Automatic material distributing machine and material distributing method based on infrared laser and computer vision

Abstract

The invention relates to an automatic material distributing machine and method based on infrared laser and computer vision. The material distributing machine comprises a center shaft, a material pumping pipe, a main telescopic arm, a rigid discharging pipe, an infrared laser, a camera, a driving device and a control center. One end of the main telescopic arm and one end of the material pumping pipe are rotationally installed on the center shaft, and the camera and the rigid discharging pipe are installed at the other end of the main telescopic arm. The rigid discharging pipe is perpendicular to the main telescopic arm. The two infrared lasers are installed on the two sides of the rigid discharging pipe. The infrared laser and the camera collect steel bar plane information and transmit the information to the control center, and the control center controls starting and stopping of the driving device. Compared with the prior art, material distribution can be achieved without manual operation, and the automation degree is high; steel bar plane information is collected through the camera and the infrared laser, the position of the steel bar is accurately obtained, discharging is accurate, and material distribution is more uniform.

Description

Technical Field

[0001] The invention relates to building construction tools, in particular to an automatic material placing machine and a material placing method based on infrared laser and computer vision. Background Art

[0002] With the development of the construction industry, traditional construction technology is actively transforming towards digitalization and intelligence. In the on-site construction of bridges, the pouring of bridge towers is crucial and determines the strength of the bridge. The concrete placing boom is an important tool for pouring bridge towers, and the pouring efficiency of the concrete placing boom determines the length of the construction period of the bridge tower. Using intelligent technology to realize the automation of the concrete placing boom can effectively improve construction efficiency.

[0003] The adjustment of the placing tube of the traditional concrete placing machine depends on manual labor. Due to the uneven arrangement of the steel bars, it is difficult to obtain the center point during placing, which can easily cause problems such as uneven placing and poor quality of the bridge tower.

[0004] Authorization announcement number CN209657113U discloses a concrete placing machine control device and a concrete placing machine, which solves the problem of inconvenience caused by the existing concrete placing machine control device and concrete placing machine having only one control system. In addition, in the concrete placing machine control device and concrete placing machine, the two control systems can work independently or in coordination, which improves the flexibility of controlling the concrete placing machine. However, the control of the control device still requires manual adjustment, and is not well adapted to bridge construction.

[0005] Application publication number CN118223406A discloses a combined bridge tower casting device based on a large hopper and a variable-length belt conveyor and a construction method thereof, comprising a large hopper, a tower top hopper support frame, a rotatable and variable-length concrete belt conveyor and a belt conveyor support frame, which improves the efficiency of combined bridge tower concrete casting and the uniformity of concrete distribution, and ensures the safety of tower top construction. The method is double-tube casting, and the casting efficiency is high. However, the feed pipe in the prior art has poor adaptability to complex steel bars, it is difficult to obtain the center point, and the uniformity of feeding is affected.

[0006] In summary, how to design a material distributing machine with uniform material distribution and high degree of automation is a technical problem that needs to be solved. Summary of the invention

[0007] The purpose of the present invention is to provide an automatic material distribution machine and material distribution method based on infrared laser and computer vision in order to overcome the defects of uneven material distribution or low automation in the above-mentioned prior art.

[0008] The purpose of the present invention can be achieved by the following technical solutions:

[0009] According to one aspect of the present invention, an automatic material placing machine based on infrared laser and computer vision is provided, which is used for placing materials on a steel bar plane. The material placing machine comprises a central axis, a material extraction pipe, a main telescopic arm, a rigid material discharge pipe, an infrared laser, a camera, a driving device and a control center; one end of the main telescopic arm and one end of the material extraction pipe are rotatably mounted on the central axis, and the camera and the rigid material discharge pipe are mounted on the other end of the main telescopic arm; the rigid material discharge pipe is perpendicular to the main telescopic arm; there are two infrared lasers, which are mounted on both sides of the rigid material discharge pipe;

[0010] The central axis, the material extraction pipe, the main telescopic arm and the rigid material discharge pipe are connected to the driving device; the infrared laser, the camera and the driving device are electrically connected to the control center, the infrared laser and the camera collect the plane information of the steel bars and transmit it to the control center, and the control center controls the opening and closing of the driving device.

[0011] As a preferred technical solution, the material placing machine also includes two auxiliary telescopic arms symmetrically arranged with the main telescopic arm as the symmetry axis, one end of the auxiliary telescopic arm is connected to the central axis, and the other end is equipped with an infrared laser; the auxiliary telescopic arm has the same length as the main telescopic arm.

[0012] As a preferred technical solution, the axis of the rigid feeding tube coincides with the axis of the camera's field of view.

[0013] According to another aspect of the present invention, a material laying method using an automatic material laying machine based on infrared laser and computer vision is provided, which specifically comprises the following steps:

[0014] Step S1, the driving device drives the central axis to rotate along a first direction, and the camera and infrared laser collect the current steel bar plane information and transmit it to the control center;

[0015] Step S2, the control center calculates the position relationship between the current steel bar plane and the concrete placing machine according to the collected information;

[0016] Step S3, the control center calculates the feeding point according to the position relationship, and controls the driving device to drive the central axis, the main telescopic arm and the rigid feeding pipe to feed the material at the feeding point;

[0017] Step S4, determine whether the central axis rotates one circle, if yes, execute step S5; otherwise, return to step S1;

[0018] Step S5, determining whether all material feeding is completed, if so, stopping the material placing machine; otherwise, changing the extension length of the main telescopic arm and returning to step S1.

[0019] As a preferred technical solution, the step S1 specifically includes the following steps:

[0020] Step S101, the camera collects the current steel bar plane image and transmits it to the control center;

[0021] Step S102, recording the current initial position, the central axis rotates, stops rotating when the infrared laser detects the steel bar, and records the angle of rotation of the central axis.

[0022] As a preferred technical solution, the step S2 specifically includes the following steps:

[0023] Step S201, the control center processes the current steel bar plane image to obtain a steel bar distribution image;

[0024] Step S202: The control center calculates the positional relationship between the current steel bar plane and the concrete placing machine according to the steel bar distribution image and the angle of rotation of the infrared laser.

[0025] As a preferred technical solution, the step S201 specifically includes the following steps:

[0026] Step S2011, obtaining a ratio k of the distance on the image of the bottom of the rigid feeding tube on the plane image of the steel bar to the actual distance according to the relative height difference between the camera and the bottom of the rigid feeding tube and the focal length of the camera;

[0027] Step S2012, based on the Canny edge detection algorithm, extract the steel bar contour to obtain a steel bar distribution image.

[0028] As a preferred technical solution, the step S202 specifically includes the following steps:

[0029] Step S2021, according to the steel bar distribution image, obtain the straight line l1 where the steel bars are located detected by the infrared laser, the axis O1 of the rigid feeding pipe, and the axis l2 of the camera field of view;

[0030] Step S2022, according to the plane geometric relationship, solve the position of the central axis in the steel bar plane, and then obtain the distribution radius R in the steel bar plane 真 ;

[0031] Step S2023, according to R 真 The relationship between the radius R of the fabric placing machine and the scale correction coefficient k is obtained 真 , and then the position relationship between the steel bar plane and the concrete placing crane is obtained.

[0032] As a preferred technical solution, the step S3 specifically includes the following steps:

[0033] Step S301, according to the positional relationship between the current steel bar plane and the concrete placing machine, the length of the main telescopic arm is fixed, and a rigid material discharge pipe is made to rotate along a first direction with the central axis as the axis, and then the rigid material discharge pipe is made to follow a trajectory in the current steel bar plane;

[0034] Step S302, extracting the intersection of the steel bar and the trajectory in the current steel bar plane;

[0035] Step S303, the midpoint of the two adjacent intersection points closest to the rigid feeding pipe in the first direction is the feeding point, and the control center calculates the angle of rotation of the central axis to reach the feeding point;

[0036] Step S304, the driving device drives the central axis and the rigid feeding pipe to feed the material.

[0037] As a preferred technical solution, in step S304, the amount M of material discharged to each feeding point is: M = α 总 m;

[0038] Among them, α 总 is the total angle of rotation of the central axis, α 总 =α1+α2; m is the unit feeding amount; α1 is the angle that the center axis rotates from the current position to the angle when the infrared laser detects the steel bar; the position of the center axis when the infrared laser detects the steel bar is defined as the first position, and α2 is the angle that the center axis rotates from the first position to the feeding point.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] 1) The automatic material placing machine provided by the present invention can realize material placing without manual operation, and has a high degree of automation; the plane information of the steel bars is collected by a camera and an infrared laser, the position of the steel bars is accurately obtained and the material is placed accurately, and the material placing is more uniform;

[0041] 2) The central axis of the present invention rotates to drive the camera and infrared laser to collect information about the current steel bar plane, and feeds the material according to the positional relationship between the current steel bar plane and the concrete placing machine, with high accuracy in positioning the feeding position; the material is fed layer by layer in a rotating manner, which is not easy to cause omissions, and is particularly suitable for the casting of circular bridge towers;

[0042] 3) The present invention determines the amount of material to be cut according to the angle of rotation of the central axis, that is, the distance between the steel bars. The amount of material to be cut is more accurate, and the uniformity of the material distribution is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a schematic diagram of the overall structure of an automatic material placing machine based on infrared laser and computer vision of the present invention;

[0044] Figure 2 It is a schematic diagram of the arrangement of the main telescopic arm and the auxiliary telescopic arm of the present invention;

[0045] Figure 3 This is a flow chart of the material distribution method of the present invention;

[0046] Figure 4It is a schematic diagram of the image of the steel bar profile of the present invention;

[0047] Figure 5 It is a schematic diagram of calculating the position relationship between the current steel bar plane and the concrete placing machine of the present invention;

[0048] Figure 6 A schematic diagram of obtaining a trajectory of the rigid feeding pipe of the present invention after rotating along a first direction with the central axis as the axis in the current steel bar plane;

[0049] The numbers in the figure show:

[0050] 1. Central axis, 2. Extraction pipe, 3. Main telescopic arm, 4. Rigid discharge pipe, 5. Infrared laser, 6. Camera, 7. Auxiliary telescopic arm. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0052] Example 1

[0053] like Figure 1 As shown, the present invention provides an automatic material placing machine based on infrared laser and computer vision, which is used for placing materials on a steel bar plane, including a central axis 1, a material extraction pipe 2, a main telescopic arm 3, a rigid material discharge pipe 4, two infrared lasers 5, a camera 6, two auxiliary telescopic arms 7, a driving device and a control center.

[0054] The central shaft 1 is connected to one end of the main telescopic arm 3, one end of the material extraction pipe 2 and one end of the auxiliary telescopic arm 7. The central shaft 1 can rotate, thereby driving the main telescopic arm 3, the material extraction pipe 2 and the auxiliary telescopic arm 7 to rotate.

[0055] The extraction pipe 2 is used to extract the raw materials to be laid, and the raw materials are concrete in the construction pouring.

[0056] The arm length of the main telescopic arm 3 is R, that is, the material feeding radius of the concrete placing boom is R, and the adjustable arm length range is R1 to R2, then the material feeding radius of the concrete placing boom is [R1, R2]. According to the actual size requirements of the steel bar plane, the material feeding range can be changed by changing the arm length of the main telescopic arm 3.

[0057] The rigid feeding tube 4 can prevent serious shaking during the feeding process from causing inaccurate feeding position.

[0058] The camera 6 and the rigid feeding tube 4 are installed at the other end of the main telescopic arm 3. To ensure sufficient stability, the rigid feeding tube 4 is perpendicular to the main telescopic arm 3 and does not shake with feeding. The verticality requirement is ±1°. The field of view of the camera 6 is toward the steel bar plane, and the axis of the rigid feeding tube 4 coincides with the axis of the field of view of the camera 6.

[0059] like Figure 2 As shown, the two auxiliary telescopic arms 7 are symmetrically arranged with the main telescopic arm 3 as the symmetry axis, and the length of the auxiliary telescopic arms 7 is the same as that of the main telescopic arm 3.

[0060] Two infrared lasers 5 are distributed and installed at one end of the two auxiliary telescopic arms 7 and are located on both sides of the rigid feeding tube 4. They include a laser transmitter and a laser receiver and can emit and receive lasers.

[0061] The driving device connects the central shaft 1, the material extraction pipe 2, the main telescopic arm 3 and the rigid material discharge pipe 4, and is used to drive the central shaft 1 to rotate, the material extraction pipe 2 to extract materials, the main telescopic arm 3 to extend and retract, and the rigid material discharge pipe 4 to discharge materials.

[0062] The control center is electrically connected to the camera 6, the infrared laser 5 and the drive device, and supports image processing and related algorithm calculations; the image captured by the camera 6 and the signal collected by the infrared laser 5 are transmitted to the control center for judging the plane position of the steel bar and identifying the position of the steel bar; the drive device receives the command of the control center to drive the central axis 1, the material extraction pipe 2, the main telescopic arm 3 and the rigid material discharge pipe 4. The optional component configuration scheme of the control center is: computing server, storage server and RTX4090GPU, and other components with image processing or algorithm calculation functions can be replaced at will.

[0063] Example 2

[0064] like Figure 3 As shown, the present invention provides an automatic material distribution method based on infrared laser and computer vision, which adopts an automatic material distribution machine based on infrared laser and computer vision.

[0065] Step 1: The camera 6 of the automatic concrete placing machine collects the current steel bar plane image and transmits it to the control center. According to the height difference h0 between the camera 6 of the automatic concrete placing machine and the bottom of the rigid feeding tube 4 and the focal length f of the camera 6 (a monocular camera can be used), the ratio k of the distance on the image of the bottom position of the rigid feeding tube 4 to the actual distance is calculated:

[0066] k=f / h0

[0067] Based on the Canny edge detection algorithm, the outline of the steel bars in the image is extracted to obtain the steel bar distribution image. The specific operation process is as follows:

[0068] 1) Input the steel bar plane image and convert the original image into grayscale based on the built-in function of OpenCV;

[0069] 2) Based on Gaussian filtering, remove image noise to avoid misidentifying noise as edges during edge detection. The 3×3 convolution kernel template is as follows:

[0070]

[0071] The dimension of the filter kernel should not be too large, otherwise the edge information may be smoothed out, making it impossible for the edge detection operator to correctly identify the edge information;

[0072] 3) Use first-order finite differences to calculate the amplitude and direction and suppress non-maximum data. The calculation method is as follows:

[0073] Using the Sobel operator as the gradient operator, we can get two 3×3 matrices N of the partial derivatives of the image in the x and y directions. y and N x , presuppose H(i,j) is the calculated image:

[0074]

[0075] Among them, c is the gradient to be calculated;

[0076] Find the gradient in the x and y directions:

[0077] g x =N x H(i,j) T , g y =N y H(i,j) T

[0078] Then the gradient amplitude and gradient direction here are:

[0079] θ=arctan(g y / g x )

[0080] 4) Use double thresholds to screen the binary image, and obtain the edge image closest to the real edge of the image by selecting appropriate large and small thresholds. The specific implementation steps are as follows:

[0081] (1) An edge image is obtained based on a high threshold. Due to the high threshold, the edges of the generated image may not be closed.

[0082] (2) In the high-threshold image, the edges are linked into contours. When the end point of the contour is reached, the algorithm searches for a point that satisfies the low threshold in the 8-neighborhood points of the breakpoint, and then collects new edges based on this point until the edge of the entire image is closed.

[0083] Step 2, the control center controls the intermediate shaft to rotate clockwise or counterclockwise to keep the material feeding radius unchanged, and the infrared laser 5 stops rotating when it detects the steel bar, and executes step 1 again, the camera 6 obtains the current steel bar plane image, and records the angle α1 of the central shaft 1;

[0084] According to the information collected by the infrared laser 5 and the current steel bar plane image collected by the camera 6, the position relationship between the current steel bar plane and the concrete placing machine is calculated. The specific operation process is as follows:

[0085] 1) If Figure 4 As shown, according to the outline of the steel bar in the image, the straight line l1 where the laser mutation point A in the image is located (i.e., the straight line where the steel bar detected by the infrared laser 5 is located), the angle α0 between the auxiliary rotating arm and the main rotating arm, the axis O1 of the feeding pipe, and the axis l2 of the field of view of the camera 6 are obtained;

[0086] 2) If Figure 5 As shown, given α0, O1, l1, l2, according to the plane geometric relationship, a rectangular coordinate system is established to solve the distribution radius R of the steel bar plane scale 真 ;

[0087] 3) According to R 真 And the actual cloth radius R, get the scale correction coefficient k 真 =R / R 真 , get the position relationship between the steel bar plane and the concrete placing crane;

[0088] like Figure 6 As shown, the distance R from the central axis 1 to the center of the feeding tube is known. According to the center position of the feeding tube in the image and the real scale mapping relationship k 真 , get the center axis 1 position O2; take O2 as the center, R 真 As the radius, obtain the path trajectory curve of the rigid feeding pipe 4 center after rotating along the first direction in the current steel bar plane, and then obtain the intersection of the trajectory curve and the contour; the two intersection points j1 and j2 closest to the current position on the path trajectory curve are known, and Corresponding to the central angle α′, the next feeding point position j3 is located at The midpoint position, the angle required to rotate from the current position to j3 is α2; the driving device drives the central axis 1 and the rigid feeding pipe 4 to feed the material, completes a single feeding, and records the rotation angle α of each feeding process 总 =α1+α2, set the unit feeding quantity m, single feeding quantity M=m·α 总 ; Repeat steps 1 and 2 to complete the unloading within the current length range of the main telescopic arm 3;

[0089] When the cumulative rotation angle reaches 360°, that is, after the intermediate shaft rotates one circle, it stops rotating, and the main and auxiliary telescopic arms 7 are controlled to extend and retract synchronously, and R is changed. The range of change is controlled by the specific size of the pier, and 5 levels can be set. The radius change of each level is ΔR=(R2-R1) / 5, and R1 and R2 are the adjustable limit values ​​of the arm length of the main telescopic arm 3; repeat steps 1 and 2 until 5 levels of pouring are completed, and the management personnel evaluate the pouring effect.

[0090] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An automatic material placing machine based on infrared laser and computer vision, used for placing materials on a steel bar plane, characterized in that: The material placing machine comprises a central axis (1), a material extraction pipe (2), a main telescopic arm (3), a rigid material discharge pipe (4), an infrared laser (5), a camera (6), a driving device and a control center; the central axis (1) is rotatable; one end of the main telescopic arm (3) and one end of the material extraction pipe (2) are mounted on the central axis (1), and the camera (6) and the rigid material discharge pipe (4) are mounted on the other end of the main telescopic arm (3); the rigid material discharge pipe (4) is perpendicular to the main telescopic arm (3); there are two infrared lasers (5), which are mounted on both sides of the rigid material discharge pipe (4); The central axis (1), the material extraction pipe (2), the main telescopic arm (3) and the rigid material discharge pipe (4) are connected to the driving device; the infrared laser (5), the camera (6) and the driving device are electrically connected to the control center; the infrared laser (5) and the camera (6) collect the plane information of the steel bars and transmit it to the control center; the control center controls the opening and closing of the driving device.

2. The automatic material placing machine based on infrared laser and computer vision according to claim 1, characterized in that: The material placing machine also includes two auxiliary telescopic arms (7) which are symmetrically arranged with the main telescopic arm (3) as a symmetry axis; one end of the auxiliary telescopic arm (7) is connected to the central axis (1) and the other end is equipped with an infrared laser (5); the auxiliary telescopic arm (7) has the same length as the main telescopic arm (3).

3. The automatic material placing machine based on infrared laser and computer vision according to claim 1, characterized in that: The axis of the rigid feeding tube (4) coincides with the axis of the field of view of the camera (6).

4. A material distributing method using the automatic material distributing machine based on infrared laser and computer vision as claimed in any one of claims 1 to 3, characterized in that: The specific steps include: Step S1, the driving device drives the central axis (1) to rotate along a first direction, and the camera (6) and the infrared laser (5) collect the current steel bar plane information and transmit it to the control center; Step S2, the control center calculates the position relationship between the current steel bar plane and the concrete placing machine according to the collected information; Step S3, the control center calculates the feeding point according to the position relationship, and controls the driving device to drive the central axis (1), the main telescopic arm (3) and the rigid feeding pipe (4) to feed the material at the feeding point; Step S4, determining whether the central axis (1) rotates one circle, if yes, proceeding to step S5; otherwise, returning to step S1; Step S5, judging whether all material feeding is completed, if so, stopping the material placing machine; otherwise, changing the extension length of the main telescopic arm (3) and returning to step S1.

5. The material distributing method according to claim 4, characterized in that: The step S1 specifically includes the following steps: Step S101, the camera (6) collects the current steel bar plane image and transmits it to the control center; Step S102, recording the current initial position, the central axis (1) rotates, the infrared laser (5) stops rotating when it detects a steel bar, and the angle of rotation of the central axis (1) is recorded.

6. The material distributing method according to claim 5, characterized in that: The step S2 specifically includes the following steps: Step S201, the control center processes the current steel bar plane image to obtain a steel bar distribution image; Step S202, the control center calculates the positional relationship between the current steel bar plane and the concrete placing machine based on the steel bar distribution image and the angle at which the infrared laser (5) rotates.

7. The material distributing method according to claim 6, characterized in that: The step S201 specifically includes the following steps: Step S2011, obtaining a ratio k of the distance on the image of the bottom position of the rigid feeding tube (4) on the steel bar plane image to the actual distance according to the relative height difference between the camera (6) and the bottom of the rigid feeding tube (4) and the focal length of the camera (6); Step S2012, based on the Canny edge detection algorithm, extract the steel bar contour to obtain a steel bar distribution image.

8. The material distributing method according to claim 6, characterized in that: The step S202 specifically includes the following steps: Step S2021, based on the steel bar distribution image, obtain the straight line l1 where the steel bars are located detected by the infrared laser (5), the axis O1 of the rigid feeding pipe (4), and the axis l2 of the field of view of the camera (6); Step S2022, according to the plane geometric relationship, solve the position of the central axis (1) in the steel bar plane, and then obtain the distribution radius R in the steel bar plane 真 ; Step S2023, according to R 真 The relationship between the radius R of the fabric placing machine and the scale correction coefficient k is obtained 真 , and then the position relationship between the steel bar plane and the concrete placing crane is obtained.

9. The material distributing method according to claim 4, characterized in that: The step S3 specifically includes the following steps: Step S301, according to the positional relationship between the current steel bar plane and the concrete placing machine, the length of the main telescopic arm (3) is fixed, and the rigid material discharge pipe (4) is rotated along the first direction with the central axis (1) as the axis to form a trajectory in the current steel bar plane; Step S302, extracting the intersection of the steel bar and the trajectory in the current steel bar plane; Step S303, the midpoint of the two adjacent intersection points closest to the rigid feeding pipe (4) in the first direction is the feeding point, and the control center calculates the angle of rotation of the central axis (1) to reach the feeding point; Step S304, the driving device drives the central shaft (1) and the rigid feeding pipe (4) to feed materials.

10. The material distributing method according to claim 9, characterized in that: In step S304, the amount M of material discharged to each feeding point is: M = α 总 m; Among them, α 总 is the total angle of rotation of the central axis (1), α 总 =α1+α2; m is the unit material discharge amount; α1 is the angle through which the central axis (1) rotates from the current position to when the infrared laser (5) detects the steel bar; the position of the central axis (1) when the infrared laser (5) detects the steel bar is defined as the first position, and α2 is the angle through which the central axis (1) rotates from the first position to the material feeding point.

Images