Visual detection method for wheel damage in mine safety transport vehicles

Abstract

The present invention relates to the field of image processing technology, and more specifically to a method for visually detecting wheel damage on mine safety transport vehicles. The method comprises: obtaining an actual temperature image of the tire of the mine safety transport vehicle upon entering a detection station and an infrared image of the tire during the cooling process; determining the regional contours of the high-temperature region of the tire, and dividing the tire into multiple target regions based on the pixel points of the regional contours of adjacent high-temperature regions; using the highest temperature value in the target region as the regional temperature at the location of the target region, and determining the heat dissipation coefficient of the target region based on the regional temperature at the location of the target region in the infrared images of adjacent frames during the cooling process; selecting the target region corresponding to the largest index as the reference region; and determining the tire thermal fatigue damage parameter of the target region. Thus, the present invention improves the reliability, effectiveness, and accuracy of detecting thermal fatigue damage on the tires of mine safety transport vehicles.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a visual detection method for wheel damage of a mine safety transport vehicle. Background Art

[0002] In mining operations, mine transport vehicles, as key equipment connecting mining areas with mineral processing areas, shoulder the heavy responsibility of transporting ore and other mineral resources. These vehicles utilize flexible and fast transport equipment like trucks, frequently operating under extreme loads. This places significant pressure on the vehicle tires during transport, significantly increasing friction between the tread and the ground, which can easily lead to tire thermal fatigue. Thermal fatigue not only affects tire performance but can even cause serious transportation accidents. Therefore, accurately detecting thermal fatigue damage in mine transport vehicle tires is crucial.

[0003] In some scenarios, infrared thermal sensors are often used to monitor the temperature of tires used in mine safety transport vehicles. This method, however, identifies thermal fatigue damage based on localized temperature anomaly thresholds. This method, however, presents significant drawbacks. Firstly, this method fails to fully analyze the dynamic impact of thermal fatigue on tire thermal balance and the potential threat to tire lifespan, and is prone to misjudgment due to incomplete temperature data. Secondly, there is an inherent temperature difference between the tire's tread pattern and the carcass surface. Using localized temperature anomaly thresholds to identify thermal fatigue damage can mistakenly identify this normal temperature difference as a thermal fatigue damage area, leading to misjudgment of the tire's usage status. This misjudgment can lead to inappropriate tire replacement timing: premature replacement can waste resources, while delayed replacement can create transportation safety hazards. Consequently, the reliability, effectiveness, and accuracy of thermal fatigue damage detection for mine safety transport vehicle tires using this method are low. Summary of the Invention

[0004] In order to solve the technical problems of low reliability, effectiveness and accuracy in detecting thermal fatigue damage of tires of mine safety transport vehicles, the purpose of the present invention is to provide a visual detection method for wheel damage of mine safety transport vehicles.

[0005] In order to solve the above technical problems, the technical solutions adopted are as follows:

[0006] An embodiment of the present invention provides a visual detection method for wheel damage of a mine safety transport vehicle, comprising: obtaining an actual temperature image of the tire of the mine safety transport vehicle entering a detection site and an infrared image during a cooling process; determining the regional contour of the high-temperature area of ​​the tire based on the actual temperature image, and dividing the tire into regions based on the pixel points of the regional contours of adjacent high-temperature areas to obtain multiple target areas; using the highest temperature value in the target area as the regional temperature of the target area, and determining the heat dissipation coefficient of the target area based on the regional temperature of the target area in the infrared image of the adjacent frame during the cooling process; determining the index of the target area as a reference area based on a first area of ​​the target area, a second area of ​​the tire as a whole, and the regional temperature of the target area, and selecting the target area corresponding to the largest index as the reference area; determining the tire thermal fatigue damage parameter of the target area based on the heat dissipation coefficient of the reference area, the heat dissipation coefficient of other target areas, the regional temperature of other target areas in the adjacent frames during the cooling process, and the regional temperature of the reference area.

[0007] Optionally, the regional contour of the high temperature area of ​​the tire is determined according to the actual temperature image, and the tire is regionally divided according to the pixel points of the regional contours of adjacent high temperature areas to obtain multiple target areas, including: performing initial regional division on the tire according to the actual temperature image to obtain the high temperature area of ​​the tire and the regional contour of the high temperature area; determining the tire tread trend curve of the tire according to the vectors in the plane where the adjacent pixel points in the regional contour are located; determining the contour similarity of adjacent high temperature areas based on the tire tread trend curve of adjacent high temperature areas and the distance between the pixel points in the regional contours of adjacent high temperature areas; when the contour similarity is less than or equal to a first threshold, determining the area between adjacent high temperature areas as a tire tread raised area; taking the average of the actual temperatures of the adjacent high temperature areas as the temperature of the tire tread raised area; marking the temperature of the tire tread raised area at the corresponding position in the actual temperature image and re-dividing the tire for a second time to obtain multiple target areas.

[0008] Optionally, performing an initial regional division of the tire based on the actual temperature image to obtain the high-temperature area of ​​the tire and the regional outline of the high-temperature area includes: calculating the maximum inter-class variance of the temperature pixel points on the tread plane in the actual temperature image; performing threshold segmentation on the actual temperature image using the maximum inter-class variance as a threshold to obtain the high-temperature area and the regional outline of the high-temperature area.

[0009] Optionally, based on the tire pattern trend curves of adjacent high-temperature areas and the distances between pixel points in the regional contours of adjacent high-temperature areas, determining the contour similarity of adjacent high-temperature areas includes: calculating a first difference between the tire pattern trend curves of adjacent high-temperature areas, and calculating a first ratio between the first difference and the tire pattern trend curve of the latter high-temperature area in the adjacent high-temperature areas; determining the minimum number of contour pixel points in the regional contours of adjacent high-temperature areas; superimposing the distances between corresponding contour pixel points in the regional contours of adjacent high-temperature areas to obtain a superimposed distance, and calculating a second ratio between the superimposed distance and the minimum number; and determining a first product between the first ratio and the second ratio as the contour similarity of adjacent high-temperature areas.

[0010] Optionally, determining the heat dissipation coefficient of the target area based on the regional temperature of the target area's position in the infrared images of adjacent frames during the cooling process includes: determining the temperature drop coefficient of adjacent frames of the target area based on the regional temperature of the target area's position in the infrared images of adjacent frames during the cooling process; determining the heat dissipation coefficient of the target area based on the temperature drop coefficient of each adjacent frame of the target area.

[0011] Optionally, determining the temperature drop coefficient of the adjacent frames of the target area based on the regional temperature of the target area in the infrared images of the adjacent frames during the cooling process includes: calculating the second difference between the regional temperature of the target area in the infrared image of the current frame during the cooling process and the regional temperature of the target area in the infrared image of the previous frame adjacent to the infrared image of the current frame; determining a third ratio between the second difference and the regional temperature of the target area in the infrared image of the previous frame adjacent to the infrared image of the current frame as the temperature drop coefficient of the adjacent frames.

[0012] Optionally, determining the heat dissipation coefficient of the target area based on the temperature drop coefficients of each adjacent frame of the target area includes: calculating the absolute value of the third difference between the temperature drop coefficients of the connected adjacent frames, and superimposing the absolute values ​​of each third difference to obtain a superimposed absolute value; calculating the fourth difference between the number of frames of the infrared image and a predetermined value, and calculating a fourth ratio between the superimposed absolute value and the fourth difference; normalizing the fourth ratio to obtain the heat dissipation coefficient.

[0013] Optionally, based on the first area of ​​the target area, the second area of ​​the tire as a whole, and the regional temperature of the target area, determining the target area as an index of the reference area includes: calculating a fifth ratio of the first area to the second area; and determining a second product between the fifth ratio and the inverse of the regional temperature as the index of the reference area.

[0014] Optionally, based on the heat dissipation coefficient of the reference area, the heat dissipation coefficient of other target areas, the regional temperature of other target areas in adjacent frames during the cooling process, and the regional temperature of the reference area, determining the tire thermal fatigue damage parameter of the target area includes: calculating a sixth ratio between the heat dissipation coefficient of the other target areas and the heat dissipation coefficient of the reference area; calculating a fifth difference between the regional temperature of other target areas in adjacent frames during the cooling process and the regional temperature of the reference area, and calculating a seventh ratio between the fifth difference and the regional temperature of the reference area; calculating a third product between the average value of the seventh ratio and the sixth ratio; and normalizing the third product to obtain the tire thermal fatigue damage parameter of the target area.

[0015] Optionally, after determining the tire thermal fatigue damage parameter of the target area based on the heat dissipation coefficient of the reference area, the heat dissipation coefficients of other target areas, the regional temperatures of other target areas in adjacent frames during the cooling process, and the regional temperature of the reference area, the method also includes: taking the target area with the largest tire thermal fatigue damage parameter as the shortboard area of ​​the thermal fatigue damage of the tire, and evaluating the service life of the tire through the shortboard area.

[0016] The present invention has the following beneficial effects: first, an actual temperature image of the tire of a mine safety transport vehicle entering a detection site and an infrared image during a cooling process are obtained; then, the regional contour of the high-temperature area of ​​the tire is determined based on the actual temperature image, and the tire is regionally divided according to the pixel points of the regional contours of adjacent high-temperature areas to obtain multiple target areas; and the highest temperature value in the target area is used as the regional temperature of the target area, and the heat dissipation coefficient of the target area is determined based on the regional temperature of the target area in the infrared image of the adjacent frame during the cooling process; secondly, based on the first area of ​​the target area, the second area of ​​the entire tire and the regional temperature of the target area, the index of the target area as the reference area is determined, and the target area corresponding to the largest index is selected as the reference area; finally, based on the heat dissipation coefficient of the reference area, the heat dissipation coefficient of other target areas, the regional temperatures of other target areas in the adjacent frames during the cooling process and the regional temperature of the reference area, the tire thermal fatigue damage parameter of the target area is determined.

[0017] In this way, the embodiment of the present invention performs threshold segmentation on the temperature field of the tire through infrared thermal imaging, extracts the high-temperature area, and divides the tire into regions based on the regional contour characteristics of the high-temperature area, and further analyzes the temperature attenuation characteristics of different regions during the cooling process, that is, the heat dissipation coefficient of each region is used to evaluate the local heat dissipation efficiency of the tire, thereby further evaluating the tire fatigue damage parameters of each region, thereby accurately locating the area of ​​heat dissipation imbalance caused by thermal fatigue, realizing effective detection of wheel damage of mine safety transport vehicles, and improving the reliability, effectiveness and accuracy of detecting thermal fatigue damage of tires of mine safety transport vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A flowchart of a method for visually detecting wheel damage on a mine safety transport vehicle provided by one embodiment of the present invention;

[0020] Figure 2 A schematic diagram of detecting the temperature of tires of a mine safety transport vehicle provided by one embodiment of the present invention;

[0021] Figure 3 A schematic structural diagram of a visual detection system for wheel damage on a mine safety transport vehicle provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0022] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a visual inspection method for wheel damage on mine safety transport vehicles proposed in accordance with the present invention. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0023] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0024] The following describes in detail a specific scheme of a method for visually detecting wheel damage of a mine safety transport vehicle provided by the present invention in conjunction with the accompanying drawings.

[0025] Example 1:

[0026] See also Figure 1 , which shows a flow chart of a method for visually detecting wheel damage of a mine safety transport vehicle provided by one embodiment of the present invention, including:

[0027] Step S101 , obtaining an actual temperature image of the tires of a mine safety transport vehicle entering a detection site and an infrared image during a cooling process.

[0028] Specifically, the present invention provides a visual inspection method for wheel damage on mine transport vehicles. By inspecting the wheels of mine transport vehicles after they have reached the end of their single-use period or their current operation, the vehicle's tires are inspected and cooled to ensure vehicle safety and enable them to return to production more quickly.

[0029] First, the embodiment of the present invention uses infrared temperature sensors and cameras to obtain the actual temperature of various areas on the tire surface of a mine safety transport vehicle entering a testing station, generating an actual temperature image. The actual temperature refers to the temperature immediately after the mine safety transport vehicle enters the testing station and before cooling. The wheels of the mine safety transport vehicle are then cooled. This cooling process must be performed after the mine safety transport vehicle has been idle for a certain period of time to prevent rapid cooling from affecting the wheel's service life and preventing high overall tire temperatures from misjudging areas of thermal fatigue. During the cooling process, multiple fixed-position infrared temperature sensors are used to capture infrared images of the tire at different angles. Visible light cameras work in tandem to provide tire tread details, and each infrared image frame is sequentially labeled according to the capture time. Next, the embodiment of the present invention associates the pixels of the infrared image with a three-dimensional point cloud using calibration parameters to create a temperature-space coordinate mapping table, enabling visualization of the temperature field. Finally, voxel grid filtering is used to reduce noise, while curvature filtering preserves edge features.

[0030] Step S102 : determining the area contour of the high temperature area of ​​the tire according to the actual temperature image, and dividing the tire into regions according to the pixel points of the area contours of adjacent high temperature areas to obtain a plurality of target areas.

[0031] Specifically, the embodiment of the present invention is based on infrared thermal imaging technology, and extracts high-temperature areas by implementing threshold segmentation on the tire temperature field of the wheels of the mine safety transport vehicle, and uses regional structural features to eliminate pattern interference factors, and further analyzes the temperature attenuation laws of different areas during multiple cooling processes, constructs a heat dissipation efficiency evaluation model, and accurately locates the heat dissipation imbalance damage area caused by thermal fatigue, thereby achieving efficient detection of tire damage on the wheels of the mine safety transport vehicle. Among them, when the mine safety transport vehicle enters the inspection station, there are differences in the heating of different areas of the tire. For example, after entering the inspection area and braking, the braking area is the area where the tire is in direct contact with the ground. Due to friction, the temperature of this area is higher, and then there is a large temperature difference between different areas of the tire surface. Therefore, the embodiment of the present invention implements regional division based on the temperature difference on the tire surface to facilitate regional processing of the tire cooling process and refine the tire thermal fatigue damage area.

[0032] Furthermore, the embodiment of the present invention is based on a mine safety transport vehicle entering a detection site, and uses an infrared temperature sensor and a camera to obtain the actual temperature of the tire. When visualizing the temperature field, a single plane in space, such as the sidewall or tread plane, is marked. For example, Figure 2 As shown, Figure 2 A schematic diagram of detecting the temperature of a tire of a mine safety transport vehicle provided by an embodiment of the present invention, using Figure 2 The temperature of the tire is detected in the manner shown.

[0033] Furthermore, as an optional embodiment of the present invention, the regional contour of the high temperature area of ​​the tire is determined according to the actual temperature image, and the tire is regionally divided according to the pixel points of the regional contours of adjacent high temperature areas to obtain multiple target areas, including: performing initial regional division on the tire according to the actual temperature image to obtain the high temperature area of ​​the tire and the regional contour of the high temperature area; determining the tire tread trend curve of the tire according to the vectors in the plane where the adjacent pixel points in the regional contour are located; determining the contour similarity of adjacent high temperature areas based on the tire tread trend curve of adjacent high temperature areas and the distance between the pixel points in the regional contours of adjacent high temperature areas; when the contour similarity is less than or equal to the first threshold, determining the area between adjacent high temperature areas as the tire tread raised area; taking the average of the actual temperatures of the adjacent high temperature areas as the temperature of the tire tread raised area; marking the temperature of the tire tread raised area at the corresponding position in the actual temperature image and re-dividing the tire for the second time to obtain multiple target areas.

[0034] Specifically, an embodiment of the present invention performs two segmentations on the actual temperature image of the tire to determine multiple target areas. Furthermore, as an optional embodiment of the present invention, performing an initial segmentation of the tire based on the actual temperature image to obtain the high-temperature area and the regional outline of the high-temperature area includes: calculating the maximum inter-class variance of temperature pixels on the tread plane in the actual temperature image; and performing threshold segmentation on the actual temperature image using the maximum inter-class variance as a threshold to obtain the high-temperature area and the regional outline of the high-temperature area.

[0035] Specifically, an embodiment of the present invention first calculates the maximum inter-class variance of the temperature pixels on the tread plane in the actual temperature image. This maximum inter-class variance is used as a threshold to perform threshold segmentation on the actual temperature image, thereby obtaining an image of the high-temperature region. Furthermore, for a single-frame image of the high-temperature region, the regional contours of each high-temperature region are obtained. This embodiment of the present invention uses a single side of the tire plane image as the starting point and the normal vector as the regional direction, and then determines the tire tread pattern curve based on the vectors within the plane of adjacent pixels in the regional contour of the high-temperature region.

[0036] Furthermore, the embodiment of the present invention uses the following formula to determine the tire tread trend curve of the tire based on the change relationship between adjacent pixel points in the regional contour of the high-temperature area:

[0037]

[0038] In the above formula, Indicates the tire tread trend curve of the tire. is the number of pixels of the region outline. is the adjacent pixel point of the area contour (i.e. pixel point, and the vector in the plane between the k-1th pixel point). It represents the tire tread trend curve formed by the vectors between adjacent pixel points of the area outline, which is used to reflect the direction of the area outline.

[0039] Furthermore, the embodiment of the present invention compares the contour similarity of adjacent high-temperature areas. If the contour similarity is high, the area between the adjacent high-temperature areas is not a pattern area, and the high-temperature area is an abnormal temperature point. Otherwise, the high-temperature area may be a normal area.

[0040] Further, as an optional embodiment of the present invention, based on the tire pattern trend curves of adjacent high-temperature areas and the distances between pixel points in the regional contours of adjacent high-temperature areas, determining the contour similarity of adjacent high-temperature areas includes: calculating a first difference between the tire pattern trend curves of adjacent high-temperature areas, and calculating a first ratio between the first difference and the tire pattern trend curve of the latter high-temperature area in the adjacent high-temperature areas; determining the minimum number of contour pixel points in the regional contours of adjacent high-temperature areas; superimposing the distances between corresponding contour pixel points in the regional contours of adjacent high-temperature areas to obtain a superimposed distance, and calculating a second ratio between the superimposed distance and the minimum number; and determining a first product between the first ratio and the second ratio as the contour similarity of adjacent high-temperature areas.

[0041] Specifically, the embodiment of the present invention uses the following formula to calculate the contour similarity of adjacent high-temperature areas:

[0042]

[0043] In the above formula, is the contour similarity between high temperature region j and the adjacent high temperature region j+1. It is the difference between the tire pattern trend curves in adjacent high-temperature areas. Represents the tire tread trend curve of the tire in high temperature area j. Represents the tire tread trend curve of the tire in high temperature area j+1. is the mean distance between corresponding pixels in the area contours of adjacent high-temperature areas. is the smaller value of the number of pixels in the area contours of high temperature area j and high temperature area j+1, to prevent the difference in the number of contour pixels in adjacent high temperature areas from causing the formula to be abnormal. represents the number of pixels in the area outline of the high temperature area j, Indicates the number of pixels in the area outline of the high temperature area j+1. The distance between corresponding pixels in the area contours of adjacent high-temperature areas may be a Euclidean distance. The difference between the tire tread trend curves of the regional profiles of adjacent high-temperature areas. The larger the value, the greater the difference between the regional profiles of adjacent high-temperature areas. is the mean distance between corresponding pixels in the contours of adjacent high-temperature areas. The smaller the value, the higher the contour similarity of adjacent high-temperature areas. The product of the difference between the tire tread trend curves of the regional contours of adjacent high-temperature regions and the average value of the distance between corresponding pixel points in the regional contours of adjacent high-temperature regions represents the contour similarity of the high-temperature regions.

[0044] Furthermore, in the embodiment of the present invention, the first threshold can be determined according to actual conditions, and is set to 0.2 in the embodiment of the present invention. When the contour similarity is less than or equal to 0.2, the area between adjacent high-temperature areas is determined to be a tire tread raised area.

[0045] Furthermore, the embodiment of the present invention obtains the tire tread convex area between the high temperature areas and calculates the temperature average of the adjacent high temperature areas. The temperature of the raised area of ​​the tread is then used as the temperature. Based on the adjusted tire tread temperature data, a new actual temperature image is determined. This new actual temperature image is then subjected to secondary threshold segmentation using the maximum inter-class variance method described in the above embodiment to obtain a secondary threshold image. Each temperature region within the secondary threshold image is marked in the initial visualized temperature field. Through these steps, the embodiment of the present invention eliminates the influence of the tire tread on the infrared detected tire temperature and achieves temperature region segmentation.

[0046] Step S103 , taking the highest temperature value in the target area as the regional temperature at the target area, and determining the heat dissipation coefficient of the target area according to the regional temperature at the target area in the infrared images of adjacent frames during the cooling process of the target area.

[0047] Specifically, during the cooling process of the tire according to the embodiment of the present invention, thermal fatigue causes double bonds in the rubber molecules to break, forming microscopic cracks within the material, which in turn blocks the heat transfer path. Different areas of the tire suffer different levels of thermal fatigue damage, resulting in different cooling effects. The more severe the thermal fatigue phenomenon, the worse the heat dissipation effect in the areas with thermal fatigue damage. Therefore, in order to obtain the heat dissipation effect of different areas of the tire during the cooling process, the embodiment of the present invention needs to analyze the temperature changes of the visualized temperature field constructed from infrared images of adjacent frames during the cooling process of the tire, obtain the changing parameters of different areas of the tire during the cooling process, and thereby obtain the heat dissipation coefficient of each target area.

[0048] Further, as an optional embodiment of the present invention, determining the heat dissipation coefficient of the target area based on the regional temperature of the target area in the infrared images of adjacent frames during the cooling process includes: determining the temperature drop coefficient of adjacent frames of the target area based on the regional temperature of the target area in the infrared images of adjacent frames during the cooling process; determining the heat dissipation coefficient of the target area based on the temperature drop coefficient of each adjacent frame of the target area.

[0049] Specifically, the embodiment of the present invention is based on the surface area of ​​the tire, starting from the highest point of the tire, and marking the target area of ​​the tire surface temperature division in clockwise direction. The target area is marked as , the total number of target areas is , the centroid of the target area is the area coordinate point. Among them, the embodiment of the present invention is based on the infrared temperature sensor to obtain the target area The highest temperature value is taken as the regional temperature .

[0050] Further, as an optional embodiment of the present invention, determining the temperature drop coefficient of the adjacent frames of the target area based on the regional temperature of the target area in the infrared images of the adjacent frames during the cooling process includes: calculating the second difference between the regional temperature of the target area in the infrared image of the current frame during the cooling process and the regional temperature of the target area in the infrared image of the previous frame adjacent to the infrared image of the current frame; determining the third ratio between the second difference and the regional temperature of the target area in the infrared image of the previous frame adjacent to the infrared image of the current frame as the temperature drop coefficient of the adjacent frames.

[0051] Specifically, the embodiment of the present invention uses the following formula to calculate the temperature drop coefficient:

[0052]

[0053] In the above formula, Indicates the target area Current frame The target area in the infrared image of the previous frame -1 is the temperature drop coefficient of the target area in the infrared image. Indicates the target area Current frame The regional temperature of the target area in the infrared image. Indicates the target area and the current frame The infrared image of the adjacent previous frame -1 target area in the infrared image The regional temperature at the location. During the cooling process, the previous frame The temperature of the infrared image is always higher than that of the next frame The temperature of the infrared image, therefore Always positive value , The larger the value, the larger the target area The better the heat dissipation effect. Traverse the temperature change parameters of each target area of ​​the tire and obtain the temperature drop coefficient of each target area of ​​the tire ; It should be noted that, in order to ensure that the calculation results are meaningful, when performing fractional operations in the embodiments of the present invention, when encountering a situation where the denominator is 0, it is necessary to add a parameter adjustment factor greater than 0 to the denominator to prevent the denominator from being 0. The value of the parameter adjustment factor is set by the implementer according to the actual situation, and this application does not impose any special restrictions.

[0054] Furthermore, the embodiment of the present invention obtains the temperature value of each target area in the visualized temperature field and the change difference between the temperature drop coefficients of the same target area between the infrared images of adjacent frames. If the change difference between the temperature drop coefficients is small, the heat dissipation effect of the target area of ​​the tire is good, otherwise it is poor. Therefore, the temperature drop coefficients between the target areas in the cooling process are compared to obtain the heat dissipation coefficient of the target area at a single location. .

[0055] Furthermore, as an optional embodiment of the present invention, determining the heat dissipation coefficient of the target area based on the temperature drop coefficients of each adjacent frame of the target area includes: calculating the absolute value of the third difference between the temperature drop coefficients of the connected adjacent frames, and superimposing the absolute values ​​of each third difference to obtain a superimposed absolute value; calculating the fourth difference between the number of frames of the infrared image and a predetermined value, and calculating a fourth ratio between the superimposed absolute value and the fourth difference; normalizing the fourth ratio to obtain the heat dissipation coefficient.

[0056] Specifically, the embodiment of the present invention uses the following formula to calculate the heat dissipation coefficient:

[0057]

[0058] In the above formula, Indicates the heat dissipation coefficient of the target area. The number of the acquisition moment of the infrared image frame. is the total number of collection moments. Indicates the target area Current frame The target area in the infrared image of the previous frame -1 is the temperature drop coefficient of the target area in the infrared image. Indicates the target area of -The target area in the infrared image of frame 1 is different from the previous frame -2 is the temperature drop coefficient of the target area in the infrared image. It is the difference between the temperature drop coefficients of the target area in the infrared images of adjacent frames, indicating the difference in the temperature drop process at adjacent acquisition moments. It is the mean of the differences in temperature drop coefficients during the cooling process, indicating the cooling effect coefficient. The larger the value, the better the cooling effect and the better the heat dissipation effect. Represents a normalization function. The embodiment of the present invention uses The function normalizes the result.

[0059] Step S104 , determining an index of the target area as a reference area based on the first area of ​​the target area, the second area of ​​the entire tire, and the regional temperature of the target area, and selecting the target area corresponding to the largest index as the reference area.

[0060] Specifically, the embodiment of the present invention is based on obtaining the heat dissipation coefficient of each target area of ​​the wheel tire of the mining transport vehicle. . When the tire of a vehicle has no thermal fatigue damage or cracks, the heat dissipation effect of each target area is balanced, that is, the difference in heat dissipation effect of each target area is small. When thermal fatigue damage exists, the heat dissipation performance of the damaged area is reduced, and the heat dissipation coefficient of the damaged area is poor compared with that of the normal area. Therefore, the embodiment of the present invention screens the target area with poor heat dissipation coefficient by comparing the difference in heat dissipation coefficients between different target areas of the tire, and obtains the area damaged by thermal fatigue. The embodiment of the present invention is based on the reference area of ​​the temperature change of the tire surface obtained as a whole. The thermal fatigue damage to different target areas of the tire is quite different. The tire tread is in direct contact with the ground, and the local area of ​​the tread is more seriously damaged by heat. The sidewall is not in direct contact with the ground, and the impact of thermal fatigue damage is relatively small. Therefore, the entire area of ​​the tire without thermal fatigue damage is a normal area.

[0061] Furthermore, as an optional embodiment of the present invention, based on the first area of ​​the target area, the second area of ​​the tire as a whole, and the regional temperature of the target area, determining the target area as an index of the reference area includes: calculating the fifth ratio of the first area to the second area; and determining the second product between the fifth ratio and the inverse of the regional temperature as the index of the reference area.

[0062] Specifically, in the embodiment of the present invention, the first area of ​​the target area is obtained by obtaining the number of pixels in the single target area. And the second area of ​​the entire tire. The embodiment of the present invention specifically uses the following formula to calculate the index of the reference area:

[0063]

[0064] In the above formula, Indicates the target area is the index of the base area. It is the second area of ​​the entire tire. Indicates the target area The first area. The area of ​​the target region The ratio of the area to the overall area. Indicates the target area regional temperature. Target area The inverse proportional coefficient of temperature, Indicates the target area Area The product of the ratio of the area of ​​the entire region and the inverse proportionality coefficient of the temperature is compared. The larger the value is, the greater the probability that it is the reference region.

[0065] Furthermore, the embodiment of the present invention selects The target area is used as the reference area ,in, Choose a function for Maximum.

[0066] Step S105 , determining tire thermal fatigue damage parameters of the target area based on the heat dissipation coefficient of the reference area, the heat dissipation coefficients of other target areas, the regional temperatures of other target areas in adjacent frames during the cooling process, and the regional temperature of the reference area.

[0067] Specifically, the embodiment of the present invention obtains the reference area by the above method. Heat dissipation coefficient in each stage of the cooling process Then, the heat dissipation coefficient of each target area is compared with that of the reference area to obtain the tire thermal fatigue damage parameters of the target area. .

[0068] Furthermore, as an optional embodiment of the present invention, determining the tire thermal fatigue damage parameter of the target area based on the heat dissipation coefficient of the reference area, the heat dissipation coefficient of other target areas, the regional temperature of other target areas in adjacent frames during the cooling process, and the regional temperature of the reference area includes: calculating the sixth ratio between the heat dissipation coefficient of other target areas and the heat dissipation coefficient of the reference area; calculating the fifth difference between the regional temperature of other target areas in adjacent frames during the cooling process and the regional temperature of the reference area, and calculating the seventh ratio between the fifth difference and the regional temperature of the reference area; calculating the third product between the average value of the seventh ratio and the sixth ratio; and normalizing the third product to obtain the tire thermal fatigue damage parameter of the target area.

[0069] Specifically, the embodiment of the present invention uses the following formula to calculate the tire thermal fatigue damage parameter of the target area:

[0070]

[0071] In the above formula, Indicates the target area Tire thermal fatigue damage parameters. is the heat dissipation coefficient of the reference area. Target area Heat dissipation coefficient and reference area The heat dissipation coefficient accounts for . Indicates the target area of ​​the current frame i regional temperature. Represents the reference area of ​​the current frame i regional temperature. is the target area of ​​the current frame i With the reference area The difference coefficient of regional temperature, the larger the value, the target area The worse the heat dissipation effect. Indicates the target area of ​​the current frame i The reference area of ​​the current frame i The mean of the coefficient of variation indicates the overall difference in the heat dissipation process. The product of the heat dissipation coefficient and the overall difference in the heat dissipation process, representing the target area The difference in heat dissipation caused by thermal fatigue damage. The activation function normalizes the result and obtains the target area Tire thermal fatigue damage parameters.

[0072] Furthermore, in the embodiments of the present invention, the thickness of different areas of the tire varies. For example, the tread is thicker in direct contact with the ground, while the sidewall is thinner in indirect contact with the ground. This results in different heat dissipation effects in different areas. Therefore, the embodiments of the present invention obtain tire thermal fatigue damage parameters for each target area of ​​the tire, including the tread and sidewall, based on the reference area, and record the processing results.

[0073] Furthermore, as an optional embodiment of the present invention, after determining the tire thermal fatigue damage parameters of the target area based on the heat dissipation coefficient of the reference area, the heat dissipation coefficients of other target areas, the regional temperatures of other target areas in adjacent frames during the cooling process, and the regional temperature of the reference area, the method also includes: taking the target area with the largest tire thermal fatigue damage parameter as the shortboard area of ​​the thermal fatigue damage of the tire, and evaluating the service life of the tire through the shortboard area.

[0074] Specifically, the embodiment of the present invention obtains the tire thermal fatigue damage parameters of the tire thermal fatigue area of ​​the rear wheels of the transport vehicle under full load. The service life of the tire can be evaluated by the area of ​​the tire that suffers the most damage, that is, the weak area of ​​the tire. Therefore, the embodiment of the present invention screens out The short plate area of ​​the tire is used as the short plate area, and the tire thermal fatigue damage parameters in the short plate area are used as the final test results for evaluating the tire service life.

[0075] The embodiment of the present invention performs threshold segmentation on the temperature field of the tire through infrared thermal imaging, extracts the high-temperature area, and divides the tire into regions based on the regional contour characteristics of the high-temperature area. The temperature attenuation characteristics of different regions during the cooling process are further analyzed, that is, the heat dissipation coefficient of each region is used to evaluate the local heat dissipation efficiency of the tire, thereby further evaluating the tire fatigue damage parameters of each region, thereby accurately locating the area of ​​heat dissipation imbalance caused by thermal fatigue, realizing effective detection of wheel damage of mine safety transport vehicles, and improving the reliability, effectiveness and accuracy of detecting thermal fatigue damage of tires of mine safety transport vehicles.

[0076] Example 2:

[0077] Corresponding to the visual detection method for wheel damage of a mine safety transport vehicle provided in the above embodiment, based on the same technical concept, an embodiment of the present invention further provides a visual detection system for wheel damage of a mine safety transport vehicle. The visual detection system for wheel damage of a mine safety transport vehicle is used to execute the above visual detection method for wheel damage of a mine safety transport vehicle. Figure 3 A schematic diagram of a visual inspection system for wheel damage in mine safety transport vehicles according to an embodiment of the present invention is shown in FIG. Figure 3The visual inspection system for wheel damage of mine safety transport vehicles may have relatively large differences due to different configurations or performances, and may include one or more processors 301 and memory 302. The memory 302 is used to store computer programs that can be run on the processor 301. The processor 301 is used to execute the program stored in the memory 302 to achieve the above Figure 1 The various steps in the method embodiment are described above. Memory 302 may be either transient or persistent storage. The application stored in memory 302 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for a visual inspection system for wheel damage in mine safety transport vehicles.

[0078] Furthermore, the processor 301 can be configured to communicate with the memory 302 to execute a series of computer-executable instructions stored in the memory 302 on the visual detection system for wheel damage on mine safety transport vehicles. The visual detection system for wheel damage on mine safety transport vehicles can also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0079] Specifically, in this embodiment, the visual detection system for wheel damage of mine safety transport vehicles includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to achieve the above Figure 1 The various steps in the method embodiment have the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not be described again here.

[0080] It should be noted that the visual detection system for wheel damage of mine safety transport vehicles provided in an embodiment of the present invention and the visual detection method for wheel damage of mine safety transport vehicles provided in an embodiment of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned visual detection method for wheel damage of mine safety transport vehicles, and has the same or similar beneficial effects, and the repetitions will not be repeated.

[0081] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0083] The embodiment of the present invention further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes Figure 1 The methods disclosed in the illustrated embodiments implement the functions and beneficial effects of the various methods in the preceding method embodiments, which will not be described in detail here.

[0084] Among them, the computer readable storage medium includes read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

Claims

1. A visual detection method for wheel damage of mine safety transport vehicles, characterized in that: include: Obtain the actual temperature image of the tires of mine safety transport vehicles entering the inspection site and the infrared image during the cooling process; Determining a region outline of a high-temperature region of the tire according to the actual temperature image, and dividing the tire into regions according to pixel points of the region outlines of adjacent high-temperature regions to obtain a plurality of target regions; The highest temperature value in the target area is used as the regional temperature of the target area, and the heat dissipation coefficient of the target area is determined according to the regional temperature of the target area in the infrared images of adjacent frames during the cooling process of the target area; determining an index of the target area as a reference area based on the first area of ​​the target area, the second area of ​​the entire tire, and the regional temperature of the target area, and selecting the target area corresponding to the largest index as the reference area; The tire thermal fatigue damage parameter of the target area is determined based on the heat dissipation coefficient of the reference area, the heat dissipation coefficients of other target areas, the regional temperatures of other target areas in adjacent frames during the cooling process, and the regional temperature of the reference area in adjacent frames.

2. The visual detection method for wheel damage of mine safety transport vehicles according to claim 1 is characterized in that: Determining the area contour of the high temperature area of ​​the tire according to the actual temperature image, and dividing the tire into regions according to the pixel points of the area contour of adjacent high temperature areas to obtain multiple target areas includes: Performing a primary area division on the tire according to the actual temperature image to obtain a high-temperature area of ​​the tire and an area contour of the high-temperature area; Determining a tire tread trend curve of the tire according to vectors in a plane where adjacent pixel points in the area outline are located; Determining the contour similarity of the adjacent high-temperature regions based on tire tread trend curves of the adjacent high-temperature regions and distances between pixel points in the region contours of the adjacent high-temperature regions; When the profile similarity is less than or equal to a first threshold, determining that the area between the adjacent high-temperature areas is a tire tread raised area; Taking the average of the actual temperatures of the adjacent high-temperature areas as the temperature of the tire tread raised area; The temperature of the raised area of ​​the tire tread is marked at a corresponding position in the actual temperature image and the tire is re-divided into secondary areas to obtain a plurality of target areas.

3. The visual detection method for wheel damage of mine safety transport vehicles according to claim 2 is characterized in that: The initial region division of the tire according to the actual temperature image to obtain the high temperature region of the tire and the region outline of the high temperature region includes: Calculating the maximum inter-class variance of temperature pixels of the tread plane in the actual temperature image; The maximum inter-class variance is used as a threshold to perform threshold segmentation on the actual temperature image to obtain the high-temperature area and the area contour of the high-temperature area.

4. The visual detection method for wheel damage of mine safety transport vehicles according to claim 2 is characterized in that: Determining the contour similarity of the adjacent high-temperature regions based on the tire tread trend curves of the adjacent high-temperature regions and the distances between the pixels in the region contours of the adjacent high-temperature regions includes: Calculating a first difference between the tire tread trend curves of the adjacent high-temperature areas, and calculating a first ratio between the first difference and the tire tread trend curve of the next high-temperature area in the adjacent high-temperature areas; Determining a minimum number of outline pixels in an area outline of the adjacent high-temperature area; Superimposing distances between corresponding outline pixel points in the area outlines of the adjacent high-temperature areas to obtain a superimposed distance, and calculating a second ratio between the superimposed distance and the minimum number; A first product of the first ratio and the second ratio is determined as the contour similarity of the adjacent high-temperature areas.

5. The visual detection method for wheel damage of mine safety transport vehicles according to claim 1 is characterized in that: Determining the heat dissipation coefficient of the target area according to the regional temperature of the target area in the infrared images of adjacent frames during the cooling process includes: Determining the temperature drop coefficient of the adjacent frames of the target area according to the regional temperature of the target area in the infrared images of the adjacent frames during the temperature reduction process; The heat dissipation coefficient of the target area is determined according to the temperature drop coefficients of the adjacent frames of the target area.

6. The visual detection method for wheel damage of mine safety transport vehicles according to claim 5 is characterized in that: The step of determining the temperature drop coefficient of adjacent frames of the target area according to the regional temperature of the target area in the infrared images of adjacent frames during the temperature reduction process includes: Calculating a second difference between a regional temperature of a location of the target area in an infrared image of a current frame during the cooling process of the target area and a regional temperature of a location of the target area in an infrared image of a previous frame adjacent to the infrared image of the current frame; A third ratio between the second difference and the regional temperature of the target region in the infrared image of the previous frame adjacent to the infrared image of the current frame is determined as the temperature drop coefficient of the adjacent frames.

7. The visual detection method for wheel damage of mine safety transport vehicles according to claim 5, characterized in that: Determining the heat dissipation coefficient of the target area according to the temperature drop coefficients of the adjacent frames of the target area includes: Calculating an absolute value of a third difference between temperature drop coefficients of connected adjacent frames, and superimposing the absolute values ​​of the third differences to obtain a superimposed absolute value; calculating a fourth difference between the number of frames of the infrared image and a predetermined value, and calculating a fourth ratio between the superimposed absolute value and the fourth difference; The fourth ratio is normalized to obtain the heat dissipation coefficient.

8. The visual detection method for wheel damage of mine safety transport vehicles according to claim 1 is characterized in that: The determining, based on the first area of ​​the target area, the second area of ​​the entire tire, and the regional temperature of the target area, that the target area is an index of the reference area includes: calculating a fifth ratio of the first area to the second area; A second product of the fifth ratio and the inverse of the zone temperature is determined as an index of the reference zone.

9. The visual detection method for wheel damage of mine safety transport vehicles according to claim 1, characterized in that: Determining the tire thermal fatigue damage parameter of the target area based on the heat dissipation coefficient of the reference area, the heat dissipation coefficients of other target areas, the regional temperatures of other target areas in adjacent frames during the cooling process, and the regional temperature of the reference area in adjacent frames includes: calculating a sixth ratio between the heat dissipation coefficient of the other target area and the heat dissipation coefficient of the reference area; calculating a fifth difference between the regional temperature of the other target regions in adjacent frames during the cooling process and the regional temperature of the reference region in adjacent frames, and calculating a seventh ratio between the fifth difference and the regional temperature of the reference region; calculating a third product between the average of the seventh ratio and the sixth ratio; The third product is normalized to obtain the tire thermal fatigue damage parameter of the target area.

10. The visual detection method for wheel damage of mine safety transport vehicles according to claim 1, characterized in that: After determining the tire thermal fatigue damage parameter of the target area based on the heat dissipation coefficient of the reference area, the heat dissipation coefficients of other target areas, the regional temperatures of other target areas in adjacent frames during the cooling process, and the regional temperature of the reference area, the method further includes: The target area where the tire thermal fatigue damage parameter is the largest is used as the short board area of ​​the tire thermal fatigue damage, and the service life of the tire is evaluated based on the short board area.

Images