Abstract: A method and a system for monitoring GIS instrument sulfur hexafluoride data based on edge computing are provided. The method includes the following specific steps: acquiring an instrument image; preprocessing the instrument image based on a generative adversarial network to obtain a first image; establishing a keypoint detection model to perform instrument reading on the first image to obtain reading data; and sending the reading data to a power supply system scheduling background, storing the data and performing early warning operation according to the reading data.

Abstract: A spiking neural network acceleration method includes constructing an approximate computation model according to a spiking neuron model and a spiking coding mode. The approximate computation model utilizes the characteristic that spiking frequency domain coding ignores the time semantics of a spiking sequence, compresses the distribution of spiking signals on a time step, and greatly reduces a spiking routing process and a subsequent neural computation process. The time-driven accelerator replans the computation process of the spiking neural network, sets a deduplication queue and a bitmap to solve the problem of spiking jitter, and realizes efficient support on the inhibitory spiking neural network.

Abstract: A method for segmenting a power line image in real time based on self-supervised learning includes: inputting an input power line sample image and power line sample image mask set for the same batch of images into a region growing algorithm to obtain a single power line sub-image and single power line mask set; randomly extracting at least one single power line image pair for combination, and combining the single power line image pair with a random background picture to generate a power line random background fusion image and power line random background mask set; and carrying out random non-repetitive region growing to obtain image inpainting regions, forming a segmentation mask with the image inpainting regions, obtaining power line segmentation images through an image inpainting algorithm, inputting the power line segmentation images into a power line real-time segmentation network for training, and carrying out predicted segmentation.

Abstract: The present disclosure disclose a vector flux weakening control system for a permanent magnet synchronous motor of an electric drive system, which includes a current closed-loop regulation module, a modulation index deviation calculation module, a current characteristic point setting module, a current compensation vector angle calculation module, a current compensation vector amplitude calculation module, a current compensation vector calculation module and a current instruction correction module.

Abstract: A simulation method of distributed collaborative control for a microgrid under the attack of false data injection based on cyber-physical fusion is provided, which includes: establishing a distributed collaborative control simulation model for the microgrid frequency based on an RT_LAB real-time simulation tool OPAL-RT; designing a distributed collaborative control algorithm of a microgrid under the attack of false data injection based on DSP; simulating real-time communication among distributed generations based on an OPNET; simulating constant injection of false data, to realize that the frequency of each distributed generation in the microgrid is finally strictly tracked to the reference frequency. According to the method provided by the present application, no extra state observer is needed to observe the angular frequency states of local and neighboring nodes, so that the adverse effects caused by the attack of false data with a constant injection can be completely eliminated.

Abstract: The present disclosure disclose a vector flux weakening control system for a permanent magnet synchronous motor of an electric drive system, which includes a current closed-loop regulation module, a modulation index deviation calculation module, a current characteristic point setting module, a current compensation vector angle calculation module, a current compensation vector amplitude calculation module, a current compensation vector calculation module and a current instruction correction module.