Electric tower anti-falling guide rail intelligent maintenance robot

Abstract

The present application relates to a kind of electric tower anti-falling guide rail intelligent maintenance robot, it solves the technical problem of how to adopt robot to carry out maintenance in the guiding type anti-falling device for overhead transmission line inspection, guide rail appears deformation defect, the connection state between adjacent two tracks is abnormal, bolt group is abnormal, manual maintenance is easy to cause safety accident, it includes mobile platform, mobile platform includes support frame, driving synchronous pulley, driven synchronous pulley, synchronous belt, drive motor, driving roller, driven roller, first rear pressing mechanism, second rear pressing mechanism, first front pressing mechanism and second front pressing mechanism, mobile platform is connected with mechanical arm.The present application can be widely applied to the detection, maintenance of rigid guide rail for electric tower injury anti-falling.

Description

Technical Field

[0001] This invention relates to the field of surveying and maintenance technology for overhead high-voltage transmission lines, and more specifically, to an intelligent maintenance robot for tower anti-fall guide rails. Background Technology

[0002] Overhead transmission lines are the primary method for long-distance, high-capacity power transmission in my country. However, these lines are typically installed in the field, making them susceptible to extreme weather events such as heavy rain, typhoons, lightning, and hail. Under the combined effects of immense alternating tension caused by vibration, bending stress, and long-term fatigue caused by rapid temperature changes, cable, insulator, and other line components are prone to mechanical damage, seriously threatening the safe operation of the lines themselves and their transmission and transformation equipment. Regular inspections of overhead transmission lines can prevent or worsen these conditions.

[0003] Currently, the inspection of overhead transmission lines mainly relies on power company personnel performing high-altitude operations. The greatest danger in these operations is the risk of workers accidentally falling and sustaining injuries or fatalities. Therefore, fall protection devices are crucial for ensuring the safety of personnel working at heights. The most basic fall protection device is a safety rope. One end of the rope is secured to the climber's back with a strap, and the other end is equipped with a hanging ring that can be fastened to foot spikes or the crossarm of the tower. Each time a climber ascends a certain distance using foot spikes, they must bend down to remove the hanging ring and fasten it to the foot spikes or crossarm above, continuing until they reach the designated position. While the safety rope can prevent falls to some extent, significant safety hazards remain during the period when the hanging ring is removed and reinstalled. Furthermore, with the rapid development of power grid construction, the towers are getting increasingly taller, with ultra-high voltage lines averaging over 70 meters in height. This means that climbers need to spend more time installing and removing hanging rings, significantly reducing work efficiency.

[0004] To further improve safety, a guide-type fall arrestor is adopted. Referring to the utility model patent with authorization announcement number CN218248181U and the patent application with application publication number CN110331883A, the guide-type fall arrestor consists of a rigid guide rail, a self-locking device, a connector, a strap, and a safety rope. The rigid guide rail is fixedly installed on the tower and is made of several sections of rail (the material of the rail is aluminum alloy or Q235 steel) spliced ​​together and fastened with bolts. The rigid guide rail is an I-shaped guide rail. The safety rope is fixed to the person climbing the tower by the strap. The hanging ring at the end of the safety rope is engaged with the self-locking device. The self-locking device is machined with a groove that matches the cross section of the guide rail. At the same time, a pulley is set at the part that contacts the end face of the guide rail so that the self-locking device can be fitted onto the guide rail and move smoothly. During normal ascent and descent of personnel, the self-locking device rises and falls synchronously with the safety rope. In the event of a fall, the immense instantaneous acceleration triggers the self-locking mechanism within the device, quickly locking it onto the guide rail. Therefore, the rigid guide rail fall arrest system not only effectively prevents falls but also overcomes the reduced operational efficiency caused by the frequent loading and unloading of lifting rings when relying solely on safety ropes.

[0005] However, after prolonged use, as the self-locking device slides back and forth along the guide rail more frequently, the guide rail, as the main load-bearing component, is prone to defects such as end face deformation and side deformation. These defects can cause the self-locking device to misalign and fail to slide. Simultaneously, the bolts connecting adjacent rail sections can loosen under alternating stress, causing misalignment, relative tilting, and gaps between the two rail sections. These abnormalities severely affect the normal operation of the self-locking device and threaten the personal safety of workers. Therefore, it is essential to regularly inspect the deformation defects of the guide rail, the condition of the bolt groups, and the connection status between adjacent rail sections to address these issues. If manual maintenance is still performed, and the fall protection system already has these hidden dangers, a safety accident is highly likely to occur during the maintenance process. Therefore, how to use robots to replace manual maintenance is a technical problem that urgently needs to be solved by those skilled in the art. Using robots for maintenance can ensure personal safety and improve maintenance efficiency. Summary of the Invention

[0006] This invention aims to address the technical problem of how to use robots for the maintenance of guide rails in overhead power transmission line inspections. When the guide rails have deformation defects, abnormal connection status between adjacent rail sections, or abnormal bolt groups, manual maintenance can easily lead to safety accidents. The invention provides an intelligent maintenance robot for power tower anti-fall guide rails that can replace manual labor to achieve automatic detection and maintenance.

[0007] This invention provides an intelligent maintenance robot for power tower anti-fall guide rails, including a mobile platform. The mobile platform includes a support frame, an active synchronous pulley, a driven synchronous pulley, a synchronous belt, a drive motor, an active roller, a driven roller, a first rear clamping mechanism, a second rear clamping mechanism, a first front clamping mechanism, and a second front clamping mechanism.

[0008] The support frame includes a right side plate, a left side plate, a rear vertical plate, a front vertical plate, a top plate, a rear horizontal plate, a front horizontal plate, a first rear adjusting screw, a second rear adjusting screw, a first front adjusting screw, a second front adjusting screw, a first rear bearing seat, a second rear bearing seat, a first front bearing seat, and a second front bearing seat. The lower parts of the right side plate and the left side plate are fixedly connected by three connecting shafts. The rear vertical plate is fixedly connected to the rear ends of the right side plate and the left side plate. The front vertical plate is fixedly connected to the front ends of the right side plate and the left side plate. The top plate is fixedly connected to the top of the right side plate and the top of the left side plate. The rear horizontal plate is fixed to the rear ends of the top of the right side plate and the top ends of the left side plate. The front cross plate is fixedly connected to the front end of the top of the right side plate and the front end of the top of the left side plate; the rear cross plate has two threaded holes, and the first rear adjusting screw and the second rear adjusting screw are respectively connected to the two threaded holes on the rear cross plate, and the first rear adjusting screw and the second rear adjusting screw pass through the rear cross plate; the front cross plate has two threaded holes, and the first front adjusting screw and the second front adjusting screw are respectively connected to the two threaded holes on the front cross plate, and the first front adjusting screw and the second front adjusting screw pass through the front cross plate; the first rear bearing seat is connected to the left side plate, and the second rear bearing seat is connected to the right side plate; the first front bearing seat is connected to the left side plate, and the second front bearing seat is connected to the right side plate.

[0009] A receiving space is formed between the right side plate, left side plate, rear vertical plate, front vertical plate, and top plate. The drive motor, driving roller, and driven roller are located within this receiving space. The right side plate has a motor connection hole, through which the drive motor connects, and the output shaft of the drive motor extends. The driving synchronous pulley is connected to the output shaft of the drive motor. The driving roller has a rotating shaft, with its left and right ends connected to the first and second rear bearing seats, respectively. The right end of the driving roller's rotating shaft extends outward from the right side plate. The driven synchronous pulley is fixedly connected to the right end of the driving roller's rotating shaft. A synchronous belt connects the driven synchronous pulley and the driving synchronous pulley. The driven roller has a rotating shaft, with its left and right ends connected to the first and second front bearing seats, respectively.

[0010] The second rear clamping mechanism includes a roller positioning block, a slider, an inner bearing, an outer bearing, a tension spring, a lower eye bolt, an upper eye bolt, a guide rail, and a roller. The roller positioning block has an inner bearing chamber and an outer bearing chamber. The inner bearing is located in the inner bearing chamber, and the outer bearing is located in the outer bearing chamber. The roller is connected to the inner bearing and the outer bearing. The slider is fixedly connected to the inner side of the roller positioning block. The lower eye bolt is fixedly connected to the top surface of the roller positioning block. The lower end of the tension spring is hung on the lower eye bolt, and the upper end of the tension spring is hung on the upper eye bolt. The slider is connected to the guide rail.

[0011] The guide rail of the second rear clamping mechanism is fixedly connected to the rear end of the right side plate. The roller of the second rear clamping mechanism is located below the right side plate. The upper lifting eye screw of the second rear clamping mechanism is connected to the right end of the rear horizontal plate. The lower end of the second rear adjusting screw contacts the top of the roller positioning block.

[0012] The first and second rear clamping mechanisms are arranged symmetrically. The first rear clamping mechanism includes a roller positioning block, a slider, an inner bearing, an outer bearing, a tension spring, a lower eye bolt, an upper eye bolt, a guide rail, and a roller. The guide rail of the first rear clamping mechanism is fixedly connected to the rear end of the left side plate. The roller of the first rear clamping mechanism is located below the left side plate. The upper eye bolt of the first rear clamping mechanism is connected to the left end of the rear cross plate. The lower end of the first rear adjusting screw contacts the top of the roller positioning block of the first rear clamping mechanism.

[0013] The second front clamping mechanism includes a roller positioning block, a slider, an inner bearing, an outer bearing, a tension spring, a lower eye bolt, an upper eye bolt, a guide rail, and a roller. The guide rail of the second front clamping mechanism is fixedly connected to the front end of the right side plate. The roller of the second front clamping mechanism is located below the right side plate. The upper eye bolt of the second front clamping mechanism is connected to the right end of the front cross plate. The lower end of the second front adjusting screw contacts the top of the roller positioning block of the second front clamping mechanism.

[0014] The first front clamping mechanism and the second front clamping mechanism are arranged symmetrically. The first front clamping mechanism includes a roller positioning block, a slider, an inner bearing, an outer bearing, a tension spring, a lower eye bolt, an upper eye bolt, a guide rail, and a roller. The guide rail of the first front clamping mechanism is fixedly connected to the front end of the left side plate. The roller of the first front clamping mechanism is located below the left side plate. The upper eye bolt of the first front clamping mechanism is connected to the left end of the front cross plate. The lower end of the first front adjusting screw contacts the top of the roller positioning block of the first front clamping mechanism.

[0015] Preferably, the mobile platform is connected to a camera for acquiring images of the object to be detected.

[0016] Preferably, the mobile platform is equipped with a sensor for detecting whether the self-locking device is malfunctioning.

[0017] Preferably, the mobile platform is equipped with sensors for detecting the robot's position information.

[0018] Preferably, a robotic arm is connected to the mobile platform.

[0019] Preferably, the intelligent maintenance robot for the power tower anti-fall guide rail also includes a robotic arm connection device, a right robotic arm, and a left robotic arm; the robotic arm connection device includes a robotic arm support beam, a linear slide rail assembly one, a linear slide rail assembly two, a right lead screw motor, a right nut, a right nut seat, a right robotic arm connection base, a right lead screw support seat, a left lead screw motor, a left nut, a left nut seat, a left robotic arm connection base, and a left lead screw support seat. Linear slide rail assembly one and linear slide rail assembly two are connected side-by-side to the bottom surface of the robotic arm support beam. Linear slide rail assembly one is provided with a first slider and a third slider, and linear slide rail assembly two is provided with a second slider and a fourth slider. The right lead screw motor is fixedly connected to the right end of the bottom surface of the robotic arm support beam, and the right lead screw support seat is fixedly connected to the robotic arm support beam. At the center of the bottom surface of the beam, the right nut is connected to the lead screw of the right lead screw motor, the end of the lead screw of the right lead screw motor is connected to the right lead screw support seat, the right nut seat is connected to the right nut, the right robotic arm connecting base is fixedly connected to the right nut seat, and the two sides of the right robotic arm connecting base are fixedly connected to the first slider and the second slider respectively; the left lead screw motor is fixedly connected to the left end of the bottom surface of the robotic arm support beam, the left lead screw support seat is fixedly connected to the center of the bottom surface of the robotic arm support beam, the left nut is connected to the lead screw of the left lead screw motor, the end of the lead screw of the left lead screw motor is connected to the left lead screw support seat, the left nut seat is connected to the left nut, the left robotic arm connecting base is fixedly connected to the left nut seat, and the two sides of the left robotic arm connecting base are fixedly connected to the third slider and the fourth slider respectively;

[0020] A boss is connected to the top plate of the support frame. The bottom surface of the robotic arm support beam is fixedly connected to the boss. The right robotic arm is fixedly connected to the right robotic arm connecting base, and the left robotic arm is fixedly connected to the left robotic arm connecting base. The free end of the right robotic arm is connected to end effector one, and the free end of the left robotic arm is connected to end effector two.

[0021] Preferably, the intelligent maintenance robot for the power tower anti-fall guide rail also includes an IMU, an encoder, and a camera for visual positioning. The IMU is connected to the mobile platform, the encoder is connected to the drive motor or the active roller, and the camera for visual positioning is connected to the front end of the mobile platform.

[0022] The camera used for visual positioning captures images of the detection rail. After preprocessing, the images are used by an edge detection algorithm to identify the gaps at the connection points of adjacent rails in the rail, and the number of gaps is obtained. The number of gaps is multiplied by the length of a single rail segment to obtain the robot's absolute position information.

[0023] The robot pose information α is obtained by calculating the trajectory from the data collected by the encoder.b =[x b ,y b ,z b ,θ b ] T The robot pose information, α, is obtained by integrating the data collected by the IMU. i =[x i ,y i ,z i ,θ i ] T The robot pose information obtained by visual positioning using a camera is α. v =[x v ,y v ,z v ,θ v ] T Then we get x k =[x,y,z,θ] T Where x, y, z, θ are derived from α b α i With α v The robot pose information is obtained after weighted fusion using the Kalman filter algorithm; from this, a predictive model of the robot's state at time k can be obtained:

[0024]

[0025] In formula (1), x k Let x be the state vector at time k. k The predicted value, x k-1 For time k-1, the state vector x k-1 The predicted value, F k It is the state transition matrix, B k For the control matrix, u k The control quantity is an external input;

[0026] Similarly, there is the observation model of the system at time k:

[0027] z k =H k x k (2)

[0028] In formula (2), z k H is the actual observed value of the system state at time k. k It is the observation matrix, used to map the state vector to the observation space;

[0029] At each time step, the Kalman filter first predicts the current state based on the prediction model, and the predicted covariance matrix P k It will also update as the state evolves:

[0030]

[0031] Kalman gain K in a Kalman filter k The calculation formula is:

[0032]

[0033] In formula (4), R k The noise covariance matrix of the observations;

[0034] Kalman gain K is obtained through a neural network. k Optimization was performed, and the optimized Kalman gain K was obtained. opt :

[0035]

[0036] The Kalman filter can utilize the optimized Kalman gain K. opt Update the state estimate and output:

[0037]

[0038] Preferably, a first depth camera is connected to the free end of the right robotic arm, and a second depth camera is connected to the free end of the left robotic arm.

[0039] The first depth camera and / or the second depth camera are configured to acquire images of the guide rail to be detected;

[0040] The image of the guide rail to be inspected is input into the YOLOv5 model, which incorporates an attention mechanism module, to identify the surface defects of the guide rail to be inspected.

[0041] After obtaining the surface defects of the guide rail to be inspected, the position information of the mobile robot is obtained and sent to the host computer.

[0042] Preferably, a first depth camera is connected to the free end of the right robotic arm, and a second depth camera is connected to the free end of the left robotic arm.

[0043] The first depth camera and / or the second depth camera are configured to acquire images of the bolt group on the guide rail to be inspected;

[0044] The image of the bolt group on the guide rail to be detected is input into the YOLOv5 model with an attention mechanism module to identify the bolt group, and then the image of a single bolt is cropped out based on the anchor frame information in the identification result;

[0045] The image of a single bolt is processed by an edge detection algorithm based on the Canny operator to obtain the edge contour of the bolt.

[0046] The edge contour is extracted by the Douglas-Puk algorithm, and the bolt edge equation is fitted by the least squares method based on the edge points and corner points. The angle θ between the line and the x-axis is calculated by the arctangent function based on the slope k of the edge equation. At the same time, it is converted from radians to degrees by the following formula (7):

[0047]

[0048] The included angles θ corresponding to the six sides of a single bolt can be solved sequentially using formula (7). i (i = 1, 2, ..., 6), and then the angle values ​​of the six edges are quantified into the angle value θ of the bolt itself using the following formula (8). bolt ,

[0049]

[0050] The quantized angle value of the bolt in its current state is calculated using formula (8). The quantized angle value θ of the bolt under normal conditions is calculated using formula (8). bolti Then, the loosening angle Δθ of the bolt is calculated using the following formula (9). i :

[0051]

[0052] loosening angle Δθ i Compared with the set threshold, if the loosening angle Δθ i If the value exceeds the threshold, it is determined to be loose;

[0053] The three-dimensional coordinates of the loose bolt in the robot coordinate system are calculated. This three-dimensional coordinate information is transmitted to the robot arm path planning algorithm to obtain the desired motion path of the robot arm. Then, the right robot arm or the right robot arm action causes the end effector one or the end effector two to tighten the loose bolt.

[0054] The beneficial effects of this invention are that it replaces manual maintenance of rigid guide rails, enabling robots to perform maintenance work, resulting in a high degree of automation and intelligence, avoiding safety accidents, and ensuring personnel safety.

[0055] It significantly improves the efficiency of maintenance operations and has the advantages of high efficiency, good operability, and high flexibility.

[0056] It has high detection accuracy, accurately detecting defects such as deformation of guide rails, abnormal conditions such as loose bolt groups, and abnormal connection conditions such as misalignment, relative tilt, and gap between adjacent rail sections.

[0057] It can adapt to different lighting conditions. Suitable for weather conditions such as direct sunlight, haze, or heavy fog.

[0058] It can accurately determine the robot's position information and perform precise positioning. It can also accurately determine the location of defects and anomalies on the guide rail.

[0059] With multiple functions, the robotic arm installed on the robot can repair bolts in abnormal condition.

[0060] Further features and aspects of the present invention will be clearly described in the following detailed description with reference to the accompanying drawings. Attached Figure Description

[0061] Figure 1 It is an isometric drawing of the maintenance robot;

[0062] Figure 2 yes Figure 1 The front view of the robot shown;

[0063] Figure 3 yes Figure 1 Left view of the robot shown;

[0064] Figure 4 yes Figure 1 An isometric view of the robot from another perspective;

[0065] Figure 5 This is an exploded view of the mobile platform;

[0066] Figure 6 It is an isometric drawing of a mobile platform;

[0067] Figure 7 It is an isometric drawing of a mobile platform;

[0068] Figure 8 This is an exploded view of the second rear clamping mechanism;

[0069] Figure 9 This is a cross-sectional view of the second rear clamping mechanism;

[0070] Figure 10 This is a schematic diagram of two robotic arms mounted on a robotic arm support beam.

[0071] Figure 11 This is a schematic diagram of the structure where the connecting bases of the two robotic arms are mounted on a linear module on the bottom surface of the robotic arm support beam.

[0072] Figure 12 This is a schematic diagram of the structure in which the first depth camera and the second depth camera are respectively installed at the free ends of the right and left robotic arms;

[0073] Figure 13 yes Figure 12Side view of the structure shown;

[0074] Figure 14 This is a flowchart of the robot localization algorithm;

[0075] Figure 15 This is a flowchart of an improvement to the Canny algorithm;

[0076] Figure 16 This is a flowchart of the bolt loosening detection algorithm;

[0077] Figure 17 This is a flowchart of the robot performing its tasks.

[0078] Explanation of symbols in the diagram:

[0079] 1. Support frame, 1-1. Right side plate, 1-1-1. Motor connection hole, 1-2. Left side plate, 1-3. Rear vertical plate, 1-4. Front vertical plate, 1-5. Top plate, 1-6. Rear closing plate, 1-7. Front closing plate, 1-8. Connecting shaft, 1-9. Triangular bracket, 1-10. Triangular bracket, 1-11. Triangular bracket, 1-12. Triangular bracket, 1-13. Eye bolt for self-locking device connection, 1-14. First rear adjusting screw, 1-15. Second rear adjusting screw, 1-16. First front adjusting screw, 1-17. Second front adjusting screw, 1-1 8. Boss; 1-19. First rear bearing housing; 1-20. Second rear bearing housing; 1-21. First front bearing housing; 1-22. Second front bearing housing; 1-23. Motor connection hole; 2. Driving synchronous pulley; 3. Driven synchronous pulley; 4. Rear cross plate; 5. First rear clamping mechanism; 5-1. Roller positioning block; 5-2. Slider; 5-3. Tension spring; 5-4. Roller; 5-5. Upper eyelet screw; 6. Second rear clamping mechanism; 6-1. Roller positioning block; 6-1-1. Threaded hole; 6-2. Slider; 6-3. Inner bearing; 6-4. Outer bearing 6-5. Shaft end retaining ring; 6-6. Bearing end cover; 6-7. Screw; 6-8. Tension spring; 6-9. Lower eyelet screw; 6-10. Upper eyelet screw; 6-11. Guide rail; 6-12. Roller; 7. Front cross plate; 8. Second front clamping mechanism; 8-1. Roller positioning block; 8-2. Tension spring; 8-3. Upper eyelet screw; 8-4. Lower eyelet screw; 8-5. Guide rail; 8-6. Roller; 9. Driving roller; 10. Driven roller; 11. Robotic arm support beam; 12. Linear slide rail assembly one; 12-1. First slider; 12-2. ... 13. Linear slide rail assembly two; 13-1. Second slide rail; 14. Right lead screw motor; 15. Right nut; 16. Right nut seat; 17. Right robotic arm connecting base; 18. Right lead screw support seat; 19. Left lead screw motor; 20. Left robotic arm connecting base; 21. Left lead screw support seat; 22. Right robotic arm; 23. Left robotic arm; 24. End effector one; 25. End effector two; 26. First depth camera; 27. Second depth camera; 28. I-shaped rigid guide rail; 29. ​​Foot pin; 30. Inter-segment connecting bolt; 31. Tension sensor. Detailed Implementation

[0080] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0081] like Figure 1-4As shown, the intelligent maintenance robot for the power tower anti-fall guide rail includes a mobile platform, a robotic arm connection device, a right robotic arm 22, a left robotic arm 23, an end effector 1 24, and an end effector 25. The robotic arm connection device is installed on the mobile platform, and the right and left robotic arms are respectively installed on the robotic arm connection device. The end effector 1 24 is connected to the free end of the right robotic arm 22, and the end effector 25 is connected to the free end of the left robotic arm 23.

[0082] The mobile platform includes a support frame 1, an active synchronous pulley 2, a driven synchronous pulley 3, a synchronous belt, a drive motor, an active roller 9, a driven roller 10, a first rear clamping mechanism 5, a second rear clamping mechanism 6, a first front clamping mechanism, and a second front clamping mechanism 8.

[0083] like Figure 5-7As shown, the support frame 1 includes a right side plate 1-1, a left side plate 1-2, a rear vertical plate 1-3, a front vertical plate 1-4, a top plate 1-5, a rear horizontal plate 4, a front horizontal plate 7, a rear closing plate 1-6, a front closing plate 1-7, a connecting shaft 1-8, triangular brackets 1-9, 1-10, 1-11, and 1-12, a self-locking device connecting eye bolt 1-13, a first rear adjusting screw 1-14, a second rear adjusting screw 1-15, a first front adjusting screw 1-16, a second front adjusting screw 1-17, a boss 1-18, a first rear bearing seat 1-19, a second rear bearing seat 1-20, and a first front axle. Bearing seat 1-21, second front bearing seat 1-22, the lower part of right side plate 1-1, and the lower part of left side plate 1-2 are fixedly connected by three connecting shafts 1-8. The rear vertical plate 1-3 is fixedly connected to the rear end of right side plate 1-1 and the rear end of left side plate 1-2 by screws. The front vertical plate 1-4 is fixedly connected to the front end of right side plate 1-1 and the front end of left side plate 1-2 by screws. The top plate 1-5 is fixedly connected to the top of right side plate 1-1 and the top of left side plate 1-2 by screws. The rear horizontal plate 4 is fixedly connected to the rear end of the top of right side plate 1-1 and the rear end of the top of left side plate 1-2 by screws. The front horizontal plate 4 is fixedly connected to the rear end of the top of left side plate 1-1 by screws. Plate 7 is fixedly connected to the front end of the top of the right side plate 1-1 and the front end of the top of the left side plate 1-2; since the middle of the top of the right side plate 1-1 is lower than both ends, and the middle of the top of the left side plate 1-2 is lower than both ends, the rear closing plate 1-6 is fixedly connected to the side of the rear end of the top of the right side plate 1-1 and the side of the rear end of the top of the left side plate 1-2 by screws; the front closing plate 1-7 is fixedly connected to the side of the front end of the top of the right side plate 1-1 and the side of the front end of the top of the left side plate 1-2 by screws; the boss 1-18 is fixedly connected to the top plate 1-5 by screws; the two triangular brackets 1-10 are connected to the rear horizontal plate 4 and Between the right side plate 1-1, two triangular brackets 1-9 connect between the rear cross plate 4 and the left side plate 1-2; two triangular brackets 1-11 connect between the front cross plate 7 and the left side plate 1-2; and two triangular brackets 1-12 connect between the front cross plate 7 and the right side plate 1-1. A self-locking device is connected to the rear vertical plate 1-3 using an eye bolt 1-13. The first rear adjusting screw 1-14 and the second rear adjusting screw 1-15 are respectively connected to the corresponding threaded holes on the rear cross plate 4 and pass through the rear cross plate 4. The first front adjusting screw 1-16 and the second front adjusting screw 1-17 are respectively connected to the corresponding threaded holes on the front cross plate 7 and pass through the front cross plate 7. The first rear bearing seat 1-19 connects to the left side plate 1-2, and the second rear bearing seat 1-20 connects to the right side plate 1-1. The first front bearing seat 1-21 connects to the left side plate 1-2, and the second front bearing seat 1-22 connects to the right side plate 1-1.

[0084] A receiving space is formed between the right side plate 1-1, left side plate 1-2, rear vertical plate 1-3, front vertical plate 1-4, and top plate 1-5, in which the drive motor, driving roller 9, and driven roller 10 are located. The right side plate 1-1 has a motor connection hole 1-1-1, where the drive motor is fixedly mounted. The output shaft of the drive motor extends from this connection hole, and the driving synchronous pulley 2 is connected to the output shaft of the drive motor. The driving roller 9 has a rotating shaft; its left end is connected to a bearing in the first rear bearing housing 1-19, and its right end is connected to a bearing in the second rear bearing housing 1-20. The right end of the rotating shaft extends outward from the right side plate 1-1, allowing the driving roller 9 to rotate under the support of the two bearing housings. The driven synchronous pulley 3 is fixedly connected to the right end of the rotating shaft of the driving roller 9. A synchronous belt connects the driven synchronous pulley 3 and the driving synchronous pulley 2. The driven roller 10 is equipped with a rotating shaft. The left end of the rotating shaft is connected to the bearing in the first front bearing housing 1-21, and the right end of the rotating shaft is connected to the rotating shaft in the second front bearing housing 1-22. Supported by the first and second front bearing housings 1-21 and 1-22, the driven roller 10 can rotate. When the drive motor is working, it drives the active synchronous pulley 2, the synchronous belt, and the moving synchronous pulley 3 to rotate the active roller 9. An electromagnetic de-energized brake can be installed at the hub flange of the driven roller 10 to reliably stop the driven roller 10, thus achieving reliable braking of the entire robot.

[0085] like Figure 10 and 11 As shown, the robotic arm connection device includes a robotic arm support beam 11, linear slide rail assembly one 12, linear slide rail assembly two 13, a right lead screw motor 14, a right nut 15, a right nut seat 16, a right robotic arm connection base 17, a right lead screw support seat 18, a left lead screw motor 19, a left nut, a left nut seat, a left robotic arm connection base 20, and a left lead screw support seat 21. Linear slide rail assembly one 12 and linear slide rail assembly two 13 are connected side-by-side to the bottom surface of the robotic arm support beam 11. Linear slide rail assembly one 12 has a first slider 12-1 and a third slider 12-2, and linear slide rail assembly two 13 has a second slider 13-1 and a fourth slider. The right lead screw motor 14... The right lead screw support seat 18 is fixedly installed at the right end of the bottom surface of the robotic arm support beam 11. The right lead screw motor 14 is equipped with a lead screw, and the right nut 15 is connected to the lead screw. The end of the lead screw of the right lead screw motor 14 is connected to the right lead screw support seat 18. The right nut seat 16 is connected to the right nut 15. The right robotic arm connecting base 17 is fixedly connected to the right nut seat 16 by screws. The two sides of the right robotic arm connecting base 17 are fixedly connected to the first slider 12-1 and the second slider 13-1, respectively. When the right lead screw motor 14 works, it can drive the right robotic arm connecting base 17 to translate along the length direction of the robotic arm support beam 11.

[0086] The left lead screw motor 19 is fixedly installed at the left end of the bottom surface of the robotic arm support beam 11. The left lead screw support seat 21 is fixedly installed at the middle of the bottom surface of the robotic arm support beam 11. The left lead screw motor 19 is provided with a lead screw, and the left nut is connected to the lead screw. The end of the lead screw of the left lead screw motor 19 is connected to the left lead screw support seat 21. The left nut seat is connected to the left nut. The left robotic arm connecting base 20 is fixedly connected to the left nut seat by screws. The two sides of the left robotic arm connecting base 20 are fixedly connected to the third slider 12-2 and the fourth slider, respectively. When the left lead screw motor works, it can drive the left robotic arm connecting base 20 to translate along the length direction of the robotic arm support beam 11.

[0087] like Figure 5 , 8 As shown in Figure 9, the second rear clamping mechanism 6 includes a roller positioning block 6-1, a slider 6-2, an inner bearing 6-3, an outer bearing 6-4, a shaft end retaining ring 6-5, a bearing end cover 6-6, a screw 6-7, a tension spring 6-8, a lower eye bolt 6-9, an upper eye bolt 6-10, a guide rail 6-11, and a roller 6-12. The top surface of the roller positioning block 6-1 is provided with a threaded hole 6-1-1. The roller positioning block 6-1 is provided with an inner bearing chamber and an outer bearing chamber. Bearing 6-3 is located in the inner bearing chamber, and bearing 6-4 is located in the outer bearing chamber. Roller 6-12 is connected to inner bearing 6-3 and outer bearing 6-4. Roller 6-12 can rotate under the support of inner bearing 6-3 and outer bearing 6-4. Shaft end retaining ring 6-5 is connected to the end of roller 6-12. Bearing end cover 6-6 is connected to the outer side of roller positioning block 6-1, and bearing end cover 6-6 blocks outer bearing 6-4. Four screws 6-7 fix slider 6-2 to the inner side of roller positioning block 6-1. Lower eye screw 6-9 is connected to threaded hole 6-1-1. The lower end of tension spring 6-8 is hung on lower eye screw 6-9, and the upper end of tension spring 6-8 is hung on upper eye screw 6-10. Slider 6-2 is connected to guide rail 6-11, and slider 6-2 can slide along guide rail 6-11.

[0088] refer to Figure 5 , 6 7. Guide rail 6-11 is fixedly installed at the rear end of right side plate 1-1, and upper eyelet screw 6-10 is connected to the right end of rear cross plate 4. Roller 6-12 is located below right side plate 1-1. The lower end of the second rear adjusting screw 1-15 contacts the top of roller positioning block 6-1. Tightening the second rear adjusting screw 1-15 causes the lower end of the second rear adjusting screw 1-15 to move downward and press against roller positioning block 6-1, causing roller positioning block 6-1 to move downward. Then, when the second rear adjusting screw 1-15 is tightened in the opposite direction, the lower end of the second rear adjusting screw 1-15 moves upward. Under the tension of tension spring 6-8, roller positioning block 6-1 moves upward, and roller 6-12 moves upward under the drive of roller positioning block 6-1.

[0089] The structure of the first rear clamping mechanism 5 is the same as that of the second rear clamping mechanism 6, the structure of the second front clamping mechanism 8 is the same as that of the second rear clamping mechanism 6, and the structure of the first front clamping mechanism is the same as that of the second rear clamping mechanism 6. The entire robot is equipped with four sets of clamping mechanisms, two sets at the rear and two sets at the front.

[0090] refer to Figure 1 , 3 Under the tension of the tension spring 6-8, the roller 6-12 of the second rear clamping mechanism 6 presses upward against the top inner side of the I-shaped rigid guide rail, applying a certain pressure to the top inner side of the I-shaped rigid guide rail. The roller 6-12 is inclined to adapt to the top inner side of the I-shaped rigid guide rail.

[0091] refer to Figure 3 The first rear clamping mechanism 5 and the second rear clamping mechanism 6 are arranged symmetrically. As can be seen from the figure, the roller positioning block 5-1 and the roller positioning block 6-1 are symmetrical. The guide rail of the first rear clamping mechanism 5 is fixedly installed at the rear end of the left side plate 1-2. This guide rail is connected and cooperates with the slider 5-2. The upper lifting eye screw 5-5 of the first rear clamping mechanism 5 is connected to the left end of the rear horizontal plate 4 (e.g., Figure 5 As shown in the figure, the upper end of the tension spring 5-3 is attached to the upper eyelet screw, and the lower end of the tension spring 5-3 is attached to the lower eyelet screw of the first rear clamping mechanism 5. The roller 5-4 is located below the left side plate 1-2. As can be seen from the figure, the roller 5-4 presses upward against the top inner side of the I-shaped rigid guide rail, and the roller 5-4 is inclined to adapt to the top inner side of the I-shaped rigid guide rail. The lower end of the first rear adjusting screw 1-14 contacts the top of the roller positioning block 5-1. Tightening the first rear adjusting screw 1-14 causes the lower end of the first rear adjusting screw 1-14 to move downward, pressing the roller positioning block 5-1 downward, causing the roller positioning block 5-1 to move downward. Then, when the first rear adjusting screw 1-14 is tightened in the opposite direction, the lower end of the first rear adjusting screw 1-14 moves upward, and under the tension of the tension spring 5-3, the roller positioning block 5-1 moves upward.

[0092] refer to Figure 2 In the second front clamping mechanism 8, the lower eyelet screw 8-4 is connected to the roller positioning block 8-1, the lower end of the tension spring 8-2 is hooked on the lower eyelet screw 8-4, and the upper end of the tension spring 8-2 is hooked on the upper eyelet screw 8-3. (Reference) Figure 5The guide rail 8-5 is fixedly installed at the front end of the right side plate 1-1, and the upper eyelet screw 8-3 is connected to the right end of the front cross plate 7. The slider in the second front clamping mechanism 8 is connected and engaged with the guide rail 8-5. The roller of the second front clamping mechanism 8 is located below the right side plate 1-1. Similarly, the inclined roller in the second front clamping mechanism 8 presses upward against the top inner side of the I-shaped rigid guide rail. Tightening the second front adjusting screw 1-17 causes its lower end to move downward, thereby pressing the roller positioning block 8-1 downward, and the roller positioning block 8-1 moves downward. Then, by twisting the second front adjusting screw 1-17 in the opposite direction, the roller positioning block 8-1 moves upward under the tension of the tension spring 8-2.

[0093] The first and second front clamping mechanisms 8 are arranged symmetrically. Similarly, the inclined roller in the first front clamping mechanism presses upward against the top inner side of the I-shaped rigid guide rail. Tightening the first front adjusting screw 1-16 allows the roller positioning block in the first front clamping mechanism to move downward or upward. The roller of the first front clamping mechanism is located below the left side plate 1-2.

[0094] The bottom surface of the robotic arm support beam 11 is fixedly connected to the boss 1-18 by screws. Then, the right robotic arm 22 is fixedly installed on the right robotic arm connecting base 17 by screws, and the left robotic arm 23 is fixedly installed on the left robotic arm connecting base 20 by screws.

[0095] End effector 1 24 is connected to the free end of the right robotic arm 22, and end effector 25 is connected to the free end of the left robotic arm 23. As shown in the figure, end effectors 1 24 and 2 25 are specifically electric impact wrenches. The motor in the electric impact wrench is a brushless DC motor. The electric impact wrench tightens the bolts on the guide rail using a torque-angle method. The workflow is divided into three stages. The first stage is the thread engagement stage, where the wrench needs to overcome the frictional torque of the thread. This stage has a longer stroke, the least resistance, and requires the highest speed. The second stage is the engagement stage, which begins when the torque value measured by the sensor exceeds the threshold specified in the second stage. This stage requires overcoming certain resistance, and the stroke before the next stage is short, so the motor speed decreases. The third stage is the tightening stage, which begins when the torque measured by the torque sensor reaches the threshold of the third stage. This stage uses an angle method for tightening, requiring the motor to rotate at a certain angle, with the lowest speed and the most precise control. When the torque measured by the sensor reaches the set value, the motor stops abruptly, completing the operation. The first and second stages employ torque tightening, while the third stage uses angle tightening for precise tightening. A three-closed-loop control architecture consisting of a current loop, a speed loop, and a position loop is used to achieve precise control of the brushless DC motor.

[0096] This invention utilizes multi-sensor fusion for robot localization, employing three types of sensors: an IMU (Inertial Measurement Unit), an encoder, and a camera. The IMU typically consists of an accelerometer, a gyroscope, and a magnetometer. The accelerometer measures the robot's acceleration along the guide rail, and the velocity and displacement are calculated through integration. The gyroscope measures the robot's angular velocity change, and the tilt angle is calculated through integration. The magnetometer measures the object's orientation relative to the Earth's magnetic field. The IMU has a high operating frequency, resulting in good local positioning performance. However, it exhibits drift over time; a small constant error becomes extremely large after multiple integrations. Therefore, it is usually necessary to combine it with other localization methods to reduce errors. The IMU can be mounted on the front crossbar of the mobile platform.

[0097] The encoder is mounted on the drive motor or the shaft of the active roller. During robot operation, each rotation of the active roller generates a constant number of pulses from the encoder. With a fixed sampling period, the number of wheel rotations within that time interval can be calculated by measuring the number of pulses generated by the wheel's rotation, thus determining the robot's displacement relative to the guide rail. There are three main methods for measuring speed using rotary encoders: the Master method (M method), the Tracking method (T method), and the Master-Tracking method (M / T method). The Master-Tracking method combines the advantages of both methods, allowing direct speed estimation using the encoder's output pulse count while also using time intervals to correct the speed measurement, improving stability and accuracy. Therefore, the rotational speed of the active roller is calculated using the Master-Tracking method's speed measurement formula, and then the pose parameters are obtained using a trajectory calculation algorithm based on the robot's motion model.

[0098] The controller can be mounted on the front panel of the mobile platform and is equipped with a wireless transmission module. The encoder is connected to the controller via signal cables. The IMU (Inertial Measurement Unit) is also connected to the controller via signal cables.

[0099] IMU positioning and encoder positioning are both relative positioning methods, which suffer from accumulated errors and require regular calibration to ensure their accuracy and stability. GPS, as a commonly used absolute positioning system, can measure altitude, but its accuracy is typically lower than that of horizontal positioning, ranging from several meters to tens of meters. To compensate for these shortcomings, a camera-based visual positioning scheme is introduced to correct for errors in relative positioning. According to the industry standard "Fall Protection Devices for Pole Operations," the length of a single vertical guide rail segment should be a fixed value of 4000mm, with an allowable deviation of ±1.5mm. This difference is relatively small, and the gaps between adjacent rail connections are clearly visible, allowing for visual positioning. Therefore, the camera used for positioning is mounted at the front end of the mobile platform (e.g., on the front horizontal or vertical plate). As the robot moves up and down along the guide rail, the camera mounted at the front of the robot captures images of the guide rail, obtaining continuous image frames. The controller then preprocesses and performs edge detection on these image frames. Edge detection uses the Hough transform algorithm, which calculates the possible straight lines formed by edge pixels in the image to identify gaps at the connections between adjacent rails. Each gap is identified and counted once to obtain the number of gaps. The number of gaps is multiplied by the length of a single track segment to obtain the robot's absolute position information, thus achieving visual positioning of the robot.

[0100] IMU and encoder-based positioning calculates the robot's position based on its kinematic model, requiring no external environmental information and offering high accuracy over short periods, but suffers from error accumulation. While visual positioning methods offer high accuracy, their positioning is discontinuous and prone to errors in identifying guide rail gaps and omissions in counting. Therefore, a suitable fusion algorithm is chosen to fuse the acquired positioning data, achieving a complementary advantage of the three methods. Commonly used fusion algorithms include particle filtering and Kalman filtering. Particle filtering can be used for nonlinear systems but has a high computational cost; Kalman filtering has a lower computational cost but is only suitable for linear systems. To overcome these shortcomings, neural networks or improved algorithms such as extended Kalman filtering or error Kalman filtering can be introduced. Considering all factors, the Kalman filtering algorithm is chosen for multi-sensor fusion positioning, while a neural network is used to improve it, enhancing the system's positioning accuracy and stability. (Reference) Figure 14 The core idea of ​​the Kalman filter algorithm is to construct a vector x from the robot's states at time k. k Let α be the robot pose information obtained by calculating the trajectory from the data collected by the encoder. b =[x b ,y b ,z b ,θ b ] T The robot pose information, α, is obtained by integrating the data collected by the IMU. i =[xi ,y i ,z i ,θ i ] T The robot pose information obtained by visual positioning through a camera is α. v =[x v ,y v ,z v ,θ v ] T Then we get x k =[x,y,z,θ] T Where x, y, z, θ are derived from α b α i With α v The robot pose information is obtained after weighted fusion using the Kalman filter algorithm. From this, a predictive model of the robot's state at time k can be derived:

[0101]

[0102] In formula (1), x k Let x be the state vector at time k. k The predicted value, x k-1 For time k-1, the state vector x k-1 The predicted value, F k It is the state transition matrix, B k For the control matrix, u k This refers to the control quantity input from an external source.

[0103] Similarly, there is the observation model of the system at time k:

[0104] z k =H k x k (2)

[0105] In formula (2), z k H is the actual observed value of the system state at time k. k It is the observation matrix, used to map the state vector to the observation space.

[0106] At each time step, the Kalman filter first predicts the current state based on the prediction model, and the predicted covariance matrix P k It will also update as the state evolves:

[0107]

[0108] The trade-offs in the reliability of each sensor and the fusion of predicted and actual observations are determined by the Kalman gain K. k Determined. In traditional Kalman filtering, K... k The calculation formula is:

[0109]

[0110] In formula (4), R k Let be the noise covariance matrix of the observations.

[0111] For complex nonlinear systems, P k With R k The changes in attitude are difficult to estimate accurately, meaning that traditional Kalman filtering may no longer be effective. Backpropagation (BP) neural networks possess nonlinear mapping and adaptive capabilities; this invention employs a BP neural network fused with extended Kalman filtering to improve the accuracy of attitude calculation. Other neural networks, such as Elman neural networks and convolutional neural networks, can also be used.

[0112] A backpropagation (BP) neural network generates an optimized Kalman gain by learning the deviation between the actual and estimated states in historical data. The network's input includes observed and predicted system states, as well as current covariance information, and the output is the optimized gain.

[0113] A backpropagation (BP) neural network structure consists of an input layer, hidden layers, and an output layer. The input quantity in the input layer includes the predicted value x. k-1 Observed value z k The predicted covariance matrix P k With noise covariance matrix R k The hidden layers are set to three layers based on engineering experience, with 15 neurons in each layer, and the sigmoid function is used for activation. The output layer uses a single neuron and a linear activation function. After receiving the observation and prediction information at the current time step, the trained BP neural network outputs the optimized Kalman gain K. opt :

[0114]

[0115] The Kalman filter can utilize the optimized Kalman gain K. opt Update the state estimate and output:

[0116]

[0117] Since the estimated state vector is generated based on the fusion of IMU and encoder data, it belongs to relative positioning and will accumulate errors over time. Therefore, absolute positioning is needed for calibration. As mentioned earlier, the vision-based absolute positioning approach uses the Hough transform algorithm to identify and count the gaps between adjacent track connections. Each time the robot passes through a gap, the counter increments by one, and the count is multiplied by the length of a single track segment to obtain the robot's absolute position at that moment. When the robot detects passing through a gap, the α value input to the BP neural network... v A sudden change will occur when the BP neural network is solving for the Kalman gain K. opt When will it affect α v By assigning sufficiently large weights, the final localization estimate x output by the Kalman filter is made to be such that... k The main source of this information is the absolute positioning information α. v The decision is made. This process constitutes the robot's positioning calibration. After calibration, the calibrated positioning estimate x is recorded. k and assign it to α v As subsequent input to the BP network, it continues until the robot passes through the next section of the guide rail gap and generates a new α. v .

[0118] like Figure 12 and 13 As shown, the first depth camera 26 is connected to the free end of the right robotic arm 22 via a camera bracket, and the second depth camera 27 is connected to the free end of the left robotic arm 23 via a camera bracket. Considering that ambient lighting may be too strong or too weak due to weather conditions, affecting the robot's visual detection performance, this invention employs a deep learning-based visual algorithm to detect surface defects on the guide rail and identify bolt group anomalies. Images of the guide rail are acquired through the first depth camera 26 and / or the second depth camera 27.

[0119] This invention selects the YOLOv5 algorithm to identify and detect surface defects such as guide rail deformation and bolt group anomalies. YOLOv5 is an anchor-frame-based target detection model. Its core idea is to divide the target detection task into three sub-tasks: bounding box regression, target classification, and confidence prediction. The YOLOv5 model predicts the target position through anchor frames and filters redundant predicted boxes using the non-maximum suppression (NMS) method to obtain the final detection result. The network structure of the YOLOv5 model includes the following three parts: Backbone, Neck, and Head. The YOLOv5 Backbone is used to extract multi-scale features from the input image. It uses CSPDarknet53 as the backbone network and effectively reduces the computational load while enhancing the feature expressiveness through the cross-stage partial network CSP module. The YOLOv5 Neck part is mainly used for multi-scale feature fusion to improve the detection capability of targets of different sizes. The Neck section also introduces the SPPF module, which increases the receptive field and aggregates key information by performing multi-scale pooling operations on the feature map. The Head section of YOLOv5 is responsible for generating the final detection results. It adopts an anchor-box-based prediction method, which divides the feature map into multiple grids, predicts multiple anchor boxes in each grid, and outputs the target category, bounding box coordinates, and confidence information. Low-confidence or overlapping prediction boxes are removed by NMS to obtain the final detection results.

[0120] In actual operation, robots may encounter extreme weather conditions such as scorching sun and heavy fog, which can reduce image quality and thus affect recognition performance. To further improve the adaptability of the selected YOLOv5 model to the working environment of this project, attention mechanisms can be introduced to improve it. Commonly used modules include SE, CBAM, BAM, and CA. For example, the CA module can be used to improve the YOLOv5 model. In the CA module, average pooling is performed on the input feature map along both the width and height directions, embedding positional information into the channel attention, thereby achieving the effect of simultaneously obtaining channel attention and spatial attention. The backbone of YOLOv5 contains the key component C3 module, which consists of three Conv modules and one Bottleneck module. It further enhances the network's feature extraction capability through residual connections and feature fusion. By adding the CA attention module to the Bottleneck residual connection of the C3 module, and then replacing all the C3 modules in the original YOLOv5 backbone network with the improved C3 module, a YOLOv5 network model with an incorporating attention mechanism is constructed. Using the improved YOLOv5 model, the robot can focus more on the area of ​​interest during the detection process, which can overcome the effects of strong or weak light environments to a certain extent.

[0121] The training dataset required to train the improved YOLOv5 model can be expanded by taking real-world photos and performing data augmentation operations such as positive and negative sample balancing and geometric transformations.

[0122] For bolts connecting adjacent tracks, abnormal bolt loosening is identified using image recognition. First, an improved YOLOv5 model is used to identify bolt groups. Then, based on the anchor frame information in the identification results, a sub-image containing only a single bolt is cropped. Next, an edge detection algorithm based on the Canny operator is used to perform edge detection processing on the individual bolt image. Methods such as bilateral filtering, non-maximum suppression, and double threshold detection can be used to improve the traditional Canny operator to eliminate false edges caused by background noise as much as possible, thereby improving the algorithm's accuracy. (Reference) Figure 15 Traditional Canny operators use the first derivative of a two-dimensional Gaussian function as an image filter, but Gaussian filtering can cause image loss and blurring of edges after smoothing. This invention uses bilateral filtering as an improved image filter for the Canny operator, resulting in a more stable and accurate smoothed image. After obtaining grayscale image information, the Canny operator calculates gradients to obtain a series of potential edge pixels. Non-maximum suppression is introduced, comparing each potential pixel along its specific gradient direction with its surrounding neighborhood. If the gradient intensity of a pixel significantly exceeds that of its neighboring pixels on either side of its gradient direction, it is considered a valid edge pixel; otherwise, it is considered a false detection and removed. Finally, dual threshold detection is used to further process the processed pixel set, filtering pixels based on the high and low threshold coefficients and histogram information to obtain the final edge point information with high confidence.

[0123] refer to Figure 16 After extracting the edge point information, the bolt outline is obtained. The Douglas-Puk algorithm is used to extract the corner points of the edge outline, and the bolt edge equation is fitted by the least squares method based on the edge points and corner points. After obtaining the edge equation expression, the bolt loosening can be evaluated. The arctangent function is used to calculate the angle θ between the straight line and the x-axis based on the slope k of the edge equation. At the same time, it is converted from radians to degrees using the following formula (7).

[0124]

[0125] The included angles θ corresponding to the six sides of a single bolt can be solved sequentially using the above formula. i (i = 1, 2, ..., 6). Then, the angle values ​​of the six edges are quantified into the bolt's own angle value θ using the following formula (8). bolt ,

[0126]

[0127] The range of the bolt's own angle value is θ. bolt ∈[0,60].

[0128] Before the robot is put into use for inspection work, edge detection and angle quantization are performed on the bolts on the guide rail in their normal state to obtain the quantized angle value θ in the normal state. bolti During robot operation, the quantized angle value of the bolt's current state, as actually detected, is... Then, the quantization angle value in the current state is obtained using the following formula (9). Quantized angle value θ under normal conditions bolti The absolute value of the difference is used to obtain the loosening angle Δθ of the i-th bolt. i ,

[0129]

[0130] loosening angle Δθ i Compared with the set threshold, if the loosening angle Δθ i If the value exceeds the threshold, it is determined to be loose.

[0131] The specific value of the threshold can be 3σ, where σ is the quantized angle value θ under multiple normal states. bolti The standard deviation of the interval error.

[0132] refer to Figure 17 The process of using the above robot is as follows:

[0133] The first step is to install the robot on the vertical I-shaped rigid guide rail 28.

[0134] The operator uses an Allen wrench to tighten the first rear adjusting screw 1-14, the second rear adjusting screw 1-15, the first front adjusting screw 1-16, and the second front adjusting screw 1-17 on the front and rear horizontal plates of the moving platform, causing them to move downwards. This, in turn, pushes the roller positioning block in contact with the platform downwards until the distance between the roller of the clamping mechanism and the bottom of the moving platform is greater than the thickness of the flange of the I-shaped rigid guide rail 28. At this point, the robot can be installed on the I-shaped rigid guide rail 28, so that the active roller 9 and the driven roller 10 contact the upper surface of the flange of the I-shaped rigid guide rail 28, while the four rollers contact the lower surface of the flange of the I-shaped rigid guide rail 28. Afterwards, the workers reverse the rotation of the first rear adjusting screw 1-14, the second rear adjusting screw 1-15, the first front adjusting screw 1-16, and the second front adjusting screw 1-17 to raise them back up. Each roller positioning block will then move upward under the restoring force of its corresponding tension spring, ultimately generating sufficient positive pressure between the four rollers and the lower surface of the flange of the I-shaped rigid guide rail 28 (e.g., Figure 1 , 2As shown in Figure 3, the frictional force provided by the positive pressure is sufficient to overcome the robot's own weight. This completes the installation of the robot on the guide rail.

[0135] The second step involves the staff sending a start command to the robot via a host computer. The controller then activates the drive motors on the mobile platform, causing the robot to climb along the I-shaped rigid guide rail 28. Figure 2 The direction indicated by the arrow in the image.

[0136] The drive motor is controlled using a PID closed-loop control system with an outer speed loop and an inner current loop to ensure smooth acceleration and deceleration and accurate speed control. The speed loop uses the target speed value input by the user as input and the actual rotational speed fed back by the motor encoder as feedback. The output of these two values, after fuzzy PID adjustment, serves as the input to the current loop. The current loop takes the output of the speed loop PID adjustment as input and the actual motor current measured by the motor's internal Hall effect sensor as feedback. The input and feedback from the current loop are then used to perform fuzzy PID adjustment, which drives the wheel motor to achieve closed-loop control.

[0137] Thirdly, the robot traverses the I-shaped rigid guide rail 28 as it climbs. During this traversal, information is collected by the IMU, encoder, and positioning camera. The robot's real-time position is calculated and recorded using a multi-sensor fusion positioning algorithm. Guide rail defects are detected using the aforementioned guide rail defect detection algorithm, which is responsible for detecting defects such as deformation, dents, and corrosion on the upper surface of the guide rail. The detection of loose bolts is completed by the aforementioned bolt identification and detection algorithm.

[0138] When defects such as deformation, dents, or corrosion are confirmed in the guide rail, the controller sends the robot's position information to the host computer, and staff will then climb the tower for maintenance.

[0139] The first depth camera 26 and the second depth camera 27 at the end of the two sets of robotic arms traverse the bolts on the guide rail, including inter-segment bolt groups and U-bolts. When a loose bolt is detected, the robot's drive motor stops to automatically brake, calculates the three-dimensional coordinates of the loose bolt in the robot's coordinate system, and then transmits this three-dimensional coordinate information to the robotic arm path planning algorithm. Then, the desired motion path of the robotic arm is obtained through forward and inverse kinematics calculations. Finally, the robotic arm is controlled to move the end effector at the end of the robotic arm to the loose bolt. End effector 1 24 (electric impact wrench) and end effector 25 (electric impact wrench) tighten the loose bolt.

[0140] The fourth step is for the robot to climb to the top of the guide rail to complete the inspection and maintenance of the entire guide rail. After that, the robot begins to descend back to the starting position, waiting for the staff to retrieve it.

[0141] As can be seen, the aforementioned robot inspection and maintenance is highly efficient, capable of automatically detecting defects in the guide rail with high accuracy; it can also automatically detect abnormalities such as loose bolts between sections of the guide rail with high accuracy. Furthermore, it can accurately determine the robot's position information and the location of defects and abnormalities on the guide rail.

[0142] It should be noted that workers can attach a fall arrestor to the eye bolts 1-13 on the self-locking device connection at the rear of the mobile platform, positioning the self-locking device on the guide rail (the self-locking device passes through the guide rail flange). The robot's climbing movement then moves the self-locking device along the guide rail. If the guide rail has defects such as warping, misalignment, or excessive gaps, the self-locking device will malfunction, moving abnormally, with difficulty moving, or failing to move. These malfunctions indicate a guide rail defect requiring repair. Furthermore, the eye bolts 1-13 on the self-locking device connection can be replaced with a tension sensor 31, such as... Figure 12 As shown, the signal line of the tension sensor 31 is connected to the controller. During the smooth and uniform movement of the self-locking device, the output signal of the tension sensor 31 will stabilize around a specific value. When the self-locking device experiences jumping, jerking, or inability to pass, the output signal of the tension sensor 31 will show a significant abrupt change. The controller receives this abrupt change and determines that there is a defect. Alternatively, after receiving this abrupt change, the controller will control the robot to retreat and re-pass through the suspected section. If the abrupt change signal occurs three times, it is considered that there is a connectivity defect in this section of the guide rail. Finally, the robot's position information at this time is fed back to the host computer. Subsequent maintenance is carried out by personnel climbing the tower.

[0143] The above explanation is for the inspection and maintenance of vertical guide rails. It should be noted that some power towers, such as angle steel towers, have horizontally arranged guide rails. The robot can also be installed on the horizontally arranged guide rails to perform inspection and maintenance operations.

[0144] It should be noted that a camera for capturing images of the I-shaped rigid guide rail 28 can be installed on the mobile platform, and the controller can determine whether there is any abnormality in the I-shaped rigid guide rail based on the captured images.

Claims

1. An intelligent maintenance robot for power tower anti-fall guide rails, characterized in that, The mobile platform includes a support frame, an active synchronous pulley, a driven synchronous pulley, a synchronous belt, a drive motor, an active roller, a driven roller, a first rear clamping mechanism, a second rear clamping mechanism, a first front clamping mechanism, and a second front clamping mechanism. The support frame includes a right side plate, a left side plate, a rear vertical plate, a front vertical plate, a top plate, a rear horizontal plate, a front horizontal plate, a first rear adjusting screw, a second rear adjusting screw, a first front adjusting screw, a second front adjusting screw, a first rear bearing seat, a second rear bearing seat, a first front bearing seat, and a second front bearing seat. The lower parts of the right side plate and the left side plate are fixedly connected by three connecting shafts. The rear vertical plate is fixedly connected to the rear ends of the right side plate and the left side plate. The front vertical plate is fixedly connected to the front ends of the right side plate and the left side plate. The top plate is fixedly connected to the top of the right side plate and the top of the left side plate. The rear horizontal plate is fixedly connected to the rear end of the top of the right side plate and the rear end of the top of the left side plate. The front cross plate is fixedly connected to the front end of the top of the right side plate and the front end of the top of the left side plate; the rear cross plate has two threaded holes, and the first rear adjusting screw and the second rear adjusting screw are respectively connected to the two threaded holes on the rear cross plate, and the first rear adjusting screw and the second rear adjusting screw pass through the rear cross plate; the front cross plate has two threaded holes, and the first front adjusting screw and the second front adjusting screw are respectively connected to the two threaded holes on the front cross plate, and the first front adjusting screw and the second front adjusting screw pass through the front cross plate; the first rear bearing seat is connected to the left side plate, and the second rear bearing seat is connected to the right side plate; the first front bearing seat is connected to the left side plate, and the second front bearing seat is connected to the right side plate; A receiving space is formed between the right side plate, left side plate, rear vertical plate, front vertical plate, and top plate. The drive motor, driving roller, and driven roller are located in this receiving space. The right side plate has a motor connection hole, and the drive motor is connected to the motor connection hole. The output shaft of the drive motor extends out from the motor connection hole. The driving synchronous pulley is connected to the output shaft of the drive motor. The driving roller has a rotating shaft. The left and right ends of the rotating shaft of the driving roller are connected to the first rear bearing seat and the second rear bearing seat, respectively. The right end of the rotating shaft of the driving roller extends outward from the right side plate. The driven synchronous pulley is fixedly connected to the right end of the rotating shaft of the driving roller. The synchronous belt is connected between the driven synchronous pulley and the driving synchronous pulley. The driven roller has a rotating shaft. The left and right ends of the rotating shaft of the driven roller are connected to the first front bearing seat and the second front bearing seat, respectively. The second rear clamping mechanism includes a roller positioning block, a slider, an inner bearing, an outer bearing, a tension spring, a lower eye bolt, an upper eye bolt, a guide rail, and a roller. The roller positioning block has an inner bearing chamber and an outer bearing chamber. The inner bearing is located in the inner bearing chamber, and the outer bearing is located in the outer bearing chamber. The roller is connected to the inner bearing and the outer bearing. The slider is fixedly connected to the inner side of the roller positioning block. The lower eye bolt is fixedly connected to the top surface of the roller positioning block. The lower end of the tension spring is hung on the lower eye bolt, and the upper end of the tension spring is hung on the upper eye bolt. The slider is connected to the guide rail. The guide rail of the second rear clamping mechanism is fixedly connected to the rear end of the right side plate. The roller of the second rear clamping mechanism is located below the right side plate. The upper lifting eye screw of the second rear clamping mechanism is connected to the right end of the rear horizontal plate. The lower end of the second rear adjusting screw contacts the top of the roller positioning block. The first and second rear clamping mechanisms are arranged symmetrically. The first rear clamping mechanism includes a roller positioning block, a slider, an inner bearing, an outer bearing, a tension spring, a lower eyelet screw, an upper eyelet screw, a guide rail, and a roller. The guide rail of the first rear clamping mechanism is fixedly connected to the rear end of the left side plate. The roller of the first rear clamping mechanism is located below the left side plate. The upper eyelet screw of the first rear clamping mechanism is connected to the left end of the rear cross plate. The lower end of the first rear adjusting screw contacts the top of the roller positioning block of the first rear clamping mechanism. The second front clamping mechanism includes a roller positioning block, a slider, an inner bearing, an outer bearing, a tension spring, a lower eye bolt, an upper eye bolt, a guide rail, and a roller. The guide rail of the second front clamping mechanism is fixedly connected to the front end of the right side plate. The roller of the second front clamping mechanism is located below the right side plate. The upper eye bolt of the second front clamping mechanism is connected to the right end of the front cross plate. The lower end of the second front adjusting screw contacts the top of the roller positioning block of the second front clamping mechanism. The first front clamping mechanism and the second front clamping mechanism are arranged symmetrically. The first front clamping mechanism includes a roller positioning block, a slider, an inner bearing, an outer bearing, a tension spring, a lower eyelet screw, an upper eyelet screw, a guide rail, and a roller. The guide rail of the first front clamping mechanism is fixedly connected to the front end of the left side plate. The roller of the first front clamping mechanism is located below the left side plate. The upper eyelet screw of the first front clamping mechanism is connected to the left end of the front cross plate. The lower end of the first front adjusting screw contacts the top of the roller positioning block of the first front clamping mechanism.

2. The intelligent maintenance robot for power tower anti-fall guide rails according to claim 1, characterized in that, The mobile platform is connected to a camera for acquiring images of the object to be detected.

3. The intelligent maintenance robot for power tower anti-fall guide rails according to claim 1, characterized in that, The mobile platform is equipped with sensors for detecting whether the self-locking device is malfunctioning.

4. The intelligent maintenance robot for power tower anti-fall guide rails according to claim 3, characterized in that, The sensor used to detect whether the self-locking device is malfunctioning is a tension sensor.

5. The intelligent maintenance robot for power tower anti-fall guide rails according to claim 1, characterized in that, The mobile platform is equipped with sensors for detecting the robot's position information.

6. The intelligent maintenance robot for power tower anti-fall guide rails according to claim 1, characterized in that, A robotic arm is connected to the mobile platform.

7. The intelligent maintenance robot for power tower anti-fall guide rails according to claim 1, characterized in that, The intelligent maintenance robot for the power tower anti-fall guide rail also includes a robotic arm connection device, a right robotic arm, and a left robotic arm. The robotic arm connection device includes a robotic arm support beam, a linear slide rail assembly one, a linear slide rail assembly two, a right lead screw motor, a right nut, a right nut seat, a right robotic arm connection base, a right lead screw support seat, a left lead screw motor, a left nut, a left nut seat, a left robotic arm connection base, and a left lead screw support seat. Linear slide rail assembly one and linear slide rail assembly two are connected side-by-side to the bottom surface of the robotic arm support beam. Linear slide rail assembly one has a first slider and a third slider, and linear slide rail assembly two has a second slider and a fourth slider. The right lead screw motor is fixedly connected to the right end of the bottom surface of the robotic arm support beam, and the right lead screw support seat is fixedly connected to the bottom surface of the robotic arm support beam. In the middle, the right nut is connected to the lead screw of the right lead screw motor, the end of the lead screw of the right lead screw motor is connected to the right lead screw support seat, the right nut seat is connected to the right nut, the right robotic arm connecting base is fixedly connected to the right nut seat, and the two sides of the right robotic arm connecting base are respectively fixedly connected to the first slider and the second slider; the left lead screw motor is fixedly connected to the left end of the bottom surface of the robotic arm support beam, the left lead screw support seat is fixedly connected to the middle of the bottom surface of the robotic arm support beam, the left nut is connected to the lead screw of the left lead screw motor, the end of the lead screw of the left lead screw motor is connected to the left lead screw support seat, the left nut seat is connected to the left nut, the left robotic arm connecting base is fixedly connected to the left nut seat, and the two sides of the left robotic arm connecting base are respectively fixedly connected to the third slider and the fourth slider; The top plate of the support frame is connected to a boss, the bottom surface of the robotic arm support beam is fixedly connected to the boss, the right robotic arm is fixedly connected to the right robotic arm connecting base, and the left robotic arm is fixedly connected to the left robotic arm connecting base; the free end of the right robotic arm is connected to an end effector one, and the free end of the left robotic arm is connected to an end effector two.

8. The intelligent maintenance robot for power tower anti-fall guide rails according to any one of claims 1-7, characterized in that, The intelligent maintenance robot for the power tower anti-fall guide rail also includes an IMU, an encoder, and a camera for visual positioning. The IMU is connected to the mobile platform, the encoder is connected to the drive motor or the active roller, and the camera for visual positioning is connected to the front end of the mobile platform. The camera used for visual positioning acquires images of the detection rail. After preprocessing, the images are used by an edge detection algorithm to identify the gaps at the connection points of adjacent rails in the rail, and the number of gaps is obtained. The number of gaps is multiplied by the length of a single rail segment to obtain the robot's absolute position information. The robot pose information, α, is obtained by calculating the trajectory from the data collected by the encoder. b =[x b ,y b ,z b ,θ b ] T The robot pose information, α, is obtained by integrating the data collected by the IMU. i =[x i ,y i ,z i ,θ i ] T The robot pose information obtained by visual positioning using a camera is α. v =[x v ,y v ,z v ,θ v ] T Then we get x k =[x,y,z,θ] T Where x, y, z, θ are derived from α b α i With α v The robot pose information is obtained after weighted fusion using the Kalman filter algorithm; from this, a predictive model of the robot's state at time k can be obtained: In formula (1), x k Let x be the state vector at time k. k The predicted value, x k-1 For time k-1, the state vector x k-1 The predicted value, F k It is the state transition matrix, B k For the control matrix, u k The control quantity is an external input; Similarly, there is the observation model of the system at time k: z k =H k x k (2) In formula (2), z k H is the actual observed value of the system state at time k. k It is the observation matrix, used to map the state vector to the observation space; At each time step, the Kalman filter first predicts the current state based on the prediction model, and the predicted covariance matrix P k It will also update as the state evolves: Kalman gain K in a Kalman filter k The calculation formula is: In formula (4), R k The noise covariance matrix of the observations; Kalman gain K is obtained through a neural network. k Optimization was performed, and the optimized Kalman gain K was obtained. opt : The Kalman filter can utilize the optimized Kalman gain K. opt Update the state estimate and output:

9. The intelligent maintenance robot for power tower anti-fall guide rails according to claim 7, characterized in that, The free end of the right robotic arm is connected to a first depth camera, and the free end of the left robotic arm is connected to a second depth camera. The first depth camera and / or the second depth camera are configured to acquire images of the guide rail to be detected; The image of the guide rail to be detected is input into the YOLOv5 model which incorporates an attention mechanism module, thereby identifying the surface defects of the guide rail to be detected. After obtaining the surface defects of the guide rail to be inspected, the position information of the mobile robot is obtained and sent to the host computer.

10. The intelligent maintenance robot for power tower anti-fall guide rails according to claim 7, characterized in that, The free end of the right robotic arm is connected to a first depth camera, and the free end of the left robotic arm is connected to a second depth camera. The first depth camera and / or the second depth camera are configured to acquire images of the bolt group on the guide rail to be inspected; The image of the bolt group on the guide rail to be detected is input into the YOLOv5 model with an attention mechanism module, so as to identify the bolt group, and then crop the image of a single bolt according to the anchor frame information in the identification result. The image of a single bolt is processed by an edge detection algorithm based on the Canny operator to obtain the edge contour of the bolt. The edge contour is extracted by the Douglas-Puk algorithm, and the bolt edge equation is fitted by the least squares method based on the edge points and corner points. The angle θ between the line and the x-axis is calculated by the arctangent function based on the slope k of the edge equation. At the same time, it is converted from radians to degrees by the following formula (7): The included angles θ corresponding to the six sides of a single bolt can be solved sequentially using formula (7). i (i = 1, 2, ..., 6), and then the angle values ​​of the six edges are quantified into the angle value θ of the bolt itself using the following formula (8). bolt , The quantized angle value of the bolt in its current state is calculated using formula (8). The quantized angle value θ of the bolt under normal conditions is calculated using formula (8). bolti Then, the loosening angle Δθ of the bolt is calculated using the following formula (9). i : loosening angle Δθ i Compared with the set threshold, if the loosening angle Δθ i If the value exceeds the threshold, it is determined to be loose; The three-dimensional coordinates of the loose bolt in the robot coordinate system are calculated. This three-dimensional coordinate information is transmitted to the robot arm path planning algorithm to obtain the desired motion path of the robot arm. Then, the right robot arm or the right robot arm action causes the end effector one or the end effector two to tighten the loose bolt.

Images