Power systems
Hamid Reza Sezavar; Saeed Hasanzadeh
Abstract
Insulator pollution levels are critical for ensuring the operational stability and safety of power transmission systems. Traditional methods for detecting pollution are often invasive, inaccurate, and time-consuming. To address these issues, this study investigates the application of Artificial Intelligence ...
Read More
Insulator pollution levels are critical for ensuring the operational stability and safety of power transmission systems. Traditional methods for detecting pollution are often invasive, inaccurate, and time-consuming. To address these issues, this study investigates the application of Artificial Intelligence (AI), specifically Gradient Boosting Machines (GBM), to classify insulator pollution levels based on Partial Discharge (PD) characteristics. We utilize a combination of time-domain and frequency-domain features extracted from PD signals to train a predictive model. The results indicate that the proposed model achieves a high classification accuracy, averaging between 92% and 95% across various contamination levels. Furthermore, the study analyzes the model's sensitivity to environmental factors, including humidity and Hydrophobicity Class (HC), revealing important insights that could influence classification performance. By employing this AI-driven approach, we aim to significantly enhance the efficiency of power grid maintenance, ultimately contributing to the long-term stability and reliability of transmission systems. The findings from this research underscore the potential of AI in revolutionizing pollution assessment methods and optimizing maintenance practices in power infrastructure.
Power systems
Amir Ghaedi; Reza Sedaghati; Mehrdad Mahmoudian; Shahriyar Bazyari
Abstract
Due to the problems associated with overhead lines, underground XLPE cables are increasingly being used in power systems. The main cause of deterioration in these cables is insulation failure, primarily arising from the partial discharge phenomenon. One of the main challenges in online PD detection is ...
Read More
Due to the problems associated with overhead lines, underground XLPE cables are increasingly being used in power systems. The main cause of deterioration in these cables is insulation failure, primarily arising from the partial discharge phenomenon. One of the main challenges in online PD detection is the presence of various noises in the environment that must be eliminated. In recent years, various types of noise with different distributions, such as impulse noises generated by power electronic devices, have been introduced into the power system. Therefore, denoising techniques should be employed to filter out the noises and interferences present in the detected PD signal. Due to the non-stationary nature of PDs, this paper suggests using the wavelet transform method, which covers both the time and frequency domains, to remove various noises from PDs. Consequently, to determine the suitable mother wavelet transform, threshold, and number of decompositions, the characteristics of PD signals occurring in the cables are investigated through experimental tests. Additionally, because different noises exist in substations, the background noise at the measurement site is recorded as a reference noise to be used in the application of the wavelet-based noise removal process. This method is examined on a sample cable, and the results are discussed. Moreover, using the suggested method, the detection of PD signals in several 20 kV substations in Iran is carried out through the use of high-frequency current transformers connected to shield wires, oscilloscopes with high-frequency bandwidth, and MATLAB software.
