Insulator picture defect detection method based on combination of FasterR-CNN + ResNet101 + FPN

Abstract

The invention discloses an insulator picture defect detection method based on combination of Faster R-CNN + ResNet101 + FPN. The method comprises: collecting an insulator defect sample picture and marking defects; carrying out denoising and anti-shake preprocessing and data expansion, and dividing into a training set and a test set; building an insulator defect detection network model by combiningthe ResNet50 network framework model and the Faster R-CNN detection network model with the FPN feature pyramid network model, and performing target detection training by using the training set to obtain a primary insulator defect detection network model; testing and adjusting parameter optimization by using the test set to obtain a final model; and processing the insulator defect picture to be detected by using the final model. The method can achieve the automatic recognition of the defects of the insulator, is higher in accuracy, is good in stability, is high in anti-interference capability,is high in universality, is good in robustness, and can be used for an intelligent inspection system of a transformer substation.

Description

technical field [0001] The invention relates to a method for identifying defects of substation insulators, in particular to a defect detection method for insulator pictures based on FasterR-CNN+ResNet101+FPN. Background technique [0002] As an important part of high-voltage transmission lines, insulators, on the one hand, play a role of mechanical support for the transmission wires, and on the other hand, effectively prevent the large current in power transmission from forming a grounding loop, which plays a very important role in the smooth and safe operation of the transmission line. role. However, because insulators are exposed to the natural environment all the year round and are eroded by harsh environments such as strong electric fields, mechanical stress, pollution, and temperature and humidity for a long time, many defects usually appear, which will reduce their insulation capabilities or even completely lose them, and interrupt power supply. , and even cause the p...

AI Technical Summary

Problems solved by technology

However, because insulators are exposed to the natural environment all the year round and are eroded by harsh environments such as strong electric fields, mechanical stress, pollution, and temperature and humidity for a long time, many defects usually appear, which will reduce their insulation capabilities or even completely lose them, and interrupt power supply. , and even cause the power grid to split, which will greatly threaten the safety of the high-voltage power grid

However, due to the complex environment of existing insulators, it is not convenient for operators to inspect, and the instability of human factors cannot guarantee the accuracy of inspections. In addition, considering the high cost and high risk of operation and maintenance, traditional low-efficiency artificial The inspection method can no longer meet the demand, and it is urgent to propose an efficient and accurate defect detection method for insulator pictures

Images