Electric equipment image analysis has important meanings to power line inspection and repairment. This paper proposes an electric equipment image recognition method based on sparse representation. Considering the image collection is inevitably influenced by the light condition and noise corruption, this paper uses Bayesian compressive sensing algorithm to solve the sparse representation problem. The algorithm has good robustness to noises and interferences, which is suitable to handle the conditions in electrical equipment images. In the experiments, three electrical equipments, i.e., insulators, power transformers, and breakers, are classified and the accuracy reaches 93.56%. In addition, the robustness of the proposed method under noise corruption is also superior. All the results validate the effectiveness of the proposed method.
With the progress and development of society, the power supply quality of power system is required to be higher and higher. It is necessary to locate the fault and remove it quickly. Therefore, it is necessary to install fault indicator on distribution line to improve the efficiency of finding fault location. As an important part of distribution network, the 10kV overhead line has the characteristics of many branches, wide coverage area, time-consuming and labor-consuming in line inspection and maintenance. The fault indicators currently used have problems such as complex structure, high cost of installation and deployment, and inaccurate fault detection. In this paper, a new type of fault indicator is proposed, which uses the comprehensive fault detection method. DSP processor is used to collect, calculate and process the voltage and current information of power grid. Through the embedded programming language, the comprehensive fault detection and identification is realized. Finally, the acquisition accuracy and fault judgment accuracy of the fault indicator are tested by simulating the fault signal in the laboratory. The experimental results show that the proposed fault indicator has high accuracy and can meet the requirements of fault indication, location and alarm.
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.