SF6 gas leakage detection robot system for GIS equipment

Abstract

The invention discloses a GIS equipment SF6 gas leakage detection robot system, which comprises a mobile robot system and a leakage detection management system, and is characterized in that the mobile robot system carries a crawler-type mobile chassis, an SLAM laser radar, an SF6 gas cloud infrared imager and the like, a global inspection path is predicted, controlled and tracked through an MPC model, and when leakage is detected, the leakage detection management system is started, and the leakage detection management system is started. And triggering an A * algorithm to generate an equipment contour bypassing path, and accurately positioning a leakage point. The leakage detection management system carries out gas leakage detection according to the collected data, dynamically judges the leakage level through a grading decision matrix, and achieves centralized processing and intelligent management of the collected data in cooperation with a visual operation interface. According to the invention, the unmanned closed-loop management of the whole process of full-coverage detection and leakage detection of the GIS equipment is realized, and the efficiency and accuracy of gas leakage detection of the GIS equipment are greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent detection of power equipment, in particular to a GIS device SF6 gas leakage detection robot system. BACKGROUND

[0002] With the expansion of the power system, GIS device is a metal-enclosed high-voltage distribution device with SF6 as the insulating medium. SF6 gas is not only a strong greenhouse gas, but its decomposition products (such as SF4, HF) are also highly toxic to the human body and can easily cause suffocation accidents in enclosed spaces. Therefore, SF6 gas leakage detection of GIS devices can effectively prevent accidents. Traditional leakage detection mainly relies on fixed sensor networks to monitor SF6 concentration and oxygen content through gas sensors arranged in the GIS room. However, once the fixed sensor is deployed, its position is fixed, and there is a monitoring blind area that cannot cover the back of the equipment, welds and other hidden areas. When leakage occurs, the sensor can only passively alarm and cannot actively locate the source of the leakage, requiring manual intervention for investigation, which is low in efficiency and high in risk.

[0003] To solve the above problems, existing technologies attempt to use inspection robots to carry gas detection modules to achieve autonomous inspection through preset paths. However, such systems still have significant limitations: Most robots can only inspect along fixed routes and cannot dynamically respond to sudden tasks such as leakage point detection. When gas leakage is detected, manual intervention or task interruption is required, resulting in low efficiency.

[0004] Some robots use SLAM to generate global paths, but rely on real-time re-planning for local obstacle avoidance, such as when turning to the back of the equipment. The calculation is complex and the positioning accuracy is insufficient when returning to the original trajectory, resulting in path deviation due to cumulative errors.

[0005] The gas detection module carried only triggers an alarm through a gas concentration threshold without quantifying the leakage risk level and considering the impact of other environments, resulting in poor performance.

[0006] At the same time, existing technologies lack a backend system that can effectively integrate real-time video and sensor data collected by mobile robots and perform intelligent analysis and management, resulting in the value of front-end detection not being fully utilized. SUMMARY

[0007] To solve the above problems, the present application provides a GIS device SF6 gas leakage detection robot system, which includes a mobile robot system and a leakage detection management system. The mobile robot system includes a mobile robot body, which carries a tracked mobile chassis, a visible light camera, a SLAM laser radar, an SF6 gas cloud infrared imager, a navigation control module, a power supply management module, a communication interface and a gimbal mechanism. The tracked mobile chassis is installed at the bottom of the mobile robot body for autonomous movement along the navigation path in the GIS device area; the visible light camera and SF6 gas cloud infrared imager are integrated on the PTZ mechanism, respectively for collecting visible light images and SF6 gas leakage infrared images of the GIS device; the PTZ mechanism is installed at the top front end of the mobile robot body for horizontal rotation and pitch adjustment to detect the angle; the SLAM laser radar is installed at the top of the mobile robot body for real-time scanning of the environment and construction of a GIS device area point cloud map; the navigation control module is in communication connection with the tracked mobile chassis and the laser radar, for executing planned movement path and positioning leakage location according to map data, and controlling the movement of the tracked mobile chassis; the power supply management module includes a lithium battery pack, a power monitoring unit and a power display unit, for monitoring battery voltage, current, power and remaining endurance time, and displaying the current remaining power in real time; the communication interface supports 4G / 5G and Wi-Fi protocols for real-time data transmission with the leakage detection management system; The leakage detection management system includes a communication module, a data processing module, a data management module and a user interface module; The communication module receives the data packets transmitted by the mobile robot system, and the data packets include visible light video stream, SF6 gas leakage infrared image and leakage location coordinate data packets; the data processing module is connected to the communication module for analyzing the leakage event information in the data packet, and determining the severity level of the leakage event according to a preset leakage level determination method; the data management module is connected to the data processing module for storing the leakage event information and the level determination result in a log; the user interface module integrates a multi-tab display interface, including a real-time monitoring page and a data report page, for visually displaying the leakage event information and the leakage location to the user, and providing historical leakage event information query and viewing functions.

[0008] Further, the method for executing planned movement path and positioning leakage location in the navigation control module includes: S1, obtaining a GIS device area point cloud map by a SLAM laser radar, setting basic path points for all GIS devices and inter-device channels, and generating a global inspection trajectory by linear interpolation; S2, constructing a dynamic model of the mobile robot system, performing global path planning based on the global inspection trajectory and the dynamic model by a trajectory tracking algorithm, and controlling the mobile robot system to perform global inspection; S3, when the SF6 gas cloud infrared imager detects gas leakage, activating local path planning, marking the leaking device as an obstacle, calculating an inflation distance based on the device half-width, the mobile robot radius and the safety margin, and taking the inflated obstacle area as the constraint boundary of local path planning; S4. Set temporary path points on the side and back of the leaking equipment. Use a local obstacle avoidance algorithm to generate a detour path that closely follows the outline of the equipment outside the expansion area. Control the mobile robot system to detour to the temporary path points to collect infrared images and location data of the leak point. S5. Record the trajectory interruption position of the mobile robot system at the starting point of the detour and the status of the mobile robot. After completing the data acquisition, control the mobile robot system to return to the interruption position and continue the global inspection.

[0009] Furthermore, in S2, the dynamic model of the mobile robot system is simplified to a two-dimensional planar motion model of pure rolling motion. The motion of the mobile robot system is transmitted through a tracked mobile chassis. The motion equation of the dynamic model is defined as follows: (1) In formula (1), Let x be the x-coordinate of the centroid of the mobile robot in a two-dimensional plane coordinate system. Let y be the ordinate of the centroid of the mobile robot in a two-dimensional plane coordinate system. The instantaneous orientation angle of the mobile robot. The linear velocity of the right track is... The linear velocity of the left track is... Track track width For time; Based on the centroid reference state of the mobile robot on the reference trajectory The actual state of the centroid on the actual trajectory Obtain the state error matrix between the actual centroid and the reference centroid of the mobile robot: (2) In formula (2), The linear velocity of the reference trajectory, The linear velocity of the actual trajectory; The state error matrix is ​​used as the state input, and the speed commands of the two track sides are used as the control output. Global path planning is performed through a trajectory tracking algorithm.

[0010] Furthermore, the trajectory tracking algorithm employs the MPC model predictive control algorithm, and the specific global path planning method includes: S2.1. By discretizing the dynamic model of the mobile robot system, a state prediction model for the mobile robot system is established: (4) In formula (4), for The state vector of the mobile robot system at any given time. for Control the input vector at all times. is a state transition matrix, is a control input matrix; S2.2, constructing a target function according to the error between the predicted state output of the mobile robot system and the actual state output: (5) In formula (5), is a state error weight matrix, is a control increment weight matrix, is a prediction time domain length, is a control time domain length, is a relaxation factor weight coefficient, is a relaxation factor, is the predicted value of the actual state of the system at the time t+1, is the estimated value of the reference state at the time t+1, is the control increment at the time t+1, S2.3, in each control period, predicting the state sequence of the mobile robot system in the future steps based on the current state, and solving the target function to generate an optimal control sequence ; S2.4, taking the first control increment to update the control instruction , outputting the control instruction to the tracked mobile chassis, controlling the movement of the mobile robot system, and synchronously acquiring the actual state feedback to the next control period.

[0011] Further, in the S4, the local obstacle avoidance method adopts the A* algorithm, and the specific local path planning method is: S4.1, setting multiple temporary path points on the side and back of the leakage device; S4.2, taking the current mobile robot position as the starting point and the first temporary path point as the ending point, generating a detour path close to the outline of the leakage device through the A* algorithm based on the constraint of the expanded obstacle region; S4.3, controlling the mobile robot system to move to the temporary path point according to the detour path, and collecting the infrared image and position data of the leakage point at the current temporary path point; S4.4, activating the next temporary path point after completing data collection, and repeating steps S4.1-S4.3 until all temporary path points are traversed; S4.5, when the data collection of all temporary path points is completed, the mobile robot is controlled to return to the trajectory interruption position to continue the global inspection.

[0012] Further, in the data processing module, a preset leakage level determination method adopts a hierarchical decision matrix, the hierarchical decision matrix is obtained by weighting two parts of a leakage area proportion and a diffusion speed, and a specific formula is: (6) In formula (6), is a leakage area proportion factor weight, is a diffusion speed factor weight, =1, the weight distribution is dynamically adjusted according to environmental parameters, and the environmental parameters include device density and personnel flow frequency; The data processing module determines the leakage level according to the threshold interval in which the leakage level score is located, and outputs the determination result to the data management module.

[0013] The beneficial effects of the present application are: The present application realizes centralized processing and intelligent management of the data returned by the mobile robot system by developing real-time communication between the host computer leakage detection management system and the mobile robot system; the accurate global trajectory tracking of the mobile robot in the GIS device area is realized through the trajectory tracking technology, and the multiple devices are sequentially inspected; at the same time, the local path planning is carried out around the leaked GIS device, the data is automatically collected at the temporary target point, the accurate data collection and accurate positioning of the leakage point are realized; the real-time continuous image sequence is synchronously collected by the visible light camera and the SF6 gas cloud infrared imager for gas leakage detection, and the hierarchical decision matrix is used for grade determination of gas leakage; the present application significantly reduces the workload of manual inspection, optimizes the detection process, and improves the reliability of GIS device operation. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 is a working logic diagram for leakage event information display of the leakage detection management system of the embodiment; Figure 2 is a real-time monitoring page function diagram of the leakage detection management system of the embodiment; Figure 3 is a data report page function diagram of the leakage detection management system of the embodiment; Figure 4 is an emergency communication network topology diagram of the embodiment; Figure 5 is a dynamic model diagram of the mobile robot system of the embodiment; Figure 6 is a state error model diagram of the trajectory tracking of the mobile robot system of the embodiment; Figure 7 is a schematic diagram of the robot triggering local path planning and bypassing the leaking device in this embodiment; Figure 8 is a schematic diagram of the overall process of determining the severity level of the leakage event in this embodiment; Figure 9 is a schematic diagram of the leakage level assessment result in this embodiment. DETAILED DESCRIPTION

[0015] The technical method of the present application will be described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0016] Embodiment One A GIS device SF6 gas leakage detection robot system, the system comprising a mobile robot system and a leakage detection management system; The mobile robot system comprises a mobile robot body, the body being mounted with a tracked mobile chassis, a visible light camera, a SLAM laser radar, an SF6 gas cloud infrared imager, a navigation control module, a power supply management module, a communication interface and a pan-tilt mechanism; The tracked mobile chassis is installed at the bottom of the mobile robot body for autonomous movement along the navigation path in the GIS device area; the visible light camera and the SF6 gas cloud infrared imager are integrated on the pan-tilt mechanism, which are respectively used for collecting visible light images and SF6 gas leakage infrared images of the GIS device; the pan-tilt mechanism is installed at the top front end of the mobile robot body for horizontal rotation and pitch adjustment of the detection angle; the SLAM laser radar is installed at the top of the mobile robot body for real-time scanning of the environment and construction of a point cloud map of the GIS device area; the navigation control module is in communication connection with the tracked mobile chassis and the laser radar, for executing planned movement path and positioning leakage location according to map data, and controlling the movement of the tracked mobile chassis; the power supply management module comprises a lithium battery pack, a power monitoring unit and a power display unit, for monitoring battery voltage, current, power and remaining endurance time, and displaying the current remaining power in real time; the communication interface supports 4G / 5G and Wi-Fi protocols for real-time data transmission with the leakage detection management system; The leakage detection management system comprises a communication module, a data processing module, a data management module and a user interface module; The communication module receives a data packet transmitted by the mobile robot system, and the data packet contains a visible light video stream, an SF6 gas leakage infrared image and a data packet of a leakage position coordinate; the data processing module is connected to the communication module, and is used for parsing leakage event information in the data packet, and determining a severity level of the leakage event according to a preset leakage level determination method; the data management module is connected to the data processing module, and is used for storing the leakage event information and the level determination result in a log; and the user interface module integrates a multi-tab display interface, including a real-time monitoring page and a data report page, and is used for visually displaying leakage event information and a leakage position to a user, and providing historical leakage event information query and viewing functions.

[0017] Specifically, as shown in Figure 1 , a working logic diagram for displaying leakage event information by the leakage detection management system provided in the embodiment is shown, after the user interface module of the leakage detection management system receives comprehensive leakage event information, the comprehensive leakage event information includes a monitoring video stream, a leakage point position and a leakage level, when the received comprehensive leakage event information is not reported repeatedly, a real-time monitoring state is displayed through the real-time monitoring page, and a position coordinate and a severity are reported in an information area, and a detection process and a detection result are displayed in a processing process column; leakage reports are archived through the data report page, and a historical data screening function is provided; the leakage detection management system of the embodiment realizes leakage detection whole-process management, and avoids a response delay problem caused by multiple system switching.

[0018] In the embodiment, the leakage detection management system is developed based on a Qt framework and a C++ language, through modular design, core functions such as communication, data processing and log management are integrated, real-time video stream can be played and a detection frame can be superimposed on the real-time video stream, and the analyzed leakage event is stored in an Excel file, as shown in Figures 2-3 , the user interface module of the leakage detection management system in the embodiment integrates a multi-tab display interface, specifically including a real-time monitoring page (as shown in Figure 2 ) and a data report page (as shown in Figure 3 ), which not only meets the emergency event rapid disposal demand, but also guarantees the traceability of historical data, and significantly improves the disposal efficiency and decision quality of the GIS equipment leakage event.

[0019] Embodiment two As shown in Figure 4 , as a preferred mode of the present application: a method for planning a moving path and positioning a leakage position in the navigation control module, comprising: S1, acquiring a GIS device area point cloud map through a SLAM laser radar, setting a basic path point for all GIS devices and device channel, and generating a global inspection track through linear interpolation; S2, a dynamic model of the mobile robot system is constructed, global path planning is performed based on the global inspection trajectory and the dynamic model through a trajectory tracking algorithm, and the mobile robot system is controlled to perform global inspection; S3, when the SF6 gas cloud infrared imager detects gas leakage, local path planning is activated, the leaking device is marked as an obstacle, the inflation distance is calculated based on the device half-width, the mobile robot radius and the safety margin, and the inflated obstacle region is taken as the constraint boundary of the local path planning; S4, temporary path points are set on the side and back of the leaking device, a detour path is generated outside the inflated region through a local obstacle avoidance algorithm, the mobile robot system is controlled to detour to the temporary path point to collect infrared images and position data of the leakage point; S5, the trajectory interruption position of the mobile robot system at the detour starting point and the mobile robot state are recorded, and after data collection is completed, the mobile robot system is controlled to return to the interruption position and continue global inspection.

[0020] As shown in Figures 5-6 , as a preferred mode of the present application: in the S2, the dynamic model of the mobile robot system is simplified to a two-dimensional plane motion model of pure rolling motion, the motion of the mobile robot system is through a tracked mobile chassis, and the motion equation of the dynamic model is defined as: (1) In formula (1), is the horizontal coordinate of the mobile robot centroid in the two-dimensional plane coordinate system, is the vertical coordinate of the mobile robot centroid in the two-dimensional plane coordinate system, is the instantaneous orientation angle of the mobile robot, is the linear velocity of the right track, is the linear velocity of the left track, is the track wheelbase, is time; According to the centroid reference state of the mobile robot on the reference trajectory and the centroid actual state on the actual trajectory , the state error matrix of the actual centroid of the mobile robot and the reference centroid is obtained: (2) In formula (2), is the linear velocity of the reference trajectory, is the linear velocity of the actual trajectory; The state error matrix is taken as the state input, and the velocity commands of the two tracks are taken as the control output, and global path planning is performed through a trajectory tracking algorithm.

[0021] Specifically, the embodiment simplifies the motion of the tracked mobile robot system with a tracked mobile chassis into pure rolling motion on a plane, the centroid of the tracked mobile robot system coincides with the geometric center of its body and counterclockwise turning is the positive direction, so as to obtain a dynamic model of the tracked mobile robot system (as shown in Figure 5 ), according to the kinematic principle, the horizontal coordinate, the vertical coordinate and the rotation angle of the centroid of the tracked mobile robot system changing with time are obtained, the horizontal coordinate, the vertical coordinate and the rotation angle equations of the centroid of the tracked mobile robot on the reference trajectory and the actual trajectory are obtained, and a state error matrix of the actual centroid of the tracked mobile robot and the reference centroid in the coordinate system (as shown in Figure 6 ) is obtained; the state error matrix is taken as the input and the velocity command of the two sides of the tracked mobile robot is taken as the output for global path planning; the embodiment provides accurate and stable motion reference for subsequent global path planning.

[0022] As a preferred mode of the application: the trajectory tracking algorithm adopts an MPC model predictive control algorithm, and the specific global path planning method comprises the following steps: S2.1, a state prediction model of the tracked mobile robot system is established by discretizing the dynamic model of the tracked mobile robot system: (4) In formula (4), is a state vector of the tracked mobile robot system at time t, is a control input vector at time t, is a state transition matrix, is a control input matrix; S2.2, a target function is constructed according to the error between the predicted state output and the actual state output of the tracked mobile robot system: (5) In formula (5), is a state error weight matrix, is a control increment weight matrix, is the length of the prediction time domain, is the length of the control time domain, is a relaxation factor weight coefficient, is a relaxation factor, is a predicted value of the actual state of the system at time t, is an estimated value of the reference state at time t, is a control increment at time t for time t+1; ​​​​​​​​S2.3, in each control cycle, predicting a state sequence of the mobile robot system in the future based on the current state, and solving a target function to generate an optimal control sequence S2.4, taking a first control increment S2.4, taking a first control increment updating the control instruction outputting the control instruction to the tracked mobile chassis to control the movement of the mobile robot system, and synchronously acquiring the actual state of the mobile robot system feedback to the next control cycle.

[0023] Specifically, the embodiment predicts the system state through the MPC model predictive control algorithm, and constructs a target function according to the error between the predicted output and the real state output of the system. The target function is constructed by adding a relaxation factor to prevent the occurrence of a calculation failure due to no solution, thereby providing a low-complexity and high-real-time path tracking framework for global path planning. When the mobile robot system moves, the state information is fed back in real time to dynamically correct the planned path, thereby effectively improving the anti-interference ability of the system.

[0024] As shown in Figure 7 , as a preferred mode of the present application: in the S4, the local obstacle-avoiding method adopts the A* algorithm, and the specific local path planning method is: S4.1, setting multiple temporary path points on the side and back of the leaking device; S4.2, taking the current mobile robot position as the starting point and the first temporary path point as the ending point, generating a detour path close to the contour of the leaking device through the A* algorithm based on the constraint of the expanded obstacle region; S4.3, controlling the mobile robot system to move to the temporary path point according to the detour path, and collecting the infrared image and position data of the leakage point at the current temporary path point; S4.4, activating the next temporary path point after completing data collection, and repeating steps S4.1-S4.3 until all temporary path points are traversed; S4.5, when the data collection of all temporary path points is completed, controlling the mobile robot to return to the trajectory interruption position to continue global inspection.

[0025] Specifically, the embodiment detects that the GIS device leaks when tracking the global trajectory, triggers the local path planning to detour the leaking device for data collection, temporarily deviates from the original path when detecting gas leakage, triggers the local path planning (such as Figure 7 ), issues temporary path points behind the GIS device, plans a detour path using the A* algorithm, and detours along the device to the temporary path point behind the GIS device (such as Figure 7 ​In the embodiment, after the data acquisition is completed, the robot returns to the track break position of the original path (as shown in Figure 7 In the embodiment, the safety margin is reserved in the expansion area to avoid the robot scratching the equipment, the full surface of the equipment is covered by the combination of the side / back path points, the precise positioning of the leakage point position is realized, the local obstacle circumvention and the global path smooth connection are connected, and the continuity of the leakage detection is ensured.

[0026] Embodiment three As a preferred mode of the present application: in the data processing module, the preset leakage level judgment method adopts a hierarchical decision matrix, the hierarchical decision matrix is obtained by weighting two parts of leakage area proportion and diffusion speed, and the specific formula is: (6) In formula (6), is the leakage area proportion factor weight, is the diffusion speed factor weight, =1, the weight distribution is dynamically adjusted according to environmental parameters, and the environmental parameters include equipment density and personnel flow frequency; The data processing module determines the leakage level according to the threshold interval in which the leakage level score is located, and outputs the determination result to the data management module.

[0027] Specifically, as shown in Figure 8 , it is the overall flow diagram for determining the severity level of the leakage event in the embodiment. The infrared image of the leakage point is obtained, then the leakage area proportion is calculated by the leakage area region / total interface area, the diffusion speed is calculated by the frame area change rate of the continuous 5 frames, and then the leakage level score is calculated by formula (6) to comprehensively evaluate the leakage level. The weight distribution is adjusted according to the equipment density and the personnel flow frequency, which can adapt to the risk characteristics of different areas of the substation.

[0028] As shown in Figure 9 , it is the leakage level evaluation result diagram provided by the embodiment. The leakage area threshold of the embodiment is set to 5000, and the leakage speed threshold is set to 20000. The specific calculation is as follows: (7) In formula (7), is the average leakage area, is the total leakage area, f is the total frame number, is the average leakage speed, is the total leakage speed, is the leakage speed score, is the leakage speed threshold, is the leakage area score, The leakage area threshold value; based on formula (6), the area ratio factor weight and the diffusion speed factor weight are each taken as 0.5 to calculate the leakage level score, when the leakage level score is less than or equal to 1, then it is determined that it is a small range leakage; when the leakage level score is greater than 1 and less than or equal to 3, it is determined that it is a medium range leakage; when the leakage level score is greater than 3, it is determined that it is a large range leakage.

[0029] Those skilled in the art will understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0030] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks. Figure 1 The functions specified in one or more flows and / or blocks.

[0031] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction devices that implement the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks. Figure 1 The functions specified in one or more flows and / or blocks.

[0032] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a device for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks. Figure 1steps of the functions specified in the block or blocks.

[0033] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the preferred embodiments by those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are intended to encompass within their scope all such variations and modifications as are included within the scope of the application.

[0034] It is apparent that those skilled in the art can make various changes and modifications to the application without departing from the spirit and scope of the application. It is therefore intended to include all such changes and modifications in the scope of the application recited in the claims and their equivalents.

Claims

1. A GIS equipment SF6 gas leakage detection robot system, characterized in that, The system comprises a mobile robot system and a leakage detection management system; The mobile robot system comprises a mobile robot body, a tracked mobile chassis, a visible light camera, a SF6 gas cloud infrared imager, a navigation control module, a power supply management module, a communication interface and a gimbal mechanism mounted on the body; The tracked mobile chassis is installed at the bottom of the mobile robot body and is used for autonomous movement along a navigation path in a GIS device area; the visible light camera and the SF6 gas cloud infrared imager are integrated on the gimbal mechanism and are used for collecting visible light images and SF6 gas leakage infrared images of the GIS device respectively; the gimbal mechanism is installed at the top front end of the mobile robot body and is used for horizontal rotation and pitch adjustment to adjust the detection angle; the SLAM laser radar is installed at the top of the mobile robot body and is used for real-time scanning of the environment and construction of a GIS device area point cloud map; the navigation control module is in communication connection with the tracked mobile chassis and the laser radar, is used for executing planned movement path and leakage location according to map data, and controls the movement of the tracked mobile chassis; the power supply management module comprises a lithium battery pack, a power monitoring unit and a power display unit, is used for monitoring the battery voltage, current, power and remaining endurance time, and displays the current remaining power in real time; the communication interface supports 4G / 5G and Wi-Fi protocols and is used for real-time data transmission with the leakage detection management system; The leakage detection management system comprises a communication module, a data processing module, a data management module and a user interface module; The communication module receives data packets transmitted by the mobile robot system, and the data packets contain visible light video streams, SF6 gas leakage infrared images and leakage location coordinate data packets; the data processing module is connected with the communication module, is used for analyzing leakage event information in the data packets, and determines the severity level of the leakage event according to a preset leakage level determination method; the data management module is connected with the data processing module, is used for storing the leakage event information and the level determination result in a log; the user interface module integrates a multi-tab display interface, including a real-time monitoring page, a location monitoring page and a data report page, is used for visually showing the leakage event information and the leakage location to the user, and provides historical leakage event information query and viewing functions.

2. The GIS equipment SF6 gas leakage detection robot system according to claim 1, characterized in that: A method for executing planned movement path and locating leakage position in the navigation control module comprises: S1, acquiring a GIS device area point cloud map through a SLAM laser radar, setting basic path points for all GIS devices and device channel, and generating a global inspection trajectory through linear interpolation; S2, constructing a dynamic model of the mobile robot system, performing global path planning through a trajectory tracking algorithm based on the global inspection trajectory and the dynamic model, and controlling the mobile robot system to perform global inspection; S3, when the SF6 gas cloud infrared imager detects gas leakage, activating local path planning, marking the leakage device as an obstacle, calculating an inflation distance based on the device half-width, the mobile robot radius and the safety margin, and taking the inflated obstacle area as a constraint boundary for local path planning; S4, temporary path points are set on the side and back of the leaking device, and a detour path close to the contour of the device is generated outside the inflation area by a local obstacle avoidance algorithm to control the mobile robot system to detour to the temporary path point to collect infrared images and position data of the leakage point; S5, the trajectory interruption position of the mobile robot system and the state of the mobile robot are recorded, and after the data collection is completed, the mobile robot system is controlled to return to the interruption position and continue global inspection.

3. The GIS equipment SF6 gas leakage detection robot system according to claim 2, characterized in that: In the S2, the dynamic model of the mobile robot system is simplified as a two-dimensional plane motion model of pure rolling motion, and the motion of the mobile robot system is realized through a tracked mobile chassis, and the motion equation of the dynamic model is defined as: （1） In equation (1), is the horizontal coordinate of the center of the mobile robot in a two-dimensional plane coordinate system, is the vertical coordinate of the center of the mobile robot in a two-dimensional plane coordinate system, is the instantaneous orientation angle of the mobile robot, is the linear velocity of the right track, is the linear velocity of the left track, is the track wheel base, is time; According to the centroid reference state of the mobile robot on the reference trajectory With the centroid actual state on the actual trajectory Obtain the state error matrix of the mobile robot centroid actual and reference centroid （2） In equation (2), is the linear velocity of the reference trajectory, is the linear velocity of the actual trajectory; The state error matrix is taken as the state input, and the speed command of the two sides of the track is taken as the control output, and the global path planning is realized through a trajectory tracking algorithm.

4. The GIS equipment SF6 gas leakage detection robot system according to claim 3, characterized in that: The trajectory tracking algorithm adopts an MPC model predictive control algorithm, and the specific global path planning method includes: S2.1, the state prediction model of the mobile robot system is established by discretizing the dynamic model of the mobile robot system: （4） In equation (4), is the state vector of the mobile robot system at time instant is the control input vector at time instant is the state transition matrix, is the control input matrix; S2.2, a target function is constructed according to the error between the predicted state output and the actual state output of the mobile robot system: （5） In equation (5), is a state error weight matrix, is a control increment weight matrix, is a prediction horizon length, is a control horizon length, is a relaxation factor weight coefficient, is a relaxation factor, is is a prediction value of the system actual state at time is a prediction value of the system actual state at time is is an estimation value of the reference state at time is an estimation value of the reference state at time is is a control increment at time is a control increment at time S2.3, in each control period, predict a future sequence of states of the mobile robot system based on the current state and solve the objective function to generate an optimal control sequence S2.3, in each control period, predict a future sequence of states of the mobile robot system based on the current state and solve the objective function to generate an optimal control sequence S2.3, in each control period, predict a future sequence of states of the S2.4, take the first control increment update control instructions output the control instructions to the tracked mobile chassis, control the motion of the mobile robot system, and synchronously acquire the actual state of the mobile robot system feedback to the next control cycle.

5. The GIS equipment SF6 gas leakage detection robot system according to claim 2, characterized in that: In the S4, the local obstacle avoidance method adopts an A* algorithm, and the specific local path planning method is: S4.1, multiple temporary path points are set on the side and back of the leaking device; S4.2, the current mobile robot position is taken as the starting point, and the first temporary path point is taken as the end point, and a detour path close to the contour of the leaking device is generated through an A* algorithm based on the constraint of the inflated obstacle area; S4.3, the mobile robot system is controlled to move to the temporary path point according to the detour path, and infrared images and position data of the leakage point are collected at the current temporary path point; S4.4, after the data collection is completed, the next temporary path point is activated, and steps S4.1-S4.3 are repeated until all temporary path points are traversed; S4.5, when the data collection of all temporary path points is completed, the mobile robot is controlled to return to the trajectory interruption position to continue global inspection.

6. The GIS equipment SF6 gas leakage detection robot system according to claim 1, characterized in that: In the data processing module, a hierarchical decision matrix is adopted as the preset leakage level determination method, and the hierarchical decision matrix is obtained by weighting the leakage area ratio and the diffusion speed, and the specific formula is: （6） In formula (6), is a leakage area ratio factor weight, is a diffusion speed factor weight, = 1, the weight distribution is dynamically adjusted according to environmental parameters, including device density and personnel flow frequency; The data processing module determines the leakage level according to the threshold interval in which the leakage level score is located, and outputs the determination result to the data management module.

Images