Intelligent identification method for unsafe behaviors of oil and gas laboratory

A security behavior and intelligent recognition technology, applied in the field of behavior recognition, to improve feature extraction capabilities and reduce safety accidents

Pending Publication Date: 2022-03-01
CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides an intelligent identification method for unsafe behaviors in an oil and gas laboratory, and the technical problem to be solved is: how to identify various unsafe behaviors in the laboratory to reduce accidents

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent identification method for unsafe behaviors of oil and gas laboratory
  • Intelligent identification method for unsafe behaviors of oil and gas laboratory
  • Intelligent identification method for unsafe behaviors of oil and gas laboratory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045]The embodiment of the present invention will be explained in detail below in conjunction with the accompanying drawings. The examples given are only for the purpose of illustration, and cannot be interpreted as limiting the present invention. The accompanying drawings are only for reference and description, and do not constitute the scope of patent protection of the present invention. limitations, since many changes may be made in the invention without departing from the spirit and scope of the invention.

[0046] Unsafe behaviors in hazardous work areas may lead to safety accidents. This example collects a large amount of unsafe behavior data for oil and gas laboratories in universities, and extracts and classifies them. As shown in Table 1, according to the different identification objects, they are classified as follows:

[0047] 1. Unsafe behavior of protective wear: Unsafe behavior of protective wear refers to the existence of a small amount of toxic and harmful ga...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the technical field of behavior recognition, and particularly discloses an intelligent recognition method for unsafe behaviors of an oil and gas laboratory, and the method comprises the steps: constructing a face recognition platform through a Retinaface network and an improved Facenet network, intercepting a face part through the Retinaface network, transmitting the face part to the improved Facenet network, comparing the face part with an existing face database, and judging the personnel entering and exiting the laboratory. The Facenet network is improved by replacing a backbone extraction network with a MoilentV1 network and using Triplet Loss and Cross-Entry Loss as loss functions, the accuracy of the network is reduced by 1.55%, and the FPS (frame number per second) is improved by 25. An improved YOLOv4-tiny network is adopted to identify unsafe behaviors of protective wearing, unsafe behaviors of dangerous area invasion, unsafe behaviors of experimenters and unsafe behaviors of illegal use of equipment, a K-means clustering method is used in a first part to select a proper prior box, an ECA attention module is added in a second part to carry out improvement, and the safety of the equipment is improved. Therefore, the feature extraction capability of the network on small targets is improved. Compared with an original YOLOv4-tiny network, the average precision mean value is improved by 21.17%.

Description

technical field [0001] The invention relates to the technical field of behavior recognition, in particular to an intelligent recognition method for unsafe behavior in an oil and gas laboratory. Background technique [0002] As the country's demand for high-tech talents increases, as an important base for teaching and scientific research, the construction of university laboratories is also advancing by leaps and bounds. Although major universities attach great importance to laboratory safety construction and management, laboratory accidents still occur frequently, especially in oil and gas laboratories. The oil and gas fire and explosion laboratory mainly conducts research on the diffusion and explosion properties of oil and natural gas, and the propagation of oil and gas explosions. Because there are many flammable and explosive materials, the experimental operation process is complicated, and the experimental personnel are highly mobile, the risk of accidents in such labor...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06V40/16G06V10/762G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/23213
Inventor 刘成鲁宁余波巫尚蔚孙新毅侯文赛蒲小霞周群
Owner CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap