CN113011780B - Task allocation method for multi-unmanned aerial vehicle cooperative power inspection - Google Patents

Task allocation method for multi-unmanned aerial vehicle cooperative power inspection Download PDF

Info

Publication number
CN113011780B
CN113011780B CN202110394113.4A CN202110394113A CN113011780B CN 113011780 B CN113011780 B CN 113011780B CN 202110394113 A CN202110394113 A CN 202110394113A CN 113011780 B CN113011780 B CN 113011780B
Authority
CN
China
Prior art keywords
unmanned aerial
aerial vehicle
task
parking point
tower
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
Application number
CN202110394113.4A
Other languages
Chinese (zh)
Other versions
CN113011780A (en
Inventor
王红星
黄郑
于滨
刘斌
吴媚
顾徐
朱洁
曹峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beihang University
Jiangsu Fangtian Power Technology Co Ltd
Original Assignee
Beihang University
Jiangsu Fangtian Power Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beihang University, Jiangsu Fangtian Power Technology Co Ltd filed Critical Beihang University
Priority to CN202110394113.4A priority Critical patent/CN113011780B/en
Publication of CN113011780A publication Critical patent/CN113011780A/en
Application granted granted Critical
Publication of CN113011780B publication Critical patent/CN113011780B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06316—Sequencing of tasks or work
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling
    • 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
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Biophysics (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Evolutionary Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Genetics & Genomics (AREA)
  • Evolutionary Computation (AREA)
  • Physiology (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a task allocation method for multi-unmanned aerial vehicle cooperative power inspection, which comprises the following steps: acquiring a parking point position, a task set and an unmanned aerial vehicle set; calculating the actual distance between each task tower and the parking point; constructing a task allocation model of the multi-unmanned aerial vehicle cooperative power inspection, wherein the allocation model takes the time for the longest unmanned aerial vehicle to complete the allocated task subset as an optimization target, and the hypothesis and constraint conditions of the task allocation model are set according to the actual condition of the power inspection; and solving the task allocation model by adopting a genetic algorithm to obtain an overall optimal solution which realizes an optimization target and meets constraint conditions. According to the invention, according to the current power inspection actual situation and the power inspection task requirement of the unmanned aerial vehicle, the input of relevant coordinates and parameter information can be realized, the task sequence of the unmanned aerial vehicle can be obtained by solving, the task time of a plurality of unmanned aerial vehicles is ensured to be close, the waiting waste of the unmanned aerial vehicle is reduced, the total time of all unmanned aerial vehicles completing all inspection tasks at a single parking point is minimized, and the power inspection efficiency is improved.

Description

Task allocation method for multi-unmanned aerial vehicle cooperative power inspection
Technical Field
The invention relates to the technical field of unmanned aerial vehicle power inspection, in particular to a task allocation method for multi-unmanned aerial vehicle cooperative power inspection.
Background
The small multi-rotor unmanned aerial vehicle has the advantages of light weight, small size, high maneuverability, small influence caused by terrain limitation, capability of hovering and shooting images and the like, and is widely applied to the field of power inspection. Efficiency and the quality of patrolling and examining of unmanned aerial vehicle electric power are patrolled and examined than traditional manual work and are patrolled and examined and have huge promotion.
Particularly, the unmanned aerial vehicle in China passes through the development of years in the aspect of power patrol, and successively passes through four stages of establishing test points, deploying, popularizing the test points and mainly patrolling people, assisting the patrolling of the unmanned aerial vehicle, mainly patrolling the unmanned aerial vehicle and assisting the unmanned aerial vehicle. And along with the popularization of internet 5G communication and the development of unmanned aerial vehicle control technology, the unmanned aerial vehicle is capable of autonomously patrolling and examining, manpower and material resources can be saved to a great extent, the patrolling and examining efficiency is improved, and the proportion of unmanned aerial vehicle autonomously patrolling and examining in power transmission lines is improved in the future by introducing complete sets of patrolling and examining equipment and other modes in each province and city power grid company.
But present unmanned aerial vehicle electric power is patrolled and examined and still is in the starting phase, mainly patrols and examines by flying hand manual operation unmanned aerial vehicle, and is subject to the shortcoming such as small-size many rotor unmanned aerial vehicle duration short, remote mobility is poor, and unmanned aerial vehicle electric power patrols and examines efficiency still has great promotion space.
At present, a part of provincial and municipal electric power companies provide a new mode of cooperative inspection of an unmanned aerial vehicle and an operation vehicle, the operation vehicle is used as a carrier and a supply station of the unmanned aerial vehicle, the advantages of the operation vehicle and the unmanned aerial vehicle are complementary, and the operation vehicle can be used as power inspection complete equipment to be put into actual power inspection work. Meanwhile, some provincial and municipal power companies have developed the cooperative routing inspection test work of unmanned aerial vehicles and operation vehicles, and the problems of disordered task allocation of the unmanned aerial vehicles, random running paths of the operation vehicles and the like occur in the actual test work. By looking up relevant documents and data, the theory research on the cooperative inspection of the unmanned aerial vehicle and the operating vehicle is less at home and abroad at present according to the knowledge of people, and the theory guidance cannot be provided for the actual power inspection work.
Disclosure of Invention
Technical problem to be solved
Aiming at the technical problem, the invention provides a task allocation method for cooperative power inspection of multiple unmanned aerial vehicles. According to the invention, under the condition that coordinates of a tower to be inspected and relevant flight parameters of the unmanned aerial vehicle are known, the task sequence of each unmanned aerial vehicle is obtained by solving through the cooperative power inspection task allocation method of the multiple unmanned aerial vehicles, so that the optimization target of minimizing the task time of the unmanned aerial vehicle which consumes the longest time is achieved.
The invention is based on the actual power inspection condition, can directly calculate according to the longitude and latitude coordinates of the tower to be inspected, does not need to convert into relative coordinates, finally solves the task distribution result to provide the task sequence corresponding to each unmanned aerial vehicle, and can greatly facilitate the operation process of the inspection personnel.
(II) technical scheme
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
the invention provides a task allocation method for multi-unmanned aerial vehicle cooperative power inspection, which is characterized by comprising the following steps:
acquiring a parking point position coordinate, a power inspection task set of an area to be inspected and an unmanned aerial vehicle set capable of executing an inspection task currently;
calculating the geographical linear distance from each electric power tower to a parking point in the electric power inspection task set of the area to be inspected;
constructing a multi-unmanned aerial vehicle cooperative power inspection task allocation model with multiple constraints based on the actual power inspection situation of the unmanned aerial vehicle and the task scene requirements;
aiming at the uniqueness of the task and the homogeneity of the unmanned aerial vehicle, a real number coding mode is adopted, and any feasible solution suitable for the task allocation problem is coded into a complete chromosome in a straight line mode;
and generating an initial population of a preset scale according with a model constraint equation according to the coding mode of the multi-unmanned aerial vehicle cooperative power inspection task distribution model information and the genetic algorithm.
And solving the multi-unmanned-aerial-vehicle cooperative power inspection task allocation model by adopting a genetic algorithm, wherein the optimal solution obtained under the maximum iteration number is the optimal task allocation scheme of the multi-unmanned-aerial-vehicle inspection system.
Further, the parking point is the parking point of operation car, and the operation car is put away at the parking point and is flown and retrieve unmanned aerial vehicle for unmanned aerial vehicle can visit the shaft tower of patrolling and examining of waiting in the parking point operation radius.
Further, the geographical straight-line distance from the parking point to all the electric power towers of the unmanned aerial vehicle is calculated by the formula (1):
d0i＝R*arccos[sin(x0)*sin(xi)+cos(x0)*cos(xi)*cos(y0-yi)]formula (1)
Wherein d is0iRepresenting the geographical straight-line distance from the electric power tower i to the parking point 0; (y)0,x0) Latitude and longitude coordinates, y, representing parking point 00Longitude, x, of parking Point 00Latitude of parking point 0; (y)i,xi) Representing the latitude and longitude coordinates, y, of the tower iiLongitude, x, of tower iiThe latitude of the tower i; r is the radius of the earth, and 6371.004km is taken.
Further, the task allocation model objective function of the cooperative power inspection tour of the multiple unmanned aerial vehicles is expressed by adopting the task time value of the unmanned aerial vehicle which is the longest in minimized time consumption, as shown in formula (2):
Minimize：max{Z0equation (2)
Wherein, aggregate
Figure GDA0003580625580000031
For the set of mission times for all drones at parking point 0,
Figure GDA0003580625580000032
for unmanned plane UiTask time at parking Point 0, Ui∈U＝{U1,U2,...,UmAnd numbering for the unmanned plane.
Further, the constraint conditions of the multi-unmanned aerial vehicle collaborative power patrol task allocation model are expressed by formulas (3) to (6):
Figure GDA0003580625580000033
Figure GDA0003580625580000034
Figure GDA0003580625580000035
Figure GDA0003580625580000036
where 0 denotes the parking point number of the work vehicle, and T ═ T { (T {)1,T2,...,TnThe unmanned aerial vehicle is a set of all towers to be patrolled within the operation radius of the parking point, the total number of the towers to be patrolled is n, and the set of unmanned aerial vehicles capable of executing the patrol task at the parking point 0 is U ═ U }1,U2,...,Um}；f0iRepresenting the number of times that the unmanned aerial vehicle i takes off at the parking point 0; d0jFor tower TjA geographical linear distance from park point 0; v is the flying speed of the unmanned aerial vehicle when the unmanned aerial vehicle comes and goes to and from the parking point and the electric power tower; x is the number ofijIs a variable of 0 to 1, when the unmanned plane UiAccess tower TjIf the value is 1, otherwise, the value is 0; cjFor unmanned aerial vehicle at shaft tower TjThe patrol time of the department;
formula (3) indicates that each tower has only one drone to visit once;
formula (4) shows that the sum of the taking-off times of all the unmanned aerial vehicles at the parking point 0 is equal to the total number of towers to be patrolled, namely, each unmanned aerial vehicle only patrols one base tower every time when taking off;
formula (5) shows that the task time of each unmanned aerial vehicle is equal to the sum of the round-trip flight time and the sum of the patrol time at the tower;
equation (6) is a decision variable constraint.
Furthermore, the genetic algorithm is adopted to solve the multi-unmanned aerial vehicle cooperative power inspection task allocation model, and an optimal task allocation scheme of the multi-unmanned aerial vehicle inspection system can be obtained.
Furthermore, as the patrol inspection time of each unmanned aerial vehicle at the tower can be regarded as approximately equal and far longer than the flight time between the round-trip parking point and the electric power tower, under the optimization target of the task time of the unmanned aerial vehicle with the longest minimum consumed time, the number of the task poles of each unmanned aerial vehicle is close as much as possible, and the total round-trip flight distance of each unmanned aerial vehicle is close, the task time of each unmanned aerial vehicle can be ensured to be close, so that the chromosome segment length corresponding to each unmanned aerial vehicle is ensured to be close as much as possible during chromosome coding.
Furthermore, the chromosome coding mode of the genetic algorithm is real number coding, each chromosome is coded into a number sequence of 1 row and n columns, wherein n is the total number of the towers to be inspected. And (3) proportionally and evenly dividing each chromosome into m sections, wherein m is the total number of unmanned aerial vehicles capable of executing tasks, and each section of chromosome represents one unmanned aerial vehicle task sequence. For example, the j-th segment of chromosome A, using AjRepresenting the task sequence of the jth drone in individual a.
Optionally, the initial chromosome generation mode is to generate a random number sequence B of 1-n, wherein n is the total number of towers to be inspected; m is the total number of unmanned aerial vehicles capable of executing the routing inspection task, n/m is calculated, the result is rounded to a, the number of task pole towers of the front m-1 unmanned aerial vehicles is a, the number of task pole towers of the last unmanned aerial vehicle is n- (m-1) × a, the task sequence of the first unmanned aerial vehicle is the 1 st to a th elements in B, the task sequence of the second unmanned aerial vehicle is the a +1 st to 2 × a th elements in B, and the rest elements are obtained by analogy in sequence, and the task sequence of the last unmanned aerial vehicle is all the remaining elements in B.
Further, the genetic algorithm takes a formula (2) as a fitness function, an optimization process of the minimum fitness function is carried out on the initial population by improving genetic operations such as selection, crossing and variation of the genetic algorithm, the best feasible solution is obtained under the fixed iteration times, and the obtained result is used as a result of the cooperative power inspection task distribution of the multiple unmanned aerial vehicles.
(III) advantageous results
Compared with the prior optimization scheme, the method has the following advantages:
1. according to the method, the background of task allocation confusion of multiple unmanned aerial vehicles in actual power inspection is taken, the task allocation model of the unmanned aerial vehicles cooperating with the power inspection is established and solved by adopting a genetic algorithm, the optimization target is the task time of the unmanned aerial vehicle with the longest minimum time consumption, the waiting waste of the unmanned aerial vehicles is reduced by converting the optimization target into the similarity of the task time of each unmanned aerial vehicle, the resources of the unmanned aerial vehicles are utilized to the maximum extent, and the power inspection efficiency of the unmanned aerial vehicles can be effectively improved.
2. The multi-unmanned-aerial-vehicle cooperative power inspection task allocation method provided by the invention can be used for calculating by directly utilizing the longitude and latitude coordinates of the actual power tower, thereby being greatly convenient for the practical application of power companies.
3. According to the method for distributing the multi-unmanned aerial vehicle collaborative power inspection tasks, the parking point and the coordinates of the power tower in the area to be inspected can be input, the optimal task distribution scheme of the unmanned aerial vehicle is obtained, the task distribution scheme is the task sequence of each unmanned aerial vehicle, and the method has a high practical application value.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is also possible for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a flow chart of a method for allocating a task for cooperative power inspection by multiple unmanned aerial vehicles according to the present invention;
FIG. 2 is a flow chart of a genetic algorithm adopted by the cooperative power inspection task allocation method of multiple unmanned aerial vehicles provided by the invention;
fig. 3 is an application scenario of a multi-unmanned-aerial-vehicle cooperative power inspection task allocation method according to a specific embodiment of the present invention;
FIG. 4 is an example of chromosome coding patterns in the genetic algorithm used in the present invention;
FIG. 5 is an example of the initial chromosome coding pattern in the genetic algorithm used in the present invention;
FIG. 6 is an example of crossover operations in a genetic algorithm used in the present invention;
FIG. 7 is an example of mutation operations in the genetic algorithm used in the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments obtained by a person skilled in the art based on the embodiments of the present invention without any creative effort belong to the protection scope of the present invention.
The invention provides a multi-unmanned aerial vehicle cooperative power inspection task allocation method, which has the following general scheme:
acquiring a parking point position, a task set and an unmanned aerial vehicle set; calculating the geographical linear distance between each task tower and the parking point; constructing a task allocation model of the multi-unmanned aerial vehicle cooperative power inspection, wherein the allocation model takes the time for the longest unmanned aerial vehicle to complete the allocated task subset as an optimization target, and the hypothesis and constraint conditions of the task allocation model are set according to the actual condition of the power inspection; and solving the task allocation model by adopting a genetic algorithm, wherein the genetic algorithm adopts a real number coding mode to obtain an overall optimal solution which realizes the optimization target and meets the constraint condition, and the overall optimal solution represents the task subset of each unmanned aerial vehicle.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Fig. 1 is a flowchart of a method for allocating a task for power inspection in cooperation with multiple unmanned aerial vehicles according to the present invention, and it can be seen from fig. 1 that the method for allocating a task for power inspection in cooperation with multiple unmanned aerial vehicles according to the present invention includes:
step S1: acquiring a parking point position coordinate, a power inspection task set of an area to be inspected and an unmanned aerial vehicle set capable of executing an inspection task currently;
step S2: calculating the geographical linear distance from each electric power tower to a parking point in the electric power inspection task set of the area to be inspected;
step S3: constructing a multi-unmanned aerial vehicle cooperative power inspection task allocation model with multiple constraints based on the actual power inspection situation of the unmanned aerial vehicle and the task scene requirements;
step S4: aiming at the uniqueness of the task and the homogeneity of the unmanned aerial vehicle, a real number coding mode is adopted, and any feasible solution suitable for the task allocation optimization problem is coded into a complete chromosome in a straight line mode;
step S5: and generating an initial population of a preset scale according with a model constraint equation according to the coding mode of the multi-unmanned aerial vehicle cooperative power inspection task distribution model information and the genetic algorithm.
Step S6: and solving the multi-unmanned-aerial-vehicle cooperative power inspection task allocation model by adopting a genetic algorithm, wherein the optimal solution obtained under the maximum iteration number is the optimal task allocation scheme of the multi-unmanned-aerial-vehicle inspection system.
Furtherly, the parking point is the parking point of operation car, and the operation car is flown and is retrieved unmanned aerial vehicle in the parking point for unmanned aerial vehicle accessible parking point operation is treated in the radius and is patrolled and examined the shaft tower.
Furthermore, the power inspection task set of the area to be inspected comprises the numbers and the position coordinates of all power towers to be inspected in the area to be inspected and the time for inspecting each tower; the set of unmanned aerial vehicles capable of executing the inspection task comprises the number, the number and the flight speed of the unmanned aerial vehicles.
Further, the geographical straight-line distance is a straight-line distance between two points in a real environment. And calculating the geographical linear distance from each electric power tower to the parking point, storing by using a one-dimensional matrix, and recording as a one-dimensional distance matrix Dmat.
Further, the geographical straight-line distance from the electric power tower to the parking point is calculated by the formula (1):
d0i＝R*arccos[sin(x0)*sin(xi)+cos(x0)*cos(xi)*cos(y0-yi)]formula (1)
Wherein d is0iRepresenting the geographical straight-line distance from the electric power tower i to the parking point 0; (y)0,x0) Latitude and longitude coordinates, y, representing parking point 00Longitude, x, of parking Point 00Latitude of parking point 0; (y)i,xi) Representing the latitude and longitude coordinates, y, of the tower iiLongitude, x, of tower iiThe latitude of the tower i; r is the radius of the earth, and 6371.004km is taken.
Further, the one-dimensional distance matrix is a matrix with n rows and 1 column, n is the total number of the towers to be inspected in the area to be inspected, and each row in the one-dimensional distance matrix stores the geographical straight-line distance from each tower to the parking point, as shown in table 1.
TABLE 1 one-dimensional distance matrix
Line number One-dimensional distance matrix Dmat
1 d01
2 d02
3 d03
··· ···
n d0n
Further, the optimization target of the task allocation model for the cooperative power inspection of the multiple unmanned aerial vehicles is the task time of the unmanned aerial vehicle with the longest minimum consumed time, namely, the task time of each unmanned aerial vehicle is guaranteed to be close as much as possible, the phenomenon that some unmanned aerial vehicle has a longer task time and causes other unmanned aerial vehicles to wait is avoided, so that the resources of the unmanned aerial vehicles are utilized to the maximum, and the total time for all unmanned aerial vehicles to complete all inspection tasks is optimized.
Further, according to the actual power patrol inspection condition, the basic hypothesis of the model distributed by the multi-unmanned aerial vehicle cooperative power patrol inspection task is that: taking off and landing the unmanned aerial vehicle from the same parking point; each unmanned aerial vehicle is homogeneous, the speed between the reciprocating parking point and the target tower is the same, and the time for each unmanned aerial vehicle to take off and land once is the same as the time for each unmanned aerial vehicle to replace the battery once; because the unmanned aerial vehicle is restricted in endurance and safe in return at the present stage, each unmanned aerial vehicle only accesses one base tower by taking off once; the inspection time of each unmanned aerial vehicle at the electric power tower is approximately equal and far longer than the flight time between the round-trip parking point and the tower.
Further, according to the actual power patrol inspection condition, the constraint conditions of the model distributed by the multi-unmanned aerial vehicle cooperative power patrol inspection task are as follows: each base tower is provided with and only one unmanned aerial vehicle for accessing once; the total takeoff times of all the unmanned aerial vehicles in the area to be patrolled are equal to the total number of all the towers to be patrolled in the area to be patrolled, namely, each unmanned aerial vehicle takes off once and only patrols one base tower.
Referring to the above steps, a multi-unmanned aerial vehicle cooperative power inspection task allocation model is established, and is expressed as formula (2) to formula (6):
Minimize：max{Z0equation (2)
Figure GDA0003580625580000081
Figure GDA0003580625580000082
Figure GDA0003580625580000083
Figure GDA0003580625580000084
Wherein 0 represents the parking point number of the working vehicle, set
Figure GDA0003580625580000085
For the set of mission times for all drones at parking point 0,
Figure GDA0003580625580000086
for unmanned plane UiTask time at parking Point 0, Ui∈U＝{U1,U2,...,UmThe unmanned plane is numbered, and T is { T ═ T }1,T2,...,TnThe tower number is n, and the tower number is n; f. of0iExpress unmanned plane UiNumber of takeoff at parking point 0; d0jFor tower TjA geographical linear distance from park point 0; v is the flying speed of the unmanned aerial vehicle when the unmanned aerial vehicle comes and goes to and from the parking point and the electric power tower; x is the number ofijIs a variable of 0 to 1, when the unmanned plane UiAccess tower TjIf the value is 1, otherwise, the value is 0; cjFor unmanned aerial vehicle at shaft tower TjThe patrol time of the department;
formula (2) represents that the objective function of the model is to minimize the task time of the unmanned aerial vehicle which consumes the longest time;
formula (3) indicates that each tower has and only has one drone to visit once;
formula (4) shows that the sum of the taking-off times of all the unmanned aerial vehicles at the parking point 0 is equal to the total number of towers to be patrolled, namely, each unmanned aerial vehicle only patrols one base tower every time when taking off;
formula (5) shows that the task time of each unmanned aerial vehicle is equal to the sum of the round-trip flight time and the sum of the patrol time at the tower;
equation (6) is a decision variable constraint.
Furthermore, because the patrol time of each unmanned aerial vehicle at the tower is far longer than the flight time between the round-trip parking point and the electric power tower, under the optimization target of the task time of the unmanned aerial vehicle with the longest minimum time consumption, the number of the task pole towers of each unmanned aerial vehicle is close as much as possible, and the total round-trip flight distance of each unmanned aerial vehicle is close, so that the task time of each unmanned aerial vehicle can be ensured to be close, and the chromosome segment length corresponding to each unmanned aerial vehicle is ensured to be close as much as possible during chromosome coding.
Further, each chromosome is coded into a number sequence of 1 row and n columns, wherein n is the total number of the towers to be inspected. And (3) proportionally and evenly dividing each chromosome into m segments, wherein m is the total number of unmanned aerial vehicles capable of executing tasks, and each segment of chromosome represents an unmanned aerial vehicle task sequence. For example, the j-th segment of chromosome A, using AjIndicating a sequence of tasks representing the jth drone in individual a.
Optionally, the initial chromosome generation mode is to generate a random number sequence B of 1-n, wherein n is the total number of towers to be inspected; m is the total number of unmanned aerial vehicles capable of executing the routing inspection task, n/m is calculated, the result is rounded to a, the number of task pole towers of the front m-1 unmanned aerial vehicles is a, the number of task pole towers of the last unmanned aerial vehicle is n- (m-1) × a, the task sequence of the first unmanned aerial vehicle is the 1 st to a th elements in B, the task sequence of the second unmanned aerial vehicle is the a +1 st to 2 × a th elements in B, and the rest elements are obtained by analogy in sequence, and the task sequence of the last unmanned aerial vehicle is all the remaining elements in B.
Furthermore, the problem of task allocation of the multi-unmanned aerial vehicle cooperative power inspection tour is an NP-Hard problem, a heuristic algorithm is adopted for solving, so that a better solution can be obtained, and the solving speed is higher. Referring to step S5 above, the initial task allocation plan is optimized and solved by using a genetic algorithm to obtain an optimal task allocation plan for each drone.
Solving the multi-unmanned-aerial-vehicle cooperative power inspection task allocation model by adopting a genetic algorithm, performing an optimization process of a minimum fitness function on an initial population by improving genetic operations such as selection, intersection, variation and the like of the genetic algorithm by taking a formula (2) as an individual fitness function, solving the best feasible solution under a fixed iteration number, and taking the solved result as the result of multi-unmanned-aerial-vehicle cooperative power inspection task allocation. The flow chart of the genetic algorithm is shown in fig. 2. Chromosome coding and population initialization referred to in fig. 2 are shown as steps S4 and S5. The selection, crossover and variant genetic operating rules are as follows:
selecting operation: individuals in the population are selected by a roulette method to carry out crossover and mutation operations. The invention discloses a multi-unmanned aerial vehicle collaborative power inspection task allocation method, which aims to minimize the task time of an unmanned aerial vehicle consuming the longest time, namely minimize a fitness function value, and the probability of individual selection in a roulette method is proportional to the fitness value thereof. Thus, scale NPPopulation of (2), fitness function value being fi,i＝1,2,...,Np(ii) a Probability p of individual i being selectedi,i＝1,2...,NPAs shown in equation (7), the higher the fitness function value, the lower the probability that the individual is selected.
Figure GDA0003580625580000101
Wherein the individual i, i ═ 1,2, NPFitness function fiThe calculation method is shown in formula (8):
fi＝max{Z0equation (8)
Wherein
Figure GDA0003580625580000102
For the set of mission times for all drones at parking point 0,
Figure GDA0003580625580000103
for unmanned plane UiTask time at parking Point 0, Ui∈U＝{U1,U2,...,UmThe unmanned aerial vehicle is numbered,
Figure GDA0003580625580000104
the calculation method is shown in equation (9).
Figure GDA0003580625580000105
Wherein T ═ { T ═ T1,T2,...,TnThe tower to be patrolled is set; d0jFor tower TjA geographical linear distance from park point 0; v is the flying speed of the unmanned aerial vehicle when the unmanned aerial vehicle comes and goes to and from the parking point and the electric power tower; x is the number ofijIs a variable of 0 to 1, when the unmanned plane UiAccess tower TjIf the value is 1, otherwise, the value is 0; cjFor unmanned aerial vehicle at shaft tower TjThe patrol time of the department.
And (3) cross operation: and selecting the individual with the lowest fitness function value in the parent through a roulette method, wherein the chromosome of the individual is the father chromosome. The present invention uses a 2-opt crossover method to generate offspring chromosomes from parent chromosomes. The introduction of the cross operation enhances the searching capability of the genetic algorithm.
Further, the 2-opt crossing method is that two points M and N are randomly selected from a parent chromosome, chromosomes before M are added into a new chromosome without changing, chromosomes between M and N are added into the new chromosome after numbering is reversed, and sequences after N are added into the new sequence without changing.
Mutation operation: the invention adopts a method of randomly selecting two pairs of nonadjacent gene positions to interchange gene values to carry out mutation operation. The introduction of mutation operation maintains the population diversity of genetic algorithm.
The following describes how to obtain the task sequence of each unmanned aerial vehicle according to the above cooperative power inspection task allocation method for multiple unmanned aerial vehicles by using a specific example. The embodiment provided by the invention is designed on the basis of the actual power patrol inspection condition and the actual power tower coordinates, and all the tower coordinates are randomized on the basis of the actual tower positions, so that the effectiveness of the method provided by the invention is illustrated through specific examples.
Under MATLAB simulation condition, supposing that m is 4 homogeneous unmanned aerial vehicles capable of executing the inspection task, the inspection area has n is 20 bases to be inspected on the tower, and the parking point and the position coordinate of the tower to be inspected are shown in table 2. Wherein, because the electric power tower waiting to be patrolled and examined is homogeneous, so every shaft tower TjTime C required to patroljAre all the same.
Further, an application scenario provided by the embodiment of the invention is shown in fig. 3, where the number 0 represents a parking point of the working vehicle, and the numbers 1 to 20 represent positions of electric power towers in an area to be inspected.
Further, the relevant parameters of the genetic algorithm in the embodiment of the present invention are set as follows: the population size is 80, the crossover probability is 0.9, the mutation probability is 0.01, and the iteration number is 500.
TABLE 2 parking point and tower longitude and latitude coordinates of area to be patrolled and examined
Serial number Longitude (longitude) Latitude Serial number Longitude (G) Latitude
Parking point 0 117.1530 33.8807 Pole tower T11 117.166742 33.859388
Pole tower T1 117.139713 33.903043 Pole tower T12 117.155077 33.869381
Pole tower T2 117.159363 33.886134 Pole tower T13 117.163622 33.895509
Pole tower T3 117.147162 33.87538 Pole tower T14 117.177978 33.892562
Pole tower T4 117.122702 33.892001 Pole tower T15 117.165139 33.858737
Pole tower T5 117.120785 33.880803 Pole tower T16 117.174174 33.868737
Pole tower T6 117.111862 33.878634 Pole tower T17 117.134719 33.884602
Pole tower T7 117.151833 33.888902 Pole tower T18 117.171926 33.88485
Pole tower T8 117.146367 33.856802 Pole tower T19 117.186436 33.862767
Pole tower T9 117.154065 33.903407 Pole tower T20 117.18737 33.892182
Pole tower T10 117.123327 33.880778
The specific distribution steps are as follows:
the longitude and latitude coordinates of the parking point are (117.1530,33.8807), and the power inspection task set of the area to be inspected is T ═ T { (T)1,T2,...,T20And (4) a set of unmanned aerial vehicles (U) capable of executing inspection tasks currently1,U2,U3,U4}。
The geographical linear distance of each element in the set T from the parking point 0 is calculated and stored in a one-dimensional distance matrix Dmat. The one-dimensional distance matrix Dmat in the embodiment provided by the present invention can be represented in the following form, which is represented by a transposed matrix form of the Dmat matrix herein for convenience of illustration.
DmatT＝[2.7706,0.8427,0.8003,3.0661,2.9739,3.8046,0.9184,2.7270,2.5268,2.7392,2.6880,1.2731,1.9165,2.6563,2.6871,2.3648,1.7424,1.8070,3.6750,3.4199]
And establishing a multi-unmanned-aerial-vehicle cooperative power inspection task allocation model as shown in the formula (2) to the formula (6).
And (3) establishing a chromosome in a straight line form by adopting a real number coding mode. An example of chromosome coding according to the embodiment of the present invention is shown in FIG. 4. Specifically, each individual chromosome is coded into a one-dimensional array, and the length of the array is equal to the total number of the electric power towers in the region to be inspected. The task allocation method provided by the invention has the optimization goal that the task time of each unmanned aerial vehicle is as close as possible, namely the length of the task sequence of each unmanned aerial vehicle is close and the total distance of the back-and-forth flight is close, so that each individual chromosome is uniformly divided into m segments according to the number m of the unmanned aerial vehicles capable of executing the routing inspection task, and each segment of chromosome is the task sequence of each unmanned aerial vehicle. In this embodiment, each individual chromosome may be evenly divided into 4 segments, each segment representing the task sequence of each drone.
And generating an initial population of a preset scale which accords with the model constraint equation. The initial chromosome is a random sequence of numbers 1 to n, and the code of the initial chromosome is shown in FIG. 5.
And solving the multi-unmanned-aerial-vehicle cooperative power inspection task allocation model by adopting a genetic algorithm, wherein the solving comprises selection, crossing and variation operations, and the optimal solution obtained under the maximum iteration number is the optimal task allocation scheme of the multi-unmanned-aerial-vehicle inspection system.
In which, a specific embodiment of the crossover operation can be shown in fig. 6, specifically, the 2-opt crossover method is used to generate the child chromosomes from the parent chromosomes, and the embodiment randomly selects "8" and "4" of the chromosomes in fig. 4 to crossover, and the crossover result is shown in fig. 6.
The embodiment of the mutation operation can be shown in fig. 7, and specifically, the mutation operation is performed by randomly selecting two pairs of gene values that are not adjacent to each other. In this example, two pairs of non-adjacent loci "8" and "4", "16" and "9" of the chromosome of FIG. 4 were randomly selected for mutation, and the mutation results are shown in FIG. 7.
The code for the genetic algorithm was run in a MATLABR2014a simulation environment, and the resulting assignment results are shown in table 3.
TABLE 3 task assignment results for multi-UAV collaborative power inspection
Figure GDA0003580625580000121
Figure GDA0003580625580000131
Because the optimization goal of the multi-unmanned aerial vehicle collaborative power inspection task allocation method provided by the invention is to minimize the task time of the unmanned aerial vehicle which consumes the longest time, even if the task time of each unmanned aerial vehicle is as close as possible, because the inspection time of the unmanned aerial vehicle at the tower is equal and far longer than the flight time between the round-trip tower and the parking point, in order to ensure that the task time of each unmanned aerial vehicle is close, the method needs to ensure that: (1) the towers in the task sequence of each unmanned aerial vehicle are close in number; (2) the total distance of the back-and-forth flight of each unmanned aerial vehicle is close.
Therefore, as can be seen from the distribution result, when the total number of towers in the area to be inspected is an integral multiple of the total number of unmanned aerial vehicles capable of executing the inspection task, each unmanned aerial vehicle can distribute the same number of electric power towers, and the optimization target of the coordinated electric power inspection task distribution model for the multiple unmanned aerial vehicles provided by the invention can be converted from the unmanned aerial vehicle task time with the longest minimum consumed time to the total flight distance of the unmanned aerial vehicle with the longest minimum round-trip flight distance, that is, the difference between the flight distance of the unmanned aerial vehicle with the longest total round-trip flight distance and the flight distance of the unmanned aerial vehicle with the shortest total round-trip flight distance. In this embodiment, the difference of minimum distance is 0.0348km, can guarantee that four unmanned aerial vehicle's task time is close, reduces unmanned aerial vehicle's the waste of waiting, and the maximize utilizes unmanned aerial vehicle resource.
Further, when the total number of towers in the area to be inspected is not an integral multiple of the total number of unmanned aerial vehicles capable of executing inspection tasks, the optimal task allocation scheme of each unmanned aerial vehicle, which takes the task time of the unmanned aerial vehicle with the longest minimum consumed time as the optimization target, can be obtained by obtaining the round-trip flight speed of the unmanned aerial vehicle and the inspection time at each tower and substituting the round-trip flight speed and the inspection time into the multi-unmanned aerial vehicle cooperative power inspection task allocation model and the solution algorithm.
In summary, the invention takes the task allocation confusion of multiple unmanned aerial vehicles existing in the actual power inspection as the background, the task allocation model of the unmanned aerial vehicles cooperating with the power inspection is established and the genetic algorithm is adopted for solving, the optimization target is the task time of the unmanned aerial vehicle with the longest minimum time consumption, the waiting waste of the unmanned aerial vehicles is reduced by converting the optimization target into the similar task time of each unmanned aerial vehicle, the unmanned aerial vehicle resources are utilized to the maximum extent, and the efficiency of the power inspection of the unmanned aerial vehicles can be effectively improved.
Furthermore, the multi-unmanned-aerial-vehicle cooperative power inspection task allocation method provided by the invention can be used for calculating by directly utilizing the longitude and latitude coordinates of the actual power tower, thereby being convenient for the actual application of a power company to a great extent.
Further, the invention provides a specific embodiment which is designed on the basis of actual power inspection conditions and actual power tower coordinates, and all tower coordinates are randomized on the basis of the actual tower positions, so that how to solve the task sequence of each unmanned aerial vehicle according to the multi-unmanned aerial vehicle cooperative power inspection task allocation method is described in detail, and the effectiveness of the method provided by the invention is illustrated through specific examples.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments can be modified, or some or all of the technical features can be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (4)

1. The utility model provides a task allocation method that many unmanned aerial vehicles patrolled and examined in coordination with electric power, its characterized in that includes:
acquiring a parking point position coordinate, a power inspection task set of an area to be inspected and an unmanned aerial vehicle set capable of executing an inspection task currently;
calculating the geographical linear distance from each electric power tower to a parking point in the electric power inspection task set of the area to be inspected;
constructing a multi-unmanned aerial vehicle cooperative power inspection task allocation model with multiple constraints based on the actual power inspection situation of the unmanned aerial vehicle and the task scene requirements;
aiming at the uniqueness of the task and the homogeneity of the unmanned aerial vehicle, a real number coding mode is adopted, and any feasible solution suitable for the task allocation problem is coded into a complete chromosome in a straight line mode;
generating an initial population of a preset scale which accords with a model constraint equation according to the coding mode of the multi-unmanned aerial vehicle cooperative power inspection task distribution model information and the genetic algorithm;
solving the multi-unmanned-aerial-vehicle cooperative power inspection task allocation model by adopting a genetic algorithm, wherein the optimal solution obtained under the maximum iteration number is the optimal task allocation scheme of the multi-unmanned-aerial-vehicle inspection system;
because the multiple unmanned aerial vehicles have the common timeliness in the task execution process, the total task time of all the unmanned aerial vehicles at a certain parking point is equal to the task time of the unmanned aerial vehicle with the longest consumed time, the optimization target of the multi-unmanned aerial vehicle cooperative power inspection task allocation model is the minimum total task time of all the unmanned aerial vehicles, so the objective function is expressed by the task time of the unmanned aerial vehicle with the longest consumed time, as shown in formula (2):
Minimize：max{Z0equation (2)
Wherein, aggregate
Figure FDA0003580625570000011
For the set of mission times for all drones at parking point 0,
Figure FDA0003580625570000012
for unmanned plane UiTask time at parking Point 0, Ui∈U＝{U1,U2,...,UmNumbering unmanned aerial vehicles;
the constraint conditions of the multi-unmanned-aerial-vehicle collaborative power inspection task allocation model are expressed by formulas (3) to (6):
Figure FDA0003580625570000013
Figure FDA0003580625570000014
Figure FDA0003580625570000015
Figure FDA0003580625570000016
where 0 denotes the parking point number of the work vehicle, and T ═ T1,T2,...,TnThe unmanned aerial vehicle is a set of all towers to be patrolled within the operation radius of the parking point, the total number of the towers to be patrolled is n, and the set of unmanned aerial vehicles capable of executing the patrol task at the parking point 0 is U ═ U }1,U2,...,Um}；f0iRepresenting the number of times that the unmanned aerial vehicle i takes off at the parking point 0; d0jFor tower TjA geographical linear distance from park point 0; v is the flying speed of the unmanned aerial vehicle when the unmanned aerial vehicle comes and goes to and from the parking point and the electric power tower; x is the number ofijIs a variable of 0 to 1, when the unmanned plane UiAccess tower TjIf the value is 1, otherwise, the value is 0; cjFor unmanned aerial vehicle at shaft tower TjThe patrol time of the department;
formula (3) indicates that each tower has only one drone to visit once;
formula (4) shows that the sum of the taking-off times of all the unmanned aerial vehicles at the parking point 0 is equal to the total number of towers to be patrolled, namely, each unmanned aerial vehicle only patrols one base tower every time when taking off;
formula (5) shows that the task time of each unmanned aerial vehicle is equal to the sum of the round-trip flight time and the sum of the patrol time at the tower;
equation (6) is a decision variable constraint.
2. The method for distributing the task of the cooperative power inspection of the multiple unmanned aerial vehicles according to claim 1, wherein the parking point is a parking point of the working vehicle, the working vehicle flies off at the parking point and recovers the unmanned aerial vehicle, so that the unmanned aerial vehicle can access a tower to be inspected within a working radius of the parking point.
3. The task allocation method for multi-unmanned aerial vehicle cooperative power inspection according to claim 1, wherein the geographical linear distance from each power tower to a parking point in the power inspection task set of the area to be inspected is obtained through calculation according to formula (1)
d0i＝R*arccos[sin(x0)*sin(xi)+cos(x0)*cos(xi)*cos(y0-yi)]Formula (1)
Wherein d is0iRepresenting the geographical straight-line distance from the electric power tower i to the parking point 0; (y)0,x0) Latitude and longitude coordinates, y, representing parking point 00Longitude, x, of parking Point 00Latitude of parking point 0; (y)i,xi) Representing the latitude and longitude coordinates, y, of the tower iiLongitude, x, of tower iiThe latitude of the tower i; r is the radius of the earth, and 6371.004km is taken.
4. The method for distributing the task of the multi-unmanned aerial vehicle cooperative power inspection according to claim 1, wherein the optimal task distribution scheme of the multi-unmanned aerial vehicle cooperative power inspection system can be obtained by solving the multi-unmanned aerial vehicle cooperative power inspection task distribution model by using a genetic algorithm, and the method comprises the following steps:
the chromosome coding mode of the genetic algorithm is real number coding, each chromosome represents an individual gene and represents a task allocation scheme, each chromosome is coded into a number sequence of 1 row and n columns, wherein n is the total number of towers to be inspected; dividing each chromosome into m segments according to proportion, wherein m is the total number of unmanned aerial vehicles capable of executing tasks, and each segment of chromosome represents an unmanned aerial vehicle task sequence;
the genetic algorithm takes a formula (2) as a fitness function, an optimization process of a minimum fitness function is carried out on an initial population by improving selection, crossing and variation of the genetic algorithm, an optimal feasible solution is obtained under a fixed iteration number, and the obtained result is used as a result of the cooperative power patrol task distribution of the unmanned aerial vehicles.
CN202110394113.4A 2021-04-13 2021-04-13 Task allocation method for multi-unmanned aerial vehicle cooperative power inspection Active CN113011780B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110394113.4A CN113011780B (en) 2021-04-13 2021-04-13 Task allocation method for multi-unmanned aerial vehicle cooperative power inspection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110394113.4A CN113011780B (en) 2021-04-13 2021-04-13 Task allocation method for multi-unmanned aerial vehicle cooperative power inspection

Publications (2)

Publication Number Publication Date
CN113011780A CN113011780A (en) 2021-06-22
CN113011780B true CN113011780B (en) 2022-05-31

Family

ID=76388677

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110394113.4A Active CN113011780B (en) 2021-04-13 2021-04-13 Task allocation method for multi-unmanned aerial vehicle cooperative power inspection

Country Status (1)

Country Link
CN (1) CN113011780B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113885555A (en) * 2021-09-14 2022-01-04 安徽送变电工程有限公司 Multi-machine task allocation method and system for power transmission line dense channel routing inspection
CN114185363B (en) * 2021-12-09 2024-04-05 国网江苏省电力有限公司泰州供电分公司 5G link-based electric power inspection unmanned aerial vehicle multi-machine integrated management system
CN114442664B (en) * 2022-01-17 2023-09-26 江苏方天电力技术有限公司 Power transmission line unmanned aerial vehicle formation collaborative inspection task allocation method considering airspace conflict
CN115454148B (en) * 2022-11-08 2023-02-17 四川腾盾科技有限公司 Method, medium and device for planning coverage path of fixed wing cluster unmanned aerial vehicle area

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105404938A (en) * 2015-11-30 2016-03-16 国网山东省电力公司烟台供电公司 Line-patrolling path optimization method for shortening patrolling time of transmission line
CN108844541A (en) * 2018-03-09 2018-11-20 广东电网有限责任公司机巡作业中心 A kind of machine based on inspection scene patrols paths planning method
CN111220159A (en) * 2020-02-10 2020-06-02 合肥工业大学 Path optimization method for multi-unmanned aerial vehicle cooperative inspection task

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11727812B2 (en) * 2017-07-27 2023-08-15 Beihang University Airplane flight path planning method and device based on the pigeon-inspired optimization

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105404938A (en) * 2015-11-30 2016-03-16 国网山东省电力公司烟台供电公司 Line-patrolling path optimization method for shortening patrolling time of transmission line
CN108844541A (en) * 2018-03-09 2018-11-20 广东电网有限责任公司机巡作业中心 A kind of machine based on inspection scene patrols paths planning method
CN111220159A (en) * 2020-02-10 2020-06-02 合肥工业大学 Path optimization method for multi-unmanned aerial vehicle cooperative inspection task

Also Published As

Publication number Publication date
CN113011780A (en) 2021-06-22

Similar Documents

Publication Publication Date Title
CN113011780B (en) Task allocation method for multi-unmanned aerial vehicle cooperative power inspection
CN112016812B (en) Multi-unmanned aerial vehicle task scheduling method, system and storage medium
Marinelli et al. En route truck–drone parcel delivery for optimal vehicle routing strategies
Gao et al. Multi-UAV reconnaissance task allocation for heterogeneous targets using grouping ant colony optimization algorithm
CN109583665B (en) Unmanned aerial vehicle charging task scheduling method in wireless sensor network
CN107579518B (en) Power system environment economic load dispatching method and apparatus based on MHBA
CN111178582B (en) Logistics distribution optimization method based on improved genetic algorithm
CN107622327A (en) Multiple no-manned plane path planning method based on cultural ant colony search mechanisms
CN109960544A (en) Task parallel scheduling method based on data driving type agile satellite
CN113705982A (en) Scheduling decision method for vehicle-mounted machine cooperative power patrol
CN110059875B (en) Public bicycle demand prediction method based on distributed whale optimization algorithm
CN113885555A (en) Multi-machine task allocation method and system for power transmission line dense channel routing inspection
CN114565239B (en) Comprehensive low-carbon energy scheduling method and system for industrial park
CN114442664B (en) Power transmission line unmanned aerial vehicle formation collaborative inspection task allocation method considering airspace conflict
CN116720642A (en) Method and system for optimizing path of cooperative distribution of vehicle and unmanned aerial vehicle
CN104217118B (en) Vessel pilot scheduling problem model and solving method
CN113485409B (en) Geographic fairness-oriented unmanned aerial vehicle path planning and distribution method and system
CN113536689B (en) Multi-unmanned aerial vehicle task allocation execution control method based on hybrid genetic intelligent algorithm
CN109784585A (en) A kind of mixing of unmanned plane unmanned boat lays dispatching method
CN114020005A (en) Flight path planning method and system for cooperative inspection of multiple unmanned aerial vehicles and distribution network lines
CN115826614A (en) Multi-unmanned aerial vehicle energy support task allocation method
Liu et al. Spatio-temporal hierarchical adaptive dispatching for ridesharing systems
Xu et al. Discrete brain storm optimization algorithm based on prior knowledge for traveling salesman problems
CN116203982A (en) Unmanned aerial vehicle power patrol track planning method and system
AlObaidi et al. Exploration-Balanced Bees Algorithms to Solve Optimization and NP-Complete Problems

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