Intelligent visual early warning system for early gas leakage

Abstract

The invention relates to an intelligent visual early warning system for early gas leakage. The intelligent visual early warning system comprises a detected area, a data collecting and processing module and a central control room, wherein the data collecting and processing module is responsible for real-time storage of monitoring videos and leakage detection and positioning, and the central controlroom is responsible for organic gas leakage display and early warning. The organic gas leakage detection positioning module adopted by the invention belongs to a deep learning hybrid model, and the trained module is embedded into an embedded information processor to realize automatic detection of organic gas leakage in a monitoring video. According to the invention, the models adopted by the system comprise an unsupervised self-encoding model and a supervised target recognition model, the unsupervised self-encoding model avoids the problem that a data set is difficult to collect and label insupervised model training, a training set required by the supervised model training only aims at a data set at a leakage source, the data set is easy to collect and label, the high detection rate andthe low false alarm rate of organic gas detection and positioning are guaranteed, and safety guarantee is provided for the field of petrochemical engineering.

Description

technical field [0001] The invention relates to an early gas leakage intelligent visual early warning system, which belongs to the technical field of organic gas leakage monitoring. Background technique [0002] In petrochemical and other process industries, the leakage of organic gas will cause safety accidents such as explosion, poisoning and environmental pollution. Therefore, early detection of on-site organic gas leakage should be carried out. In terms of organic gas leakage monitoring, traditional sensors have a high rate of false alarms when detecting gas leakage, are greatly affected by the site environment, and cannot accurately determine the location of the leakage, so there is a high risk. Compared with the sensor monitoring method, the infrared camera monitoring method can realize the visual monitoring of organic gas leakage, but it needs to manually observe the real-time monitoring video and judge whether organic gas leakage occurs. , Misreporting situation. ...

AI Technical Summary

Problems solved by technology

However, the network model constructed by deep learning requires a large amount of abnormally labeled data for training. Organic gas leakage is a rare event. In reality, it is difficult to collect a large amount of labeled data that characterizes the abnormal characteristics of organic gas leakage. Detects data similar to leaked gas anomalies as leaked gas anomalies, leading to abnormal false alarms in the system

The network model based on unsupervised deep learning theory can characterize the abnormal spatio-temporal characteristics of non-leakage gas without a large amount of anomaly labeling data, so as to overcome the defects of deep supervised learning detection model, but the model cannot intuitively give the abnormal location of leaking gas

Images