The increasing household loads make series arc faults more complex, which are difficult to be detected by traditional circuit breakers and lead to the frequent occurrence of residential fire accidents. In this paper, a comprehensive approach of complex load recognition and series arc detection is proposed on the basis of principal component analysis and support vector machine (PCA-SVM) combination model. Several typical loads were selected and analyzed, especially nonlinear and complex loads like power electronics load and multi-state load. Three time-domain parameters, maximum slip difference (MSD), zero current period (ZCP) and maximum Euclidean distance (MED), and nine frequency-domain harmonics information are collected to complex waveforms. To decrease the computation cost and further to enhance the response velocity, all the time-domain and frequency-domain information were blended and dimensionally reduced to three parameters by principal component analysis (PCA). Prior to the series arc detection, load recognition is trained and completed with the artificial intelligence (AI) algorithm. At last, the comprehensive model of load recognition and series arc detection is achieved based on a support vector machine (SVM). The accuracy of load recognition and series arc detection reaches 99.1% and 99.3%, respectively, demonstrating the excellent performances of the intelligent approach to diagnose the series arcing activities in modern household applications.
Bushings are served as an important component of the power transformers; it's of great significance to keep the bushings in good insulation condition. The infrared images of the bushing are proposed to diagnose the fault with the combination of image segmentation and deep learning, including object detection, fault region extraction, and fault diagnosis. By building an object detection system with the frame of Mask Region convolutional neural network (CNN), the bushing frame can be exactly extracted. To distinguish the fault region of bushings and the background, a simple linear iterative clustering‐based pulse coupled neural network is proposed to improve the fault region segmentation performance. Then, two infrared image feature parameters, the relative position and area, are explored to classify fault type effectively based on the K‐means cluster technique. With the proposed joint algorithm on bushing infrared images, the accuracy reaches 98%, compared with 44% by the conventional CNN classification method. The integrated algorithm provides a feasible and advantageous solution for the field application of bushing image‐based diagnosis.
Power transformer bushings withstand great electrical and mechanical stress during high voltage and high current working conditions. Sealing failure poses a great threat to the long-term and reliable operation of the bushing and power transformer; however, the criterion to evaluate the sealing status of a bushing caused by mechanical problems is still lacking. In this paper, a transformer bushing model is established to gain theoretical insight into the relationship between temperature and pressure of a compact multilayer bushing. To evaluate the bushing mechanical status, different sealing conditions are tested based on the temperature and pressure monitoring within the physical 110 kV bushing. The results show that mechanical sealing failure can be diagnosed when the fluctuation of the oil pressure value exceeds the theoretical curve in steady state by 3 kPa. With different reliability coefficients, gas leakage and oil leakage are available to be further determined. The primary and auxiliary criteria based on oil pressure and its gradient are proposed to evaluate comprehensively the actual sealing condition of the bushing, and a wireless oil pressure module is developed at the bottom valve, which is quite beneficial to field online application. It is promising to extend the online mechanical monitoring and diagnosis to oil-immersed power equipment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.