Robot inspection task configuration method and system based on substation panoramic perception

Abstract

The present invention provides a robot inspection task configuration method and system based on substation panoramic perception. The present invention utilizes the spatial vector of the robot pan-tilt center and the inspection point to realize automatic calculation of the best inspection stop point, the best pan-tilt posture and the best zoom multiple of the inspection robot; it solves the difficult problem that routine inspection tasks need to be manually configured, effectively reduces the workload of on-site operation and maintenance personnel in inspection task configuration, and improves configuration efficiency; in addition, the inspection task configuration is linked with the substation panoramic perception data, and the optimal configuration data of the inspection robot is quickly matched based on the inspection point, so that the robot can collect inspection data from the best docking position and observation angle, thereby ensuring the quality of inspection data collection.

Description

Technical Field

[0001] The present invention relates to the field of substation inspection technology, and in particular to a robot inspection task configuration method and system based on substation panoramic perception. Background Art

[0002] Currently, using robots for routine inspections of power grid equipment requires operators to pre-configure inspection tasks. During task configuration, operators remotely control the robot along the inspection route to the vicinity of the power equipment to be inspected and dock. They then adjust the pan / tilt (Pan / Tilt) to align the detection sensors with the inspection points of each device in the current area. The robot's docking point position and pan / tilt preset position data corresponding to the current inspection point are stored in the inspection task. Once the inspection point data at the current docking point is stored, the operator remotely controls the robot to traverse all inspection points included in the inspection task, following the aforementioned method, thus completing the configuration of the inspection task.

[0003] Due to the numerous devices and inspection points within a substation, existing inspection task configuration methods suffer from the high workload and low efficiency of manually configuring on-site inspection points, hindering the effectiveness of robotic inspections. Furthermore, when robots perform specialized inspections on a single device, it is difficult to ensure optimal viewing of the device's operating status. Summary of the Invention

[0004] The purpose of the present invention is to provide a robot inspection task configuration method and system based on substation panoramic perception, aiming to solve the problems of large configuration workload and low configuration efficiency in the inspection task configuration in the existing technology, realize the automatic configuration of inspection tasks, and improve the quality of data collection.

[0005] To achieve the above technical objectives, the present invention provides a method for configuring robot inspection tasks based on substation panoramic perception, the method comprising the following operations:

[0006] Establish a three-dimensional spatial model of the substation and perform semantic processing on the power equipment in the model;

[0007] Generate a list of inspection points and simulate inspection operations through the robot's 3D model;

[0008] Obtain three-dimensional spatial information of inspection points within the effective working distance range of the robot inspection sensor, and construct a spatial vector between the center of the robot pan / tilt platform and each inspection point;

[0009] Based on the space vector, the optimal stop point position, optimal pan / tilt posture and optimal zoom ratio of the robot are determined to form the robot inspection task configuration data.

[0010] Preferably, the method further comprises:

[0011] The clustering algorithm is used to merge the stop points, and the optimal gimbal posture and optimal zoom ratio corresponding to the inspection points covered by the merged points are calculated to form the final robot routine inspection task configuration data.

[0012] Preferably, the semantic processing of the power equipment in the model specifically includes: associating the existing substation panoramic perception data and the power equipment semantic information with the power equipment in the model to obtain the power equipment semantic information.

[0013] Preferably, the optimal stopping point position P and the optimal gimbal posture T are determined as follows:

[0014] P = argmin(P k →|n k |),k=1,2,L m

[0015]

[0016] Among them, the symbol → indicates the corresponding; n k is the vector connecting the inspection point and the center point of the PTZ, n i P is the plane normal vector of the inspection point of the power equipment to be inspected; k 、T k They are the robot pose sequence and the gimbal pose sequence respectively.

[0017] Preferably, the optimal zoom factor is determined as follows:

[0018]

[0019] Among them, n k is the vector connecting the inspection point and the center point of the PTZ, and the image magnification K can be selected according to actual needs.

[0020] The present invention also provides a robot inspection task configuration system based on substation panoramic perception, the system comprising:

[0021] The 3D spatial modeling module is used to build a 3D spatial model of the substation and perform semantic processing on the power equipment in the model;

[0022] The simulation inspection module is used to generate a list of inspection points and simulate the inspection operation through the robot's three-dimensional model;

[0023] A space vector construction module is used to obtain three-dimensional spatial information of inspection points within the effective working distance range of the robot inspection sensor and construct a space vector between the center of the robot pan-tilt platform and each inspection point;

[0024] The inspection task configuration module is used to determine the robot's optimal stop point position, optimal pan-tilt posture and optimal zoom ratio based on the space vector to form the robot's inspection task configuration data.

[0025] Preferably, the system further comprises:

[0026] The stop point merging module is used to merge the stop points using a clustering algorithm, calculate the optimal gimbal posture and optimal zoom ratio corresponding to the inspection points covered by the merged points, and form the final robot routine inspection task configuration data.

[0027] Preferably, the optimal stopping point position P and the optimal gimbal posture T are determined as follows:

[0028] P = argmin(P k →|n k |),k=1,2,L m

[0029]

[0030] Among them, the symbol → indicates the corresponding; n k is the vector connecting the inspection point and the center point of the PTZ, n i P is the plane normal vector of the inspection point of the power equipment to be inspected; k 、T k They are the robot pose sequence and the gimbal pose sequence respectively;

[0031] The optimal zoom ratio is determined as follows:

[0032]

[0033] Among them, n k is the vector connecting the inspection point and the center point of the PTZ, and the image magnification K can be selected according to actual needs.

[0034] The present invention also provides a terminal device, which includes a processor and a memory, the processor is used to implement various instructions; the memory is used to store multiple instructions, and the instructions are suitable for being loaded and executed by the processor to implement the robot inspection task configuration method based on substation panoramic perception.

[0035] The present invention also provides a computer-readable storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded and executed by a processor of a terminal device for the method for configuring robot inspection tasks based on panoramic perception of substations.

[0036] The effects provided in the summary of the invention are only the effects of the embodiments, not all the effects of the invention. One of the above technical solutions has the following advantages or beneficial effects:

[0037] Compared with the existing technology, the present invention uses the spatial vector between the robot's pan-tilt center and the inspection point to automatically calculate the inspection robot's optimal stopping point, optimal pan-tilt posture, and optimal zoom ratio. This solves the problem of manual configuration required for routine inspection tasks, effectively reduces the workload of on-site operation and maintenance personnel in configuring inspection tasks, and improves configuration efficiency.

[0038] The present invention links the inspection task configuration with the panoramic perception data of the substation, quickly matches the optimal configuration data of the inspection robot based on the inspection points, and enables the robot to collect inspection data from the best docking position and observation angle, thereby ensuring the quality of inspection data collection. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of inspection points for determining the effective working distance range of a robot inspection sensor provided in an embodiment of the present invention;

[0040] Figure 2 Schematic diagram of the space vectors between the center of the robot pan-tilt platform and each inspection point provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to clearly illustrate the technical features of the present solution, the present invention is described in detail below through specific implementation methods and in conjunction with the accompanying drawings. The disclosure below provides many different embodiments or examples for realizing different structures of the present invention. In order to simplify the disclosure of the present invention, the components and settings of specific examples are described below. In addition, the present invention may repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplicity and clarity and does not itself indicate the relationship between the various embodiments and / or settings discussed. It should be noted that the components illustrated in the accompanying drawings are not necessarily drawn to scale. The present invention omits descriptions of well-known components and processing technologies and processes to avoid unnecessarily limiting the present invention.

[0042] The following describes in detail a method and system for configuring robot inspection tasks based on substation panoramic perception provided by an embodiment of the present invention in conjunction with the accompanying drawings.

[0043] like Figure 1 As shown, the present invention discloses a method for configuring robot inspection tasks based on substation panoramic perception, the method comprising the following operations:

[0044] S1. Establish a three-dimensional spatial model of the substation and perform semantic processing on the power equipment in the model;

[0045] A 3D spatial model of the substation is created using 3D scanning modeling methods. The existing substation panoramic perception data and power equipment semantic information are then associated with the power equipment in the model, thereby achieving semantic processing of the 3D spatial model. 3D scanning modeling methods include 3D scanning and robotic 3D-SLAM mapping.

[0046] S2. Generate a list of inspection points and simulate the inspection operation through the robot's three-dimensional model;

[0047] Based on the semantic information of the equipment to be inspected, its location within the substation's 3D spatial model is determined. For example, on-site maintenance personnel can use the semantic information of the equipment to be inspected to select the equipment within the model. The 3D spatial information of the inspection points of the equipment to be inspected is then added to the inspection task, generating a list of inspection points. This 3D spatial information includes the coordinates and spatial posture of the inspected equipment. A 3D robot model is then added to the 3D substation model, allowing it to perform simulated inspections along the inspection route.

[0048] S3. Obtain three-dimensional spatial information of inspection points within the effective working distance range of the robot inspection sensor, and construct a spatial vector between the center of the robot pan / tilt platform and each inspection point;

[0049] During the inspection robot simulation operation, combined with Figure 1 and Figure 2 According to the effective working distance parameters of the inspection sensor installed on the robot, the three-dimensional spatial information of the inspection points within the effective working radius of the inspection sensor is selected from the generated inspection point list, and the space vector between the center of the robot gimbal and each inspection point is constructed in real time, that is, the line vector between the gimbal center and the inspection point.

[0050] S4. Determine the optimal stop position, optimal pan / tilt posture, and optimal zoom ratio of the robot based on the spatial vector to form robot inspection task configuration data;

[0051] The method for determining the optimal stopping point position P and the optimal gimbal posture T of the robot is specifically as follows:

[0052] P = argmin(P k →|n k |),k=1,2,L m

[0053]

[0054] Among them, the symbol → means "corresponds to"; n k is the vector connecting the inspection point and the center point of the PTZ, n i P is the plane normal vector of the inspection point of the power equipment to be inspected. k 、Tk They are the robot pose sequence and the gimbal pose sequence respectively.

[0055] exist Figure 2 In, p k ,P k ,T k k=1, 2, L m are respectively the sequence of robot gimbal center points p and the corresponding robot pose P and gimbal posture T toward the inspection point during the simulation inspection.

[0056] Based on the robot's optimal stop point position P and the image magnification K when collecting images at this position, the optimal zoom factor Z required for inspection data collection can be obtained as follows:

[0057]

[0058] The image magnification K can be selected according to actual needs.

[0059] S5. Establish a three-dimensional spatial model of the substation and perform semantic processing on the power equipment in the model;

[0060] To reduce the number of stops, a clustering algorithm is used to merge stops whose distance is less than a manually set threshold. The previously described method is then used to recalculate the gimbal posture and zoom factor corresponding to the inspection points covered by the merged points, thereby forming the final robot routine inspection task configuration data. The clustering algorithm includes distance clustering and K-means clustering.

[0061] When the inspection robot uses this configuration data to perform inspections, configuration deviations caused by errors in the substation's 3D spatial modeling can be compensated using pan-tilt visual servoing or manual fine-tuning. The inspection robot can also perform special inspections of specific equipment or inspection points within the substation, such as during sequential control operations to monitor the on / off status of a specific switch within the substation.

[0062] On-site operation and maintenance personnel can use the device semantic information to directly select the corresponding equipment or inspection points in the model, and then query the corresponding stop points, gimbal posture and zoom ratio from the optimal inspection task data obtained in step S4 above. After that, the inspection task points are formed and the path planning algorithm is used to plan the robot's operation path, which can be sent to the inspection robot for execution.

[0063] This embodiment utilizes the three-dimensional spatial model of the substation and panoramic perception data to automatically calculate the optimal stopping point, optimal pan-tilt posture, and optimal zoom ratio for robot inspections, thereby realizing the automatic configuration of routine inspection tasks and effectively reducing the workload of on-site operation and maintenance personnel in configuring inspection tasks.

[0064] The embodiment of the present invention further discloses a robot inspection task configuration system based on substation panoramic perception, the system comprising:

[0065] The 3D spatial modeling module is used to build a 3D spatial model of the substation and perform semantic processing on the power equipment in the model;

[0066] The simulation inspection module is used to generate a list of inspection points and simulate the inspection operation through the robot's three-dimensional model;

[0067] A space vector construction module is used to obtain three-dimensional spatial information of inspection points within the effective working distance range of the robot inspection sensor and construct a space vector between the center of the robot pan-tilt platform and each inspection point;

[0068] An inspection task configuration module is used to determine the optimal stop point position, optimal pan / tilt posture, and optimal zoom ratio of the robot based on the space vector to form robot inspection task configuration data;

[0069] The stop point merging module is used to merge the stop points using a clustering algorithm, calculate the optimal gimbal posture and optimal zoom ratio corresponding to the inspection points covered by the merged points, and form the final robot routine inspection task configuration data.

[0070] The implementation of the above system has been described in the method described above and will not be repeated here.

[0071] An embodiment of the present invention also discloses a terminal device, which includes a processor and a memory, the processor is used to implement various instructions; the memory is used to store multiple instructions, and the instructions are suitable for the processor to load and execute the robot inspection task configuration method based on substation panoramic perception as described above.

[0072] An embodiment of the present invention also discloses a computer-readable storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded and executed by a processor of a terminal device to perform the aforementioned robot inspection task configuration method based on substation panoramic perception.

[0073] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements 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 robot inspection task configuration method based on substation panoramic perception, characterized in that: The method comprises the following operations: Establish a three-dimensional spatial model of the substation and perform semantic processing on the power equipment in the model; Generate a list of inspection points and simulate inspection operations through the robot's 3D model; Obtain the three-dimensional spatial information of the inspection points within the effective working distance range of the robot inspection sensor, and construct the spatial vector between the robot pan-tilt center and each inspection point; Based on the space vector, determine the optimal stop point position, optimal gimbal posture and optimal zoom multiple of the robot to form robot inspection task configuration data; The determination of the optimal stopping point position P and the optimal gimbal posture T are as follows: P=argmin(P k →|n k |),k=1,2,…m Among them, the symbol → indicates that it corresponds to; n k is the vector connecting the inspection point and the center point of the PTZ, n i P is the plane normal vector of the inspection point of the power equipment to be inspected; k 、T k They are the robot pose sequence and the gimbal pose sequence respectively; The optimal zoom ratio is determined as follows: Among them, n k is the line vector between the inspection point and the center point of the PTZ, and the image magnification K is selected according to actual needs.

2. A robot inspection task configuration method based on substation panoramic perception according to claim 1, characterized in that: The method further comprises: The clustering algorithm is used to merge the stop points, and the optimal gimbal posture and optimal zoom ratio corresponding to the inspection points covered by the merged points are calculated to form the final robot routine inspection task configuration data.

3. A robot inspection task configuration method based on substation panoramic perception according to claim 1, characterized in that: The semantic processing of the power equipment in the model specifically includes: associating the existing substation panoramic perception data and the power equipment semantic information with the power equipment in the model to obtain the power equipment semantic information.

4. A robot inspection task configuration system based on substation panoramic perception, characterized in that: The system comprises: The three-dimensional space modeling module is used to build a three-dimensional spatial model of the substation and perform semantic processing on the power equipment in the model; The simulation inspection module is used to generate a list of inspection points and simulate the inspection operation through the robot's three-dimensional model; A space vector construction module is used to obtain the three-dimensional space information of the inspection points within the effective working distance range of the robot inspection sensor, and to construct the space vector between the robot pan-tilt center and each inspection point; An inspection task configuration module is used to determine the optimal stop point position, optimal gimbal posture and optimal zoom multiple of the robot based on the space vector to form robot inspection task configuration data; The determination of the optimal stopping point position P and the optimal gimbal posture T are as follows: P=argmin(P k →|n k |),k=1,2,…m Among them, the symbol → indicates that it corresponds to; n k is the vector connecting the inspection point and the center point of the PTZ, n i P is the plane normal vector of the inspection point of the power equipment to be inspected; k 、T k They are the robot pose sequence and the gimbal pose sequence respectively; The optimal zoom ratio is determined as follows: Among them, n k is the line vector between the inspection point and the center point of the PTZ, and the image magnification K is selected according to actual needs.

5. A robot inspection task configuration system based on substation panoramic perception according to claim 4, characterized in that: The system further comprises: The docking point merging module is used to merge the docking points using a clustering algorithm, calculate the optimal gimbal posture and optimal zoom ratio corresponding to the inspection points covered by the merged points, and form the final robot routine inspection task configuration data.

6. A terminal device, comprising a processor and a memory, wherein the processor is used to implement each instruction; and the memory is used to store multiple instructions, characterized in that: The instructions are suitable for being loaded by a processor and executing the robot inspection task configuration method based on substation panoramic perception as described in any one of claims 1-3.

7. A computer-readable storage medium storing a plurality of instructions, characterized in that: The instructions are suitable for being loaded by a processor of a terminal device and executing the robot inspection task configuration method based on substation panoramic perception as described in any one of claims 1-3.

Images