Cloud-side collaborative power distribution station flame intelligent monitoring method and system

Abstract

The invention discloses a cloud-side collaborative power distribution station flame intelligent monitoring method and system. The method comprises the following steps: collecting a flame data set and marking the flame data set; carrying out migration training and then quantifying into a model Qint8; initializing the summation tree to obtain a video image; filtering out the flame redundant frame to obtain a flame key frame pkey; inputting the flame key frame pkey into a detection network Qint8 for detection; extracting m samples, reminding a user to mark, and uploading the samples marked by the user; enabling the cloud platform to randomly combine the received samples and the existing samples again according to a certain proportion to obtain a new flame data set; then carrying out migration training in combination with an existing network weight; after training is completed, updating the training weight in a soft updating mode; and quantifying into a model Qint8 and issuing. The system comprises a cloud platform, an edge computing platform and video equipment. Through a mode of searching data at an edge end and training the data at a cloud end, the utilization rate of computing resources is improved, task delay is reduced, and the detection precision can be continuously improved.

Description

technical field [0001] The invention relates to the technical field of intelligent video monitoring, in particular to a method and system for intelligent monitoring of fire in a cloud-edge collaborative power distribution station. Background technique [0002] For a long time, the maintenance and management of distribution substations (or switching stations, hereinafter collectively referred to as distribution substations) has been one of the weak links in the reliability of power system operation. The maintenance and management of distribution substation is related to the safety of the whole power system. Since the parameters of the equipment in the distribution station (voltage, current, temperature of high-voltage switch contacts, etc.) It is easy to burn the equipment, cause equipment damage and external power outage, and affect the reliability of power supply. Therefore, real-time monitoring of abnormal conditions in distribution substations is required in order to de...

AI Technical Summary

Problems solved by technology

Although cloud computing uses super computing power to process and analyze data collected and uploaded from the device layer to the cloud platform in terms of processing big data, the surge in the number of devices has led to a surge in the amount of data generated by devices. However, the growth rate of network bandwidth The growth of data is far behind the data, making the network bandwidth a bottleneck, and the increasingly complex network environment makes the problem of network delay more obvious

Therefore, there are network transmission problems in the technical solution of using cloud computing to monitor the abnormal conditions of distribution stations.

However, the technical solution of using edge computing to monitor the abnormal conditions of distribution stations has the problems of insufficient computing power and local storage redundancy.

And neither of the two technical solutions can adapt to the environment and continuously improve the system detection performance

Images