Contact network maintenance method based on digital twinning technology

Abstract

The invention relates to an overhead line system maintenance method based on a digital twinning technology, and belongs to the technical field of overhead line system maintenance. The invention discloses an overhead line system maintenance method based on a digital twin technology. The method comprises the following steps: acquiring real world data of an overhead line system through a laser radar sensor and a depth camera on an inspection vehicle; based on the digital twinning technology and the real world data of the overhead line system, a digital twinning platform of the overhead line system is established through a virtual simulation platform; simulating the maintenance process of the contact network on the digital twin platform of the contact network to obtain a virtual maintenance path of the mechanical arm; an operator enters the digital twin platform of the contact network through the virtual reality technology and observes the virtual motion path of the mechanical arm through a full-known visual angle, a proper path is obtained, and planning is conducted through rviz; and through linkage of the rviz and the mechanical arm, the display maintenance path of the mechanical arm is controlled according to the virtual motion path of the mechanical arm, and the overhead line system is overhauled. The overhead line system maintenance system can help the overhead line system maintenance task to be easily completed in severe weather in plateau areas.

Description

Technical Field

[0001] The invention relates to a contact network maintenance method based on digital twin technology, and belongs to the technical field of contact network maintenance. Background Art

[0002] With the continuous growth of my country's social economy, the level of electrification technology has been continuously improved. As the core facility of electrified railway power supply, the stability of the contact network is directly related to the safety and efficiency of railway transportation. In plateau areas, due to harsh natural conditions such as low temperature and lack of oxygen, especially at night, the maintenance of the contact network poses a great threat to the life safety and work efficiency of maintenance personnel. Therefore, it is particularly urgent to explore new and efficient intelligent maintenance methods. Summary of the invention

[0003] In order to overcome the defects in the prior art, the present invention aims to provide a contact network maintenance method based on digital twin technology.

[0004] The technical solution provided by the present invention to solve the above technical problems is: a contact network maintenance method based on digital twin technology, comprising the following steps:

[0005] Step 1: Obtain real-world data of the contact network through the lidar sensor and depth camera on the inspection vehicle;

[0006] Step 2: Based on digital twin technology and real-world data of the contact network, a digital twin platform for the contact network is established through a virtual simulation platform;

[0007] Step 3: Simulate the catenary maintenance process on the catenary digital twin platform to obtain the virtual motion path of the robotic arm;

[0008] The yolov5 algorithm and hand-eye calibration technology are used to achieve precise control of the robotic arm;

[0009] Step 4: The operator enters the contact network digital twin platform through virtual reality technology and observes the virtual motion path of the robot arm from an omniscient perspective, obtains a suitable path, and plans it through rviz;

[0010] Step 5: Link the robot arm with rviz, control the displayed maintenance path of the robot arm according to the virtual motion path of the robot arm, and inspect the contact network.

[0011] A further technical solution is to perform simulation in step three through a VR headset.

[0012] A further technical solution is that the simulation process in step three is:

[0013] Step 1: Use the yolov5 algorithm and hand-eye calibration technology to calibrate the coordinates of the robotic arm;

[0014] Step 2: After the coordinate calibration is completed, the virtual motion path of the robot arm is generated to complete the simulation process.

[0015] A further technical solution is that in the step 1, a one-to-one modeling is performed in the contact network digital twin platform according to the real world contact network. In the virtual setting, the VR headset coordinates are set as the original coordinates. The VR headset can be used as a camera in the virtual world, and the yolov5 algorithm is imported. When a target such as a screw appears in the field of vision, the yolov5 algorithm marks the target, and the relative coordinates of the target relative to the headset can be obtained, so that hand-eye marking can be performed.

[0016] A further technical solution is that in the virtual world in step three, the functions of the two VR handles are changed into two hands, one hand fixes other joints, and the other hand moves the target joint, that is, when the robotic arm moves to the corresponding position, each joint is in an ideal position, and other joints move to other places along with the moving joint.

[0017] A further technical solution is that the specific process of step four is: make a wired connection with the P port in the virtual simulation platform, put on PICO glasses to enter the virtual simulation world, observe the virtual motion path of the robotic arm from an omniscient perspective, and if it is found to be suitable, determine it as a suitable route and plan it through rviz; if it is not suitable, repeat steps three to four until it is suitable.

[0018] The present invention has the following beneficial effects: the present invention installs a laser radar on the inspection vehicle to facilitate finding the location of the contact network at night, and by inputting the yolov5 model code into the depth camera of the mechanical arm, it can detect in real time whether the contact network has problems such as loose screws or damage, and selects corresponding tools for repair according to the missing or damaged parts, and finally the maintenance personnel give instructions to the mechanical arm through the human-computer interaction system, and use VR technology to artificially enter the virtual world to determine the appropriate path; the present invention can help to easily complete the contact network maintenance task in severe weather in plateau areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0020] The technical solution of the present invention will be described clearly and completely below 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 creative work are within the scope of protection of the present invention.

[0021] like Figure 1As shown, a contact network maintenance method based on digital twin technology of the present invention comprises the following steps:

[0022] Step 1: Obtain real-world data of the contact network through the lidar sensor and depth camera on the inspection vehicle;

[0023] Step 2: Based on digital twin technology and real-world data of the contact network, a digital twin platform for the contact network is established through a virtual simulation platform;

[0024] Step 3: Simulate the catenary maintenance process on the catenary digital twin platform to obtain the virtual motion path of the robotic arm;

[0025] Step 1: Based on the camera parameters, hand-eye parameters, and using the yolov5 algorithm and hand-eye calibration technology, calibrate the robot arm coordinates;

[0026] In the contact network digital twin platform, a one-to-one modeling is carried out according to the contact network in the real world. In the virtual setting, the coordinates of the VR headset are set as the original coordinates. The VR headset can be used as a camera in the virtual world. The yolov5 algorithm is imported. When a target such as a screw appears in the field of vision, the yolov5 algorithm marks the target, and the relative coordinates of the target relative to the headset can be obtained, so that the hand-eye marking can be performed. Then, in the real world, a person puts on a VR headset and moves to the same position as in the virtual world. Because the virtual world is modeled one-to-one with the reality, the robot arm can be directly operated to speed up the hand-eye calibration speed, so as to grasp the target; that is, the yolov5 algorithm and hand-eye calibration technology are used to achieve precise control of the robot arm;

[0027] Wear VR glasses to find the contact network parts, calibrate the part coordinates based on the VR coordinates, and then use the base as the basic coordinate system to get the relative base coordinates of the parts. The specific formula is as follows:

[0028]

[0029] Where: target is the coordinate system of the parts on the contact network; base is the basic coordinate system;

[0030] Step 2: After the camera parameters and hand-eye parameters are calibrated and the coordinates are calibrated, a virtual motion path of the robot is generated to complete the simulation process.

[0031] Among them, the optimization of the robot arm virtual motion path algorithm, the original traditional solution is to use moveit in ros for path planning, but when using moveit, only one joint can be controlled when the mobile robot arm reaches the ideal path. Although this joint reaches the ideal position, it will cause other joints to move. If in the virtual world, the functions of the two VR handles are changed to two hands, one hand fixes other joints, and the other hand moves the target joint, then when the robot arm moves to the corresponding position, each joint is in the ideal position, and other joints move to other places with the moving joints. The advantage of this optimization method is that after fixing other joints, the path of the moving joint is the optimal path, which can reduce unnecessary energy loss of the robot arm;

[0032] Step 4: The operator enters the contact network digital twin platform through virtual reality technology and observes the virtual motion path of the robot arm from an omniscient perspective, obtains a suitable path, and plans it through rviz;

[0033] The specific process is as follows: connect the P port to the virtual simulation platform by wire, put on PICO glasses to enter the virtual simulation world, and observe the virtual motion path of the robot arm from an omniscient perspective. If it is found to be suitable, it is determined as a suitable route and planned through rviz; if it is not suitable, repeat steps 3 to 4 until it is suitable;

[0034] Step 5: Link the robot arm with rviz, control the displayed maintenance path of the robot arm according to the virtual motion path of the robot arm, and inspect the contact network.

[0035] The above description is not intended to limit the present invention in any form. Although the present invention has been disclosed through the above embodiments, it is not intended to limit the present invention. Any technician familiar with the profession can make some changes or modifications to equivalent embodiments of equivalent changes using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are within the scope of the technical solution of the present invention.

Claims

1. A contact network maintenance method based on digital twin technology, characterized in that: The following steps are involved: Step 1: Obtain real-world data of the contact network through the lidar sensor on the inspection vehicle; Step 2: Based on digital twin technology and real-world data of the contact network, a digital twin platform for the contact network is established through a virtual simulation platform; Step 3: Simulate the catenary maintenance process on the catenary digital twin platform to obtain the virtual motion path of the robotic arm; The yolov5 algorithm and hand-eye calibration technology are used to achieve precise control of the robotic arm; Step 4: The operator enters the contact network digital twin platform through virtual reality technology and observes the virtual motion path of the robot arm from an omniscient perspective, obtains a suitable path, and plans it through rviz; Step 5: Link the robot arm with rviz, control the displayed maintenance path of the robot arm according to the virtual motion path of the robot arm, and inspect the contact network.

2. The contact network maintenance method based on digital twin technology according to claim 1 is characterized in that: The simulation in step three is performed through a VR head display.

3. The contact network maintenance method based on digital twin technology according to claim 2 is characterized in that: The simulation process in step 3 is as follows: Step 1: Use the yolov5 algorithm and hand-eye calibration technology to calibrate the coordinates of the robotic arm; Step 2: After the coordinate calibration is completed, the virtual motion path of the robot arm is generated to complete the simulation process.

4. The contact network maintenance method based on digital twin technology according to claim 3 is characterized in that: In the step 1, a one-to-one modeling is performed in the contact network digital twin platform according to the contact network in the real world. In the virtual setting, the coordinates of the VR headset are set as the original coordinates. The VR headset can be used as a camera in the virtual world. The yolov5 algorithm is imported. When a target such as a screw appears in the field of vision, the yolov5 algorithm marks the target, and the relative coordinates of the target relative to the headset can be obtained, so that hand-eye marking can be performed.

5. The contact network maintenance method based on digital twin technology according to claim 3 is characterized in that: In step 2, in the virtual world, the functions of the two VR handles are changed to two hands, one hand fixes other joints, and the other hand moves the target joint, that is, when the robotic arm moves to the corresponding position, each joint is in the ideal position, and other joints move to other places along with the moving joint.

6. The contact network maintenance method based on digital twin technology according to claim 1 is characterized in that: The specific process of step 4 is: make a wired connection with the P port in the virtual simulation platform, put on PICO glasses to enter the virtual simulation world, observe the virtual motion path of the robotic arm from an omniscient perspective, and if it is found to be suitable, determine it as a suitable route and plan it through rviz; if it is not suitable, repeat steps 3 to 4 until it is suitable.

Images