CN115755954A - Routing inspection path planning method and system, computer equipment and storage medium - Google Patents
Routing inspection path planning method and system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115755954A CN115755954A CN202211332855.5A CN202211332855A CN115755954A CN 115755954 A CN115755954 A CN 115755954A CN 202211332855 A CN202211332855 A CN 202211332855A CN 115755954 A CN115755954 A CN 115755954A
- Authority
- CN
- China
- Prior art keywords
- initial
- routing inspection
- workload
- data
- inspection area
- 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.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The scheme relates to a routing inspection path planning method, a routing inspection path planning system, computer equipment and a storage medium. The method comprises the following steps: acquiring polling data, and calculating the clustering number according to the distance-based intra-class division index BWP of the polling data; dividing routing inspection areas through a K-Means algorithm according to the routing inspection data and the clustering number to obtain each initial routing inspection area; calculating the workload of each initial routing inspection area, and performing secondary division on each initial routing inspection area according to each workload to obtain each target routing inspection area; and planning paths of the target inspection regions through an ant colony algorithm and a genetic algorithm. The method is characterized in that the large-scale power transmission line inspection area is divided based on BWP and K-Means algorithms, the inspection area is adjusted, the optimal path in each area is solved by combining the ant colony algorithm and the genetic algorithm, the optimal path algorithm solving efficiency can be improved, and the workload of each unmanned aerial vehicle is balanced.
Description
Technical Field
The invention relates to the technical field of power transmission line inspection, in particular to an inspection path planning method, an inspection path planning system, computer equipment and a storage medium.
Background
The transmission line is an important component of the power system, and the safe operation of the transmission line is an important guarantee for the overall stability of the system. In order to ensure the stable and safe operation of the power transmission line, the power transmission line needs to be regularly inspected. The daily inspection of the power transmission line is a basic and important work for ensuring the reliability of power supply. At present, the created power transmission line inspection modes comprise manual inspection, unmanned aerial vehicle inspection, vehicle inspection and the like, and in recent years, due to the rapid development of Unmanned Aerial Vehicles (UAVs), the UAVs have good flexibility and controllability, and the UAVs are mostly adopted in the power transmission line to complete daily inspection tasks. Unmanned aerial vehicle is carrying out the in-process that transmission line patrolled and examined, because transmission line patrols and examines that the regional scope is generally great, the unmanned aerial vehicle of difference patrols and examines the required time diverse that patrols and examines of group.
Therefore, when the traditional unmanned aerial vehicle patrols and examines the power transmission line, in the process of solving the optimal path, the working time required by different unmanned aerial vehicle patrolling and examining groups to patrol and examine the path is possibly different greatly, and the problem that the workload of each unmanned aerial vehicle patrolling and examining group is unbalanced exists.
Disclosure of Invention
Based on this, in order to solve the above technical problem, a routing inspection path planning method, a routing inspection path planning system, a computer device and a storage medium are provided, which can adjust an inspection area and balance the workload of each unmanned aerial vehicle.
A routing inspection path planning method comprises the following steps:
acquiring polling data, and calculating the clustering number according to the distance-based intra-class division index BWP of the polling data;
dividing routing inspection areas through a K-Means algorithm according to the routing inspection data and the clustering number to obtain each initial routing inspection area;
calculating the workload of each initial routing inspection area, and performing secondary division on each initial routing inspection area according to each workload to obtain each target routing inspection area;
and planning paths of the target inspection regions through an ant colony algorithm and a genetic algorithm.
In one embodiment, the dividing routing inspection areas by a K-Means algorithm according to the routing inspection data and the number of clusters includes:
calculating BWP index values of the single data objects based on the single data objects in the routing inspection data;
calculating an average BWP value according to each BWP index value;
determining optimal clustering data from the clustering quantity according to the average BWP value;
and dividing routing inspection areas through a K-Means algorithm according to the routing inspection data and the optimal clustering quantity.
In one embodiment, the dividing the inspection areas by the K-Means algorithm to obtain each initial inspection area includes:
determining each initial clustering center from each data point of the routing inspection data through a K-Means algorithm according to the optimal clustering quantity;
calculating the distance from each residual data point to each initial clustering center, and dividing each residual data point into the class to which each initial clustering center belongs according to the distance;
and judging whether each initial clustering center is converged, if so, outputting a classification result, and dividing routing inspection areas according to the classification result to obtain each initial routing inspection area.
In one embodiment, the calculating the workload of each initial inspection area and performing secondary division on each initial inspection area according to each workload includes:
calculating the workload of each initial routing inspection area, sequencing the workload, calculating the difference value between the maximum workload and the minimum workload, if the difference value is greater than a workload threshold value, removing the farthest data point which is away from the initial clustering center in the initial routing inspection area corresponding to the maximum workload, and adding the farthest data point to the class which is the second smallest away from the initial clustering center;
when an initial routing inspection area with the maximum workload larger than the maximum workload threshold exists, calculating a first distance from each data point in the initial routing inspection area to the initial clustering center, calculating a second distance from each data point to other initial clustering centers, and moving the data points according to the first distance and the second distance;
and calculating the ratio of the workload of each initial routing inspection area to the maximum workload in all areas, and moving data points according to the ratio.
In one embodiment, before the path planning by the ant colony algorithm and the genetic algorithm, the method further comprises:
generating an initial population by adopting an ant colony algorithm, and initializing parameters of the ant colony algorithm;
constructing a solution space of the ant colony algorithm, and initializing the positions of ants;
randomly distributing ants, updating pheromones and calculating traversal paths of the ants;
and taking the path iterated once as an initial population of the genetic algorithm.
In one embodiment, before the path planning by the ant colony algorithm and the genetic algorithm, the method further comprises:
setting parameters of the genetic algorithm and initializing the genetic algorithm;
the initialization parameters comprise population size, cross probability, mutation probability and iteration times.
In one embodiment, the path planning is performed by an ant colony algorithm and a genetic algorithm, and comprises the following steps:
carrying out crossover and mutation operations on chromosomes in the initial population through the genetic algorithm;
decoding the chromosome to obtain the planning and dividing results of the distribution path;
obtaining the fitness value of each individual in the initial population, and selecting excellent individuals to enter the next generation by adopting a roulette mode;
adjusting the population scale by adopting a variable-scale population scale genetic algorithm;
and when the genetic algorithm reaches the maximum iteration times, ending the algorithm and outputting the shortest distribution path.
A system for routing inspection, the system comprising:
the cluster number calculation module is used for acquiring the routing inspection data and calculating the cluster number according to the routing inspection data based on the inter-class intra-class division index BWP of the distance;
the initial routing inspection area dividing module is used for dividing routing inspection areas through a K-Means algorithm according to the routing inspection data and the clustering number to obtain each initial routing inspection area;
the inspection area adjusting module is used for calculating the workload of each initial inspection area and carrying out secondary division on each initial inspection area according to each workload to obtain each target inspection area;
and the path planning module is used for planning paths of the target inspection regions through an ant colony algorithm and a genetic algorithm.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring polling data, and calculating the clustering number according to the distance-based intra-class division index BWP of the polling data;
dividing routing inspection areas through a K-Means algorithm according to the routing inspection data and the clustering number to obtain each initial routing inspection area;
calculating the workload of each initial routing inspection area, and performing secondary division on each initial routing inspection area according to each workload to obtain each target routing inspection area;
and planning paths of the target inspection regions through an ant colony algorithm and a genetic algorithm.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring polling data, and calculating the clustering number according to the distance-based intra-class division index BWP of the polling data;
dividing routing inspection areas through a K-Means algorithm according to the routing inspection data and the clustering number to obtain each initial routing inspection area;
calculating the workload of each initial routing inspection area, and performing secondary division on each initial routing inspection area according to each workload to obtain each target routing inspection area;
and planning paths of the target inspection regions through an ant colony algorithm and a genetic algorithm.
According to the routing inspection path planning method, the routing inspection path planning system, the computer equipment and the storage medium, the number of clusters is calculated by acquiring routing inspection data and dividing an index BWP in the class between classes based on the distance according to the routing inspection data; dividing routing inspection areas through a K-Means algorithm according to the routing inspection data and the clustering number to obtain each initial routing inspection area; calculating the workload of each initial routing inspection area, and performing secondary division on each initial routing inspection area according to each workload to obtain each target routing inspection area; and planning paths of the target inspection regions through an ant colony algorithm and a genetic algorithm. The method is characterized in that the large-scale power transmission line inspection area is divided based on BWP and K-Means algorithms, the inspection area is adjusted, the optimal path in each area is solved by combining the ant colony algorithm and the genetic algorithm, the optimal path algorithm solving efficiency can be improved, and the workload of each unmanned aerial vehicle is balanced.
Drawings
Fig. 1 is an application environment diagram of a routing inspection path planning method in an embodiment;
fig. 2 is a schematic flow chart of a routing inspection path planning method in one embodiment;
FIG. 3 is a schematic flow chart of the division of the patrol area in one embodiment;
FIG. 4 is a schematic flow chart of dividing the preliminary routing inspection area based on the K-Means algorithm in one embodiment;
FIG. 5 is a schematic diagram illustrating a routing inspection path planning process based on an ant colony algorithm and a genetic algorithm in one embodiment;
fig. 6 is a block diagram of the routing inspection path planning system in one embodiment;
FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The routing inspection path planning method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. As shown in fig. 1, the application environment includes a computer device 110, wherein the computer device 110 may be a robot, an unmanned aerial vehicle, or the like. The computer device 110 may obtain the inspection data, and calculate the cluster number according to the inter-class intra-class division index BWP of the inspection data based on the distance; the computer device 110 can divide the polling areas through a K-Means algorithm according to the polling data and the clustering quantity to obtain each initial polling area; the computer device 110 can calculate the workload of each initial patrol inspection area, and perform secondary division on each initial patrol inspection area according to each workload to obtain each target patrol inspection area; the computer device 110 may perform path planning for each target inspection area through an ant colony algorithm and a genetic algorithm.
In one embodiment, as shown in fig. 2, a routing inspection path planning method is provided, which includes the following steps:
The computer equipment can acquire the data of patrolling and examining, wherein, the data of patrolling and examining can include the map that needs to carry out the transmission line and patrol and examine, the data such as the unmanned aerial vehicle quantity of patrolling and examining. In the routing inspection area division process, the computer device can calculate the clustering number according to the routing inspection data based on the inter-class intra-class division index BWP of the distance. Wherein the size of the clustering quantity can directly influence the clustering result.
And step 204, dividing the inspection areas through a K-Means algorithm according to the inspection data and the clustering quantity to obtain each initial inspection area.
The K-Means algorithm is influenced by various factors when routing inspection areas are divided, and specific influence factors can include the number of clusters, the inter-class relation, the selection of an initial cluster center, the shortest distance between target points, the maximum workload of the routing inspection areas, the lowest load rate, the workload balance and the like.
Wherein, the relationship between the classes: data sets belonging to different classes do not have an intersection, and each data point only belongs to one class; when the K-Means algorithm is used, it is required to ensure that no intersection exists between the classes, and each data point is classified into a unique class; the Euclidean distance between two data points is used as the shortest distance between target points; the large workload difference among the inspection areas can lead some inspection groups to finish tasks too early or too late, thus leading to low inspection efficiency, and therefore, the inspection areas need to meet the requirements of maximum workload and minimum load rate, and the overall balance of the workload of the areas is ensured.
And step 206, calculating the workload of each initial inspection area, and performing secondary division on each initial inspection area according to each workload to obtain each target inspection area.
The computer equipment can respectively calculate the workload of each initial routing inspection area, and the area division result is optimized and adjusted according to the maximum workload, the minimum load rate and the constraint condition of workload balance of the routing inspection areas, so that each target routing inspection area is obtained.
And 208, planning paths of all the target inspection areas through an ant colony algorithm and a genetic algorithm.
In the embodiment, the computer device calculates the clustering number by acquiring the routing inspection data and according to the routing inspection data based on the inter-class and intra-class division index BWP of the distance; dividing the inspection areas through a K-Means algorithm according to the inspection data and the clustering quantity to obtain each initial inspection area; calculating the workload of each initial routing inspection area, and performing secondary division on each initial routing inspection area according to each workload to obtain each target routing inspection area; and planning paths of all the target inspection areas through an ant colony algorithm and a genetic algorithm. The method is characterized in that the large-scale power transmission line inspection area is divided based on BWP and K-Means algorithms, the inspection area is adjusted, the optimal path in each area is solved by combining the ant colony algorithm and the genetic algorithm, the optimal path algorithm solving efficiency can be improved, and the workload of each unmanned aerial vehicle is balanced.
In an embodiment, the routing inspection path planning method provided by the present invention may further include a process of dividing the initial routing inspection area, where the specific process includes: calculating the BWP index values of the single data objects based on the single data objects in the routing inspection data; calculating an average BWP value according to each BWP index value; determining the optimal clustering data from the clustering quantity according to the average BWP value; and dividing the polling areas by a K-Means algorithm according to the polling data and the optimal clustering quantity.
In the K-Means algorithm, different routing inspection areas are calculated by taking the distance as a measurement, so that the clustering result presents the effects of intra-class compactness and inter-class separation for determining the optimal clustering number, and the optimal clustering number is obtained by performing clustering evaluation on the algorithm by adopting BWP (bwe-max).
In particular, BWP starts with a distance measure and defines the best clustering result as the result that minimizes the distance within and between clusters. Firstly, aiming at a single data object in a data set to be divided, obtaining a BWP index value of the single data object based on a defined inter-class distance and an intra-class distance; and then calculating to obtain an average BWP value of the whole data set, and judging the clustering effectiveness of the whole data object set.
The relevant parameters of the BWP metric are now defined as follows: setting a clustering space of data objects to K = { X, R }, where X = { X = 1 ,x 2 ,...,x n }. Assuming that n data are divided into c classes, the inter-class distance d (i, j) is the average distance from the jth data of the ith class to the data objects of other classes, and the calculation formula is as follows:
the minimum inter-class distance min d (i, j) is calculated as:
where k represents the number of clusters,i represents the i-th class and,
the jth data object representing the ith class,
r-th data, n, representing the k-th class k Represents the amount of data in the kth class, | | 2 Represents the square of the euclidean distance; defining the distance w (i, j) in the class as the average distance from the jth data of the ith class to other data objects in the class, and calculating the formula as follows:
wherein the content of the first and second substances,
the s-th data representing the i-th class; defining the cluster distance baw (i, j) as the sum of the minimum inter-class distance and the intra-class distance, and the cluster dispersion distance bsw (i, j) as the difference between the minimum inter-class distance and the intra-class distance, then the BWP value is the ratio of baw (i, j) to bsw (i, j), and the calculation formula is:
the larger the BWP index value is, the better the clustering effect of the data is represented; and designing an average BWP value based on the definition of the BWP index, and realizing the clustering effect evaluation on the whole data set by using the average BWP index value of all data in the data set. When the average BWP index value of the whole data set is maximum, the corresponding cluster number is the optimal cluster number of the data set, and the calculation formula is as follows:
k opt ＝argmax{BWP avg (k)}。
when the initial routing inspection area is divided, the computer device adopts a K-Means algorithm to preliminarily divide the area based on BWP evaluation criteria, firstly, a data set to be classified containing n data objects and a value range of a clustering number K are input, clustering results of the data set to be classified and the clustering number K are respectively calculated in the value range of K, corresponding BWP values are calculated according to clustering results obtained by different K values, and the clustering number with the maximum BWP value and the clustering results are output as final results.
In an embodiment, the routing inspection path planning method provided by the present invention may further include a process of obtaining each initial routing inspection area, where the specific process includes: determining each initial clustering center from each data point of the inspection data through a K-Means algorithm according to the optimal clustering quantity; calculating the distance from each residual data point to each initial clustering center, and dividing each residual data point into the class to which each initial clustering center belongs according to the distance; and judging whether each initial clustering center is converged, if so, outputting a classification result, and dividing the inspection areas according to the classification result to obtain each initial inspection area.
In this embodiment, when the initial clustering center is selected, in order to avoid the clustering result falling into the local optimal solution, a point with the highest density is selected from all the data points as a first initial clustering center point, a point with the largest distance from the first initial clustering center is selected as a second initial clustering center point, a point with the shortest distance from the first two points is selected as a third initial clustering center point, and so on until k initial clustering center points are selected.
Specifically, when a clustering result is calculated, firstly, k data points (c 1, c 2.. Once, ck) are selected as an initial clustering center according to an initial clustering center selection strategy; secondly, calculating the distance between the rest data points and each clustering center, and dividing each data point into the cluster center class closest to the data point based on the minimum distance constraint; then calculating new cluster center according to formula
And judging whether the clustering center is converged, if so, terminating the calculation and outputting a classification result, and if not, returning to perform the calculation again.
In one embodiment, the routing inspection path planning method provided by the embodiment may further include a process of performing secondary division on the initial routing inspection area, that is, optimizing and adjusting the result of area division by considering the constraint conditions of maximum workload, minimum load rate and workload balance of the initial routing inspection area; the specific process comprises the following steps: and calculating the workload of each initial routing inspection area, sequencing, calculating the difference value between the maximum workload and the minimum workload, removing the farthest data point from the initial clustering center in the initial routing inspection area corresponding to the maximum workload if the difference value is greater than a workload threshold, and adding the farthest data point to the class which is the second smallest away from the initial clustering center.
Firstly, adjusting and optimizing based on workload balance conditions: and calculating and sequencing the workload of each region in the region division result, selecting the maximum workload and the minimum workload for comparison, finishing adjustment if the difference value between the maximum workload and the minimum workload is not more than a set workload threshold, removing the point farthest from the clustering center in the region with the maximum workload if the difference value is more than the set workload threshold, adding the point to the class with the second smallest distance from the clustering center, recalculating the workload and the clustering center, and so on until the constraint condition is met.
When an initial routing inspection area with the maximum workload larger than the maximum workload threshold exists, calculating a first distance from each data point in the initial routing inspection area to an initial clustering center, calculating a second distance from each data point to other initial clustering centers, and moving the data points according to the first distance and the second distance.
Secondly, adjusting and optimizing based on the maximum workload condition: on the basis of the adjustment result of the last step, combining the longest working time of the unmanned aerial vehicle, setting a maximum workload threshold value in each area, calculating whether each area has the condition of exceeding the maximum workload, if not, completing the adjustment, if so, calculating the distance Di from each node i in each area to the clustering center point of the area, namely a first distance, simultaneously calculating the distance Di from each node to other clustering centers, namely a second distance, moving the node with the maximum Di to the area with the smaller Di and meeting the workload limit, recalculating the workload, and so on until the constraint condition is met.
And calculating the ratio of the workload of each initial routing inspection area to the maximum workload in all the areas, and moving the data points according to the ratio.
And finally, adjusting and optimizing based on the minimum load rate: defining the load rate as the ratio of the workload of each area to the maximum workload of all the areas, setting the minimum load rate threshold of the areas on the basis of the adjustment result of the last step, calculating the load rate value of each area and sequencing, if no area lower than the threshold exists, completing the adjustment, if the area with the minimum load rate exists, starting the adjustment from the area with the minimum load rate, calculating the distance Di from each node i of other areas to the clustering center point of the area, moving the node with the minimum Di value to the current area, recalculating the workload and the clustering center, and so on until the constraint condition is met. And obtaining a final routing inspection area division result after the adjustment is finished.
In one embodiment, the process of dividing the routing inspection area is as shown in fig. 3: after inputting data, first computing BWP value; selecting the optimal clustering quantity according to the calculated BWP value; solving based on a K-Means algorithm to obtain a primary region division result; and then, performing area division optimization, and obtaining area division final results, namely all target inspection areas, based on the area division results of the inspection areas under the constraint conditions of maximum workload, minimum load rate and workload balance.
In one embodiment, the process of partitioning the preliminary routing area based on the K-Means algorithm is shown in FIG. 4: after the data and the cluster number range are input, the cluster result and the BWP value can be calculated, and then the cluster number and the result with the maximum BWP value are output. Wherein, the process of calculating the clustering result comprises the following steps: setting an initial clustering center, calculating the distance from a data point to each clustering center, dividing the data points according to the minimum distance principle, calculating a new clustering center, judging whether the clustering center is converged, and if so, acquiring a clustering result; if not, resetting the initial clustering center.
In an embodiment, the routing inspection path planning method provided by the present invention may further include a process of performing ant colony algorithm initialization, where the specific process includes: adopting an ant colony algorithm to generate an initial population, and initializing parameters of the ant colony algorithm; constructing a solution space of an ant colony algorithm, and initializing the positions of ants; randomly distributing ants, updating pheromones and calculating traversal paths of the ants; and taking the path iterated once as an initial population of the genetic algorithm.
In an embodiment, the routing inspection path planning method provided by the present invention may further include a process of initializing a genetic algorithm, where the specific process includes: setting parameters of a genetic algorithm, and initializing the genetic algorithm; the initialization parameters comprise population size, cross probability, mutation probability and iteration times.
In one embodiment, the routing inspection path planning method may further include a path planning process, and the specific process includes: carrying out crossover and mutation operations on chromosomes in the initial population through a genetic algorithm; carrying out decoding operation on the chromosome to obtain the planning and dividing results of the distribution path; acquiring the fitness value of each individual in the initial population, and selecting excellent individuals to enter the next generation by adopting a roulette mode; adopting a variable-scale population scale genetic algorithm to adjust the population scale; and when the genetic algorithm reaches the maximum iteration times, ending the algorithm and outputting the shortest distribution path.
Wherein, the intersection part adopts two-point intersection, and the variation part adopts two-point interchange variation. When the chromosome is decoded, the chromosome can be decoded based on the constraints of maximum working time, elimination of sub-loops and the like, so that the planning and dividing results of the distribution path are obtained.
In one embodiment, the process of path planning is shown in fig. 5:
generating an initial population by adopting an ant colony algorithm, initializing parameters of the algorithm, constructing a solution space of the ant colony algorithm, and initializing the positions of ants; then, randomly distributing the ants, updating pheromones and calculating the paths traversed by the ants; taking the path iterated once as an initial population of the genetic algorithm;
setting parameters of a genetic algorithm, and initializing the algorithm, wherein the parameters comprise population scale, cross probability, mutation probability and iteration times;
and carrying out crossover and mutation operations on chromosomes in the population. Wherein, the crossing part adopts two-point crossing, and the variation part adopts two-point interchange variation;
decoding the chromosome based on the maximum working time, the elimination of the sub-loop and other constraints to obtain the planning and dividing results of the distribution path;
obtaining the fitness value of each individual in the population according to an objective function, and selecting excellent individuals to enter the next generation by adopting a roulette mode;
adopting a variable-scale population scale genetic algorithm to adjust the population scale;
and judging whether the end condition of the genetic algorithm is met. If the maximum iteration times are reached, finishing the algorithm and outputting the shortest distribution path; otherwise, the next generation of iteration is continued until the end condition is reached.
It should be understood that, although the steps in the above-described flowcharts are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in the above-described flowcharts may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or the stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 6, there is provided a patrol route planning system, including: cluster number calculation module 610, initial patrol area division module 620, patrol area adjustment module 630 and path planning module 640, wherein:
the cluster number calculation module 610 is configured to obtain the inspection data, and calculate the cluster number according to the inter-class intra-class division index BWP of the inspection data based on the distance;
the initial routing inspection area dividing module 620 is used for dividing routing inspection areas through a K-Means algorithm according to routing inspection data and the clustering number to obtain each initial routing inspection area;
the inspection area adjusting module 630 is configured to calculate workloads of each initial inspection area, and perform secondary division on each initial inspection area according to each workload to obtain each target inspection area;
and the path planning module 640 is configured to perform path planning on each target inspection area through an ant colony algorithm and a genetic algorithm.
In one embodiment, the initial inspection area dividing module 620 is further configured to calculate, based on the single data object in the inspection data, respective BWP index values of the respective single data objects; calculating an average BWP value according to each BWP index value; determining the optimal clustering data from the clustering quantity according to the average BWP value; and dividing the polling areas by a K-Means algorithm according to the polling data and the optimal clustering quantity.
In one embodiment, the initial routing inspection area dividing module 620 is further configured to determine each initial clustering center from each data point of the routing inspection data through a K-Means algorithm according to the optimal clustering number; calculating the distance from each residual data point to each initial clustering center, and dividing each residual data point into the class to which each initial clustering center belongs according to the distance; and judging whether each initial clustering center is converged, if so, outputting a classification result, and dividing the inspection areas according to the classification result to obtain each initial inspection area.
In an embodiment, the inspection region adjusting module 630 is further configured to calculate and sequence workloads of the initial inspection regions, calculate a difference between the maximum workload and the minimum workload, remove a farthest data point from the initial cluster center in the initial inspection region corresponding to the maximum workload if the difference is greater than a workload threshold, and add the farthest data point to a class that is the second smallest from the initial cluster center; when an initial routing inspection area with the maximum workload larger than the maximum workload threshold exists, calculating a first distance from each data point in the initial routing inspection area to an initial clustering center, calculating a second distance from each data point to other initial clustering centers, and moving the data points according to the first distance and the second distance; and calculating the ratio of the workload of each initial routing inspection area to the maximum workload in all the areas, and moving the data points according to the ratio.
In one embodiment, the path planning module 640 is further configured to generate an initial population by using an ant colony algorithm, and initialize parameters of the ant colony algorithm; constructing a solution space of an ant colony algorithm, and initializing the positions of ants; randomly distributing ants, updating pheromones and calculating traversal paths of the ants; and taking the path iterated once as an initial population of the genetic algorithm.
In one embodiment, the path planning module 640 is further configured to set parameters of a genetic algorithm and initialize the genetic algorithm; the initialization parameters comprise population size, cross probability, mutation probability and iteration times.
In one embodiment, the path planning module 640 is further configured to perform crossover and mutation operations on chromosomes in the initial population through a genetic algorithm; carrying out decoding operation on the chromosome to obtain the planning and dividing results of the distribution path; acquiring the fitness value of each individual in the initial population, and selecting excellent individuals to enter the next generation by adopting a roulette mode; adjusting the population scale by adopting a variable-scale population scale genetic algorithm; and when the genetic algorithm reaches the maximum iteration times, ending the algorithm and outputting the shortest distribution path.
In one embodiment, a computer device is provided, which may be a drone, the internal structure of which may be as shown in fig. 7. The computer device comprises a processor, a memory, a network interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a patrol route planning method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring polling data, and calculating the clustering number according to an inter-class intra-class division index BWP of the polling data based on distance;
dividing the inspection areas through a K-Means algorithm according to the inspection data and the clustering quantity to obtain each initial inspection area;
calculating the workload of each initial routing inspection area, and performing secondary division on each initial routing inspection area according to each workload to obtain each target routing inspection area;
and planning paths of each target inspection area through an ant colony algorithm and a genetic algorithm.
In one embodiment, the processor, when executing the computer program, further performs the steps of: calculating the BWP index values of the single data objects based on the single data objects in the routing inspection data; calculating an average BWP value according to each BWP index value; determining the optimal clustering data from the clustering quantity according to the average BWP value; and dividing the polling areas by a K-Means algorithm according to the polling data and the optimal clustering quantity.
In one embodiment, the processor, when executing the computer program, further performs the steps of: determining each initial clustering center from each data point of the inspection data through a K-Means algorithm according to the optimal clustering quantity; calculating the distance from each residual data point to each initial clustering center, and dividing each residual data point into the class to which each initial clustering center belongs according to the distance; and judging whether each initial clustering center is converged, if so, outputting a classification result, and dividing the inspection areas according to the classification result to obtain each initial inspection area.
In one embodiment, the processor, when executing the computer program, further performs the steps of: calculating the workload of each initial routing inspection area, sequencing the workload, calculating the difference value between the maximum workload and the minimum workload, if the difference value is greater than a workload threshold value, removing the farthest data point which is away from the initial clustering center in the initial routing inspection area corresponding to the maximum workload, and adding the farthest data point to the class which is away from the initial clustering center by the second smallest distance; when an initial routing inspection area with the maximum workload larger than the maximum workload threshold exists, calculating a first distance from each data point in the initial routing inspection area to an initial clustering center, calculating a second distance from each data point to other initial clustering centers, and moving the data points according to the first distance and the second distance; and calculating the ratio of the workload of each initial routing inspection area to the maximum workload in all the areas, and moving the data points according to the ratio.
In one embodiment, the processor, when executing the computer program, further performs the steps of: adopting an ant colony algorithm to generate an initial population, and initializing parameters of the ant colony algorithm; constructing a solution space of an ant colony algorithm, and initializing the positions of ants; randomly distributing ants, updating pheromones and calculating traversal paths of the ants; and taking the path iterated once as an initial population of the genetic algorithm.
In one embodiment, the processor, when executing the computer program, further performs the steps of: setting parameters of a genetic algorithm, and initializing the genetic algorithm; the initialization parameters comprise population size, cross probability, mutation probability and iteration times.
In one embodiment, the processor when executing the computer program further performs the steps of: carrying out crossover and mutation operations on chromosomes in the initial population through a genetic algorithm; carrying out decoding operation on the chromosome to obtain the planning and dividing results of the distribution path; acquiring the fitness value of each individual in the initial population, and selecting excellent individuals to enter the next generation by adopting a roulette mode; adjusting the population scale by adopting a variable-scale population scale genetic algorithm; and when the genetic algorithm reaches the maximum iteration times, ending the algorithm and outputting the shortest distribution path.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, performs the steps of:
acquiring polling data, and calculating the clustering number according to an inter-class intra-class division index BWP of the polling data based on distance;
dividing the inspection areas through a K-Means algorithm according to the inspection data and the clustering quantity to obtain each initial inspection area;
calculating the workload of each initial routing inspection area, and performing secondary division on each initial routing inspection area according to each workload to obtain each target routing inspection area;
and planning paths of all the target inspection areas through an ant colony algorithm and a genetic algorithm.
In one embodiment, the computer program when executed by the processor further performs the steps of: calculating the BWP index values of the single data objects based on the single data objects in the routing inspection data; calculating an average BWP value according to each BWP index value; determining the optimal clustering data from the clustering quantity according to the average BWP value; and dividing the polling areas by a K-Means algorithm according to the polling data and the optimal clustering quantity.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining each initial clustering center from each data point of the inspection data through a K-Means algorithm according to the optimal clustering quantity; calculating the distance from each residual data point to each initial clustering center, and dividing each residual data point into the class to which each initial clustering center belongs according to the distance; and judging whether each initial clustering center is converged, if so, outputting a classification result, and dividing the inspection areas according to the classification result to obtain each initial inspection area.
In one embodiment, the computer program when executed by the processor further performs the steps of: calculating the workload of each initial routing inspection area, sequencing the workload, calculating the difference value between the maximum workload and the minimum workload, if the difference value is greater than a workload threshold value, removing the farthest data point which is away from the initial clustering center in the initial routing inspection area corresponding to the maximum workload, and adding the farthest data point to the class which is away from the initial clustering center by the second smallest distance; when an initial routing inspection area with the maximum workload larger than the maximum workload threshold exists, calculating a first distance from each data point in the initial routing inspection area to an initial clustering center, calculating a second distance from each data point to other initial clustering centers, and moving the data points according to the first distance and the second distance; and calculating the ratio of the workload of each initial patrol area to the maximum workload in all the areas, and moving the data points according to the ratio.
In one embodiment, the computer program when executed by the processor further performs the steps of: adopting an ant colony algorithm to generate an initial population, and initializing parameters of the ant colony algorithm; constructing a solution space of an ant colony algorithm, and initializing the positions of ants; randomly distributing ants, updating pheromones and calculating paths traversed by the ants; and taking the path iterated once as an initial population of the genetic algorithm.
In one embodiment, the computer program when executed by the processor further performs the steps of: setting parameters of a genetic algorithm, and initializing the genetic algorithm; the initialization parameters comprise population size, cross probability, mutation probability and iteration times.
In one embodiment, the computer program when executed by the processor further performs the steps of: carrying out crossover and mutation operations on chromosomes in the initial population through a genetic algorithm; carrying out decoding operation on the chromosome to obtain the planning and dividing results of the distribution path; acquiring the fitness value of each individual in the initial population, and selecting excellent individuals to enter the next generation by adopting a roulette mode; adjusting the population scale by adopting a variable-scale population scale genetic algorithm; and when the genetic algorithm reaches the maximum iteration times, ending the algorithm and outputting the shortest distribution path.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (10)
1. A routing inspection path planning method is characterized by comprising the following steps:
acquiring polling data, and calculating the clustering number according to the distance-based intra-class division index BWP of the polling data;
dividing routing inspection areas through a K-Means algorithm according to the routing inspection data and the clustering number to obtain each initial routing inspection area;
calculating the workload of each initial routing inspection area, and performing secondary division on each initial routing inspection area according to each workload to obtain each target routing inspection area;
and planning paths of the target inspection regions through an ant colony algorithm and a genetic algorithm.
2. The inspection path planning method according to claim 1, wherein the dividing of the inspection area by the K-Means algorithm according to the inspection data and the cluster number includes:
calculating a BWP index value of each single data object based on the single data object in the routing inspection data;
calculating an average BWP value according to each BWP index value;
determining optimal clustering data from the number of clusters according to the average BWP value;
and dividing routing inspection areas through a K-Means algorithm according to the routing inspection data and the optimal clustering quantity.
3. The inspection path planning method according to claim 2, wherein the dividing of the inspection areas by the K-Means algorithm to obtain each initial inspection area comprises:
determining each initial clustering center from each data point of the routing inspection data through a K-Means algorithm according to the optimal clustering quantity;
calculating the distance from each residual data point to each initial clustering center, and dividing each residual data point into the class to which each initial clustering center belongs according to the distance;
and judging whether each initial clustering center is converged, if so, outputting a classification result, and dividing routing inspection areas according to the classification result to obtain each initial routing inspection area.
4. The inspection path planning method according to claim 3, wherein the calculating of the workload of each initial inspection area and the secondary division of each initial inspection area according to each workload include:
calculating the workload of each initial routing inspection area, sequencing the workload, calculating the difference value between the maximum workload and the minimum workload, if the difference value is greater than a workload threshold value, removing the farthest data point which is away from the initial clustering center in the initial routing inspection area corresponding to the maximum workload, and adding the farthest data point to the class which is the second smallest away from the initial clustering center;
when an initial routing inspection area with the maximum workload larger than the maximum workload threshold exists, calculating a first distance from each data point in the initial routing inspection area to the initial clustering center, calculating a second distance from each data point to other initial clustering centers, and moving the data points according to the first distance and the second distance;
and calculating the ratio of the workload of each initial routing inspection area to the maximum workload in all areas, and moving data points according to the ratio.
5. The inspection path planning method according to claim 1, wherein before the path planning by the ant colony algorithm and the genetic algorithm, the method further includes:
generating an initial population by adopting an ant colony algorithm, and initializing parameters of the ant colony algorithm;
constructing a solution space of the ant colony algorithm, and initializing the positions of ants;
randomly distributing ants, updating pheromones and calculating traversal paths of the ants;
and taking the path iterated once as an initial population of the genetic algorithm.
6. The inspection path planning method according to claim 5, wherein before the path planning by the ant colony algorithm and the genetic algorithm, the method further includes:
setting parameters of the genetic algorithm and initializing the genetic algorithm;
the initialization parameters comprise population size, cross probability, mutation probability and iteration times.
7. The inspection path planning method according to claim 6, wherein path planning is performed by an ant colony algorithm and a genetic algorithm, and includes:
carrying out crossover and mutation operations on chromosomes in the initial population through the genetic algorithm;
decoding the chromosome to obtain the planning and dividing results of the distribution path;
obtaining the fitness value of each individual in the initial population, and selecting excellent individuals to enter the next generation by adopting a roulette mode;
adopting a variable-scale population scale genetic algorithm to adjust the population scale;
and when the genetic algorithm reaches the maximum iteration times, ending the algorithm and outputting the shortest distribution path.
8. A system for routing inspection, the system comprising:
the cluster number calculation module is used for acquiring the routing inspection data and calculating the cluster number according to the routing inspection data based on the inter-class intra-class division index BWP of the distance;
the initial routing inspection area dividing module is used for dividing routing inspection areas through a K-Means algorithm according to the routing inspection data and the clustering number to obtain each initial routing inspection area;
the inspection area adjusting module is used for calculating the workload of each initial inspection area and carrying out secondary division on each initial inspection area according to each workload to obtain each target inspection area;
and the path planning module is used for planning paths of the target inspection regions through an ant colony algorithm and a genetic algorithm.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211332855.5A CN115755954B (en) | 2022-10-28 | 2022-10-28 | Routing inspection path planning method, system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211332855.5A CN115755954B (en) | 2022-10-28 | 2022-10-28 | Routing inspection path planning method, system, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115755954A true CN115755954A (en) | 2023-03-07 |
| CN115755954B CN115755954B (en) | 2023-07-25 |
Family
ID=85355702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211332855.5A Active CN115755954B (en) | 2022-10-28 | 2022-10-28 | Routing inspection path planning method, system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115755954B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116481546A (en) * | 2023-04-26 | 2023-07-25 | 大连海事大学 | Path planning method for unmanned aerial vehicle navigation mark inspection |
| CN116562598A (en) * | 2023-07-07 | 2023-08-08 | 成都花娃网络科技有限公司 | Distribution scheduling method, device and storage medium |
| CN117439899A (en) * | 2023-12-20 | 2024-01-23 | 陕西华海信息技术有限公司 | Communication machine room inspection method and system based on big data |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018045372A1 (en) * | 2016-09-02 | 2018-03-08 | Snowflake Computing Inc. | Incremental clustering maintenance of a table |
| CN108256969A (en) * | 2018-01-12 | 2018-07-06 | 杭州电子科技大学 | A kind of public bicycles lease point dispatcher-controlled territory division methods |
| CN108332753A (en) * | 2018-01-30 | 2018-07-27 | 北京航空航天大学 | A kind of unmanned plane electric inspection process paths planning method |
| CN108898183A (en) * | 2018-07-02 | 2018-11-27 | 中国人民解放军战略支援部队信息工程大学 | A kind of inspection route formulating method and device |
| CN109871886A (en) * | 2019-01-28 | 2019-06-11 | 平安科技（深圳）有限公司 | Abnormal point ratio optimization method, apparatus and computer equipment based on spectral clustering |
| CN110011223A (en) * | 2019-05-07 | 2019-07-12 | 江苏方天电力技术有限公司 | Multiple no-manned plane cooperation method for inspecting and system suitable for region transmission line of electricity |
| KR102107506B1 (en) * | 2018-12-31 | 2020-05-07 | 목포해양대학교 산학협력단 | Method for optimal arrangement of patrol ship for quick response of marine accident |
| CN111311003A (en) * | 2020-02-18 | 2020-06-19 | 长春一汽国际物流有限公司 | Component sorting method for flexible production |
| CN112731967A (en) * | 2020-12-24 | 2021-04-30 | 中科院计算技术研究所大数据研究院 | Multi-unmanned aerial vehicle collaborative task planning method based on clustering and genetic algorithm |
| CN113077109A (en) * | 2021-04-19 | 2021-07-06 | 广东电网有限责任公司 | Intelligent scheduling system, method, equipment and medium for machine patrol plan |
| CN113286129A (en) * | 2021-07-23 | 2021-08-20 | 北京图知天下科技有限责任公司 | Inspection method and system for photovoltaic power station |
| CN113673299A (en) * | 2021-06-23 | 2021-11-19 | 佳源科技股份有限公司 | Power distribution room small animal detection method based on deep semantic feature extraction |
| CN113741527A (en) * | 2021-09-13 | 2021-12-03 | 德仕能源科技集团股份有限公司 | Oil well inspection method, equipment and medium based on multiple unmanned aerial vehicles |
| CN113780311A (en) * | 2021-09-09 | 2021-12-10 | 广东电网有限责任公司 | Tower vine climbing detection method, device, equipment and storage medium |
| EP3940494A1 (en) * | 2020-07-17 | 2022-01-19 | Wuhan University of Science and Technology | Path planning method for substation inspection robot |
| CN114037918A (en) * | 2021-11-10 | 2022-02-11 | 吉林大学 | Photovoltaic hot spot detection method based on unmanned aerial vehicle inspection and image processing |
| CN114578848A (en) * | 2022-01-14 | 2022-06-03 | 华东师范大学 | Unmanned aerial vehicle routing inspection path planning method based on discrete point density and global planning |
| WO2022135138A1 (en) * | 2020-12-21 | 2022-06-30 | 南方电网电力科技股份有限公司 | Robot task deployment method and system, device, and storage medium |
-
2022
- 2022-10-28 CN CN202211332855.5A patent/CN115755954B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018045372A1 (en) * | 2016-09-02 | 2018-03-08 | Snowflake Computing Inc. | Incremental clustering maintenance of a table |
| CN108256969A (en) * | 2018-01-12 | 2018-07-06 | 杭州电子科技大学 | A kind of public bicycles lease point dispatcher-controlled territory division methods |
| CN108332753A (en) * | 2018-01-30 | 2018-07-27 | 北京航空航天大学 | A kind of unmanned plane electric inspection process paths planning method |
| CN108898183A (en) * | 2018-07-02 | 2018-11-27 | 中国人民解放军战略支援部队信息工程大学 | A kind of inspection route formulating method and device |
| KR102107506B1 (en) * | 2018-12-31 | 2020-05-07 | 목포해양대학교 산학협력단 | Method for optimal arrangement of patrol ship for quick response of marine accident |
| CN109871886A (en) * | 2019-01-28 | 2019-06-11 | 平安科技（深圳）有限公司 | Abnormal point ratio optimization method, apparatus and computer equipment based on spectral clustering |
| CN110011223A (en) * | 2019-05-07 | 2019-07-12 | 江苏方天电力技术有限公司 | Multiple no-manned plane cooperation method for inspecting and system suitable for region transmission line of electricity |
| CN111311003A (en) * | 2020-02-18 | 2020-06-19 | 长春一汽国际物流有限公司 | Component sorting method for flexible production |
| EP3940494A1 (en) * | 2020-07-17 | 2022-01-19 | Wuhan University of Science and Technology | Path planning method for substation inspection robot |
| WO2022135138A1 (en) * | 2020-12-21 | 2022-06-30 | 南方电网电力科技股份有限公司 | Robot task deployment method and system, device, and storage medium |
| CN112731967A (en) * | 2020-12-24 | 2021-04-30 | 中科院计算技术研究所大数据研究院 | Multi-unmanned aerial vehicle collaborative task planning method based on clustering and genetic algorithm |
| CN113077109A (en) * | 2021-04-19 | 2021-07-06 | 广东电网有限责任公司 | Intelligent scheduling system, method, equipment and medium for machine patrol plan |
| CN113673299A (en) * | 2021-06-23 | 2021-11-19 | 佳源科技股份有限公司 | Power distribution room small animal detection method based on deep semantic feature extraction |
| CN113286129A (en) * | 2021-07-23 | 2021-08-20 | 北京图知天下科技有限责任公司 | Inspection method and system for photovoltaic power station |
| CN113780311A (en) * | 2021-09-09 | 2021-12-10 | 广东电网有限责任公司 | Tower vine climbing detection method, device, equipment and storage medium |
| CN113741527A (en) * | 2021-09-13 | 2021-12-03 | 德仕能源科技集团股份有限公司 | Oil well inspection method, equipment and medium based on multiple unmanned aerial vehicles |
| CN114037918A (en) * | 2021-11-10 | 2022-02-11 | 吉林大学 | Photovoltaic hot spot detection method based on unmanned aerial vehicle inspection and image processing |
| CN114578848A (en) * | 2022-01-14 | 2022-06-03 | 华东师范大学 | Unmanned aerial vehicle routing inspection path planning method based on discrete point density and global planning |
Non-Patent Citations (3)
| Title |
|---|
| XIU YUE: "UAV Path Planning Based on K-Means Algorithm and Simulated Annealing Algorithm", 《2018 37TH CHINESE CONTROL CONFERENCE》, pages 2290 - 2295 * |
| 张永涛: "基于枚举法的变电站巡检机器人巡视路线优化", 《浙江电力》, vol. 40, no. 1, pages 12 - 17 * |
| 李建峰;段宇涵;王仓继;王西鹏;郭鹏;张友民;: "无人机在输电线路巡检中的应用", 电网与清洁能源, no. 08, pages 66 - 69 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116481546A (en) * | 2023-04-26 | 2023-07-25 | 大连海事大学 | Path planning method for unmanned aerial vehicle navigation mark inspection |
| CN116481546B (en) * | 2023-04-26 | 2024-02-23 | 大连海事大学 | Path planning method for unmanned aerial vehicle navigation mark inspection |
| CN116562598A (en) * | 2023-07-07 | 2023-08-08 | 成都花娃网络科技有限公司 | Distribution scheduling method, device and storage medium |
| CN116562598B (en) * | 2023-07-07 | 2023-09-19 | 成都花娃网络科技有限公司 | Distribution scheduling method, device and storage medium |
| CN117439899A (en) * | 2023-12-20 | 2024-01-23 | 陕西华海信息技术有限公司 | Communication machine room inspection method and system based on big data |
| CN117439899B (en) * | 2023-12-20 | 2024-03-01 | 陕西华海信息技术有限公司 | Communication machine room inspection method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115755954B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115755954A (en) | Routing inspection path planning method and system, computer equipment and storage medium | |
| Nguyen et al. | Filter based backward elimination in wrapper based PSO for feature selection in classification | |
| CN107862416B (en) | Emergency material storage warehouse site selection optimization method based on box uncertainty set | |
| Zhang et al. | Simulation optimization using the particle swarm optimization with optimal computing budget allocation | |
| CN113742089B (en) | Method, device and equipment for distributing neural network computing tasks in heterogeneous resources | |
| CN105117326A (en) | Test case set generation method based on combination chaotic sequence | |
| CN116681104B (en) | Model building and realizing method of distributed space diagram neural network | |
| CN114461386A (en) | Task allocation method and task allocation device | |
| CN115965138A (en) | Peak-valley electricity price time period prediction method, peak-valley electricity price time period prediction device, computer equipment and medium | |
| CN111461284A (en) | Data discretization method, device, equipment and medium | |
| Jin et al. | Mapping very large scale spiking neuron network to neuromorphic hardware | |
| CN111711702B (en) | Distributed cooperative interaction method and system based on communication topology | |
| CN110275895B (en) | Filling equipment, device and method for missing traffic data | |
| CN1658560A (en) | Quickly data copy method based on prediction | |
| Pan et al. | Distribution consistent neural architecture search | |
| CN109978138A (en) | The structural reliability methods of sampling based on deeply study | |
| CN116523001A (en) | Method, device and computer equipment for constructing weak line identification model of power grid | |
| CN114881158A (en) | Defect value filling method and device based on random forest and computer equipment | |
| CN114819151A (en) | Biochemical path planning method based on improved agent-assisted shuffled frog leaping algorithm | |
| CN114115818A (en) | Micro-service dividing method, device, equipment and medium | |
| CN114386555A (en) | Emergency task allocation method based on multi-objective optimization | |
| Younis et al. | Approximated unimodal region elimination-based global optimisation method for engineering design | |
| CN112925793A (en) | Distributed mixed storage method and system for multiple structural data | |
| CN112118135A (en) | Minimum resource configuration method and device for cloud edge cooperative architecture industrial internet platform | |
| CN113391850B (en) | Task scheduling method, device and equipment based on edge cloud cooperation and storage medium |
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 |