Energy efficient fault detection and classification using hyperparameter-tuned machine learning classifiers with sensors

Bhattacharya, Debshree; Nigam, Manoj Kumar

doi:10.1016/j.measen.2023.100908

Cited by 5 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both models undergo validation based on accuracy and loss metrics. The comparison in latest works [20][21][22] reveals that CNN surpasses conventional models in terms of accuracy performance.…”

Section: Related Workmentioning

confidence: 95%

Comparative assessment of fault detection methods in transmission line during power swing: analyzing single and hybrid networks for the southern Kerala grid

Ramesh,

Das

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

The blocking function of power oscillation is a highly eﬀective feature found in distance relays. Its purpose is to prevent unintentional tripping of transmission lines. It is crucial to accurately diﬀerentiate between faults and power oscillations in order to minimise the occurrence of widespread power outages and monetary losses. Therefore, the detection and classiﬁcation of faults arising from power swings are critical challenges in ensuring the smooth operation and overall health of transmission lines, particularly in extrahigh-voltage (EHV) and ultra-high-voltage (UHV) power systems. Modern methods rely on machine learning methods which are in their infancy. The paper proposes to identify various fault conditions in transmission lines during power swing by using a hybrid Neural Network architecture. In this research, diﬀerent designs such as 2-D convolution neural network (2D-CNN), 1-D convolution neural network (1D-CNN), long short-term memory (LSTM), and CNN-LSTM hybrid networks are investigated to understand the eﬀect of various deep learning approaches. Along with the southern Kerala Grid, the standard, 9-bus system is selected as a test case for examining various fault circumstances of the system during power swing. Multiple tests were conducted to determine the optimal deep learning architecture, including model parameters and conﬁgurations, for accurate fault detection.

show abstract

Section: Related Workmentioning

confidence: 95%