CN116307335B - Method and system for planning tour-inspection path of region of interest - Google Patents
Method and system for planning tour-inspection path of region of interest Download PDFInfo
- Publication number
- CN116307335B CN116307335B CN202310573606.3A CN202310573606A CN116307335B CN 116307335 B CN116307335 B CN 116307335B CN 202310573606 A CN202310573606 A CN 202310573606A CN 116307335 B CN116307335 B CN 116307335B
- Authority
- CN
- China
- Prior art keywords
- interest
- region
- parameter
- path
- planning
- 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.)
- Active
Links
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for planning a routing inspection path of an interested region, which relate to the technical field of data processing, and are used for marking the interested region, obtaining information of the interested region, extracting interested grades and interested attention parameters, obtaining an interest grade list set and an attention parameter list set, and setting grade coefficients based on the interest grade list set; the method comprises the steps of carrying out path planning influence parameter correlation analysis on a focused parameter list set, determining constraint factors, constructing a fitness function, establishing an optimizing space, carrying out routing inspection path optimization, and solving the problems that routing inspection planning analysis on a path of interest in the prior art is not strict enough, so that the combination degree of the planned path and the demand is insufficient, routing inspection conflict cannot be timely and effectively processed, and a certain routing inspection limitation exists. The adaptive planning of the inspection is carried out by combining the interest demands, the inspection primary and secondary are effectively guaranteed, the path optimizing re-planning is timely carried out aiming at the existing inspection conflict, and the inspection effect is maximally guaranteed.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for planning a patrol path of a region of interest.
Background
In the regional inspection process, certain inspection limitations exist due to wide regions and poor destination, so that the inspection effect is influenced. When the inspection planning configuration is carried out on the region of interest, the analysis level is shallow, and potential uncontrollable factors exist in the planned path due to the limitation of the technology.
In the prior art, the routing inspection planning analysis aiming at the interested path is not strict enough, so that the combination degree of the planning path and the demand is insufficient, the existing routing inspection conflict cannot be effectively processed in time, and a certain routing inspection limitation exists.
Disclosure of Invention
The application provides a routing inspection path planning method and system for a region of interest, which are used for solving the technical problems that routing inspection planning analysis for the region of interest is not strict enough, so that the combination degree of the planned path and the demand is insufficient, routing inspection conflict cannot be timely and effectively processed, and a certain routing inspection limitation exists in the prior art.
In view of the above problems, the present application provides a method and a system for planning a patrol path of a region of interest.
In a first aspect, the present application provides a method for planning a patrol path of a region of interest, where the method includes:
labeling an interesting region to obtain interesting region information, wherein the interesting region information comprises interesting region coordinates, interesting grades and interesting attention parameters;
extracting interest levels and interest attention parameters according to the interest region information to obtain an interest level list set and an interest parameter list set;
setting a grade coefficient based on the distribution condition of the interest grades in the interest grade list set;
performing path planning influence parameter correlation analysis on the attention parameter list set, and determining constraint factors based on the correlation;
taking the constraint factors as constraint conditions, taking the coordinates of the region of interest as an optimization variable and taking the grade coefficients as weight values of the optimization variable, and constructing an adaptability function;
and establishing an optimizing space based on the fitness function, and optimizing the routing inspection path of the region of interest through the optimizing space to obtain routing inspection path planning.
In a second aspect, the present application provides a system for planning an inspection path for a region of interest, the system comprising:
the information acquisition module is used for marking the region of interest and obtaining region of interest information, wherein the region of interest information comprises region of interest coordinates, interest levels and interest attention parameters;
the information extraction module is used for extracting interest levels and interest attention parameters according to the interest area information to obtain an interest level list set and an interest parameter list set;
the grade coefficient setting module is used for setting grade coefficients based on the distribution conditions of the interested grades in the interest grade list set;
the constraint factor determining module is used for carrying out path planning influence parameter correlation analysis on the attention parameter list set and determining constraint factors based on the correlation;
the function construction module is used for constructing an adaptability function by taking the constraint factors as constraint conditions, taking the coordinates of the region of interest as an optimization variable and taking the grade coefficients as weight values of the optimization variable;
and the path optimizing module is used for establishing an optimizing space based on the fitness function, and carrying out routing inspection path optimization on the region of interest through the optimizing space to obtain routing inspection path planning.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the inspection path planning method for the region of interest, the region of interest is marked, region of interest information is obtained, the region of interest information comprises region coordinates, interest levels and interest attention parameters, the interest levels and the interest attention parameters are extracted, an interest level list set and an interest parameter list set are obtained, and level coefficient setting is carried out based on the distribution condition of the interest levels in the interest level list set; and carrying out path planning influence parameter correlation analysis on the attention parameter list set, determining a constraint factor based on the correlation and taking the constraint factor as a constraint condition, taking the coordinates of the region of interest as an optimization variable and the grade coefficient as a weight value of the optimization variable, constructing an adaptability function, establishing an optimizing space, carrying out routing inspection path optimization on the region of interest, and obtaining routing inspection path planning. The method solves the problems that in the prior art, routing inspection planning analysis aiming at the interested path is not strict enough, so that the combination degree of the planned path and the demand is insufficient, the existing routing inspection conflict cannot be effectively processed in time, and a certain routing inspection limitation exists. The adaptive planning of the inspection is carried out by combining the interest demands, the inspection primary and secondary are effectively guaranteed, the path optimizing re-planning is timely carried out aiming at the existing inspection conflict, and the inspection effect is maximally guaranteed.
Drawings
Fig. 1 is a schematic flow chart of a routing inspection path planning method for a region of interest;
fig. 2 is a schematic diagram of a process for obtaining information of an area of interest in a method for planning a routing inspection path of the area of interest;
fig. 3 is a schematic diagram of a fitness function construction flow in a method for planning a routing inspection path of a region of interest;
fig. 4 is a schematic structural diagram of an inspection path planning system for a region of interest.
Reference numerals illustrate: the system comprises an information acquisition module 11, an information extraction module 12, a rank coefficient setting module 13, a constraint factor determination module 14, a function construction module 15 and a path optimizing module 16.
Detailed Description
The method and the system for planning the routing inspection path of the region of interest are provided, the region of interest is marked, the information of the region of interest is obtained, the interest grade and the interest attention parameter are extracted, an interest grade list set and an interest parameter list set are obtained, and grade coefficient setting is carried out based on the interest grade list set; the method comprises the steps of carrying out path planning influence parameter correlation analysis on a focused parameter list set, determining constraint factors, taking coordinates of an interested region as an optimization variable and the grade coefficient as a weight value of the optimization variable, constructing a fitness function, establishing an optimizing space, and carrying out routing inspection path optimization on the interested region, so that the technical problems that routing inspection planning analysis on the interested path in the prior art is not strict enough, the combination degree of the planned path and the requirement is insufficient, routing inspection conflict cannot be effectively treated in time, and a certain routing inspection limitation exists are solved.
Example 1
As shown in fig. 1, the present application provides a method for planning a patrol path of a region of interest, where the method
Step S100: labeling an interesting region to obtain interesting region information, wherein the interesting region information comprises interesting region coordinates, interesting grades and interesting attention parameters;
further, as shown in fig. 2, the labeling the region of interest to obtain the region of interest information, step S100 of the present application further includes:
step S110: obtaining a patrol target, and determining an interested region based on target parameter matching between the patrol target and all regions;
step S120: acquiring a region map based on the region of interest, and determining region-of-interest coordinates based on a map range, wherein the region-of-interest coordinates comprise region frame coordinates and ground object coordinates;
step S130: determining the interest level according to the matching degree of the target parameter and the interest area;
step S140: and according to the matching of the ground object operation parameters of the region of interest and the target parameters, determining matching operation parameters, wherein the matching operation parameters comprise acquisition targets, operation periods and operation time, and the matching operation parameters are used as the interesting parameters.
Specifically, in the regional inspection process, due to wide regions and poor purposes, certain inspection limitations exist to influence the inspection effect.
Specifically, the inspection target is the basis for performing interest identification of all areas, such as object types, and the like, the inspection target is subjected to target parameter extraction, including static parameters and dynamic parameters, and is further matched with all the areas, the area similar to the inspection target in the target parameter is determined as the area of interest, the area of interest is marked, and then specific information analysis and matching are performed. Specifically, a region definition range including all the regions of interest is obtained and used as a space field, a coordinate axis is determined based on space dimensions, a space coordinate system under the region definition range is constructed, positioning layout of region boundaries and ground objects is carried out on the region coordinates of interest, layout coordinates under the space coordinate system are identified, the region frame coordinates and the ground object coordinates of all the regions of interest are included, coordinate statistics and attribution identification are carried out, and the region coordinates of the interest are generated.
And further performing interested grade analysis setting on the interested region, taking the matching degree of the target parameter and the interested region as a grade configuration standard, wherein the higher the similarity with the target parameter is, the higher the corresponding matching degree is, the higher the grade configuration is, and setting a plurality of grades of interested, namely, custom-defined equipartition standard for distinguishing the region, respectively performing matching degree analysis and grade demarcation on the interested region, and determining the interested grade.
Further carrying out dynamic matching analysis on the region of interest, collecting ground object operation parameters of the region of interest, matching the ground object operation parameters with the target parameters, screening consistent operation parameters matched with the target parameters, wherein the consistent operation parameters comprise an acquisition target, an operation period and operation time, the acquisition target comprises operation control parameters of all ground objects and the like, carrying out matching analysis and parameter association on the ground objects by ground object, and determining a plurality of operation parameter sequences representing interest as the interest attention parameters. And integrating the coordinates of the region of interest, the interest level and the interest attention parameter aiming at each region of interest, wherein the region of interest information has coverage area completeness and information consistency as the region of interest information.
Step S200: extracting interest levels and interest attention parameters according to the interest region information to obtain an interest level list set and an interest parameter list set;
step S300: setting a grade coefficient based on the distribution condition of the interest grades in the interest grade list set;
specifically, based on the region of interest information, identifying and extracting each region of interest and corresponding interest levels, mapping and associating the regions of interest and the corresponding interest levels, generating a plurality of sequences characterized as region-level sequences, and integrating the sequences as the interest level list set; similarly, based on the region of interest information, extracting a plurality of operation parameters matched with ground objects of each region of interest, performing mapping association integration on the plurality of operation parameters of the region of interest and the ground objects, generating a plurality of sequences which are characterized as region-attention parameters, integrating the sequences as an attention parameter list set, wherein the interest grade list set and the attention parameter list set are different dimension data sets established through information analysis attribution. And further, unifying characterization data of the interest level of each region based on the interest level list.
Specifically, the data representation formats of the interesting grades of the areas covered in the interesting grade list are different, for example, arabic numerals of 1, 2, 3 and the like are partially adopted for grade representation, grade representation of a, b, c and the like is partially adopted, or grade representation of excellent, good and the like is adopted, subsequent analysis is limited due to the difference of the data grades, representation format conversion is carried out based on the distribution condition of the interesting grades in the interesting grade list, a unified measurement standard is determined, grade coefficients are configured to define a grade interval, namely the interesting grade coefficients can be attributed to the same grade coefficients in the same grade interval range, customized setting can be carried out in combination with the requirement of attribution precision, for example, the interesting grade coefficients are attributed to the same grade coefficients, conversion setting of the interesting grade list is carried out, the grade coefficients in the same data representation format are generated, each interesting area corresponds to one grade coefficient respectively, and convenience is provided for subsequent inspection planning analysis through conversion of grade representation.
Step S400: performing path planning influence parameter correlation analysis on the attention parameter list set, and determining constraint factors based on the correlation;
further, performing path planning influence parameter correlation analysis on the parameter list set, and determining a constraint factor based on the correlation, where step S400 further includes:
step S410: setting path planning influence parameters, wherein the path planning influence parameters comprise path nodes, node residence time and node inspection equipment parameter adjustment loss;
step S420: performing correlation calculation according to the path nodes, the node residence time, the node inspection equipment parameter adjustment loss and each parameter in the attention parameter list set to obtain a correlation degree, and determining a correlation coefficient based on the correlation degree;
step S430: calculating according to the values of the parameters in the attention parameter list and the correlation coefficient to obtain the correlation of the parameters;
step S440: based on the correlation of the parameters, the correlation is screened from large to small according to the preset screening quantity, and the obtained influence parameters are used as constraint factors.
Further, according to the path node, the node residence time, the node inspection equipment parameter adjustment loss, and each parameter in the attention parameter list, performing correlation calculation to obtain a correlation, where step S420 further includes:
step S421: constructing a parameter database based on the path nodes, the node residence time, the node inspection equipment parameter adjustment loss and all parameters in the attention parameter list set;
step S422: calculating the support degree of single parameters for path planning from the parameter database to obtain an initial candidate set;
step S423: screening a first frequent item set with the support degree larger than the minimum support degree from the initial candidate set;
step S424: carrying out confidence calculation based on the support degree, screening that the support degree is larger than the second support degree on the basis of the first frequent item set, and obtaining a second frequent item set by the confidence degree being larger than the minimum confidence degree;
step S425: and the same is done until a preset condition is met, an Nth frequent item set is obtained, and N is a positive integer greater than 2;
step S426: and carrying out correlation calculation according to the parameter relation determined by the frequent item set to obtain the correlation.
Further, the confidence calculating based on the support degree, step S424 of the present application further includes:
step S4241: according to the formula: c (a, B) =Calculating to obtain confidence, wherein C (A, B) is the confidence,support for AB combination, +.>、/>Is a single degree of support.
Specifically, the interest point in the routing inspection process is located, the interest point is used as a necessary routing inspection point, routing inspection time meeting routing inspection requirements of each node is determined as the path node, the node residence time is used, wherein the residence time of each node is different, corresponding routing inspection equipment is different from a start-stop time sequence node and equipment routing inspection parameters due to the fact that routing inspection requirements of different routing inspection nodes are different, node routing inspection equipment parameter adjustment loss of each routing inspection node is determined on the basis, and the path node, the node residence time and the node routing inspection equipment parameter adjustment loss are used as the path planning influence parameters. And further, carrying out correlation analysis on the path nodes, the node residence time and the node inspection equipment parameter adjustment loss.
Specifically, node attribution integration is performed on the path node, the node residence time, the node inspection equipment parameter adjustment loss and the attention parameter list set, a plurality of node parameter combinations are determined, and the parameter database is generated. And counting and determining the occurrence times of the single parameter in the parameter database aiming at the single parameter in the parameter database, and taking the occurrence times as the parameter support degree, wherein the higher the occurrence times of the parameter is, the higher the occurrence probability is, the higher the corresponding support degree is, and respectively and independently determining the support degree of each parameter in the parameter database, and mapping the support degree and the single parameter is corresponding to the support degree to be used as the initial candidate set.
If the parameter support is too small, which indicates that the probability of occurrence is low, and the probability of occurrence is likely to be that the accidental situation belongs to invalid data, the initial candidate set is screened, specifically, the minimum support is set, namely, the critical limit support for measuring the validity of the parameter is set in a self-defining mode, each support in the initial candidate set is checked with the minimum support respectively, parameters larger than the minimum support are screened, and the first frequent item set is constructed. Further, performing combination support calculation on any two items in the first frequent item set, namely determining the number of times of occurrence of combination of two items of parameters, performing confidence calculation on any two items of combination parameters, and inputting a confidence calculation formula: c (a, B) =Wherein C (A, B) is confidence level, < >>Support for AB combination, +.>、/>Is a single support, and all the parameters can be determined by pre-analysis statistics.
The second support degree and the minimum confidence degree are further set, the second support degree is a set critical minimum support degree for carrying out any two combined parameter screening, the minimum confidence degree is a set critical confidence degree for carrying out parameter screening, the parameter screening is carried out on the first frequent item set, if the support degree of the combined parameter is larger than the second support degree and the confidence degree is larger than the minimum confidence degree, the parameter combination is a strongly correlated combined parameter, the support degree in the first frequent item set is larger than the second support degree, and the confidence degree is larger than the combined parameter of the minimum confidence degree, and the combination parameter is used as the second frequent item set.
Further, performing a combination of any three parameters in the second frequent item set, performing calculation screening of the support degree and the confidence degree again, determining a third frequent item set, and performing such pushing until the preset condition is met, stopping performing parameter association analysis screening, where the preset condition is a stopping condition, for example, the maximum screening frequency is reached or the number of frequent items reaches a critical value, and obtaining the nth frequent item set. And carrying out correlation calculation on the parameters determined by the frequent items, wherein the correlation calculation comprises the simultaneous occurrence frequency of a single parameter and at least one parameter or the determination of a plurality of parameters, wherein the higher the frequency is, the higher the correlation is, the consideration is required in the inspection process, the correlation coefficient is determined based on the correlation, the correlation coefficient is the characteristic data of the correlation degree among the parameters, and the correlation coefficient is in direct proportion to the correlation.
And further performing multiplication operation on the numerical value of each parameter in the attention parameter list and the correlation coefficient, namely performing multiplication operation and summation on each parameter and one or more parameters with a combination relation, and determining the correlation of each parameter. And sequencing the relevance of each parameter from large to small, obtaining the preset screening quantity, namely, the critical parameter quantity defining the quantity of the influence parameters in a self-defined mode, intercepting a relevance sequencing result based on the preset screening quantity, and determining a plurality of high-relevance influence parameters meeting the preset screening data quantity as the constraint factors. And through parameter correlation analysis screening, the suitability of the constraint factors is ensured to the maximum extent, and the subsequent inspection analysis data volume is reduced to improve the processing efficiency.
Step S500: taking the constraint factors as constraint conditions, taking the coordinates of the region of interest as an optimization variable and taking the grade coefficients as weight values of the optimization variable, and constructing an adaptability function;
further, as shown in fig. 3, the step S500 of constructing the fitness function using the constraint factor as a constraint condition, the region of interest coordinate as an optimization variable, and the level coefficient as a weight value of the optimization variable further includes:
step S510: performing constraint data exception analysis on the constraint factors, wherein when constraint data of the constraint factors are overlapped, the constraint data of the constraint factors are abnormal;
step S520: labeling constraint data existing in each region of interest based on the abnormal information;
step S530: dividing the region of interest by using the labels, and determining planning grouping information;
step S540: and determining a grouping constraint factor as a constraint condition based on the planning grouping information, respectively constructing a grouping fitness function for each planning grouping, and respectively carrying out path planning on each planning grouping.
Specifically, constraint data anomaly analysis is performed on the constraint factors, and if constraint data of the constraint factors overlap, for example, data conflict exists, and inspection requirements of a plurality of regions of interest exist in a time period, the constraint data of the constraint factors are judged to be abnormal. And identifying and positioning constraint data existing in each region of interest based on the abnormal information, for example, identifying and positioning the content of interest which needs to be observed in the time length of at least two regions of interest, namely 2 points to 3 points, and carrying out matching labeling on path nodes and node stay time. And further dividing the region of interest by using the labels, for example, carrying out group attribution for the patrol conflict existing in the same time interval, and determining planning grouping information. For the data conflict, at least two inspection robots can be started to operate simultaneously, and grouping constraint factors, namely constraint factors existing among groups, are further determined based on the planning grouping information. And aiming at each planning grouping information, taking the constraint factors as constraint conditions, taking the coordinates of the region of interest as an optimization variable, taking the grade coefficient as a weight value of the optimization variable, taking low constraint item avoidance in conflict as an obstacle avoidance mechanism, and respectively constructing grouping adaptability functions for each planning grouping, wherein the obstacle avoidance mode can comprise suspension avoidance, deceleration avoidance, detour obstacle avoidance and the like. And carrying out avoidance analysis based on the fitness function to determine the avoidance information corresponding to the highest fitness as the path planning of the corresponding planning group.
Step S600: and establishing an optimizing space based on the fitness function, and optimizing the routing inspection path of the region of interest through the optimizing space to obtain routing inspection path planning.
Further, step S600 of the present application further includes:
step S610: obtaining a path distribution map, performing path fitting based on a path planning result and the path distribution map of each planning group, and determining a path conflict node;
step S620: based on the path conflict node, determining conflict planning groups, and selecting the planning groups with less constraint factors as adjustment planning groups;
step S630: and adding the path conflict node serving as a tabu node into the constraint factor of the adjustment planning group to carry out path planning again, so as to obtain a new path planning result.
Specifically, optimizing spaces are respectively built for each planning group, mapping matching of fitness functions is performed, and the matched fitness functions are embedded into the corresponding optimizing spaces to execute path optimization. Specifically, the path distribution diagram is a visual distribution diagram of paths in a routing inspection area, positioning matching is performed in the path distribution diagram for path planning results of each planning packet in each planning packet, path fitting is performed, conflict node identification is performed based on the path fitting results, a plurality of positions with time node routing inspection conflicts are determined to serve as the path conflict nodes, and the path planning results are the paths to be routed. Based on the path conflict node, at least two paths with conflicts in the same node are attributed to the same group, the conflict planning group is determined, the quantity of constraint factors is used as an avoidance principle, the planning group with less constraint factors in the conflict planning group is used as the adjustment planning group, the path conflict node is further used as the tabu node, namely, the tabu node is excluded from a planning range, the tabu node is added into the constraint factors of the adjustment planning group to carry out planning limitation, path planning is carried out again, adaptability calculation and correction optimizing are carried out aiming at a path planning result, and a planning path with highest adaptability is determined and is used as the new routing planning result so as to ensure orderly and stable performance of inspection.
Example two
Based on the same inventive concept as the inspection path planning method for a region of interest in the foregoing embodiment, as shown in fig. 4, the present application provides an inspection path planning system for a region of interest, where the system includes:
the information acquisition module 11 is used for marking an interesting region and acquiring interesting region information, wherein the interesting region information comprises interesting region coordinates, interesting grades and interesting attention parameters;
the information extraction module 12 is configured to extract an interest level and an interest attention parameter according to the interest region information, so as to obtain an interest level list set and an interest parameter list set;
a grade coefficient setting module 13, wherein the grade coefficient setting module 13 is used for setting grade coefficients based on the distribution condition of interested grades in the interest grade list set;
a constraint factor determining module 14, where the constraint factor determining module 14 is configured to perform a path planning influence parameter correlation analysis on the parameter list set of interest, and determine a constraint factor based on the correlation;
the function construction module 15 is configured to construct an fitness function by using the constraint factors as constraint conditions, using the coordinates of the region of interest as an optimization variable, and using the level coefficients as weight values of the optimization variable;
the path optimizing module 16 is configured to establish an optimizing space based on the fitness function, and perform routing inspection path optimization on the region of interest through the optimizing space to obtain routing inspection path planning.
Further, the system further comprises:
the region determining module is used for obtaining a patrol target, and determining an interested region based on target parameter matching between the patrol target and all regions;
the coordinate determining module is used for obtaining a region map based on the region of interest and determining the coordinate of the region of interest based on a map range, wherein the coordinate of the region of interest comprises a region frame coordinate and a ground object coordinate;
the grade determining module is used for determining the interested grade according to the matching degree of the target parameter and the interested region;
the parameter matching module is used for determining matching operation parameters according to the ground object operation parameters of the region of interest and the target parameters, wherein the matching operation parameters comprise an acquisition target, an operation period and an operation time, and the matching operation parameters are used as the interesting parameter.
Further, the system further comprises:
the parameter setting module is used for setting path planning influence parameters, wherein the parameter setting module comprises path nodes, node residence time and parameter adjustment loss of the node inspection equipment;
the correlation coefficient determining module is used for performing correlation calculation on each parameter in the attention parameter list according to the path nodes, the node residence time and the node inspection equipment parameter adjustment loss to obtain a correlation degree, and determining a correlation coefficient based on the correlation degree;
the correlation calculation module is used for calculating and obtaining the correlation of each parameter according to the numerical value of each parameter in the attention parameter list and the correlation coefficient;
the constraint factor determining module is used for screening the correlation from large to small according to the preset screening quantity based on the correlation of the parameters, and the obtained influence parameters are used as constraint factors.
Further, the system further comprises:
the database construction module is used for constructing a parameter database based on the path nodes, the node residence time, the node inspection equipment parameter adjustment loss and all parameters in the attention parameter list;
the initial candidate set determining module is used for calculating the support degree of single parameters for path planning from the parameter database to obtain an initial candidate set;
the first frequent item set screening module is used for screening a first frequent item set with the support degree larger than the minimum support degree in the initial candidate set;
the second frequent item set screening module is used for carrying out confidence calculation based on the support degree, screening the support degree to be larger than the second support degree on the basis of the first frequent item set, and obtaining a second frequent item set by the confidence degree being larger than the minimum confidence degree;
the system comprises an nth frequent item set acquisition module, a first frequent item set acquisition module and a second frequent item set acquisition module, wherein the nth frequent item set acquisition module is used for acquiring an nth frequent item set by analogy until a preset condition is met, and N is a positive integer greater than 2;
and the correlation acquisition module is used for carrying out correlation calculation according to the parameter relation determined by the frequent item set to obtain the correlation.
Further, the system further comprises:
the confidence coefficient calculating module is used for calculating the confidence coefficient according to the formula: c (a, B) =Calculating to obtain confidence, wherein C (A, B) is confidence, and ++>Support for AB combination, +.>、/>Is a single degree of support.
Further, the system further comprises:
the abnormality analysis module is used for carrying out constraint data abnormality analysis on the constraint factors, and when the constraint data of the constraint factors are overlapped, abnormality exists;
the data labeling module is used for labeling constraint data existing in each region of interest based on the abnormal information;
the regional division module is used for dividing the region of interest by using labels and determining planning grouping information;
and the path planning module is used for determining a grouping constraint factor as a constraint condition based on the planning grouping information, respectively constructing a grouping fitness function for each planning grouping, and respectively carrying out path planning on each planning grouping.
Further, the system further comprises:
the path conflict node determining module is used for obtaining a path distribution diagram, carrying out path fitting based on a path planning result and the path distribution diagram of each planning group, and determining a path conflict node;
the adjustment planning grouping determination module is used for determining conflict planning groupings based on the path conflict nodes, and selecting planning groupings with fewer constraint factors as adjustment planning groupings;
and the path planning result acquisition module is used for adding the path conflict node serving as a tabu node into the constraint factor of the adjustment planning group to carry out path planning again so as to obtain a new path planning result.
In the present disclosure, through the foregoing detailed description of a method for planning a routing inspection path of a region of interest, those skilled in the art may clearly know a method and a system for planning a routing inspection path of a region of interest in the present embodiment, and for the apparatus disclosed in the embodiments, the description is relatively simple because it corresponds to the method disclosed in the embodiments, 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 (5)
1. The method for planning the routing inspection path of the region of interest is characterized by comprising the following steps:
labeling an interesting region to obtain interesting region information, wherein the interesting region information comprises interesting region coordinates, interesting grades and interesting attention parameters;
extracting interest levels and interest attention parameters according to the interest region information to obtain an interest level list set and an interest parameter list set;
setting a grade coefficient based on the distribution condition of the interest grades in the interest grade list set;
performing path planning influence parameter correlation analysis on the attention parameter list set, and determining constraint factors based on the correlation;
taking the constraint factors as constraint conditions, taking the coordinates of the region of interest as an optimization variable and taking the grade coefficients as weight values of the optimization variable, and constructing an adaptability function;
establishing an optimizing space based on the fitness function, and optimizing a routing inspection path of the region of interest through the optimizing space to obtain a routing inspection path plan;
the labeling the region of interest to obtain region of interest information includes:
obtaining a patrol target, and determining an interested region based on target parameter matching between the patrol target and all regions;
acquiring a region map based on the region of interest, and determining region-of-interest coordinates based on a map range, wherein the region-of-interest coordinates comprise region frame coordinates and ground object coordinates;
determining the interest level according to the matching degree of the target parameter and the interest area;
according to the ground object operation parameters of the region of interest and the target parameters, determining matched operation parameters, wherein the matched operation parameters comprise acquisition targets, operation periods and operation time, and the matched operation parameters are used as the interesting parameters;
the path planning influence parameter correlation analysis is performed on the attention parameter list set, and constraint factors are determined based on the correlation, and the method comprises the following steps:
setting path planning influence parameters, wherein the path planning influence parameters comprise path nodes, node residence time and node inspection equipment parameter adjustment loss;
performing correlation calculation according to the path nodes, the node residence time, the node inspection equipment parameter adjustment loss and each parameter in the attention parameter list set to obtain a correlation degree, and determining a correlation coefficient based on the correlation degree;
calculating according to the values of the parameters in the attention parameter list and the correlation coefficient to obtain the correlation of the parameters;
based on the correlation of the parameters, screening the correlation from large to small according to the preset screening quantity, wherein the obtained influence parameters are used as constraint factors;
the constructing the fitness function by taking the constraint factors as constraint conditions, taking the coordinates of the region of interest as an optimization variable and taking the grade coefficients as weight values of the optimization variable comprises the following steps:
performing constraint data exception analysis on the constraint factors, wherein when constraint data of the constraint factors are overlapped, the constraint data of the constraint factors are abnormal;
labeling constraint data existing in each region of interest based on the abnormal information;
dividing the region of interest by using the labels, and determining planning grouping information;
and determining a grouping constraint factor as a constraint condition based on the planning grouping information, respectively constructing a grouping fitness function for each planning grouping, and respectively carrying out path planning on each planning grouping.
2. The method of claim 1, wherein performing a correlation calculation with each parameter in the parameter list of interest based on the path node, the node dwell time, the node inspection device parameter adjustment loss, and obtaining a correlation comprises:
constructing a parameter database based on the path nodes, the node residence time, the node inspection equipment parameter adjustment loss and all parameters in the attention parameter list set;
calculating the support degree of single parameters for path planning from the parameter database to obtain an initial candidate set;
screening a first frequent item set with the support degree larger than the minimum support degree from the initial candidate set;
carrying out confidence calculation based on the support degree, screening that the support degree is larger than the second support degree on the basis of the first frequent item set, and obtaining a second frequent item set by the confidence degree being larger than the minimum confidence degree;
and the same is done until a preset condition is met, an Nth frequent item set is obtained, and N is a positive integer greater than 2;
and carrying out correlation calculation according to the parameter relation determined by the frequent item set to obtain the correlation.
3. The method of claim 2, wherein the confidence calculation based on support comprises:
according to the formula: c (a, B) =Calculating to obtain confidence, wherein C (A, B) is confidence, and ++>Support for AB combination, +.>、/>Is a single degree of support.
4. The method as recited in claim 1, further comprising:
obtaining a path distribution map, performing path fitting based on a path planning result and the path distribution map of each planning group, and determining a path conflict node;
based on the path conflict node, determining conflict planning groups, and selecting the planning groups with less constraint factors as adjustment planning groups;
and adding the path conflict node serving as a tabu node into the constraint factor of the adjustment planning group to carry out path planning again, so as to obtain a new path planning result.
5. A system for routing inspection of a region of interest, comprising:
the information acquisition module is used for marking the region of interest and obtaining region of interest information, wherein the region of interest information comprises region of interest coordinates, interest levels and interest attention parameters;
the information extraction module is used for extracting interest levels and interest attention parameters according to the interest area information to obtain an interest level list set and an interest parameter list set;
the grade coefficient setting module is used for setting grade coefficients based on the distribution conditions of the interested grades in the interest grade list set;
the constraint factor determining module is used for carrying out path planning influence parameter correlation analysis on the attention parameter list set and determining constraint factors based on the correlation;
the function construction module is used for constructing an adaptability function by taking the constraint factors as constraint conditions, taking the coordinates of the region of interest as an optimization variable and taking the grade coefficients as weight values of the optimization variable;
the path optimizing module is used for establishing an optimizing space based on the fitness function, and carrying out routing inspection path optimization on the region of interest through the optimizing space to obtain routing inspection path planning;
the region determining module is used for obtaining a patrol target, and determining an interested region based on target parameter matching between the patrol target and all regions;
the coordinate determining module is used for obtaining a region map based on the region of interest and determining the coordinate of the region of interest based on a map range, wherein the coordinate of the region of interest comprises a region frame coordinate and a ground object coordinate;
the grade determining module is used for determining the interested grade according to the matching degree of the target parameter and the interested region;
the parameter matching module is used for matching the ground object operation parameters of the region of interest with the target parameters to determine matching operation parameters, wherein the matching operation parameters comprise an acquisition target, an operation period and an operation time, and the matching operation parameters are used as the interesting parameter;
the parameter setting module is used for setting path planning influence parameters, wherein the parameter setting module comprises path nodes, node residence time and parameter adjustment loss of the node inspection equipment;
the correlation coefficient determining module is used for performing correlation calculation on each parameter in the attention parameter list according to the path nodes, the node residence time and the node inspection equipment parameter adjustment loss to obtain a correlation degree, and determining a correlation coefficient based on the correlation degree;
the correlation calculation module is used for calculating and obtaining the correlation of each parameter according to the numerical value of each parameter in the attention parameter list and the correlation coefficient;
the constraint factor determining module is used for screening the correlation from large to small according to the preset screening quantity based on the correlation of each parameter, and the obtained influence parameter is used as a constraint factor;
the abnormality analysis module is used for carrying out constraint data abnormality analysis on the constraint factors, and when the constraint data of the constraint factors are overlapped, abnormality exists;
the data labeling module is used for labeling constraint data existing in each region of interest based on the abnormal information;
the regional division module is used for dividing the region of interest by using labels and determining planning grouping information;
and the path planning module is used for determining a grouping constraint factor as a constraint condition based on the planning grouping information, respectively constructing a grouping fitness function for each planning grouping, and respectively carrying out path planning on each planning grouping.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310573606.3A CN116307335B (en) | 2023-05-22 | 2023-05-22 | Method and system for planning tour-inspection path of region of interest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310573606.3A CN116307335B (en) | 2023-05-22 | 2023-05-22 | Method and system for planning tour-inspection path of region of interest |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116307335A CN116307335A (en) | 2023-06-23 |
| CN116307335B true CN116307335B (en) | 2023-08-04 |
Family
ID=86830894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310573606.3A Active CN116307335B (en) | 2023-05-22 | 2023-05-22 | Method and system for planning tour-inspection path of region of interest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116307335B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102798394A (en) * | 2011-05-26 | 2012-11-28 | 上海博泰悦臻电子设备制造有限公司 | Route planning method and system |
| CN103631974A (en) * | 2013-12-24 | 2014-03-12 | 国家电网公司 | Power-distribution inspection path planning method based on Android |
| CN106570649A (en) * | 2016-11-09 | 2017-04-19 | 国网江西省电力公司检修分公司 | Realization method and inspection system for intelligent inspection and route planning based on cloud computing |
| CN111401146A (en) * | 2020-02-26 | 2020-07-10 | 长江大学 | Unmanned aerial vehicle power inspection method, device and storage medium |
| WO2020193155A1 (en) * | 2019-03-27 | 2020-10-01 | Zf Friedrichshafen Ag | Method and control device for lane guidance |
| CN114861557A (en) * | 2022-07-05 | 2022-08-05 | 武汉大学 | Multi-objective optimization method and system for dynamically using neural network |
| CN115935610A (en) * | 2022-11-15 | 2023-04-07 | 国网浙江省电力有限公司湖州供电公司 | Method and system for optimizing routing inspection strategy of unmanned aerial vehicle on overhead line |
| CN116105739A (en) * | 2023-02-27 | 2023-05-12 | 国网河南省电力公司濮阳供电公司 | Unmanned aerial vehicle wind power detection dynamic path optimal planning method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114895707B (en) * | 2022-05-13 | 2023-06-30 | 华南农业大学 | Agricultural unmanned aerial vehicle path planning method and system based on variable frequency bat algorithm |
-
2023
- 2023-05-22 CN CN202310573606.3A patent/CN116307335B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102798394A (en) * | 2011-05-26 | 2012-11-28 | 上海博泰悦臻电子设备制造有限公司 | Route planning method and system |
| CN103631974A (en) * | 2013-12-24 | 2014-03-12 | 国家电网公司 | Power-distribution inspection path planning method based on Android |
| CN106570649A (en) * | 2016-11-09 | 2017-04-19 | 国网江西省电力公司检修分公司 | Realization method and inspection system for intelligent inspection and route planning based on cloud computing |
| WO2020193155A1 (en) * | 2019-03-27 | 2020-10-01 | Zf Friedrichshafen Ag | Method and control device for lane guidance |
| CN111401146A (en) * | 2020-02-26 | 2020-07-10 | 长江大学 | Unmanned aerial vehicle power inspection method, device and storage medium |
| CN114861557A (en) * | 2022-07-05 | 2022-08-05 | 武汉大学 | Multi-objective optimization method and system for dynamically using neural network |
| CN115935610A (en) * | 2022-11-15 | 2023-04-07 | 国网浙江省电力有限公司湖州供电公司 | Method and system for optimizing routing inspection strategy of unmanned aerial vehicle on overhead line |
| CN116105739A (en) * | 2023-02-27 | 2023-05-12 | 国网河南省电力公司濮阳供电公司 | Unmanned aerial vehicle wind power detection dynamic path optimal planning method and system |
Non-Patent Citations (1)
| Title |
|---|
| 面向复杂空间的移动机器人路径规划问题研究;申浩阳;《信息科技》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116307335A (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106646338B (en) | A kind of quickly accurate indoor orientation method | |
| CN111464938B (en) | Positioning method, positioning device, electronic equipment and computer readable storage medium | |
| CN106851571B (en) | Decision tree-based rapid KNN indoor WiFi positioning method | |
| CN104540221A (en) | WLAN indoor positioning method based on semi-supervised SDE algorithm | |
| CN110234062B (en) | Positioning method, positioning device, server and computer readable storage medium | |
| CN108828519B (en) | High-precision indoor visible light positioning method based on machine learning | |
| CN114486764B (en) | Agricultural non-point source pollution monitoring system based on full spectrum water quality analyzer | |
| CN111148057B (en) | Indoor positioning method, system, computer equipment and readable storage medium | |
| CN102253365B (en) | Indoor positioning method based on estimation of wireless signal source parameters | |
| CN114942842A (en) | Control system and control method of intelligent terminal of Internet of things | |
| CN112669190A (en) | Detection method and device for abnormal emission behavior of pollution source and computer equipment | |
| JP2013153286A (en) | Information processing device and cluster generation method | |
| CN115808170A (en) | Indoor real-time positioning method integrating Bluetooth and video analysis | |
| CN116307335B (en) | Method and system for planning tour-inspection path of region of interest | |
| CN108574927B (en) | Mobile terminal positioning method and device | |
| CN115979215B (en) | Floor recognition method and device and computer readable storage medium | |
| CN108495261B (en) | Indoor position accurate positioning method and system based on wireless sensor | |
| CN115936680A (en) | Intelligent order dispatching method and system for equipment operation and maintenance | |
| CN116164730A (en) | Photovoltaic equipment positioning navigation method and related equipment | |
| CN112862921B (en) | Power grid distribution image drawing method | |
| CN115018014A (en) | Machine learning-assisted communication scene classification method based on multi-source information | |
| CN115550757A (en) | Electric power distribution shaft tower monitoring and early warning system | |
| CN113850173A (en) | Method, device and medium for eliminating repeated positioning of faulty photovoltaic module | |
| AU2017255214B2 (en) | A geolocating system for a mobile device | |
| CN109639463A (en) | A kind of determination method of Internet of Things monitoring point neighbouring relations |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |