CN117313969A - Substation robot inspection path optimization method and device - Google Patents
Substation robot inspection path optimization method and device Download PDFInfo
- Publication number
- CN117313969A CN117313969A CN202311256853.7A CN202311256853A CN117313969A CN 117313969 A CN117313969 A CN 117313969A CN 202311256853 A CN202311256853 A CN 202311256853A CN 117313969 A CN117313969 A CN 117313969A
- Authority
- CN
- China
- Prior art keywords
- sensor
- information
- inspection
- obstacle
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 139
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000005457 optimization Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 31
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 238000004458 analytical method Methods 0.000 claims description 17
- 230000035945 sensitivity Effects 0.000 claims description 14
- 230000011218 segmentation Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 238000007728 cost analysis Methods 0.000 claims description 4
- 238000011897 real-time detection Methods 0.000 claims description 2
- 230000002452 interceptive effect Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 description 9
- 238000000605 extraction Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000010813 municipal solid waste Substances 0.000 description 1
- 238000004540 process dynamic Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a substation robot inspection path optimization method and device, and relates to the technical field of path optimization, wherein the method comprises the following steps: establishing a grid map model of a substation environment map by using a grid method, and mapping equipment in a substation into the grid map model to obtain a plurality of target points; acquiring a patrol starting point of the substation robot, and performing global path planning according to the patrol starting point and a plurality of target points; when the substation robot carries out a patrol task, detecting the non-fixed obstacle in real time; performing influence range identification on a corresponding target point in the path according to the detection result, and determining obstacle influence information; based on the detection result and the obstacle influence information, global path planning is adjusted, the problems that in the prior art, path planning is unreasonable and real-time performance is poor due to insufficient rigor and insufficient completeness of inspection work of a substation robot are solved, and inspection efficiency of the substation robot is improved.
Description
Technical Field
The invention relates to the technical field of path optimization, in particular to a substation robot inspection path optimization method and device.
Background
In an electrical power system, a substation is a vital facility, and its operating state directly affects the stability and reliability of the power supply. In order to ensure the normal operation of the substation, equipment inspection is usually required periodically. However, due to the complex environment of the transformer substation, manual inspection is not only inefficient, but also has certain potential safety hazards. Therefore, it has become a trend to use robots for inspection. However, the existing substation robot inspection technology still has some problems, mainly represented by unreasonable inspection path planning, and when the methods process dynamic changes in complex environments, the real-time performance is poor, the inspection path is difficult to adjust adaptively, so that the inspection efficiency is low, and meanwhile, path conflicts, equipment damages and the like can be caused. Therefore, aiming at the optimization problem of the inspection path of the substation robot, the novel path optimization method is provided, and has important practical significance.
The problem that the route planning is unreasonable and the real-time performance is poor due to insufficient rigor and insufficient completeness of inspection work of the substation robot in the prior art, so that the inspection efficiency of the final substation robot is low.
Disclosure of Invention
The application provides a substation robot inspection path optimization method and device, solves the problems of unreasonable path planning and poor instantaneity caused by insufficient rigorous inspection work and insufficient completeness of the substation robot in the prior art, and improves inspection efficiency of the substation robot.
In view of the above, the present application provides a substation robot tour path optimization method.
In a first aspect, the present application provides a substation robot inspection path optimization method, where the method includes: establishing a grid map model of a substation environment map by using a grid method, and mapping equipment in a substation into the grid map model to obtain a plurality of target points; acquiring a patrol starting point of the substation robot, and performing global path planning according to the patrol starting point and a plurality of target points; when the substation robot carries out a patrol task, detecting the non-fixed obstacle in real time; performing influence range identification on a corresponding target point in the path according to the detection result, and determining obstacle influence information; and adjusting the global path planning based on the detection result and the obstacle influence information.
In a second aspect, the present application provides a substation robot inspection path optimizing apparatus, the apparatus including: the target point acquisition module: establishing a grid map model of a substation environment map by using a grid method, and mapping equipment in a substation into the grid map model to obtain a plurality of target points; and a path planning module: acquiring a patrol starting point of the substation robot, and performing global path planning according to the patrol starting point and a plurality of target points; and a patrol task module: when the substation robot carries out a patrol task, detecting the non-fixed obstacle in real time; obstacle influencing module: performing influence range identification on a corresponding target point in the path according to the detection result, and determining obstacle influence information; and a planning and adjusting module: and adjusting the global path planning based on the detection result and the obstacle influence information.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the substation robot inspection path optimization method and device, the grid map model of the substation environment map is established through the grid method, equipment in the substation is mapped into the grid map model to obtain a plurality of target points, the inspection starting point of the substation robot is obtained, global path planning is conducted according to the inspection starting point and the plurality of target points, when the substation robot performs inspection tasks, real-time detection is conducted on non-fixed obstacles, then the influence range identification is conducted on the corresponding target points in the paths according to detection results, obstacle influence information is determined, finally global path planning is adjusted based on the detection results and the obstacle influence information, the problems that in the prior art, the inspection work of the substation robot is unreasonable due to insufficient rigor and incomplete path planning, and real-time performance is poor are solved, and improvement of inspection efficiency of the substation robot is achieved.
Drawings
Fig. 1 is a schematic flow chart of a substation robot inspection path optimization method;
fig. 2 is a schematic structural diagram of a substation robot inspection path optimizing device.
Reference numerals illustrate: the system comprises a target point acquisition module 11, a path planning module 12, a patrol task module 13, a barrier influencing module 14 and a planning and adjusting module 15.
Detailed Description
According to the substation robot inspection path optimization method and device, a grid map model of a substation environment map is established through a grid method, equipment in a substation is mapped into the grid map model to obtain a plurality of target points, an inspection starting point of the substation robot is obtained, global path planning is conducted according to the inspection starting point and the plurality of target points, when the substation robot performs inspection tasks, non-fixed obstacles are detected in real time, then the corresponding target points in the paths are identified according to detection results, obstacle influence information is determined, and finally global path planning is adjusted based on detection results and the obstacle influence information. The method solves the problems of unreasonable path planning and poor instantaneity caused by insufficient rigorous and incomplete inspection work of the substation robot in the prior art, and improves inspection efficiency of the substation robot.
Example 1
As shown in fig. 1, the application provides a substation robot inspection path optimization method and device, and the method includes:
establishing a grid map model of a substation environment map by using a grid method, and mapping equipment in a substation into the grid map model to obtain a plurality of target points;
the grid method is a map modeling method, and the working environment of the AGV is subjected to unit segmentation and is represented by square blocks with equal size. And establishing an environment map of the transformer substation, namely a grid map model by a grid method. The grid map model is used for dividing the geographic space of the transformer substation into grids with equal sizes, and endowing each grid with corresponding attribute information. The size of the grid is determined and affects the accuracy and detail of the map. Determining a mapping range, adjusting the mapping range into a whole transformer substation, mapping the transformer substation, acquiring data of a geographical space range of the transformer substation, acquiring position information of equipment, topography, buildings and the like in the transformer substation, converting the collected data into a grid form to obtain grid data, filling the grid data into a grid corresponding to the grid data to obtain a grid map model of a transformer substation environment map, marking equipment of the transformer substation to obtain a plurality of marking points, outputting the marking points to obtain a plurality of target points, acquiring the plurality of target points, and providing a data basis for subsequently acquiring a patrol starting point of a transformer substation robot and performing global path planning according to the patrol starting point and the plurality of target points.
Acquiring a patrol starting point of the substation robot, and performing global path planning according to the patrol starting point and a plurality of target points;
the inspection starting point is a fixed point position, the inspection starting point is set according to the charging position of the substation inspection robot, a grid map model of a substation environment map is provided with a mark, and a target point marked as the inspection starting point is acquired to obtain the inspection starting point. Planning a global path according to a plurality of target points, planning the global path, taking rationality of a patrol path into consideration, fully inspecting equipment in a transformer substation in the shortest time, analyzing an optimal path of the target points through a global path planning algorithm, wherein the path planning algorithm comprises but is not limited to Dijkstra algorithm and the like, setting the patrol starting point in the path planning algorithm, inputting other target points into a corresponding algorithm for calculation, carrying out data processing through the path planning algorithm, obtaining a corresponding path, outputting the obtained path, completing global path planning, and providing a data basis for subsequent adjustment of the global path planning based on detection results and barrier influence information.
When the substation robot carries out a patrol task, detecting the non-fixed obstacle in real time;
when the substation robot carries out a patrol task, certain obstacles can appear, the obstacles are divided into fixed obstacles and non-fixed obstacles, the fixed obstacles are some fixed equipment of a substation or some objects which are newly placed by a substation person and the like and cannot move, the fixed obstacles are marked in a grid map model, mark position information is acquired, the mark position information is sent to the patrol robot, the patrol robot can automatically plan a corresponding avoidance route after receiving the position information, and the fixed obstacles are avoided; when the obstacle is a non-fixed obstacle, the non-fixed obstacle is a movable obstacle, such as an electrical equipment element left by a substation worker during operation, some trash and sundries which float into the substation from the outside of the substation, and the like, the non-fixed obstacle can obstruct the robot to carry out inspection, and cannot acquire the stable position of the non-fixed obstacle, and when the non-fixed obstacle in the present situation acquires the position information, the position information of the non-fixed target obstacle may change at the next moment, and cannot be positioned according to the position information at the last moment. Therefore, the robot is required to judge the non-fixed obstacle in real time, an image acquisition device is added to the robot, the image information of the inspection path is acquired through the image acquisition device, the obstacle recognition is carried out according to the image information, the obstacle recognition result is acquired, and the current obstacle is avoided according to the recognition result. By detecting the non-fixed obstacle, the real-time performance of the robot for avoiding the obstacle can be remarkably improved, analysis is performed according to the real-time condition of the inspection path, and the inspection efficiency is improved.
Performing influence range identification on a corresponding target point in the path according to the detection result, and determining obstacle influence information;
after the detection of the obstacle is completed, the influence condition of the obstacle is analyzed, and the obstacle not only can influence the inspection path of the robot, but also can interfere the inspection work of the robot. When an obstacle is on a routing inspection path of a robot, the obstacle on the path needs to be subjected to influence analysis, the position and the state of the obstacle are judged, the position is predicted, the influence range of the obstacle is determined, the movement influence range of the robot is determined according to the influence range, and corresponding path planning adjustment is performed according to the movement influence range. When the obstacle shields the equipment and influences the robot to carry out the inspection work on the equipment, the shielding range of the obstacle is determined according to the information such as the position state of the obstacle, corresponding inspection adjustment is carried out according to the shielding range of the obstacle, the inspection angle of the equipment which influences the obstacle is adjusted, the inspection work on the obstacle is completed, the influence condition of the obstacle which is more accurate can be obtained by determining the influence information of the obstacle, a more reasonable and accurate processing method can be obtained according to the influence condition, and the inspection efficiency of the robot is improved.
And adjusting the global path planning based on the detection result and the obstacle influence information.
And adjusting global path planning according to the detection result and the obstacle influence information, constructing a path planning model according to a path planning algorithm, wherein the constructed path planning model comprises three layers, namely an information input layer, a path processing layer and a path output layer. The information input layer is used for inputting the patrol starting point and the plurality of target points, planning a path at the path processing layer according to the patrol starting point and the plurality of target points to obtain a planned path, performing binarization processing on the detection result and the obstacle influence information, adding the binarization processing result and the obstacle influence information to the path processing layer for processing, adjusting the planned path by the path processing layer according to the detection result and the obstacle influence information to obtain an adjusted planned path, and outputting the adjusted planned path at the path output layer to obtain a final path. The global path planning is adjusted according to the detection result and the obstacle influence information, so that the obtained planned path accords with the real-time path condition, the robot is inspected according to the path, the influence of the obstacle on the robot can be reduced, and the robot inspection efficiency is improved.
Further, the method further comprises:
acquiring patrol equipment information of a plurality of target points, wherein the patrol equipment information comprises patrol equipment coordinates, patrol target parameters and equipment running time;
carrying out inspection classification based on the inspection target parameters and the running time of the equipment to obtain classification information, carrying out inspection switching cost analysis of each class based on each classification information, and determining inspection switching cost among the classes;
and carrying out path optimization by taking the minimum time of the inspection target as the target based on the inspection switching cost, the inspection starting point and the inspection equipment coordinates.
For example, when the target point is inspected, some devices have long running time because the devices of the target point are different, so that the devices need to be inspected for multiple times to ensure safety, the inspection interval time is limited, and some devices have short running time and do not need to be inspected for multiple times. Because the equipment of a plurality of target points is in disorder distribution, when the path planning is carried out on a plurality of equipment needing to be inspected for a plurality of times, the switching cost analysis is involved, namely when the inspection is finished on one equipment, the equipment which is far away but needs to be inspected for a plurality of times is inspected or the equipment which is common equipment but is near to the equipment is inspected, the cost of the equipment which is near to the equipment and the cost of the equipment which is far away can be obtained, the two costs are analyzed, and the option with lower cost is selected for inspection. Acquiring inspection equipment information of a plurality of target points, wherein the inspection equipment information comprises inspection equipment coordinates, inspection target parameters and equipment running time; the inspection target parameters are various parameter information of inspection equipment. Classifying the inspection according to inspection target parameters and equipment running time, for example, classifying the inspection equipment into a plurality of inspection equipment, common inspection equipment and the like, acquiring different classification results according to different classification standards to obtain classification information, analyzing inspection switching cost of each class according to each classification information, determining inspection switching cost of each class, and carrying out path optimization by taking the least whole inspection as a target according to the inspection switching cost, the inspection starting point and the inspection equipment coordinates to provide a data basis for adjusting global path planning based on detection results and obstacle influence information.
Further, the method further comprises:
acquiring initial signal characteristics of a robot;
collecting working signal characteristics of the robot in the inspection process;
acquiring a signal loss value curve based on the working signal characteristics and the initial signal characteristics;
and when the loss value or the fluctuation coefficient of the signal loss value curve reaches a preset threshold value, generating signal interference early warning information.
Due to the complex environment of the substation, there is a large amount of electromagnetic signal interference, which may come from various electrical equipment and facilities. These disturbances can cause disturbances to the wireless communication of the robot, resulting in poor communication or signal loss, thereby affecting the inspection effect of the robot. The method comprises the steps of acquiring an initial signal under a non-working environment of the robot, and extracting signal characteristics of the acquired signal to obtain initial signal characteristics. And acquiring signals of the robot in the inspection process, and extracting features of the signals in the inspection process to obtain working signal features in the inspection process. And comparing and analyzing the initial signal characteristics and the working signal characteristics to obtain a comparison analysis result, and outputting the comparison analysis result to obtain a signal loss curve which represents the signal loss condition of the robot during working. And (3) carrying out threshold setting on the signal loss value to obtain a preset threshold, when the loss value or the fluctuation coefficient of the signal loss value curve reaches the preset threshold, indicating that a large amount of loss conditions exist in the signal, carrying out early warning on the conditions, and generating signal interference early warning information, so that a robot can be timely found and correspondingly processed when the signal is interfered, and the conditions of inspection interruption and the like caused by the signal interference are reduced.
Further, the method further comprises:
acquiring sensor setting information of an interference target point;
based on the inspection target parameters of the interference target points, performing sensitivity matching according to the working signal characteristics and the sensor setting information, and determining cooperative sensor information;
based on the signal interference early warning information and the cooperative sensor information, transmitting a cooperative instruction, wherein the cooperative instruction comprises a patrol target parameter;
and sensing and collecting according to the inspection target parameters through a cooperative sensor, and sending the collected parameters to the robot.
The sensor setting information refers to the setting of the sensor device at the target interference point, and the setting of the sensor parameters is performed on the sensor, and the sensor parameter setting is the sensor setting information. The method comprises the steps of acquiring sensor setting information, performing sensitivity matching on working signal characteristics and the sensor setting information based on the inspection target parameters of interference electricity, acquiring cooperative sensor information, and determining the cooperative sensor information. According to the signal interference early warning information and the cooperative sensor information, the patrol target parameters are added into the cooperative instruction, the cooperative instruction is sent, the cooperative sensor is used for conducting sensing acquisition according to the patrol target parameters, the acquisition parameters are sent to the robot, the robot is used for conducting patrol according to the acquisition parameters, acquisition of the acquisition parameters is achieved, and a data base is provided for generation of subsequent signal interference early warning information.
Further, the method further comprises:
acquiring a sensor setting position, a sensor type and sensor target equipment according to the sensor setting information;
extracting sensor signal sensitivity characteristics and sensor data precision characteristics based on the sensor type to obtain a sensor sensitive signal range and sensor data precision;
extracting target inspection equipment and target parameter precision requirements according to the inspection target parameters;
performing sensitivity matching by using the working signal characteristics and the sensor sensitive signal range, and determining matched sensor information;
and determining sensor data precision according to the matched sensor information, and taking the matched sensor information as the collaborative sensor information when the sensor data precision meets the target parameter precision requirement.
Sensitivity matching is performed on the sensor setting information, and the cooperative sensor information is determined. And acquiring the set position of the sensor, the type of the sensor and the target equipment corresponding to the sensor according to the set information of the sensor to obtain the set information of the sensor, and acquiring the set position of the sensor, the type of the sensor and the target equipment of the sensor. The sensor type is obtained, sensor signal sensitivity characteristics and sensor data precision characteristics are extracted from the sensor according to the sensor type, and characteristic extraction results are obtained, wherein the characteristic extraction results are sensor sensitive signal range and sensor data precision. Extracting the precision requirements of target inspection equipment and target parameters according to the inspection target parameters, and performing sensitivity matching through the working signal characteristics and the sensor sensitive signal range to obtain a matching result, wherein the matching result is matching sensor information; and determining the sensor data precision according to the matched sensor information, taking the matched sensor information as cooperative sensor information when the sensor data precision meets the target parameter precision requirement, acquiring the cooperative sensor information, and providing a data basis for the follow-up signal interference early warning information and the cooperative sensor information, sending a cooperative instruction, wherein the cooperative instruction comprises a patrol target parameter.
Further, the method further comprises:
when the sensor data precision does not meet the target parameter precision requirement, performing sensor target equipment and sensing data precision matching based on the target parameter precision requirement and the sensor setting information, and determining a precision matching sensor;
and establishing connection between the precision matching sensor and the matching sensor information, and taking the precision matching sensor and the matching sensor information as the cooperative sensor information.
When the accuracy of the sensor data does not meet the accuracy requirement of the target parameter, the accuracy of the sensor data needs to be readjusted, and the accuracy matching sensor is redetermined. And carrying out precision matching on the sensor target equipment and the sensing data according to the target parameter precision requirement and the sensor setting information, matching the corresponding sensor target equipment and the corresponding sensing data precision according to the corresponding sensor setting and parameter precision requirement to obtain a matching result, and outputting the matching result to obtain the precision matching sensor. And connecting the precision matching sensor with the matching sensor information, and performing collaborative sensing on the precision matching sensor and the matching sensor information, namely taking the precision matching sensor and the matching sensor information as collaborative sensor information. And in coordination with the determination of the sensor information, the accuracy of the matched sensor information can be improved, and the accuracy of the whole system is further improved.
Further, the method further comprises:
acquiring a fixed equipment setting position based on a grid map model;
the fixed equipment setting position is identified and sent to a robot identification path;
and carrying out image acquisition on the inspection path through a robot camera to obtain image acquisition information, identifying the image acquisition information through a two-channel semantic segmentation model, and carrying out two-channel step size picture analysis as the non-stationary obstacle when non-stationary equipment exists to obtain the identification volume and the identification state of the non-stationary obstacle.
When detecting the non-fixed obstacle, the image acquisition equipment is required to be activated to acquire the inspection path, the acquired image is analyzed, an analysis result is obtained, and the real-time monitoring of the non-fixed obstacle is completed through the analysis result. Firstly, according to a grid map model, the position of a fixed device, namely the fixed device setting position, is obtained in the grid map model, the fixed device setting position is obtained, the fixed device setting position is identified, the fixed device setting position is sent to a robot recognition path, the fixed device setting position is added to the recognition path, the fixed device setting position is marked as an immovable identification, the recognition path is planned according to the identification, and the path planning of the non-fixed obstacle is completed. When the non-stationary obstacle is analyzed, the image acquisition equipment is required to be activated, the inspection path is subjected to image acquisition through the image acquisition equipment, acquired image acquisition information is acquired, the image acquisition information is identified by using a two-channel semantic segmentation model, wherein the two-channel semantic segmentation model is an obstacle identification model constructed by carrying out two-channel on the basis of the semantic segmentation model, the image acquisition information is identified by the two-channel semantic segmentation model, the image information of the non-stationary obstacle is subjected to step size picture analysis through a first channel, namely, the interval time of acquiring the image acquisition information of the non-stationary obstacle is analyzed, the movement condition of the non-stationary obstacle is judged, the state of the non-stationary obstacle is identified, the volume and the identification state of the non-stationary obstacle are identified through a second channel, the identification result is the identification volume and the identification state of the non-stationary obstacle, the identification volume and the identification state of the non-stationary obstacle are real-time monitoring results of the non-stationary obstacle, and the real-time monitoring results of the non-stationary obstacle are obtained, and data is provided for the subsequent identification of the corresponding influence range in the path according to the detection result.
Further, the method further comprises:
extracting the obstacle recognition position, recognition volume and recognition state according to the detection result;
determining obstacle movement characteristics according to the identification state;
according to the obstacle movement characteristics, performing obstacle movement prediction, determining a predicted path, and performing interference analysis by using the predicted path and a planned path to determine a predicted movement interference range;
according to the obstacle recognition position and recognition volume, analyzing the equipment shielding relation of the target point, and determining the shielding range;
and correcting the shielding range by using the predicted moving interference range, and determining obstacle influence information.
The non-stationary obstacle has mobility, and the movement of the non-stationary obstacle also has certain timeliness, when the acquired image acquisition information of the non-stationary obstacle at the current moment is analyzed correspondingly to obtain a planned path, but the position of the non-stationary obstacle is found to be changed after the planned path is acquired, and the path planning of the non-stationary obstacle cannot be used continuously before the planned path is acquired, so that the movement of the non-stationary obstacle is required to be predicted correspondingly, the possible position of the non-stationary obstacle is acquired, and the influence of the non-stationary obstacle on robot inspection can be reduced by performing corresponding processing according to the predicted position. And extracting the obstacle recognition position, recognition volume and recognition state according to the detection result, acquiring corresponding obstacle moving image acquisition information according to the recognition state, and extracting moving features according to the obstacle image acquisition information to acquire moving feature extraction results, namely obstacle moving features. And carrying out movement prediction on the obstacle according to the obstacle movement characteristics, generating a movement curve of the obstacle movement characteristics, and prolonging the curve to obtain an obstacle prediction path. According to the method, interference analysis is carried out according to a predicted path and a planned path, an interference analysis result is obtained, the result is an interference analysis range, equipment shielding relation analysis is carried out according to an obstacle recognition position and a recognition volume, obstacle construction is carried out in a grid map, the obstacle recognition position and the recognition volume are input, a complete obstacle model is constructed, the shielding range is determined in the grid map, the shielding range is obtained, finally, the shielding range is corrected according to a predicted moving interference range, the shielding range is added according to the shielding range corresponding to the predicted moving interference range, obstacle influence information is determined, obstacle image information is determined, the influence of non-fixed obstacles on the robot inspection work can be reduced to the maximum extent, and the inspection efficiency is further improved.
Example two
Based on the same inventive concept as the substation robot inspection path optimization method in the foregoing embodiment, as shown in fig. 2, the present application provides a substation robot inspection path optimization device, where the device includes:
the target point acquisition module 11: the target point obtaining module 11 is configured to establish a grid map model of a substation environment map by using a grid method, map devices in the substation into the grid map model, and obtain a plurality of target points;
path planning module 12: the path planning module 12 is configured to obtain a patrol start point of the substation robot, and perform global path planning according to the patrol start point and a plurality of target points;
patrol task module 13: the inspection task module 13 is used for detecting the non-fixed obstacle in real time when the substation robot performs an inspection task;
the obstacle influencing module 14: the obstacle influencing module 14 is configured to identify an influence range of a corresponding target point in the path according to the detection result, and determine obstacle influencing information;
planning adjustment module 15: the plan adjustment module 15 is configured to adjust a global path plan based on the detection result and the obstacle impact information.
Further, the path planning module 12 includes the following steps:
acquiring patrol equipment information of a plurality of target points, wherein the patrol equipment information comprises patrol equipment coordinates, patrol target parameters and equipment running time;
carrying out inspection classification based on the inspection target parameters and the running time of the equipment to obtain classification information, carrying out inspection switching cost analysis of each class based on each classification information, and determining inspection switching cost among the classes;
and carrying out path optimization by taking the minimum time of the inspection target as the target based on the inspection switching cost, the inspection starting point and the inspection equipment coordinates.
Further, the path planning module 12 includes the following steps:
acquiring initial signal characteristics of a robot;
collecting working signal characteristics of the robot in the inspection process;
acquiring a signal loss value curve based on the working signal characteristics and the initial signal characteristics;
and when the loss value or the fluctuation coefficient of the signal loss value curve reaches a preset threshold value, generating signal interference early warning information.
Further, the path planning module 12 includes the following steps:
acquiring sensor setting information of an interference target point;
based on the inspection target parameters of the interference target points, performing sensitivity matching according to the working signal characteristics and the sensor setting information, and determining cooperative sensor information;
based on the signal interference early warning information and the cooperative sensor information, transmitting a cooperative instruction, wherein the cooperative instruction comprises a patrol target parameter;
and sensing and collecting according to the inspection target parameters through a cooperative sensor, and sending the collected parameters to the robot.
Further, the path planning module 12 includes the following steps:
acquiring a sensor setting position, a sensor type and sensor target equipment according to the sensor setting information;
extracting sensor signal sensitivity characteristics and sensor data precision characteristics based on the sensor type to obtain a sensor sensitive signal range and sensor data precision;
extracting target inspection equipment and target parameter precision requirements according to the inspection target parameters;
performing sensitivity matching by using the working signal characteristics and the sensor sensitive signal range, and determining matched sensor information;
and determining sensor data precision according to the matched sensor information, and taking the matched sensor information as the collaborative sensor information when the sensor data precision meets the target parameter precision requirement.
Further, the path planning module 12 includes the following steps:
when the sensor data precision does not meet the target parameter precision requirement, performing sensor target equipment and sensing data precision matching based on the target parameter precision requirement and the sensor setting information, and determining a precision matching sensor;
and establishing connection between the precision matching sensor and the matching sensor information, and taking the precision matching sensor and the matching sensor information as the cooperative sensor information.
Further, the inspection task module 13 includes the following steps:
acquiring a fixed equipment setting position based on a grid map model;
the fixed equipment setting position is identified and sent to a robot identification path;
and carrying out image acquisition on the inspection path through a robot camera to obtain image acquisition information, identifying the image acquisition information through a two-channel semantic segmentation model, and carrying out two-channel step size picture analysis as the non-stationary obstacle when non-stationary equipment exists to obtain the identification volume and the identification state of the non-stationary obstacle.
Further, the inspection task module 13 includes the following steps:
extracting the obstacle recognition position, recognition volume and recognition state according to the detection result;
determining obstacle movement characteristics according to the identification state;
according to the obstacle movement characteristics, performing obstacle movement prediction, determining a predicted path, and performing interference analysis by using the predicted path and a planned path to determine a predicted movement interference range;
according to the obstacle recognition position and recognition volume, analyzing the equipment shielding relation of the target point, and determining the shielding range;
and correcting the shielding range by using the predicted moving interference range, and determining obstacle influence information.
Through the foregoing detailed description of a substation robot inspection path optimization method, those skilled in the art can clearly know a substation robot inspection path optimization method in this embodiment, and for the apparatus disclosed in the embodiment, the description is relatively simple, and relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. A substation robot tour path optimization method, the method comprising:
establishing a grid map model of a substation environment map by using a grid method, and mapping equipment in a substation into the grid map model to obtain a plurality of target points;
acquiring a patrol starting point of the substation robot, and performing global path planning according to the patrol starting point and a plurality of target points;
when the substation robot carries out a patrol task, detecting the non-fixed obstacle in real time;
performing influence range identification on a corresponding target point in the path according to the detection result, and determining obstacle influence information;
and adjusting the global path planning based on the detection result and the obstacle influence information.
2. The method of claim 1, wherein the obtaining the patrol start point of the substation robot and performing global path planning according to the patrol start point and the plurality of target points comprises:
acquiring patrol equipment information of a plurality of target points, wherein the patrol equipment information comprises patrol equipment coordinates, patrol target parameters and equipment running time;
carrying out inspection classification based on the inspection target parameters and the running time of the equipment to obtain classification information, carrying out inspection switching cost analysis of each class based on each classification information, and determining inspection switching cost among the classes;
and carrying out path optimization by taking the minimum time of the inspection target as the target based on the inspection switching cost, the inspection starting point and the inspection equipment coordinates.
3. The method as recited in claim 2, further comprising:
acquiring initial signal characteristics of a robot;
collecting working signal characteristics of the robot in the inspection process;
acquiring a signal loss value curve based on the working signal characteristics and the initial signal characteristics;
and when the loss value or the fluctuation coefficient of the signal loss value curve reaches a preset threshold value, generating signal interference early warning information.
4. The method of claim 3, wherein the generating signal-to-interference pre-warning information, then comprises:
acquiring sensor setting information of an interference target point;
based on the inspection target parameters of the interference target points, performing sensitivity matching according to the working signal characteristics and the sensor setting information, and determining cooperative sensor information;
based on the signal interference early warning information and the cooperative sensor information, transmitting a cooperative instruction, wherein the cooperative instruction comprises a patrol target parameter;
and sensing and collecting according to the inspection target parameters through a cooperative sensor, and sending the collected parameters to the robot.
5. The method of claim 4, wherein the determining cooperative sensor information based on the inspection target parameter of the interfering target point and the sensitivity matching of the operating signal characteristic to the sensor setting information comprises:
acquiring a sensor setting position, a sensor type and sensor target equipment according to the sensor setting information;
extracting sensor signal sensitivity characteristics and sensor data precision characteristics based on the sensor type to obtain a sensor sensitive signal range and sensor data precision;
extracting target inspection equipment and target parameter precision requirements according to the inspection target parameters;
performing sensitivity matching by using the working signal characteristics and the sensor sensitive signal range, and determining matched sensor information;
and determining sensor data precision according to the matched sensor information, and taking the matched sensor information as the collaborative sensor information when the sensor data precision meets the target parameter precision requirement.
6. The method as recited in claim 5, further comprising:
when the sensor data precision does not meet the target parameter precision requirement, performing sensor target equipment and sensing data precision matching based on the target parameter precision requirement and the sensor setting information, and determining a precision matching sensor;
and establishing connection between the precision matching sensor and the matching sensor information, and taking the precision matching sensor and the matching sensor information as the cooperative sensor information.
7. The method of claim 1, wherein the substation robot performs real-time detection of the non-stationary obstacle while performing the inspection task, comprising:
acquiring a fixed equipment setting position based on a grid map model;
the fixed equipment setting position is identified and sent to a robot identification path;
and carrying out image acquisition on the inspection path through a robot camera to obtain image acquisition information, identifying the image acquisition information through a two-channel semantic segmentation model, and carrying out two-channel step size picture analysis as the non-stationary obstacle when non-stationary equipment exists to obtain the identification volume and the identification state of the non-stationary obstacle.
8. The method of claim 7, wherein the determining obstacle impact information by performing impact range identification on the corresponding target point in the path according to the detection result comprises:
extracting the obstacle recognition position, recognition volume and recognition state according to the detection result;
determining obstacle movement characteristics according to the identification state;
according to the obstacle movement characteristics, performing obstacle movement prediction, determining a predicted path, and performing interference analysis by using the predicted path and a planned path to determine a predicted movement interference range;
according to the obstacle recognition position and recognition volume, analyzing the equipment shielding relation of the target point, and determining the shielding range;
and correcting the shielding range by using the predicted moving interference range, and determining obstacle influence information.
9. A substation robot tour path optimization apparatus, characterized by steps for performing any one of the substation robot tour path optimization methods described in claims 1-8, the apparatus comprising:
the target point acquisition module: establishing a grid map model of a substation environment map by using a grid method, and mapping equipment in a substation into the grid map model to obtain a plurality of target points;
and a path planning module: acquiring a patrol starting point of the substation robot, and performing global path planning according to the patrol starting point and a plurality of target points;
and a patrol task module: when the substation robot carries out a patrol task, detecting the non-fixed obstacle in real time;
obstacle influencing module: performing influence range identification on a corresponding target point in the path according to the detection result, and determining obstacle influence information;
and a planning and adjusting module: and adjusting the global path planning based on the detection result and the obstacle influence information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311256853.7A CN117313969A (en) | 2023-09-27 | 2023-09-27 | Substation robot inspection path optimization method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311256853.7A CN117313969A (en) | 2023-09-27 | 2023-09-27 | Substation robot inspection path optimization method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117313969A true CN117313969A (en) | 2023-12-29 |
Family
ID=89280590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311256853.7A Pending CN117313969A (en) | 2023-09-27 | 2023-09-27 | Substation robot inspection path optimization method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117313969A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118274845A (en) * | 2024-05-29 | 2024-07-02 | 天津地铁智慧科技有限公司 | Subway station robot inspection system and inspection method |
-
2023
- 2023-09-27 CN CN202311256853.7A patent/CN117313969A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118274845A (en) * | 2024-05-29 | 2024-07-02 | 天津地铁智慧科技有限公司 | Subway station robot inspection system and inspection method |
| CN118274845B (en) * | 2024-05-29 | 2024-08-20 | 天津地铁智慧科技有限公司 | Subway station robot inspection system and inspection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109800697B (en) | Transformer target detection and appearance defect identification method based on VGG-net style migration | |
| CN111337030A (en) | Backpack-based laser radar scanning system and navigation positioning method | |
| CN109738460A (en) | A kind of evaluation detection system for civil engineering structure visual defects | |
| CN115686014B (en) | Subway inspection robot based on BIM model | |
| CN117313969A (en) | Substation robot inspection path optimization method and device | |
| CN111384776B (en) | VR-based transformer substation three-dimensional panoramic state monitoring method and system | |
| CN211375602U (en) | Mobile intelligent noise live-action cloud picture modeling system for transformer substation | |
| CN116231504A (en) | Remote intelligent inspection method, device and system for booster station | |
| CN116777187A (en) | Multi-path inspection intelligent central control scheduling method and platform | |
| CN117809191B (en) | Intelligent monitoring and early warning method and system for three-dimensional ranging of power transmission line | |
| CN115941529A (en) | Cable tunnel detection method and system based on robot | |
| CN116954234A (en) | Robot inspection control method and system | |
| CN116203970A (en) | Intelligent obstacle avoidance method and system for inspection robot | |
| CN115272560B (en) | Substation equipment hidden danger positioning method and system based on three-dimensional sound field cloud picture | |
| CN117589177B (en) | Autonomous navigation method based on industrial large model | |
| CN117216341A (en) | Visualization method and system for distributed space-time data of power grid | |
| CN117935453B (en) | Port machine remote control method and system based on binocular camera | |
| US20220390931A1 (en) | Object Handling in an Absolute Coordinate System | |
| CN117226846A (en) | Control method and system for substation equipment maintenance robot | |
| CN118012087A (en) | Unmanned plane collaborative inspection method, unmanned plane collaborative inspection device, unmanned plane collaborative inspection equipment and storage medium | |
| CN117572863A (en) | Path optimization method and system for substation robot | |
| CN117471565A (en) | Underwater detection method, system and medium for intelligent robot | |
| CN114179093B (en) | Substation inspection robot system and obstacle avoidance method thereof | |
| CN116055521A (en) | Inspection system and image recognition method for electric inspection robot | |
| CN112270357A (en) | VIO vision system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |