[0025] The technical solutions of the embodiments of the present invention will be further described below in conjunction with the drawings and specific embodiments.
[0026] Such as figure 1 Shown is a flowchart of an embodiment of a working condition detection method of the present invention, and the method includes:
[0027] Step 101: Collect image information of the belt conveyor;
[0028] Step 102: Analyze and process the image information to determine the operating condition of the belt conveyor.
[0029] In the above step 101, collecting the image information of the belt conveyor can be achieved by setting multiple cameras above the belt conveyor; in the above step 102, the working conditions of the belt conveyor include many parameters, such as the belt conveyor The running speed, the degree of deviation, the degree of longitudinal tearing of the conveyor belt, the distinction between smoke and dust, the detection of piles, the detection of foreign objects and the detection of overloading, etc., the following is to clarify the implementation process of the present invention with respect to these parameter information. among them, Figure 2-Figure 13 The B in all means conveyor belt:
[0030] 1. Judge the running speed of belt conveyor:
[0031] The feature points in two adjacent images are collected periodically, and the displacement of the above feature points is calculated; for example, in this embodiment, by collecting figure 2 Medium conveyor belt B at t n-1 Feature point A and image 3 Medium conveyor belt B at t n The displacement L between the characteristic points A at the moment, the operating speed v of the belt conveyor is calculated according to the following formula:
[0032] v = L Δt X ∂
[0033] Among them, Δt=t n -t n-1; L is the displacement of the characteristic point A in the two images; Δt represents the running time of the belt conveyor, and α is the geometric correction coefficient.
[0034] In addition, such as figure 2 , image 3 As shown, there can be multiple feature points on the conveyor belt, and the specific number can be set according to needs, but in general, the feature points can be divided into a combination of local geometric points inherent in the conveyor belt or material and manual pre-made on the edge of the conveyor belt Mark two kinds.
[0035] 2. Determining whether the belt conveyor is off-track: By comparing the real-time image of the belt conveyor with the standard image saved locally, the amount of off-tracking of the belt conveyor is calculated. For example, you can record the normal operation of the conveyor as Figure 4 The distance between the left edge of the conveyor belt and the left edge of the image shown in l 0 , Real-time measurement acquisition Figure 5 The distance between the left edge of the middle conveyor belt and the left edge of the image l 1 , To calculate the offset of the conveyor belt Δl:
[0036] Δl=l 0 -l 1
[0037] Among them, when Δl>0, it is left deviation; otherwise, it is right deviation.
[0038] 3. Determine whether the belt conveyor has longitudinal tearing: During the operation of the belt conveyor, the conveyor belt is longitudinally torn due to large foreign objects such as sharp gangue, coal and long iron falling on the conveyor belt and jamming. crack. The belt is widened due to the foreign matter stuck in the crack. By measuring whether the width of the conveyor belt in the image becomes wider, it can be determined whether the conveyor belt is torn longitudinally. Image 6 X in 0 Indicates the normal width of the conveyor belt without longitudinal tearing, Figure 7 X in 1 Indicates the width of the conveyor belt after longitudinal tearing, when x 0 1 It can be determined that the conveyor belt has longitudinal tearing.
[0039] 4. Smoke detection: due to mechanical reasons, the conveyor belt and the supporting roller friction and heat, and smoke is generated, and then a fire occurs. The fire can be prevented by monitoring the smoke. The method of judging smoke through the image is similar to judging the presence of dust in the image through the image; but because the color of the smoke is blue, and the color of the dust is basically the same as the color of the material, the smoke can be distinguished by analyzing the different colors in the image And dust.
[0040] 5. Stacking detection: The stacking phenomenon mainly occurs at the conveyor head or other unloading points; by analyzing the collected images of the unloading point, the contour size of the pile is monitored. When the contour of the pile exceeds a predetermined value, It is judged that a pile-up phenomenon has occurred. The predetermined value of the above-mentioned stockpile can be set as required, for example, Figure 8 The contour size of the middle pile C is set to a predetermined value, when Picture 9 When the contour size of the middle stock pile C is greater than the above-mentioned predetermined value, it can be confirmed Picture 9 Stacking phenomenon occurred in the
[0041] 6. Foreign body detection: Foreign body detection is mainly to detect whether there are items on the conveyor belt that affect the safe operation of the conveyor, such as sticks, long irons, people, etc. Because the conveyor mainly carries bulk materials, its shape is obviously different from foreign objects, so through real-time analysis of the collected images, foreign objects can be found, for example, by Picture 10 with Picture 11 The material on the conveyor belt in the image is compared with the shape of the stick D, and it is judged that D is a foreign body.
[0042] 7. Overload detection: For bulk materials, whether the conveyor is overloaded can be judged according to the width of the material flow. Measured by image processing Picture 12 The width of the stream E in is y1, Figure 13 The width of the material flow E in the middle is y2. When y2 is greater than y1, it is judged as overload operation. In addition, after calibration or by knowing the dynamic accumulation angle and bulk density of the material, the conveying volume can also be calculated.
[0043] The above working condition detection method collects the image information of the belt conveyor, and analyzes and processes the image information to determine the working condition of the belt conveyor, avoiding setting multiple sensors at multiple locations on the conveyor belt and reducing The complexity of detection improves the reliability and sensitivity of detection.
[0044] Such as Figure 14 Shown is a schematic structural diagram of an embodiment of a working condition detection device of the present invention. The device includes: a collection unit 11 for collecting image information of a belt conveyor; a processing unit 12 for analyzing and processing the aforementioned image information; The unit 13 is used for judging the working condition of the belt conveyor according to the information processed by the processing unit 12.
[0045] Among them, the above-mentioned acquisition unit can be embedded in the same entity as the processing unit and the detection unit. Of course, it can also be separately arranged in different entities as required. However, no matter which setting method, as long as it includes the above-mentioned acquisition unit, processing unit and detection unit The functions of the unit belong to the technical solution to be protected by the present invention.
[0046] The above-mentioned working condition detection device collects the image information of the belt conveyor through the collection unit, analyzes and processes the above-mentioned image information through the processing unit, and judges the working condition of the belt conveyor through the detection unit, which avoids the excessive use of the conveyor belt. Multiple sensors are arranged in each position, which reduces the complexity of detection and improves the reliability and sensitivity of detection.
[0047] Such as Figure 15 Shown is a schematic structural diagram of an embodiment of a working condition detection system of the present invention. The system includes: a working condition detecting device 1 and a belt conveyor 2. The working condition detecting device 1 is used to collect image information of the above-mentioned belt conveyor 2 Analyze and process the image information, and determine the operating condition of the belt conveyor 2 based on the analyzed and processed information.
[0048] The above-mentioned working condition detection system collects the image information of the belt conveyor and analyzes and processes the image information to determine the working condition of the belt conveyor, avoiding the installation of multiple sensors at multiple locations on the conveyor belt, which reduces The complexity of detection improves the reliability and sensitivity of detection.
[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions recorded in the foregoing embodiments are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
