Device and method for detecting position of equipment based on machine vision
By adopting machine vision-based detection devices on site in hot rolling mills, the problem of traditional proximity switches being easily damaged in high temperature and humid environments is solved, and long-distance contactless detection of equipment locations is achieved, maintenance costs are reduced and production efficiency is improved.
Patent Information
- Application Number
- CN202411440299.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2025-02-07
AI Technical Summary
In the hot rolling mill site where high temperature and humid temperatures, traditional proximity switches are used to detect the location of the equipment that is prone to damage and the maintenance cost is high, resulting in inaccurate detection of the position of the mechanical equipment and production losses.
Using machine vision-based detection devices, through PLC system, machine vision system and image acquisition device, the camera collects equipment images, and the machine vision system performs information processing, calibrates the X and Y axis positions of the equipment, and realizes long-distance contactless device position detection. .
Long-distance contactless detection of equipment locations is realized, manual maintenance is avoided, maintenance costs are reduced, production efficiency is improved, and production losses caused by equipment failure are avoided.
Smart Images
Figure CN119394169A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of equipment detection, and relates to mechanical equipment position detection, and specifically to a device and method for detecting equipment position based on machine vision. Background Art
[0002] In the hot rolling mill, there is a high temperature environment and a large amount of cooling water in the humid environment. The traditional proximity switch is used to detect the position of the equipment. The proximity switch is close to the equipment, and the equipment is constantly moving, which is easy to cause damage to the proximity switch, especially in unfavorable environments such as high temperature and humidity. The proximity switches are all connected by cables, which has high investment costs and maintenance problems. The position sensors for on-site detection of the position of the equipment are difficult to maintain, resulting in increased maintenance costs and spare parts costs. In addition, when the mechanical equipment is worn, the mechanical equipment cannot be detected, and production losses are caused by equipment failures caused by misdetection and missed detection. Summary of the invention
[0003] The purpose of the present invention is to provide a device and method for detecting equipment position based on machine vision, which adopts machine vision technology to realize long-distance and non-contact equipment position detection through equipment images, avoid manual operation and maintenance, and improve work efficiency.
[0004] The technical solution adopted by the present invention to achieve the above-mentioned purpose is: A device for detecting the position of equipment based on machine vision comprises a PLC system, a machine vision system and an image acquisition device. The PLC system and the machine vision system use a wireless communication system for data transmission. The image acquisition device is connected to the machine vision system. A camera serves as an image acquisition device of the machine vision system to acquire state position signals of mechanical equipment. The machine vision system is used to process the state position signals of the acquired mechanical equipment to correct the X and Y axis positions of the image. The PLC system is used to perform interlocking control according to the equipment position.
[0005] A method for detecting device position based on machine vision comprises the following steps: S1. Collecting image features of mechanical equipment through an image acquisition device; S2. According to the image features of the mechanical equipment, feature calibration is performed on the X-axis and Y-axis positions of the mechanical equipment image; S3. During the flipping process of the mechanical equipment, determine whether the mechanical equipment is at the X-axis or Y-axis position based on the X-axis and Y-axis calibration position features of the mechanical equipment image. If the X-axis and Y-axis calibration position features of the mechanical equipment image are not at the X-axis or Y-axis position, the mechanical equipment is determined to be in the flipping process. When the X-axis and Y-axis calibration position feature contours of the mechanical equipment image are in the X-axis direction, the mechanical equipment is determined to be in the lying position. When the X-axis and Y-axis calibration position features of the mechanical equipment image are in the Y-axis direction, the mechanical equipment is determined to be in the standing position.
[0006] The beneficial effects of the present invention are as follows: the present invention utilizes machine vision technology, adopts an image acquisition device to acquire image features of mechanical equipment, calibrates the X- and Y-axis positions of the mechanical equipment image, edits the position of the mechanical equipment through a program in the machine vision system, and utilizes machine vision to replace traditional limit detection equipment to flip the position of the mechanical equipment, thereby realizing long-distance contactless detection, avoiding manual maintenance, and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0007] Figure 1 It is a schematic diagram of the hardware structure of the device; In the figure, 1. PLC system; 2. Wireless communication system; 3. Machine vision system; 4. Image acquisition device; 5. Mechanical equipment to be tested; Figure 2 It is a characteristic calibration horizontal position picture of the steel coil turning machine; Figure 3 This is a characteristic calibration standing picture of the steel coil turning machine. DETAILED DESCRIPTION
[0008] The method of the present invention is further described below with reference to the accompanying drawings and embodiments: A device for detecting the position of a device based on machine vision, such as Figure 1 As shown, it includes a PLC system 1, a machine vision system 3 and an image acquisition device 4. The PLC system 1 and the machine vision system 3 use a wireless communication system 2 for data transmission. The image acquisition device 4 is connected to the machine vision system 3 through a cable. A camera or a camera is used as the image acquisition device 4 of the machine vision system 3 to collect the state position information of the mechanical equipment. The machine vision system 3 is used to process the collected state position signal of the mechanical equipment and correct the X-axis and Y-axis positions of the image equipment. The PLC system 1 uses SIMATICS7-1500 to perform interlocking control according to the equipment position control needs. The machine vision system 3 uses existing machine vision technology and uses open source program control to calibrate the X and Y axes of the equipment image. The equipment position is edited through the open source program, and the machine vision technology is used to replace the traditional limit detection mechanical equipment flip position, and long-distance contactless detection is realized. Example
[0009] Taking the position detection of a steel coil turning machine as an example, the method of detecting the position of a steel coil turning machine using machine vision includes the following steps: S1, collecting the image features of the steel coil turning machine through the camera; S2. According to the image features of the steel coil turning machine, the X-axis and Y-axis positions of the steel coil turning machine image are calibrated, such as Figure 2 and Figure 3 As shown, the groove profile position of the steel coil turning machine is calibrated; S3. During the turning process of the steel coil turning machine, judge whether the mechanical equipment is at the X-axis or Y-axis position according to the X-axis and Y-axis calibration position features of the steel coil turning machine image. If the X-axis and Y-axis calibration position features of the steel coil turning machine image, that is, the groove contour is not at the X-axis or Y-axis position, it is judged that the steel coil turning machine is in the turning process. When the groove contour of the calibration position feature is in the X-axis direction, it is judged that the steel coil turning machine is in the lying position. When the groove contour of the calibration position feature is in the Y-axis direction, it is judged that the steel coil turning machine is in the standing position.
[0010] In this way, machine vision technology is adopted and mechanical equipment positioning is realized by utilizing machine vision system programming design. It can replace the equipment proximity switch to realize remote contactless detection, avoid the problems of false detection and missed detection of traditional limit detection caused by external reasons, and realize threshold control of mechanical equipment wear by correcting the X-axis and Y-axis position of the image, thus avoiding the problem that mechanical equipment cannot be detected due to wear of mechanical equipment, realizing maintenance-free mechanical equipment position detection equipment, reducing maintenance costs, and avoiding production losses caused by equipment failure due to false detection and missed detection during the detection process.
Claims
1. A device for detecting the position of a device based on machine vision, characterized in that: It includes a PLC system, a machine vision system and an image acquisition device. The PLC system and the machine vision system use a wireless communication system for data transmission. The image acquisition device is connected to the machine vision system. The camera serves as an image acquisition device of the machine vision system to collect status and position signals of mechanical equipment. The machine vision system is used to process the status and position signals of the collected mechanical equipment and correct the X and Y axis positions of the image. The PLC system is used to perform interlocking control according to the needs of equipment position control.
2. A method for detecting the position of a device based on machine vision, characterized in that: The steps include: S1. Collecting image features of mechanical equipment through an image acquisition device; S2. According to the image features of the mechanical equipment, feature calibration is performed on the X-axis and Y-axis positions of the mechanical equipment image; S3. During the flipping process of the mechanical equipment, determine whether the mechanical equipment is at the X-axis or Y-axis position based on the X-axis and Y-axis calibration position features of the mechanical equipment image. If the X-axis and Y-axis calibration position features of the mechanical equipment image are not at the X-axis or Y-axis position, the mechanical equipment is determined to be in the flipping process. When the X-axis and Y-axis calibration position feature contours of the mechanical equipment image are in the X-axis direction, the mechanical equipment is determined to be in the lying position. When the X-axis and Y-axis calibration position features of the mechanical equipment image are in the Y-axis direction, the mechanical equipment is determined to be in the standing position.