Underground support transfer robot insertion cooperative control method

Abstract

The invention discloses an underground support transfer robot insertion cooperative control method, which belongs to the technical field of underground support transfer robots, and comprises the following steps: enabling a support transfer robot to run along a preset track, detecting position information and insertion position of a hydraulic support, judging whether the hydraulic support is detected or not, stopping beside the hydraulic support, and stopping the support transfer robot when the hydraulic support is detected. The U-shaped frame is controlled to insert the hydraulic support; according to the method, various sensors are adopted, the surrounding environment is sensed by the support carrying robot, two ultrasonic sensors are used for finely adjusting the inserting position of the U-shaped frame, the inserting stability is guaranteed, and due to the fact that the underground mine environment is complex and the road surface is uneven, the stability of the U-shaped frame is improved. According to the method, the pressure sensor and the attitude sensor are used for detecting pressure information and space attitude information in the inserting process in real time, feedback is conducted in real time, stable operation of the U-shaped frame is controlled, the carrying efficiency and safety are improved, and the actual application effect of the whole method is good.

Description

Technical Field

[0001] The present invention belongs to the technical field of underground support transport robots, and in particular relates to an insertion cooperative control method of an underground support transport robot. Background Art

[0002] With the continuous development of coal mining technology, the non-production auxiliary time occupied by underground transportation equipment has affected the economic benefits of coal mines, which has put forward higher requirements for underground transportation equipment.

[0003] Underground support handling robots are crucial hydraulic support transport equipment in the coal mining industry. Due to their compact size and maneuverability, they are widely used for transporting support in narrow tunnels. Furthermore, support handling robots utilize multi-sensor fusion technology to accurately perceive their surroundings, enabling autonomous navigation and positioning. This effectively reduces the workload of underground workers and improves underground transportation efficiency.

[0004] Currently, the insertion control of support handling robots is still manually operated. Due to insufficient lighting in the tunnel or improper operator operation, it is very easy to cause inaccurate insertion positioning. In addition, during the hydraulic support lifting process, under high load conditions, if the roadway surface is uneven, the two arms of the U-shaped frame will bear different pressures. This can easily lead to unstable insertion operation, affecting insertion efficiency and easily causing safety accidents. To solve these problems, a collaborative control method for the insertion of underground support handling robots is urgently needed. Summary of the Invention

[0005] The present invention aims to address the current problem of manual control of stent handling robots, which can easily lead to inaccurate positioning due to insufficient lighting in the tunnel or improper operator operation. Furthermore, during the hydraulic support lifting process, under high loads, uneven roadway surfaces can cause unequal pressures on the two arms of the U-shaped frame, leading to unstable installation, reduced efficiency, and a high risk of safety accidents. Therefore, a coordinated control method for stent handling robots is proposed.

[0006] In order to achieve the above-mentioned object, the present invention adopts the following technical solution: a coordinated control method for inserting and inserting a downhole support handling robot, comprising the following steps:

[0007] S1, making the bracket transport robot move along a predetermined trajectory;

[0008] S2, detecting the position information and insertion position of the hydraulic support;

[0009] S3, determining whether a hydraulic support is detected;

[0010] S4. Stop beside the hydraulic support and control the U-shaped frame to insert the hydraulic support;

[0011] S5. Measure the distance between the two arms of the U-shaped frame and the hydraulic support respectively;

[0012] S6. The measured distance information is transmitted to the main controller, and the main controller adjusts the position of the U-shaped frame to keep the position of the U-shaped frame symmetrical;

[0013] S7, during the lifting process, real-time detection of pressure changes;

[0014] S8, the attitude sensor detects the spatial attitude of the U-shaped frame in real time, and both transmit the detected signal to the fuzzy PID controller;

[0015] S9. Perform machine deep learning on the above process;

[0016] S10. Evaluate the above process

[0017] As a further description of the above technical solution:

[0018] In S2, the position information and insertion position of the hydraulic support are detected by the front sensing camera and laser radar installed on the cantilever beam.

[0019] As a further description of the above technical solution:

[0020] In S3, it is determined whether a hydraulic support is detected. If no hydraulic support is detected, the process returns to S1; if a hydraulic support is detected, the process directly proceeds to the next step.

[0021] As a further description of the above technical solution:

[0022] In S4, the robot stops next to the hydraulic support and controls the U-shaped frame to insert the hydraulic support. Specifically, the front-facing camera and lidar sense environmental information on both sides of the support handling robot, acquire the hydraulic support's position information and the insertion position information, and transmit this information to the main controller, which controls the U-shaped frame to insert the hydraulic support.

[0023] As a further description of the above technical solution:

[0024] In S5, the distances between the two arms of the U-shaped frame and the hydraulic support are measured respectively by ultrasonic sensors installed on both sides of the U-shaped frame.

[0025] As a further description of the above technical solution:

[0026] In S5, the two ultrasonic sensors are the first ultrasonic sensor and the second ultrasonic sensor, which are respectively installed on the left arm and the right arm, and measure the distance between the two arms of the U-shaped frame and the hydraulic support to obtain X1 and X2.

[0027] As a further description of the above technical solution:

[0028] In S6, the measured distance information is transmitted to the main controller, and the main controller adjusts the position of the U-shaped frame. If X2 is greater than X1, the transverse cylinder is controlled to move a distance of (X2-X1) / 2 so that the distances between the two arms and the hydraulic support are the same. If X1 is greater than X2, the transverse cylinder is controlled to move a distance of (X1-X2) / 2 so that the distances between the two arms and the hydraulic support are the same. In this way, the position of the U-shaped frame is adjusted to keep it symmetrical.

[0029] As a further description of the above technical solution:

[0030] In S7, during the lifting process, the pressure change is detected in real time by the pressure sensors installed at the bottom of the two arms of the U-shaped frame.

[0031] As a further description of the above technical solution:

[0032] In S8, the posture sensor detects the spatial posture of the U-shaped frame in real time, and both transmit the detected signals to the fuzzy PID controller. The fuzzy PID controller adjusts the movement speed of the rotating cylinder, the lateral movement cylinder, the luffing cylinder and the lifting cylinder in real time. The specific process is that the first pressure sensor and the second pressure sensor installed at the bottom of the two arms of the U-shaped frame transmit the detected real-time pressure signal and the signal detected by the posture sensor on the U-shaped frame to the fuzzy PID controller. The fuzzy PID controller adjusts the opening of the hydraulic system electro-hydraulic proportional valve in real time by judging the size of the detected pressure of the two arms of the U-shaped frame and the spatial posture information, and controls the rotating cylinder, the lateral movement cylinder, the luffing cylinder and the lifting cylinder to operate at a safe movement speed.

[0033] As a further description of the above technical solution:

[0034] In the S9, the machine deep learning algorithm is introduced into the fuzzy PID controller, and after the LSTM model is trained with simulation data, the working condition prediction data is provided to the fuzzy PID controller, and the prediction function of the deep learning model is used to compensate for the feedback delay and improve the control efficiency, which can effectively respond to complex working conditions. After the introduction of deep learning, the first pressure sensor and the second pressure sensor installed at the bottom of the two arms of the U-shaped frame transmit the detected real-time pressure signal and the signal detected by the posture sensor on the U-shaped frame to the LSTM intelligent module, and the LSTM intelligent module is used to predict the original data, and the prediction result is used as the fuzzy PID controller. The fuzzy PID controller adjusts the opening of the electro-hydraulic proportional valve of the hydraulic system in real time by judging the size of the pressure of the two arms of the U-frame and the spatial posture information received, and controls the rotary cylinder, lateral cylinder, boom cylinder and lifting cylinder to operate at a safe movement speed. The machine deep learning algorithm adopts one or more of the convolutional neural network, recursive neural network and transfer learning algorithm. In S10, the above process is evaluated, and the evaluation results are excellent, good and poor. When the evaluation results are good or poor, the above process is reviewed again, and anomalies and loopholes are found, and correction plans are automatically generated. The number of correction plans is 5-8.

[0035] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0036] In the present invention, the method adopts multiple sensors to realize the perception of the surrounding environment by the bracket handling robot, and uses two ultrasonic sensors to fine-tune the insertion position of the U-shaped frame, thereby ensuring the stability of the subsequent insertion. Moreover, due to the complex environment and uneven road surface in the mine, the method uses pressure sensors and posture sensors to detect the pressure information and spatial posture information in the insertion process in real time, and provides real-time feedback to control the smooth operation of the U-shaped frame, thereby improving the handling efficiency and safety. The overall method has good practical application effect.

[0037] In the present invention, the method also introduces a deep learning algorithm, which can perform deep learning on the data processing and calculation process of the method, so that in subsequent processing, the data processing volume can be greatly reduced, the processing time can be shortened, and the practical application efficiency of the method can be greatly improved. The method is also provided with an independent evaluation process, which can review each step, find anomalies and loopholes, and automatically generate correction plans, thereby improving the accuracy and effectiveness of the method and improving the practical application effect of the method. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The figure is a flow chart of a collaborative control method for inserting and installing an underground support handling robot.

[0039] Figure 2 This is a control block diagram of the hydraulic system in a collaborative control method for inserting an underground support handling robot.

[0040] Figure 3 This is a U-shaped frame control block diagram for a coordinated control method for inserting an underground support handling robot.

[0041] Figure 4 This is a schematic diagram of the combined three-dimensional structure of a U-frame and a U-frame cantilever beam in a coordinated control method for inserting an underground support handling robot. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 making any creative efforts shall fall within the scope of protection of the present invention.

[0043] Example 1

[0044] See also Figure 1-4 The present invention provides a technical solution: a coordinated control method for inserting and inserting a downhole support handling robot, comprising the following steps:

[0045] S1, making the bracket transport robot move along a predetermined trajectory;

[0046] S2, detecting the position information and insertion position of the hydraulic support through the front sensing camera and laser radar installed on the cantilever beam;

[0047] S3, determine whether a hydraulic support is detected, if not, return to S1, if a hydraulic support is detected, directly proceed to the next step;

[0048] S4. Stopping next to the hydraulic support, controlling the U-shaped frame to insert the hydraulic support. Specifically, the forward-facing camera and lidar sense the environment on both sides of the support handling robot, obtaining the position of the hydraulic support and the insertion position. This information is transmitted to the main controller, which controls the U-shaped frame to insert the hydraulic support.

[0049] S5. Using ultrasonic sensors installed on both sides of the U-shaped frame, respectively, measure the distances between the two arms of the U-shaped frame and the hydraulic support. The two ultrasonic sensors are a first ultrasonic sensor and a second ultrasonic sensor, which are installed on the left arm and the right arm, respectively. The distances between the two arms of the U-shaped frame and the hydraulic support are measured to obtain X1 and X2.

[0050] S6. The measured distance information is transmitted to the main controller, which adjusts the position of the U-shaped frame. If X2 is greater than X1, the lateral cylinder is controlled to move a distance of (X2-X1) / 2 to make the distances between the two arms and the hydraulic support the same. If X1 is greater than X2, the lateral cylinder is controlled to move a distance of (X1-X2) / 2 to make the distances between the two arms and the hydraulic support the same. In this way, the position of the U-shaped frame is adjusted to maintain symmetry.

[0051] S7. During the lifting process, the pressure change is detected in real time by the pressure sensors installed at the bottom of the two arms of the U-shaped frame;

[0052] S8. The posture sensor detects the spatial posture of the U-shaped frame in real time. Both transmit the detected signals to the fuzzy PID controller. The fuzzy PID controller adjusts the movement speed of the rotating cylinder, the traverse cylinder, the luffing cylinder and the lifting cylinder in real time. The specific process is that the first pressure sensor and the second pressure sensor installed at the bottom of the two arms of the U-shaped frame transmit the detected real-time pressure signal and the signal detected by the posture sensor on the U-shaped frame to the fuzzy PID controller. The fuzzy PID controller adjusts the opening of the electro-hydraulic proportional valve of the hydraulic system in real time by judging the size of the detected pressure of the two arms of the U-shaped frame and the spatial posture information, and controls the rotating cylinder, the traverse cylinder, the luffing cylinder and the lifting cylinder to operate at a safe movement speed;

[0053] S9. Introduce the machine deep learning algorithm into the fuzzy PID controller. After the LSTM model is trained with simulation data, it provides the working condition prediction data for the fuzzy PID controller. The prediction function of the deep learning model is used to compensate for the feedback delay, improve the control efficiency, and effectively respond to complex working conditions. After the introduction of deep learning, the first pressure sensor and the second pressure sensor installed at the bottom of the two arms of the U-shaped frame transmit the detected real-time pressure signal and the signal detected by the posture sensor on the U-shaped frame to the LSTM intelligent module. The LSTM intelligent module is used to predict the original data, and the prediction result is used as the input of the fuzzy PID controller. The fuzzy PID controller adjusts the opening of the hydraulic system electro-hydraulic proportional valve in real time by judging the size of the received pressure of the two arms of the U-shaped frame and the spatial posture information, and controls the rotary cylinder, traverse cylinder, boom cylinder and lifting cylinder to operate at a safe movement speed. The machine deep learning algorithm adopts convolutional neural network and transfer learning algorithm;

[0054] S10. Evaluate the above process, and the evaluation results are excellent, good, and poor. When the evaluation results are good or poor, re-examine the above process, find anomalies and loopholes, and automatically generate a correction plan. The number of correction plans is 5.

[0055] In this embodiment, the method uses multiple sensors to enable the bracket handling robot to perceive the surrounding environment, and uses two ultrasonic sensors to fine-tune the insertion position of the U-shaped frame to ensure the stability of subsequent insertion.

[0056] Example 2

[0057] See also Figure 1-4 The present invention provides a technical solution: a coordinated control method for inserting and inserting a downhole support handling robot, comprising the following steps:

[0058] S1, making the bracket transport robot move along a predetermined trajectory;

[0059] S2, detecting the position information and insertion position of the hydraulic support through the front sensing camera and laser radar installed on the cantilever beam;

[0060] S3, determine whether a hydraulic support is detected, if not, return to S1, if a hydraulic support is detected, directly proceed to the next step;

[0061] S4. Stopping next to the hydraulic support, controlling the U-shaped frame to insert the hydraulic support. Specifically, the forward-facing camera and lidar sense the environment on both sides of the support handling robot, obtaining the position of the hydraulic support and the insertion position. This information is transmitted to the main controller, which controls the U-shaped frame to insert the hydraulic support.

[0062] S5. Using ultrasonic sensors installed on both sides of the U-shaped frame, respectively, measure the distances between the two arms of the U-shaped frame and the hydraulic support. The two ultrasonic sensors are a first ultrasonic sensor and a second ultrasonic sensor, which are installed on the left arm and the right arm, respectively. The distances between the two arms of the U-shaped frame and the hydraulic support are measured to obtain X1 and X2.

[0063] S6. The measured distance information is transmitted to the main controller, which adjusts the position of the U-shaped frame. If X2 is greater than X1, the lateral cylinder is controlled to move a distance of (X2-X1) / 2 to make the distances between the two arms and the hydraulic support the same. If X1 is greater than X2, the lateral cylinder is controlled to move a distance of (X1-X2) / 2 to make the distances between the two arms and the hydraulic support the same. In this way, the position of the U-shaped frame is adjusted to maintain symmetry.

[0064] S7. During the lifting process, the pressure change is detected in real time by the pressure sensors installed at the bottom of the two arms of the U-shaped frame;

[0065] S8. The posture sensor detects the spatial posture of the U-shaped frame in real time. Both transmit the detected signals to the fuzzy PID controller. The fuzzy PID controller adjusts the movement speed of the rotating cylinder, the traverse cylinder, the luffing cylinder and the lifting cylinder in real time. The specific process is that the first pressure sensor and the second pressure sensor installed at the bottom of the two arms of the U-shaped frame transmit the detected real-time pressure signal and the signal detected by the posture sensor on the U-shaped frame to the fuzzy PID controller. The fuzzy PID controller adjusts the opening of the electro-hydraulic proportional valve of the hydraulic system in real time by judging the size of the detected pressure of the two arms of the U-shaped frame and the spatial posture information, and controls the rotating cylinder, the traverse cylinder, the luffing cylinder and the lifting cylinder to operate at a safe movement speed;

[0066] S9. Introducing the machine deep learning algorithm into the fuzzy PID controller, and after the LSTM model is trained with simulation data, providing the working condition prediction data for the fuzzy PID controller, and using the prediction function of the deep learning model to compensate for the feedback delay, improve the control efficiency, and effectively respond to complex working conditions. After the introduction of deep learning, the first pressure sensor and the second pressure sensor installed at the bottom of the two arms of the U-shaped frame transmit the detected real-time pressure signal and the signal detected by the posture sensor on the U-shaped frame to the LSTM intelligent module, and use the LSTM intelligent module to predict the original data, and use the prediction result as the input of the fuzzy PID controller. The fuzzy PID controller adjusts the opening of the hydraulic system electro-hydraulic proportional valve in real time by judging the size of the pressure of the two arms of the U-shaped frame and the spatial posture information, and controls the rotary cylinder, traverse cylinder, boom cylinder and lifting cylinder to operate at a safe movement speed, wherein the machine deep learning algorithm adopts a convolutional neural network;

[0067] S10. Evaluate the above process, and the evaluation results are excellent, good, and poor. When the evaluation results are good or poor, re-examine the above process, find anomalies and loopholes, and automatically generate correction plans. The number of correction plans is 6.

[0068] In this embodiment, the method uses pressure sensors and posture sensors to detect the pressure information and spatial posture information during the insertion process in real time, and provides real-time feedback to control the smooth operation of the U-shaped frame, thereby improving the handling efficiency and safety. The overall method has good practical application effect.

[0069] Example 3

[0070] See also Figure 1-4 The present invention provides a technical solution: a coordinated control method for inserting and inserting a downhole support handling robot, comprising the following steps:

[0071] S1, making the bracket transport robot move along a predetermined trajectory;

[0072] S2, detecting the position information and insertion position of the hydraulic support through the front sensing camera and laser radar installed on the cantilever beam;

[0073] S3, determine whether a hydraulic support is detected, if not, return to S1, if a hydraulic support is detected, directly proceed to the next step;

[0074] S4. Stopping next to the hydraulic support, controlling the U-shaped frame to insert the hydraulic support. Specifically, the forward-facing camera and lidar sense the environment on both sides of the support handling robot, obtaining the position of the hydraulic support and the insertion position. This information is transmitted to the main controller, which controls the U-shaped frame to insert the hydraulic support.

[0075] S5. Using ultrasonic sensors installed on both sides of the U-shaped frame, respectively, measure the distances between the two arms of the U-shaped frame and the hydraulic support. The two ultrasonic sensors are a first ultrasonic sensor and a second ultrasonic sensor, which are installed on the left arm and the right arm, respectively. The distances between the two arms of the U-shaped frame and the hydraulic support are measured to obtain X1 and X2.

[0076] S6. The measured distance information is transmitted to the main controller, which adjusts the position of the U-shaped frame. If X2 is greater than X1, the lateral cylinder is controlled to move a distance of (X2-X1) / 2 to make the distances between the two arms and the hydraulic support the same. If X1 is greater than X2, the lateral cylinder is controlled to move a distance of (X1-X2) / 2 to make the distances between the two arms and the hydraulic support the same. In this way, the position of the U-shaped frame is adjusted to maintain symmetry.

[0077] S7. During the lifting process, the pressure change is detected in real time by the pressure sensors installed at the bottom of the two arms of the U-shaped frame;

[0078] S8. The posture sensor detects the spatial posture of the U-shaped frame in real time. Both transmit the detected signals to the fuzzy PID controller. The fuzzy PID controller adjusts the movement speed of the rotating cylinder, the traverse cylinder, the luffing cylinder and the lifting cylinder in real time. The specific process is that the first pressure sensor and the second pressure sensor installed at the bottom of the two arms of the U-shaped frame transmit the detected real-time pressure signal and the signal detected by the posture sensor on the U-shaped frame to the fuzzy PID controller. The fuzzy PID controller adjusts the opening of the electro-hydraulic proportional valve of the hydraulic system in real time by judging the size of the detected pressure of the two arms of the U-shaped frame and the spatial posture information, and controls the rotating cylinder, the traverse cylinder, the luffing cylinder and the lifting cylinder to operate at a safe movement speed;

[0079] S9. Introducing the machine deep learning algorithm into the fuzzy PID controller, and after the LSTM model is trained with simulation data, providing the working condition prediction data for the fuzzy PID controller, and using the prediction function of the deep learning model to compensate for the feedback delay, improve the control efficiency, and effectively respond to complex working conditions. After the introduction of deep learning, the first pressure sensor and the second pressure sensor installed at the bottom of the two arms of the U-shaped frame transmit the detected real-time pressure signal and the signal detected by the posture sensor on the U-shaped frame to the LSTM intelligent module, and use the LSTM intelligent module to predict the original data, and use the prediction result as the input of the fuzzy PID controller. The fuzzy PID controller adjusts the opening of the hydraulic system electro-hydraulic proportional valve in real time by judging the size of the pressure of the two arms of the U-shaped frame and the spatial posture information, and controls the rotary cylinder, traverse cylinder, boom cylinder and lifting cylinder to operate at a safe movement speed. The machine deep learning algorithm adopts convolutional neural network and recurrent neural network;

[0080] S10. Evaluate the above process, and the evaluation results are excellent, good, and poor. When the evaluation results are good or poor, re-examine the above process, find anomalies and loopholes, and automatically generate correction plans. The number of correction plans is 8.

[0081] In this embodiment, the method also introduces a deep learning algorithm, which can perform deep learning on the data processing and calculation process of the method, so that in subsequent processing, the data processing volume can be greatly reduced, the processing time can be shortened, and the actual application efficiency of the method can be greatly improved. The method also has an independent evaluation process, which can review each step, find anomalies and loopholes, and automatically generate correction plans, thereby improving the accuracy and effectiveness of the method and improving the actual application effect of the method.

[0082] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A coordinated control method for inserting a support handling robot in a well, characterized in that: The steps include: S1, making the bracket handling robot move along a predetermined trajectory; S2, detecting the position information and insertion position of the hydraulic support; S3, determining whether a hydraulic support is detected; S4, stop beside the hydraulic support and control the U-shaped frame to insert the hydraulic support; S5. Measure the distances between the two arms of the U-shaped frame and the hydraulic support respectively; S6, transmitting the measured distance information to the main controller, and the main controller adjusts the position of the U-shaped frame to keep the position of the U-shaped frame symmetrical; S7, real-time detection of pressure changes during the lifting process; S8, the attitude sensor detects the spatial attitude of the U-shaped frame in real time, and both transmit the detected signals to the fuzzy PID controller; S9. Perform machine deep learning on the above process; S10. Evaluate the above process.

2. The method for coordinated control of underground support handling robot insertion according to claim 1 is characterized in that: In S2, the position information and insertion position of the hydraulic support are detected by the front sensing camera and laser radar installed on the cantilever beam.

3. The method for coordinated control of underground support handling robot insertion according to claim 1 is characterized in that: In S3, it is determined whether a hydraulic support is detected. If no hydraulic support is detected, the process returns to S1; if a hydraulic support is detected, the process directly proceeds to the next step.

4. The method for coordinated control of underground support handling robot insertion according to claim 1, characterized in that: In S4, the robot stops beside the hydraulic support and controls the U-shaped frame to insert the hydraulic support. Specifically, the front sensing camera and the laser radar sense the environmental information on both sides of the support handling robot, and obtain the position information and the insertion position information of the hydraulic support. The obtained information is transmitted to the main controller, and the main controller controls the U-shaped frame to insert.

5. The method for coordinated control of underground support handling robot insertion according to claim 1, characterized in that: In S5, the distances between the two arms of the U-shaped frame and the hydraulic support are measured respectively by ultrasonic sensors installed on both sides of the U-shaped frame.

6. The method for coordinated control of underground support handling robot insertion according to claim 1, characterized in that: In S5, the two ultrasonic sensors are respectively a first ultrasonic sensor and a second ultrasonic sensor, which are respectively installed on the left arm and the right arm, and measure the distance between the two arms of the U-shaped frame and the hydraulic support to obtain X1 and X2.

7. The method for coordinated control of underground support handling robot insertion according to claim 1, characterized in that: In S6, the measured distance information is transmitted to the main controller, and the main controller adjusts the position of the U-shaped frame. If X2 is greater than X1, the transverse cylinder is controlled to move a distance of (X2-X1) / 2 so that the distances between the two arms and the hydraulic support are the same. If X1 is greater than X2, the transverse cylinder is controlled to move a distance of (X1-X2) / 2 so that the distances between the two arms and the hydraulic support are the same. In the above manner, the position of the U-shaped frame is adjusted to keep it symmetrical.

8. The method for coordinated control of underground support handling robot insertion according to claim 1, characterized in that: In S7, during the lifting process, the pressure change is detected in real time by the pressure sensor installed at the bottom of the two arms of the U-shaped frame.

9. The method for coordinated control of underground support handling robot insertion according to claim 1, characterized in that: In S8, the posture sensor detects the spatial posture of the U-frame in real time, and both transmit the detected signals to the fuzzy PID controller. The fuzzy PID controller adjusts the movement speed of the rotating cylinder, the lateral movement cylinder, the luffing cylinder and the lifting cylinder in real time. The specific process is that the first pressure sensor and the second pressure sensor installed at the bottom of the two arms of the U-frame transmit the detected real-time pressure signal and the signal detected by the posture sensor on the U-frame to the fuzzy PID controller. The fuzzy PID controller adjusts the opening of the electro-hydraulic proportional valve of the hydraulic system in real time by judging the size of the detected pressure of the two arms of the U-frame and the spatial posture information, and controls the rotating cylinder, the lateral movement cylinder, the luffing cylinder and the lifting cylinder to run at a safe movement speed.

10. The method for coordinated control of underground support handling robot insertion according to claim 1, characterized in that: In the S9, the machine deep learning algorithm is introduced into the fuzzy PID controller, and after the LSTM model is trained with simulation data, the working condition prediction data is provided to the fuzzy PID controller, and the prediction function of the deep learning model is used to compensate for the feedback delay and improve the control efficiency, which can effectively respond to complex working conditions. After the introduction of deep learning, the first pressure sensor and the second pressure sensor installed at the bottom of the two arms of the U-shaped frame transmit the detected real-time pressure signal and the signal detected by the posture sensor on the U-shaped frame to the LSTM intelligent module, and the original data is predicted by the LSTM intelligent module, and the prediction result is used as the fuzzy PID controller The fuzzy PID controller adjusts the opening of the electro-hydraulic proportional valve of the hydraulic system in real time by judging the size of the pressure of the two arms of the U-frame and the spatial posture information received, and controls the rotation cylinder, the lateral movement cylinder, the variable amplitude cylinder and the lifting cylinder to run at a safe movement speed. The machine deep learning algorithm adopts one or more of the convolutional neural network, the recursive neural network and the transfer learning algorithm. In S10, the above process is evaluated, and the evaluation results are excellent, good and poor. When the evaluation results are good and poor, the above process is reviewed again, and the anomalies and loopholes are found, and correction plans are automatically generated. The number of correction plans is 5-8.

Images