

Resources

About