Shanghai Jiao Tong University

Siheng Xiong

Yadong Liu

Xiuchen Jiang

Zhe Li

Peng Xu

Xiaofei Fu

Yingjie Yan

Ling Pei

Lei Su

Zihan Cong

Lingen Luo

The present invention provides a high-precision identification method and system for substations, including building a Mask RCNN objection recognition network model based on convolutional neural networks; inputting acquired image information of a object into the Mask RCNN object recognition network model for preliminary recognition and outputting a recognition result of the object; using an information entropy to create a semantic decision tree and correcting the recognition result of the object according to a principle of relative correlation between different objects and outputting a final recognition decision result; reading the recognition decision result to obtain a true type of the object to be recognized. The present invention greatly improves the accuracy of image recognition of substations, and has a positive role in the research and development of automatic inspection equipment for inspection robots.

High-precision identification method and system for substations

The present disclosure provide a method for identifying power equipment targets based on human-level concept learning, including: creating a dataset of power equipment images, and annotating power equipment in power equipment images; training neural network and Bayesian network with the annotated dataset and respectively acquire identification results and conditional probabilities; calculating probabilities of unions with the conditional probabilities; and filtering the identification result corresponding to the highest probability of the union as identification result of the dataset of the power equipment images and complete the identification of the power equipment. The present disclosure combines Mask R-CNN and probabilistic graphical model. The bottom layer uses Mask R-CNN, and the top layer uses Bayesian network to train in identifying power equipment images, so that a small amount of data samples can achieve good recognition, which improved the performance of Mask R-CNN model.

Method for identifying power equipment targets based on human-level concept learning

Power distribution network early failure detection method comprising: a waveform is decomposed into an approximation part and detail parts by wavelet transform, wherein the approximation part is referred to as an approximate shape primitive, and the detail parts are referred to as distortion primitives; the distortion primitives are divided into three primitives including harmonics, pulses and other distortions based on extreme points; characteristics of the primitives and time relationships between the primitives are extracted; probability distribution of the waveform is constructed according to the characteristics of the primitives and the time relationships between the primitives; and a judgment result of the waveform is obtained according to probability distribution of waveforms of different types.

Method for detecting power distribution network early failure

Growing community of inventors

Shanghai, China

Siheng Xiong