Liang Lifan

TL;DR: In this article, a security and fire-protection remote monitoring system and a method applied to a 500kV transformer substation is presented, which combines visual monitoring and scheduling of the power grid, linkage and automatic push of video are achieved.

TL;DR: Wang et al. as mentioned in this paper proposed a method for detecting the closing operation of an isolating switch based on machine vision, which combines depth learning with classic machine vision method to estimate the position and angle of the knife and switch.

TL;DR: Wang et al. as discussed by the authors proposed an evaluation method of a lightning arrester running state based on big data. But the evaluation method is limited to big data only, and the evaluation of the running state is not applicable to small data.

TL;DR: In this paper, the authors proposed a self-defined feature extraction method for image noise detection based on transformer substation images, and the method comprises the steps: collecting a transform substation image, and calculating an image x-direction gradient graph and an image y-direction gradients graph; traversing the to-be-detected image and calculating a gradient direction angle of each pixel point according to the gradient map; giving a direction distribution number, calculating the direction distribution value of pixel point in each direction according to gradient value and the direction angle; calculating anintegral graph

TL;DR: In this article, a transformer substation online monitoring system emergency alarm method periodically and dynamically calculate the alarm reference value of the device so as to improve the validity of device alarm reference setting, provide a method and a means for accurate assessment of a device health condition and improve the accuracy of device alarms.