Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A camera moving method for detecting faults

A camera and fault technology, applied in the field of fault detection, can solve the problems of installing multiple cameras for multi-view monitoring, low efficiency of monitoring mechanical faults, and inability to assist employees to find fault points in time, so as to reduce detection time and increase monitoring employee tasks volume, to avoid the effect of uploading a large amount of data

Inactive Publication Date: 2018-12-14
四川能投云电科技有限公司
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The object of the present invention is to provide a method for moving a camera for fault detection, which not only solves the problem of low efficiency of monitoring mechanical faults by manually guarding the machine, but also solves the problem of installing multiple cameras for multi-view monitoring, and Failure to assist employees to find out the point of failure in time

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] A camera moving method for fault detection includes a cloud platform, a camera and a PC end, the camera is set up on the cloud platform, and the camera is connected to the PC terminal. The method includes the following steps:

[0032] S1: A three-dimensional space coordinate system established with the initial installation position of the gimbal as the origin and the horizontal plane as the reference plane;

[0033] S2: Calculate the coordinates of the easy-to-fault points according to the three-dimensional space coordinate system, and set the vertical and horizontal motion ranges of the pan / tilt according to the distribution of the easy-to-fault points;

[0034] S3: Obtain the preset position of the pan / tilt according to the coordinates of the fault-prone point;

[0035] S4: Record the preset position and the dwell time of each preset position into the PTZ;

[0036] S5: A cruising route formed by connecting multiple preset positions, call point-to-point cruising, and ...

Embodiment 2

[0040] Embodiment 2: In this embodiment, on the basis of the foregoing embodiments, further, the method for determining whether a fault occurs at a fault-prone point during operation of the pan / tilt includes the following steps:

[0041] S6.1: Establish fault characteristic database;

[0042] S6.2: Establish a convolutional neural network to learn the fault feature database;

[0043] S6.3: Obtain two consecutive frames of images in the video stream of the camera;

[0044] S6.4: Perform image recognition on the two frames of images acquired in S6.2 through a convolutional neural network.

[0045]Enter the fault features of the easy-to-fault points into the fault feature database. The fault features of the easy-to-fault points include oil leakage, water seepage, sparks, stuck, component overdistance, etc. The fault feature database is used as the input terminal of the convolutional neural network for the convolutional neural network. Network learning, when the camera moves to ...

Embodiment 3

[0046] Embodiment three: the present embodiment is based on the foregoing embodiments, and the method for determining whether a fault occurs at a fault-prone point during the operation of the pan / tilt platform includes obtaining two frames of images at intervals in the video stream of the camera, which are used for motion The component compares the two frames of images, and if the similarity of the technical features of the two frames of images is greater than the preset threshold, it is judged as a fault. The recording method of S6 includes adjusting the optical zoom factor. When it is judged to be a mechanical failure, the PC sends an instruction to adjust the optical zoom factor to the camera, thereby increasing the optical zoom factor of the camera, and taking a close-up of the fault point, which is convenient for employees to retrieve the video later. Provides a clear picture when stream analyzing the cause of a failure. The dwelling time of the prefabricated position inc...

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 field of detecting faults, in particular to a camera moving method for detecting faults. The invention discloses a camera moving method for detecting faults, comprising apan-and-tilt, a camera and a PC end, wherein the camera is mounted on the pan-and-tilt, the camera is connected with the PC end, and the method comprises the steps: a three-dimensional space coordinate system is established; the coordinates of the easy-to-failure points are sorted out, and the preset positions are obtained according to the coordinates of the easy-to-failure points, cruise lines connected by a plurality of preset positions are called, cruise between the points is called, and the pan-and-tilt runs repeatedly on the set cruise lines, and the easy-to-failure points are detected inthe course of operation, and the results are recorded. The invention not only solves the problem of low efficiency of using manual garrison to monitor mechanical failure beside the machine, but alsosolves the problem of low efficiency of using manual garrison to monitor mechanical failure beside the machine and the problem of inability to assist the staff to find out the failure point in time.

Description

technical field [0001] The invention relates to the field of fault detection, in particular to a camera moving method for fault detection. Background technique [0002] Since entering the 21st century, the concepts of "people-oriented" and "energy saving and environmental protection" have been deeply rooted in the hearts of the people, and new requirements have been put forward for factory automation. With the continuous development and innovation of computer technology, wireless technology, field bus technology, industrial Ethernet technology, IT technology, robotics technology, sensor technology and safety technology, factory automation has experienced stand-alone automation, workshop automation, and whole plant automation. After several important stages such as centralized control, it is developing towards factory comprehensive automation (also known as overall automation), that is, integrating process control, supervisory control, product design, quality monitoring, fact...

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): H04N7/18H04N5/232G06T7/00G06K9/00H04W4/029
CPCH04N17/002G06T7/0004G06V20/40
Inventor 宋振清文富平
Owner 四川能投云电科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com