Novel criteria for silicone rubber insulators condition monitoring based on leakage current analysis: Considering asymmetric aging and pollution

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 133, P. 108175 - 108175

Published: March 19, 2024

Language: Английский

---

Real-Time Salt Contamination Monitoring System and Method for Transmission Line Insulator Based on Artificial Intelligence

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(4), P. 1506 - 1506

Published: Feb. 13, 2024

Insulators on overhead power lines have long been exposed to the outdoors and are susceptible pollution salt contamination. Due factors such as wind gravity, in atmosphere gradually deposits surface of insulator. In humid windy conditions, conductive pollutants begin dissolve water insulator, increasing leakage current affecting insulation performance. This study mainly uses a data acquisition system measure insulator weather parameters (including temperature, relative humidity, pressure, speed, ultraviolet) around Artificial intelligence is then applied establish prediction model for based parameters. The established accurately predicts through order observe real-time status this establishes monitoring platform that integrates predicted with It allows users or maintenance personnel connect server network results can contamination insulators transmission lines, enabling operation understand actual situation real-time. not only prevent outages due but also reduce workload personnel. Moreover, strategy upgraded from time-base condition-base maintenance, significantly improving efficiency lines.

Language: Английский

---

Framework for decision-making in preventive maintenance: Electric field analysis and partial discharge diagnosis of high-voltage insulators

Electric Power Systems Research, Journal Year: 2024, Volume and Issue: 233, P. 110447 - 110447

Published: May 17, 2024

Language: Английский

---

An improved transfer learning model for detection of insulator defects in power transmission lines

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 27, 2025

Language: Английский

---

A New Box‐Counting‐Based‐Image Fractal Dimension Estimation Method for Discharges Recognition on Polluted Insulator Model

IET Science Measurement & Technology, Journal Year: 2025, Volume and Issue: 19(1)

Published: Jan. 1, 2025

ABSTRACT This study presents an innovative approach to identify electrical discharges by proposing algorithm incorporating fractal geometry concepts. Based on the box‐counting method, our is developed detect and track progression of leading flashover. achieved calculating dimension discharge images which are visual representations activity recorded during experiments a planar glass insulator model subjected different levels contamination. First, RGB image transformed into binary matrix using NIBLAK binarization algorithm. Subsequently, acquired converted square matrix, its computed for various resolutions. The final calculated least squares method. latter applied dimensions (FDs) across all According algorithm, have FD values ranging from 1.15 1.25. increases observed with voltage non‐soluble deposit density (NSDD). also increase FD. Specifically, considered “no‐arc” if less than 1.2 “arc” otherwise.

Language: Английский

---

Experimental validation of machine learning for contamination classification of polluted high voltage insulators using leakage current

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 17, 2025

This paper presents a comprehensive experimental validation of machine learning for contamination classification polluted high voltage insulators using leakage current. A meticulous dataset current porcelain with varying pollution levels was developed under controlled laboratory conditions. Critical parameters temperature and humidity were also included in the to reflect impact environmental conditions bring close real world scenarios. The generated preprocessed critical features extracted from time, frequency, time-frequency domains. Four distinct models, encompassing decision trees neural networks, trained evaluated on this dataset. Bayesian optimization technique used optimize Machine Learning Models. models demonstrated exceptional performance, accuracies consistently exceeding 98 %. Notably, tree-based exhibited significantly faster training times compared their network counterparts. study underscores effectiveness improving reliability insulator maintenance monitoring systems, paving way more robust predictive strategies.

Language: Английский

---

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Sensors, Journal Year: 2024, Volume and Issue: 24(4), P. 1113 - 1113

Published: Feb. 8, 2024

The electrical energy supply relies on the satisfactory operation of insulators. ultrasound recorded from insulators in different conditions has a time series output, which can be used to classify faulty random convolutional kernel transform (Rocket) algorithms use filters extract various features data. This paper proposes combination Rocket algorithms, machine learning classifiers, and empirical mode decomposition (EMD) methods, such as complete ensemble with adaptive noise (CEEMDAN), wavelet (EWT), variational (VMD). results show that EMD combined MiniRocket, significantly improve accuracy logistic regression insulator fault diagnosis. proposed strategy achieves an 0.992 using CEEMDAN, 0.995 EWT, 0.980 VMD. These highlight potential incorporating methods failure detection models enhance safety dependability power systems.

Language: Английский

---

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Medium Voltage Insulator Classification based on Ultrasound Sensor

Published: Jan. 22, 2024

The electrical energy supply relies on the satisfactory operation of insulators. ultrasound recorded from insulators in different conditions has a time series output, which can be used to classify faulty random convolutional kernel transform (Rocket) algorithms use filters extract various features data. This paper proposes combination Rocket algorithms, machine learning classifiers, and empirical mode decomposition (EMD) methods, such as complete ensemble with adaptive noise (CEEMDAN), wavelet (EWT), variational (VMD). results show that EMD methods combined MiniRocket, significantly improve accuracy logistic regression insulator fault diagnosis. proposed strategy achieves respectively an 0.992 using CEEMDAN, 0.995 EWT, 0.980 VMD. These highlight potential incorporating failure detection models enhance safety dependability power systems.

Language: Английский

---

Research on the prediction method of porcelain insulator pollution degree based on electric field monitoring

Electric Power Systems Research, Journal Year: 2024, Volume and Issue: 233, P. 110488 - 110488

Published: May 22, 2024

Language: Английский

---

Artificial intelligence approaches for accurate assessment of insulator cleanliness in high-voltage electrical systems

Electrical Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 27, 2024

Language: Английский

---