5G pump station intelligent robot system and operation and inspection method thereof

Abstract

The invention relates to the technical field of intelligent robots, in particular to a 5G pump station intelligent robot system and an operation and inspection method thereof.The 5G pump station intelligent robot system comprises an AGV, and a tail end jig assembly comprises a thermal imaging sensor, a temperature, humidity and smoke sensor, a pan-tilt camera, a laser displacement sensor and a torsion assembly which are installed on a cooperative mechanical arm; through cooperation of the thermal imaging sensor, the temperature, humidity and smoke sensor and the pan-tilt camera, intelligent inspection of the high-voltage switch cabinet and the low-voltage switch cabinet of the pump station can be realized, and through cooperation of the pan-tilt camera, the laser displacement sensor and the torsion assembly, intelligent operation of the high-voltage switch cabinet of the pump station can be realized. According to the system, by integrating various sensors, autonomous navigation, 5G communication and intelligent control technologies, intelligent operation and inspection of the high-voltage switch cabinet are realized, the operation precision and the inspection efficiency are improved, and the manual labor intensity and potential safety hazards are reduced. The system can be widely applied to intelligent management of industries such as water conservancy and electric power.

Description

Technical Field

[0001] The present invention relates to the field of intelligent robot technology, and in particular to a 5G pump station intelligent robot system and an operation and inspection method thereof. Background Art

[0002] Power grid switchgear robots are high-tech products based on intelligence and automation, primarily used for switchgear maintenance and management in the power industry. With the continued expansion of power systems and the increasing complexity of their operations, traditional manual inspections are no longer sufficient. Furthermore, due to the complex environments and poor working conditions of switchgear, manual inspections present numerous safety risks.

[0003] Based on the "5G+Industrial Internet" architecture, and utilizing the 5G virtual private network and industrial Internet platform already built at Baoying Station, we explore and research typical application scenarios such as 5G+intelligent operation and intelligent inspection.

[0004] Research has found that existing intelligent robots struggle to simultaneously implement intelligent push-pull carts for high-voltage switchgear in pump stations, as well as intelligent inspections of both high-voltage and low-voltage switchgear. Furthermore, they struggle to comprehensively assess equipment failures and environmental issues in these two systems, resulting in low operational accuracy and inspection efficiency. To address these shortcomings, we propose a 5G pump station intelligent robot system and its operation and inspection methods. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to propose a 5G pump station intelligent robot system and its operation and inspection method, which can realize the intelligent operation of the high-voltage switchgear of the pump station and the intelligent inspection of the high-voltage switchgear and low-voltage switchgear, improve the operation accuracy and inspection efficiency, and reduce the labor intensity and safety hazards.

[0006] Based on the above objectives, the present invention provides a 5G pump station intelligent robot system, including: The AGV car adopts a dual-wheel differential drive and is based on SLAM technology. It uses laser radar to generate an environmental map, locate its own position and detect surrounding obstacles in real time to achieve autonomous obstacle avoidance. The vehicle body distribution box is installed on the AGV and is used to load electrical and mechanical components related to power distribution and control; An electric lift platform, which is arranged on the vehicle body distribution box, and a collaborative robot arm is installed on the top of the electric lift platform, and an end fixture assembly is installed at the end of the collaborative robot arm; The end fixture assembly includes a thermal imaging sensor, a temperature, humidity, and smoke sensor, a pan-tilt camera, a laser displacement sensor, and a torque assembly installed on the collaborative robot arm. The laser displacement sensor is used to measure the displacement change of the trolley in real time. Through the cooperation of the thermal imaging sensor, the temperature, humidity, and smoke sensor, and the pan-tilt camera, intelligent inspection of the high-voltage switchgear of the pump station can be achieved. Through the cooperation of the pan-tilt camera, the laser displacement sensor, and the torque assembly, intelligent operation of the high-voltage switchgear of the pump station can be achieved. The electric lifting platform is used to adjust the height of the collaborative robot arm so that the end fixture assembly can adapt to operations and inspection tasks at different heights.

[0007] Preferably, it further includes a control system disposed in the vehicle body distribution box, the control system including a main controller, a software algorithm and a communication module; The main controller is used to process sensor monitoring data and perform path planning and decision making; The software algorithms are integrated into the main controller and include computer vision algorithms, data analysis algorithms, path algorithms, and behavior control algorithms. These algorithms interact through a real-time data bus to form a closed-loop control logic to ensure that the robot can complete operation and inspection tasks efficiently and accurately. The communication module is used to communicate data with the industrial Internet platform through the 5G network to achieve management, scheduling, and control of the intelligent robot and to connect with the automated monitoring system.

[0008] It allows on-duty personnel to remotely control and view real-time video streams, sensor data, etc. on the industrial Internet platform, and automatically save inspection data, recording various data and problems found during inspection and closing operations.

[0009] The industrial Internet platform is deployed on the management and scheduling network. The start-up and shutdown process instructions of the automated monitoring system can be sent to the platform in a one-way manner, and the platform video signal can be connected to the video surveillance system to ensure the integration of the platform with the existing system.

[0010] Preferably, a remote monitoring platform is installed on the vehicle body distribution box, and the remote monitoring platform is used to monitor the operation and inspection process in real time.

[0011] Preferably, the torque assembly includes a force sensor, a torque wrench and a torque sleeve, the force sensor is mounted on the end of the collaborative robot arm, the torque wrench is mounted on the force sensor, and the torque sleeve is mounted on the output end of the torque wrench.

[0012] Preferably, the force sensor is used to monitor the operating torque in real time and trigger a protection mechanism when a threshold is exceeded; The torque wrench is used to perform push and pull operations of the trolley according to the set torque; The torque sleeve is adapted to the operating interface of the high-voltage switch cabinet trolley and cooperates with the torque wrench to transmit torque.

[0013] The AGV preferably uses an automatic charging mode to ensure 24 / 7 uninterrupted operation. A manual charging port and a manual charger are also provided to accommodate manual charging in emergencies. This project intends to use an SCS-2002 charging station. When the AGV is charging and the battery level is above 30%, if a task is received, the AGV will interrupt charging to perform the task. If the battery level drops below 30%, the AGV will automatically stop charging and will no longer perform the task.

[0014] A method for operating a 5G pump station intelligent robot system, comprising the following steps: Step S1: According to task assignment, the intelligent robot moves from the charging area or inspection area to the operation area; Operation takes priority. If an inspection is in progress, the system will automatically move to the operation area according to the task. Step S2: The intelligent robot accurately identifies the location number of the high-voltage switchgear through the pan-tilt camera, performs a double check of the QR code and the identification plate, and stops accurately at a reasonable location to prevent it from accidentally entering the live compartment; Step S3: Verify the high-voltage switchgear trolley and the opening and closing states. When the high-voltage switchgear trolley is in the working position and in the opening state, it can be pulled out for operation; when the high-voltage switchgear trolley is in the working position and in the closing state, it is strictly prohibited to pull out the trolley; when the high-voltage switchgear trolley is in the test position and in the opening state, it can be pushed in for operation; when the high-voltage switchgear trolley is in the test position and in the closing state, it is strictly prohibited to push in the trolley; Step S4: After determining that the operation is possible, the operation position is visually located, and the trolley is pushed and pulled through the end fixture assembly (the intended test operation is ≥ 20 times / unit when the high-voltage switchgear is not energized); Step S5: After the operation is completed, the status indicator light signal is visually recognized, the number of rotations is recorded, and the feedback is sent to the industrial Internet platform (the automated monitoring system also has input signal feedback), and the vehicle automatically returns to the charging area.

[0015] Preferably, in step S3, the trolley and the opening and closing states are detected by identifying the pictures taken by the PTZ camera, that is, the state recognition is performed by a computer vision algorithm. The specific detection steps are as follows: Step S3.1: The PTZ camera takes a picture and performs image processing on the picture; Step S3.2: Preprocess the image and input it into the YOLO object detection model to identify the main panels on the switch cabinet; Step S3.3: Preprocess the identified panel image and input it into the deep learning classification model to accurately identify the status of the panel lights or knobs.

[0016] A 5G pump station intelligent robot system inspection method includes the following steps: Step P1: According to the preset time, the intelligent robot regularly moves from the charging area to the inspection area; The operation takes priority, and if the operation is in progress, the operation task will continue to be executed; Step P2: Conduct intelligent inspections on high-voltage switchgear and low-voltage switchgear equipment according to the preset routes; Step P3: After the inspection is completed, the robot automatically returns to the charging area. When the battery is low, the robot returns to the charging area to automatically charge.

[0017] Preferably, step P2 includes the following steps: Step P2.1: The status of the instruments and indicator lights of the high-voltage switchgear equipment is photographed using a pan-tilt camera and identified using a visual algorithm. Step P2.2: Detect the surface temperature distribution of the high-voltage switchgear equipment using a thermal imaging sensor; Step P2.3: The ambient temperature and humidity are detected in real time by the temperature, humidity and smoke sensors carried by the robot. Abnormal thresholds can be preset for temperature and humidity. If the detection value exceeds the threshold range during inspection, it indicates an abnormality.

[0018] The beneficial effects of the present invention are as follows: Intelligent operation of high-voltage switchgear: Without modifying the high-voltage switchgear, an intelligent robot is used to realize the intelligent push-pull trolley of the high-voltage switchgear, and automatically locate and identify the status of the trolley and indicator lights according to the scheduling task, while meeting the five electrical protection requirements.

[0019] Intelligent inspection of high and low voltage switchgear: Use intelligent robots to realize intelligent inspection of high and low voltage switchgear, and regularly inspect high and low voltage equipment instruments, indicator light status, temperature and humidity according to preset routes.

[0020] 3. It also avoids personal risks: it completely replaces manual operation and completely eliminates high-voltage electrical operation risks such as electric shock and arc burns, especially ensuring personnel safety in fault or abnormal conditions.

[0021] Avoid misoperation: Accurately execute the operation process through preset procedures to prevent serious accidents caused by human factors (such as wrong intervals or wrong sequences).

[0022] Quick response: Available 24 hours a day. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 Schematic diagram of the structure of the intelligent robot of the present invention; Figure 2 It is a structural schematic diagram of the end fixture assembly of the present invention; Figure 3 This is a schematic diagram of the deployment of the system integration and industrial Internet platform of the present invention.

[0025] In the picture: 1. AGV car; 2. Vehicle body distribution box; 3. Electric lifting platform; 4. Collaborative robot arm; 5. End fixture assembly; 6. Thermal imaging sensor; 7. Temperature, humidity and smoke sensor; 8. Pan-tilt camera; 9. Laser displacement sensor; 10. Remote monitoring pan-tilt; 11. Force sensor; 12. Torque wrench; 13. Torque socket. DETAILED DESCRIPTION

[0026] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0027] like Figure 1 、 Figure 2 、 Figure 3 As shown, a 5G pump station intelligent robot system includes an AGV car 1, which adopts a dual-wheel differential drive and uses laser radar to generate an environmental map based on SLAM technology. It can locate its own position and detect surrounding obstacles in real time to achieve autonomous obstacle avoidance. The vehicle body distribution box 2 is arranged on the AGV trolley 1 and is used to load electrical and mechanical components related to power distribution and control; An electric lift platform 3 is provided on the vehicle body distribution box 2, and a collaborative robot arm 4 is installed on the top of the electric lift platform 3, and an end fixture assembly 5 is installed at the end of the collaborative robot arm 4; The end fixture assembly 5 includes a thermal imaging sensor 6, a temperature and humidity smoke sensor 7, a pan-tilt camera 8, a laser displacement sensor 9, and a torque assembly installed on the collaborative robot arm 4. Through the cooperation of the thermal imaging sensor 6, the temperature and humidity smoke sensor 7, and the pan-tilt camera 8, intelligent inspection of the high-voltage switchgear and low-voltage switchgear of the pump station can be realized. Through the cooperation of the pan-tilt camera 8, the laser displacement sensor 9, and the torque assembly, intelligent operation of the high-voltage switchgear of the pump station can be realized. The electric lifting platform 3 is used to adjust the height of the collaborative robot arm 4 so that the end fixture assembly 5 can adapt to operations and inspection tasks at different heights.

[0028] It also includes a control system arranged in the vehicle body distribution box 2, the control system including a main controller, software algorithms and a communication module; The main controller is used to process sensor monitoring data and perform path planning and decision making; The software algorithms are integrated into the main controller and include computer vision algorithms, data analysis algorithms, path algorithms, and behavior control algorithms. These algorithms interact through a real-time data bus to form a closed-loop control logic to ensure that the robot can complete operation and inspection tasks efficiently and accurately. The communication module is used to communicate data with the industrial Internet platform through the 5G network to achieve management, scheduling, and control of intelligent robots and connect with the automated monitoring (SCADA) system.

[0029] The industrial Internet platform is deployed on the management and scheduling network. The start-up and shutdown process instructions of the automated monitoring system can be sent to the platform in a one-way manner, and the platform video signal can be connected to the video surveillance system to ensure the integration of the platform with the existing system.

[0030] A remote monitoring platform 10 is installed on the vehicle body distribution box 2, and the remote monitoring platform 10 is used to monitor the operation and inspection process in real time.

[0031] The torque assembly includes a force sensor 11 , a torque wrench 12 and a torque sleeve 13 . The force sensor 11 is mounted on the end of the collaborative robot arm 4 , and the torque wrench 12 is mounted on the force sensor 11 . The torque sleeve 13 is mounted on the output end of the torque wrench 12 .

[0032] The force sensor 11 is used to monitor the operating torque in real time and trigger the protection mechanism when the threshold is exceeded; The torque wrench 12 is used to perform the push and pull operation of the trolley according to the set torque; The torque sleeve 13 is adapted to the operating interface of the high-voltage switchgear trolley and cooperates with the torque wrench 12 to transmit torque.

[0033] AGV 1 adopts automatic charging mode. When AGV 1 is charging and the power level is higher than 30%, if a task is received at this time, AGV 1 will interrupt charging to perform the task; when the power level of AGV 1 is lower than 30%, it will automatically stop charging and no longer perform the task.

[0034] A method for operating a 5G pump station intelligent robot system, comprising the following steps: Step S1: According to task assignment, the intelligent robot moves from the charging area or inspection area to the operation area; Operation takes priority. If an inspection is in progress, the system will automatically move to the operation area according to the task. Step S2: The intelligent robot accurately identifies the location number of the high-voltage switchgear through the pan-tilt camera 8, and performs a double check of the QR code and the identification plate, and stops accurately at a reasonable position to prevent it from accidentally entering the live interval; Step S3: Verify the high-voltage switchgear trolley and the opening and closing states. When the high-voltage switchgear trolley is in the working position and in the opening state, it can be pulled out for operation; when the high-voltage switchgear trolley is in the working position and in the closing state, it is strictly prohibited to pull out the trolley; when the high-voltage switchgear trolley is in the test position and in the opening state, it can be pushed in for operation; when the high-voltage switchgear trolley is in the test position and in the closing state, it is strictly prohibited to push in the trolley; In step S3, the trolley and the opening and closing states are detected by identifying the images taken by the PTZ camera 8, that is, the state recognition is performed by computer vision algorithm. The specific detection steps are as follows: Step S3.1: The pan-tilt camera 8 takes a picture and performs image processing on the taken picture; Step S3.2: Preprocess the image and input it into the YOLO object detection model to identify the main panels on the switch cabinet; Step S3.3: Preprocess the identified panel image and input it into the deep learning classification model to accurately identify the status of the panel lights or knobs.

[0035] Step S4: After determining that the operation is possible, the operation position is visually located, and the trolley is pushed or pulled through the end fixture assembly 5; Step S5: After the operation is completed, the status indicator light signal is visually recognized, the number of rotations is recorded, and the feedback is fed back to the industrial Internet platform, and the vehicle automatically returns to the charging area.

[0036] A 5G pump station intelligent robot system inspection method includes the following steps: Step P1: According to the preset time, the intelligent robot regularly moves from the charging area to the inspection area; The operation takes priority, and if the operation is in progress, the operation task will continue to be executed; Step P2: Conduct intelligent inspections on high-voltage switchgear and low-voltage switchgear equipment according to the preset routes; Step P3: After the inspection is completed, the robot automatically returns to the charging area. When the battery is low, the robot returns to the charging area to automatically charge.

[0037] Step P2 includes the following steps: Step P2.1: The status of the instruments and indicator lights of the high and low voltage switchgear equipment are photographed by the pan-tilt camera 8 and identified using a computer vision algorithm; Step P2.2: Detect the surface temperature distribution of the high and low voltage switchgear equipment using the thermal imaging sensor 6; Step P2.3: The ambient temperature and humidity are detected in real time by the temperature, humidity and smoke sensor 7 carried by the robot. The temperature and humidity can be set to abnormal thresholds. If the detection value exceeds the threshold range during the inspection, it indicates that there is an abnormality.

[0038] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Within the scope of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the above aspects of the present invention, which are not provided in detail for the sake of simplicity.

[0039] The embodiments of the present invention are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A 5G pump station intelligent robot system, characterized in that: include: The AGV car (1) adopts a dual-wheel differential drive and is based on SLAM technology. It uses laser radar to generate an environmental map, locates its own position and detects surrounding obstacles in real time to achieve autonomous obstacle avoidance. A vehicle body distribution box (2), the vehicle body distribution box (2) being arranged on the AGV trolley (1) and being used for loading electrical and mechanical components related to power distribution and control; An electric lift (3), the electric lift (3) being arranged on a vehicle body distribution box (2), and a collaborative robot arm (4) being installed on the top of the electric lift (3), and an end fixture assembly (5) being installed at the end of the collaborative robot arm (4); The end fixture assembly (5) includes a thermal imaging sensor (6), a temperature and humidity smoke sensor (7), a pan-tilt camera (8), a laser displacement sensor (9), and a torque assembly installed on the collaborative robot arm (4). Through the cooperation of the thermal imaging sensor (6), the temperature and humidity smoke sensor (7), and the pan-tilt camera (8), intelligent inspection of the high-voltage switch cabinet and the low-voltage switch cabinet of the pump station can be realized. Through the cooperation of the pan-tilt camera (8), the laser displacement sensor (9), and the torque assembly, intelligent operation of the high-voltage switch cabinet of the pump station can be realized. The electric lifting platform (3) is used to adjust the height of the collaborative robot arm (4) so ​​that the end fixture assembly (5) can adapt to operations and inspection tasks at different heights.

2. A 5G pump station intelligent robot system according to claim 1, characterized in that: It also includes a control system arranged in the vehicle body distribution box (2), the control system including a main controller, a software algorithm and a communication module; The main controller is used to process sensor monitoring data and perform path planning and decision making; The software algorithms are integrated into the main controller and include computer vision algorithms, data analysis algorithms, path algorithms, and behavior control algorithms. These algorithms interact through a real-time data bus to form a closed-loop control logic to ensure that the robot can complete operation and inspection tasks efficiently and accurately. The communication module is used to communicate data with the industrial Internet platform through the 5G network to achieve management, scheduling, and control of the intelligent robot and to connect with the SCADA system.

3. A 5G pump station intelligent robot system according to claim 1, characterized in that: A remote monitoring platform (10) is installed on the vehicle body distribution box (2), and the remote monitoring platform (10) is used for real-time monitoring of operation and inspection processes.

4. A 5G pump station intelligent robot system according to claim 1, characterized in that: The torque assembly comprises a force sensor (11), a torque wrench (12) and a torque sleeve (13), wherein the force sensor (11) is mounted on the end of the collaborative robot arm (4), the torque wrench (12) is mounted on the force sensor (11), and the torque sleeve (13) is mounted on the output end of the torque wrench (12).

5. A 5G pump station intelligent robot system according to claim 4, characterized in that: The force sensor (11) is used to monitor the operating torque in real time and trigger a protection mechanism when the torque exceeds a threshold; The torque wrench (12) is used to perform the push and pull operation of the trolley according to the set torque; The torque sleeve (13) is adapted to the operating interface of the high-voltage switch cabinet trolley and cooperates with the torque wrench (12) to transmit torque.

6. A 5G pump station intelligent robot system according to claim 1, characterized in that: The AGV trolley (1) adopts an automatic charging mode. When the AGV trolley (1) is charging and the power level is higher than 30%, if a task is received at this time, the AGV trolley (1) will interrupt charging to perform the task; when the power level of the AGV trolley (1) is lower than 30%, it will automatically stop charging and no longer perform the task.

7. The method for operating a 5G pump station intelligent robot system according to any one of claims 1 to 6, characterized in that: The following steps are involved: Step S1: According to task assignment, the intelligent robot moves from the charging area or inspection area to the operation area; Operation takes priority. If an inspection is in progress, the system will automatically move to the operation area according to the task. Step S2: The intelligent robot accurately identifies the location number of the high-voltage switchgear through the pan-tilt camera (8), and performs a double check of the QR code and the identification plate, and stops accurately at a reasonable position to prevent it from mistakenly entering the live interval; Step S3: Verify the high-voltage switchgear trolley and the opening and closing states. When the high-voltage switchgear trolley is in the working position and in the opening state, it can be pulled out for operation; when the high-voltage switchgear trolley is in the working position and in the closing state, it is strictly prohibited to pull out the trolley; when the high-voltage switchgear trolley is in the test position and in the opening state, it can be pushed in for operation; when the high-voltage switchgear trolley is in the test position and in the closing state, it is strictly prohibited to push in the trolley; Step S4: After determining that the operation is possible, the operation position is visually located, and the trolley is pushed and pulled through the end fixture assembly (5); Step S5: After the operation is completed, the status indicator light signal is visually recognized, the number of rotations is recorded, and the feedback is fed back to the industrial Internet platform, and the vehicle automatically returns to the charging area.

8. The method for operating a 5G pump station intelligent robot system according to claim 7, characterized in that: In step S3, the trolley and the state of the switch are detected by identifying the pictures taken by the PTZ camera (8), that is, the state is identified by the computer vision algorithm. The specific detection steps are as follows: Step S3.1: The pan-tilt camera (8) takes a picture and performs image processing on the taken picture; Step S3.2: Preprocess the image and input it into the YOLO object detection model to identify the main panels on the switch cabinet; Step S3.3: Preprocess the identified panel image and input it into the deep learning classification model to accurately identify the status of the panel lights or knobs.

9. A 5G pump station intelligent robot system inspection method according to any one of claims 1-6, characterized in that: The following steps are involved: Step P1: According to the preset time, the intelligent robot regularly moves from the charging area to the inspection area; The operation takes priority, and if the operation is in progress, the operation task will continue to be executed; Step P2: Conduct intelligent inspections on high-voltage switchgear and low-voltage switchgear equipment according to the preset routes; Step P3: After the inspection is completed, the robot automatically returns to the charging area. When the battery is low, the robot returns to the charging area to automatically charge.

10. A 5G pump station intelligent robot system inspection method according to claim 9, characterized in that: Step P2 includes the following steps: Step P2.1: The status of the instruments and indicator lights of the high and low voltage switchgear equipment are photographed by the pan-tilt camera (8) and identified using computer vision algorithms; Step P2.2: Detect the surface temperature distribution of the high and low voltage switchgear equipment using a thermal imaging sensor (6); Step P2.3: The ambient temperature and humidity are detected in real time by the temperature, humidity and smoke sensor (7) carried by the robot. The temperature and humidity can be set to a preset abnormal threshold. If the detection value exceeds the threshold range during the inspection, it indicates that there is an abnormality.

Images