An automatic welding position recognition method for hot melt gaskets

Abstract

The present application relates to the field of intelligent construction, especially to a hot melt gasket automatic welding position recognition method, comprising: detecting the equipment vibration frequency, and determining the image acquisition condition as image acquisition compliance according to the preset vibration frequency range where the equipment vibration frequency is located, or adjusting the equipment operation parameter or the acquisition quality cannot meet the acquisition demand; determining to collect and process according to the image quality reference value average value and the image quality fluctuation coefficient, or recognizing the welding position according to the acquisition image with the maximum image quality reference value; in the collection and processing, determining the collection and processing mode as adjusting the collection frequency according to the image quality fluctuation coefficient difference or adjusting the auxiliary light source according to the image quality fluctuation coefficient difference according to the comparison result of the maximum value of the image quality reference value and the preset image quality reference value; the present application considers the influence of image acquisition accuracy on subsequent hot melt gasket installation position recognition accuracy, and improves the recognition efficiency.

Description

Technical Field

[0001] This invention relates to the field of intelligent construction, and in particular to a method for automatic welding position identification of hot melt gaskets. Background Technology

[0002] Intelligent installation of hot-melt washers is a crucial step in the waterproofing and drainage construction of railway tunnels. Existing hot-melt washers are circular washers with a circular groove in the center of the outer side and a central through-hole in the groove. Currently, these washers are installed manually by workers; however, the experience of the workers can affect the installation quality, and manual installation is time-consuming. Therefore, intelligent equipment is now commonly used for automated installation.

[0003] Chinese Patent Publication No. CN119910667A discloses an automated gripping control method for hot melt washers on an automatic laying trolley. The method includes: S1, acquiring the position of the hot melt washer using image acquisition with the robot arm's set position as the center; when the two-dimensional coordinates of the hot melt washer's position match the two-dimensional coordinates of the robot arm's set position, the robot arm control system initiates the control method; S2, calculating the vertical height value between the robot arm's real-time position and the hot melt washer's position; calculating the current error height between the robot arm's current descent height and the target descent height based on the vertical height value; S3, feeding back the current error height to the robot arm control system; S4, the robot arm control system outputs a control signal based on the current error height, precisely controlling the robot arm's position through the control signal, returning to execute S2 until the target descent height is reached, thus achieving automated gripping control of the hot melt washer. This significantly improves the system's performance and enhances the efficiency and robustness of the robot arm control system. However, it is evident that the above technical solution has the following problems: the presence of smoke and dust in the construction scene and the vibration of surrounding construction equipment will affect image acquisition. The above technical solution does not take into account the impact of image acquisition accuracy on the subsequent accuracy of hot melt gasket installation position recognition, thus resulting in poor installation effect. Summary of the Invention

[0004] To address this issue, the present invention provides an automatic welding position identification method for hot melt gaskets, which overcomes the problem in the prior art that the influence of environmental factors on image acquisition accuracy is not considered, resulting in poor identification of the installation position of hot melt gaskets and thus affecting welding accuracy.

[0005] To achieve the above objectives, the present invention provides an automatic welding position identification method for hot melt gaskets, comprising:

[0006] The vibration frequency of the equipment is detected, and the image acquisition conditions are determined based on the preset vibration frequency range in which the equipment vibration frequency is located: the image acquisition is qualified, the equipment operating parameters are adjusted, or the acquisition quality cannot meet the acquisition requirements.

[0007] The image acquisition condition is that the image acquisition is qualified. The image quality reference value of each acquired image is detected, and the image quality fluctuation coefficient is determined based on the image quality reference value.

[0008] The acquisition and processing can be determined based on the average image quality reference value and the image quality fluctuation coefficient, or the welding position can be identified based on the acquired image with the largest image quality reference value.

[0009] During the acquisition and processing, the acquisition and processing method is determined based on the comparison between the maximum value of the image quality reference value and the preset image quality reference value. This method involves adjusting the acquisition frequency based on the difference in the image quality fluctuation coefficient or adjusting the auxiliary light source based on the difference in the image quality fluctuation coefficient.

[0010] Furthermore, the vibration frequency of the equipment is detected, and the image acquisition conditions are determined based on the preset vibration frequency range in which the equipment vibration frequency falls.

[0011] If the equipment vibration frequency is within the first preset vibration frequency range, then the image acquisition condition is that the image acquisition is qualified.

[0012] If the equipment vibration frequency is within the second preset vibration frequency range, the image acquisition condition is to adjust the equipment operating parameters.

[0013] If the device vibration frequency is within the third preset vibration frequency range, the image acquisition condition is that the acquisition quality cannot meet the acquisition requirements.

[0014] Furthermore, the image acquisition condition is to detect the reference difference of the device vibration frequency when adjusting the device operation parameters, and to reduce the movement speed of the robotic arm based on the reference difference of the device vibration frequency.

[0015] The decrease in the robotic arm's moving speed is positively correlated with the difference in the equipment's vibration frequency reference value.

[0016] Furthermore, when the image acquisition condition is that the image acquisition is qualified, the image quality reference value of each acquired image is detected, and the image quality fluctuation coefficient is determined based on the image quality reference value;

[0017] If the average value of the image quality reference is less than the average value of the preset image quality reference, or if the image quality fluctuation coefficient is greater than or equal to the preset image quality fluctuation coefficient, then data acquisition processing will be performed.

[0018] If the average image quality reference value is greater than or equal to the preset average image quality reference value and the image quality fluctuation coefficient is less than the preset image quality fluctuation coefficient, then the welding position is identified based on the acquired image with the largest image quality reference value.

[0019] Furthermore, the formula for calculating the image quality fluctuation coefficient S is as follows:

[0020]

[0021] Where Si is the image quality reference value corresponding to the i-th acquired image, S0 is the average value of the image quality reference value, and n is the total number of acquired images.

[0022] Furthermore, during the acquisition and processing, the maximum value of the image quality reference value is detected, and the acquisition and processing method is determined based on the comparison between the maximum value of the image quality reference value and the preset image quality reference value.

[0023] If the maximum value of the image quality reference value is greater than the preset image quality reference value, the acquisition and processing method is to adjust the acquisition frequency according to the difference in the image quality fluctuation coefficient.

[0024] If the maximum value of the image quality reference value is less than or equal to the preset image quality reference value, the acquisition and processing method is to adjust the auxiliary light source according to the difference in the image quality fluctuation coefficient.

[0025] Furthermore, under the first adjustment condition, the acquisition frequency is increased based on the difference in image quality fluctuation coefficient;

[0026] The difference in the image quality fluctuation coefficient is positively correlated with the increase in the acquisition frequency;

[0027] The first adjustment condition is that the maximum value of the image quality reference value is greater than the preset image quality reference value.

[0028] Furthermore, under the second adjustment condition, the brightness of the auxiliary light source is adjusted by increasing the number of settings based on the difference in image quality fluctuation coefficient;

[0029] The difference in the image quality fluctuation coefficient is positively correlated with the increase in the number of times the auxiliary light source brightness is set;

[0030] The second adjustment condition is that the maximum value of the image quality reference value is less than or equal to the preset image quality reference value.

[0031] Furthermore, the image quality reference value is determined based on the number of feature points and the contrast of the acquired image;

[0032] The image quality reference value is positively correlated with the number of feature points and the contrast.

[0033] Compared with the prior art, the beneficial effects of the present invention are that the technical solution of the present invention detects the vibration frequency of the equipment, determines the image acquisition conditions according to the preset vibration frequency range in which the equipment vibration frequency is located, and sets the corresponding adjustment of the equipment operation parameters for specific image acquisition conditions, so that the equipment operation parameters are more in line with the actual application scenario, thereby improving the accuracy of subsequent position recognition.

[0034] Furthermore, in the technical solution of the present invention, the acquisition and processing is determined based on the average value of the image quality reference value and the image quality fluctuation coefficient, or the welding position is identified based on the acquired image with the largest image quality reference value. The acquired images are analyzed to determine whether welding position identification can be performed. The influence of image accuracy on subsequent position identification is taken into account, thereby improving the identification efficiency. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of the automatic welding position identification method for hot melt gaskets according to the present invention;

[0036] Figure 2 A flowchart for determining image acquisition conditions based on the preset vibration frequency range of the equipment vibration frequency;

[0037] Figure 3 This is a flowchart illustrating how the acquisition and processing method is determined based on a comparison between the maximum value of the image quality reference value and a preset image quality reference value, according to the present invention. Detailed Implementation

[0038] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0039] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0040] It should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0041] Please see Figures 1 to 3 As shown, the present invention provides an automatic welding position identification method for hot melt gaskets, comprising:

[0042] The vibration frequency of the equipment is detected, and the image acquisition conditions are determined based on the preset vibration frequency range in which the equipment vibration frequency is located: the image acquisition is qualified, the equipment operating parameters are adjusted, or the acquisition quality cannot meet the acquisition requirements.

[0043] The image acquisition condition is that the image acquisition is qualified. The image quality reference value of each acquired image is detected, and the image quality fluctuation coefficient is determined based on the image quality reference value.

[0044] The acquisition and processing can be determined based on the average image quality reference value and the image quality fluctuation coefficient, or the welding position can be identified based on the acquired image with the largest image quality reference value.

[0045] During the acquisition and processing, the acquisition and processing method is determined based on the comparison between the maximum value of the image quality reference value and the preset image quality reference value. This method involves adjusting the acquisition frequency based on the difference in the image quality fluctuation coefficient or adjusting the auxiliary light source based on the difference in the image quality fluctuation coefficient.

[0046] This invention is applied to the automatic identification of welding positions during the welding process of hot melt gaskets. Specifically, this invention is applied to the identification and management of image acquisition accuracy to improve the identification accuracy of subsequent welding positions. This invention uses an identification device, the specific parameters of which are not limited, but the identification device should have image acquisition and automatic movement functions. The specific method of welding position identification is not limited. In particular, preprocessing the acquired images and using a depth recognition model to identify the welding positions in the acquired images is a content that is easily understood by those skilled in the art and will not be elaborated here.

[0047] Preferably, the vibration frequency of the equipment is detected, and the image acquisition conditions are determined according to the preset vibration frequency range in which the equipment vibration frequency is located.

[0048] If the vibration frequency of the equipment is within the first preset vibration frequency range, then the image acquisition condition is that the image acquisition is qualified.

[0049] If the equipment vibration frequency is within the second preset vibration frequency range, the image acquisition condition is to adjust the equipment operating parameters.

[0050] If the device vibration frequency is within the third preset vibration frequency range, the image acquisition condition is that the acquisition quality cannot meet the acquisition requirements.

[0051] The vibration frequency of the device is the maximum value collected by the vibration sensor installed on the identification device during image acquisition. The values ​​within the first preset vibration frequency range are all greater than or equal to 0 and less than or equal to the first preset vibration frequency. The values ​​within the second preset vibration frequency range are all greater than the first preset vibration frequency and less than or equal to the second preset vibration frequency. The values ​​within the third preset vibration frequency range are all greater than the second preset vibration frequency. The first preset vibration frequency is less than the second preset vibration frequency. The user can set the values ​​of the first and second preset vibration frequencies according to the actual application environment. The higher the image acquisition accuracy, the smaller the values ​​of the first and second preset vibration frequencies.

[0052] When the image acquisition quality cannot meet the acquisition requirements, manual welding is performed.

[0053] Preferably, the image acquisition condition is to detect the reference difference of the device vibration frequency when adjusting the device operation parameters, and to reduce the movement speed of the robotic arm based on the reference difference of the device vibration frequency.

[0054] The decrease in the robotic arm's moving speed is positively correlated with the difference in the equipment's vibration frequency reference value.

[0055] The robotic arm's moving speed refers to the speed at which the robotic arm mounted on the identification device moves during its operation.

[0056] The equipment vibration frequency reference difference is the difference between the equipment vibration frequency and the first preset vibration frequency.

[0057] Preferably, the image acquisition condition is that when the image acquisition is qualified, the image quality reference value of each acquired image is detected, and the image quality fluctuation coefficient is determined based on the image quality reference value;

[0058] If the average value of the image quality reference is less than the average value of the preset image quality reference, or if the image quality fluctuation coefficient is greater than or equal to the preset image quality fluctuation coefficient, then data acquisition processing will be performed.

[0059] If the average image quality reference value is greater than or equal to the preset average image quality reference value and the image quality fluctuation coefficient is less than the preset image quality fluctuation coefficient, then the welding position is identified based on the acquired image with the largest image quality reference value.

[0060] The preset image quality fluctuation coefficient and the preset image quality reference value can be set by the user according to the actual application scenario. The greater the user's demand for image acquisition accuracy, the larger the preset image quality fluctuation coefficient and the preset image quality reference value should be.

[0061] Preferably, the formula for calculating the image quality fluctuation coefficient S is:

[0062]

[0063] Where Si is the image quality reference value corresponding to the i-th acquired image, S0 is the average value of the image quality reference value, and n is the total number of acquired images.

[0064] Preferably, during the acquisition and processing, the maximum value of the image quality reference value is detected, and the acquisition and processing method is determined based on the comparison between the maximum value of the image quality reference value and the preset image quality reference value.

[0065] If the maximum value of the image quality reference value is greater than the preset image quality reference value, the acquisition and processing method is to adjust the acquisition frequency according to the difference in the image quality fluctuation coefficient.

[0066] If the maximum value of the image quality reference value is less than or equal to the preset image quality reference value, the acquisition and processing method is to adjust the auxiliary light source according to the difference in the image quality fluctuation coefficient.

[0067] The method for determining the preset image quality reference value is the same as that for other preset values, and will not be elaborated here.

[0068] The acquisition frequency is the total number of images acquired in a single location identification process.

[0069] Preferably, under the first adjustment condition, the acquisition frequency is increased based on the difference in image quality fluctuation coefficient;

[0070] The difference in the image quality fluctuation coefficient is positively correlated with the increase in the acquisition frequency;

[0071] The first adjustment condition is that the maximum value of the image quality reference value is greater than the preset image quality reference value.

[0072] Preferably, under the second adjustment condition, the brightness of the auxiliary light source is adjusted by increasing the number of times based on the difference in the image quality fluctuation coefficient;

[0073] The difference in the image quality fluctuation coefficient is positively correlated with the increase in the number of times the auxiliary light source brightness is set;

[0074] The second adjustment condition is that the maximum value of the image quality reference value is less than or equal to the preset image quality reference value.

[0075] Preferably, the image quality reference value is determined based on the number of feature points and the contrast of the acquired image;

[0076] The image quality reference value is positively correlated with the number of feature points and the contrast.

[0077] The identification device is equipped with an auxiliary light source to emit light to the area for location identification in order to improve the image acquisition effect. The brightness of the auxiliary light source corresponding to the image acquired is different each time the image is acquired. As the number of times the brightness of the auxiliary light source is set increases, the brightness of the auxiliary light source is changed each time the image is acquired. The brightness of the auxiliary light source differs by 20 candela between each change.

[0078] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0079] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for automatic welding position identification of hot melt gaskets, characterized in that, include: The vibration frequency of the equipment is detected, and the image acquisition conditions are determined according to the preset vibration frequency range in which the equipment vibration frequency is located. If the equipment vibration frequency is within the first preset vibration frequency range, the image acquisition condition is that the image acquisition is qualified; if the equipment vibration frequency is within the second preset vibration frequency range, the image acquisition condition is that the equipment operation parameters are adjusted; if the equipment vibration frequency is within the third preset vibration frequency range, the image acquisition condition is that the acquisition quality cannot meet the acquisition requirements. The image acquisition condition is that the image acquisition is qualified. The image quality reference value of each acquired image is detected, and the image quality fluctuation coefficient is determined based on the image quality reference value. The image acquisition condition is to detect the reference difference of the equipment vibration frequency when adjusting the equipment operation parameters, and to reduce the movement speed of the robotic arm according to the reference difference of the equipment vibration frequency. The amount of reduction in the movement speed of the robotic arm is positively correlated with the reference difference of the equipment vibration frequency. When the image acquisition condition is that the image acquisition is qualified, the image quality reference value of each acquired image is detected, and the image quality fluctuation coefficient is determined based on the image quality reference value. If the average image quality reference value is less than the preset average image quality reference value or the image quality fluctuation coefficient is greater than or equal to the preset image quality fluctuation coefficient, then acquisition processing is performed. If the average image quality reference value is greater than or equal to the preset average image quality reference value and the image quality fluctuation coefficient is less than the preset image quality fluctuation coefficient, then the welding position is identified based on the acquired image with the largest image quality reference value. The acquisition and processing can be determined based on the average image quality reference value and the image quality fluctuation coefficient, or the welding position can be identified based on the acquired image with the largest image quality reference value. During the acquisition and processing, the acquisition and processing method is determined based on the comparison between the maximum value of the image quality reference value and the preset image quality reference value. This method involves adjusting the acquisition frequency based on the difference in the image quality fluctuation coefficient or adjusting the auxiliary light source based on the difference in the image quality fluctuation coefficient.

2. The automatic welding position identification method for hot melt gaskets according to claim 1, characterized in that, The formula for calculating the image quality fluctuation coefficient S is as follows: Where Si is the image quality reference value corresponding to the i-th acquired image, S0 is the average value of the image quality reference value, and n is the total number of acquired images.

3. The automatic welding position identification method for hot melt gaskets according to claim 2, characterized in that, During the acquisition and processing, the maximum value of the image quality reference value is detected, and the acquisition and processing method is determined based on the comparison between the maximum value of the image quality reference value and the preset image quality reference value. If the maximum value of the image quality reference value is greater than the preset image quality reference value, the acquisition and processing method is to adjust the acquisition frequency according to the difference in the image quality fluctuation coefficient. If the maximum value of the image quality reference value is less than or equal to the preset image quality reference value, the acquisition and processing method is to adjust the auxiliary light source according to the difference in the image quality fluctuation coefficient.

4. The automatic welding position identification method for hot melt gaskets according to claim 3, characterized in that, Under the first adjustment condition, the acquisition frequency is increased based on the difference in image quality fluctuation coefficient; The difference in the image quality fluctuation coefficient is positively correlated with the increase in the acquisition frequency; The first adjustment condition is that the maximum value of the image quality reference value is greater than the preset image quality reference value.

5. The automatic welding position identification method for hot melt gaskets according to claim 4, characterized in that, Under the second adjustment condition, the brightness of the auxiliary light source is adjusted by increasing the number of times based on the difference in the image quality fluctuation coefficient. The difference in the image quality fluctuation coefficient is positively correlated with the increase in the number of times the auxiliary light source brightness is set; The second adjustment condition is that the maximum value of the image quality reference value is less than or equal to the preset image quality reference value.

6. The automatic welding position identification method for hot melt gaskets according to claim 5, characterized in that, The image quality reference value is determined based on the number of feature points and the contrast of the acquired image; The image quality reference value is positively correlated with the number of feature points and the contrast.

Images