CN114279636A - Multi-unmanned aerial vehicle gas leakage source positioning method based on improved seagull algorithm - Google Patents
Multi-unmanned aerial vehicle gas leakage source positioning method based on improved seagull algorithm Download PDFInfo
- Publication number
- CN114279636A CN114279636A CN202111594830.8A CN202111594830A CN114279636A CN 114279636 A CN114279636 A CN 114279636A CN 202111594830 A CN202111594830 A CN 202111594830A CN 114279636 A CN114279636 A CN 114279636A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- gull
- improved
- unmanned aerial
- gas leakage
- 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.)
- Withdrawn
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention creatively combines an improved gull algorithm with an unmanned aerial vehicle cluster, and discloses a multi-unmanned aerial vehicle gas leakage source positioning method based on the improved gull algorithm. Compared with the traditional tracing method relying on a fixed monitoring station or a ground mobile robot, the unmanned aerial vehicle cluster is used as a tracing platform for gas leakage, and the method has the advantages of low cost, wide search range, strong flexibility, high tracing efficiency and the like. Compared with a standard gull algorithm, the gas leakage source positioning method based on the improved gull algorithm has the following innovations: the value range of the balance operator B is narrowed, the step length is greatly reduced, and the global search capability is greatly improved; the spiral radius r is set as a fixed value, so that the individual cannot have a relatively disordered moving direction in the iteration process, and the stability of the algorithm is improved; due to the introduction of the foraging behavior, other individuals can explore themselves while following the optimal individuals, and the local optimal state is avoided.
Description
Technical Field
The invention relates to a method for positioning a multi-unmanned-wing aircraft cooperative gas leakage source, and belongs to the field of multi-rotor-wing unmanned aerial vehicles and atmospheric environment monitoring.
Background
As an important support for economic development in China, the influence of industrial development on economy is obvious, but the problem of environmental pollution is continuously highlighted. At present, atmospheric environmental pollution occurs frequently, for example, abnormal odor generated by emission of pollution gas in the industrial production process often causes discontent emotion and complaint of residents, and how to find a pollution source in the shortest time is very important for providing the fastest technical support for atmospheric environmental pollution treatment. At present, a fixed monitoring station or a ground mobile robot is mostly adopted in a gas leakage source positioning method, the defect that the fixed monitoring station is limited by the position is obvious, when a pollution source leaks, the pollution source is likely to be inaccurately positioned due to uneven distribution of the positions of the fixed monitoring station, so that the best time for finding the pollution source is missed, and the ground mobile robot can change the position of the ground mobile robot in the tracing process, but is difficult to adapt to the characteristics of high diffusion speed and wide diffusion range of gas pollutants in an atmospheric medium and is difficult to continuously work. At present, unmanned aerial vehicle is being in the high-speed development stage in the application of environment field, and unmanned aerial vehicle has advantages such as with low costs, search range is wide and the flexibility is strong to unmanned aerial vehicle regard as atmosphere pollution sources location platform, can enlarge the scope of tracing to the source, improves the efficiency of tracing to the source.
Aiming at the current increasingly serious environmental pollution problem and the limitation of the existing gas leakage source positioning method, the invention aims to solve the technical problem of positioning the gas leakage source of the multi-unmanned aerial vehicle based on the group intelligent algorithm.
At present, the swarm intelligence optimization algorithm mainly comprises a genetic algorithm, a particle swarm algorithm, an artificial fish swarm algorithm and the like, and the gull algorithm is just proposed in 2019 and gradually starts to be applied in aspects of marketing strategy planning, optimized logging interpretation, image segmentation and the like. This patent is used for the first time this gull algorithm to solve the technical problem of gas leakage source location, nevertheless still has following problem in the application: in the standard gull algorithm, the most important characteristic of the gull is migration and attack behaviors, and the setting of a balance operator B in the migration behavior enables the algorithm to greatly prolong the distance between the current individual and the optimal individual, so that the individual can approach the optimal individual in a larger step length in the next step of position updating, the integral convergence speed is faster, but the optimal value is easy to miss in the iteration process; secondly, random values of the radius r of the spiral in the attack behavior can make the moving direction of the individual more disordered; finally, the algorithm is lack of a random exploration process of the individuals on the whole, so that other individuals can unconditionally follow the current optimal individuals in the iteration process, and the local optimal situation is easy to fall into.
Disclosure of Invention
The invention aims to make up for the defects of the existing leakage source positioning technology, creatively combines a multi-unmanned aerial vehicle cluster with an improved gull algorithm, and provides a multi-unmanned aerial vehicle gas leakage source positioning method based on the improved gull algorithm. Aiming at the defects of the standard gull algorithm, the invention provides an improved gull algorithm. Firstly, the value range of the balance operator B is reduced, the step length is greatly reduced, and the global search capability of the algorithm is greatly improved. Secondly, the spiral radius r is set as a fixed value, so that the individual cannot have a disordered moving direction in the iteration process. Finally, the foraging behavior is added on the basis of the original gull algorithm, so that the individual exploration capacity is enhanced, and the algorithm is not easy to fall into local optimum in the iteration process.
A multi-unmanned aerial vehicle gas leakage source positioning method based on an improved gull algorithm comprises the following steps:
step 1: detecting that the concentration value of the gas pollutant obviously exceeds the daily monitoring range in a downwind area of a gas leakage source, preliminarily judging that enterprise steal behavior possibly exists, and starting an emergency tracing program;
step 2: setting N unmanned aerial vehicles in an area to be monitored, and setting initial positions of the unmanned aerial vehicles;
and step 3: searching a gas leakage source by adopting an improved seagull algorithm;
and 4, step 4: updating the position of each unmanned aerial vehicle;
and 5: judging whether the gas leakage source is successfully positioned, if so, executing the step 6, otherwise, returning to the step 3;
step 6: unmanned aerial vehicle finds the gas leakage source, and emergent tracing to the source is finished, and output gas leaks the source position.
The improved gull algorithm provided in the step 3 comprises the following steps:
step 1: initialization setting, including population number popsize, dimension D of solution space, maximum iteration number T of algorithm, and variable fcThe maximum number of attempts try _ number,Maximum moving step length and population initial position;
step 2: calculating the fitness value of each individual of the initial population to obtain the position P of the current optimal individualbs(t)；
And step 3: performing global search according to migration behavior in improved gull algorithm, and utilizing position P of current optimal individualbs(t) obtaining the new position D of the seagulls(t)；
And 4, step 4: local search is carried out according to the attack behavior in the improved gull algorithm, and the new position D of the gull is utilizeds(t) obtaining the attack position P of the gulls(t)；
And 5: according to the foraging behavior of the sea gull, using the attack position P of the sea gulls(t), maximum number of trials try _ number, and maximum step size of movement update position L of gulls(t) and a contaminant gas concentration value Y (t);
step 6: judging whether the iteration times are reached, if so, turning to a step 7, otherwise, returning to the step 2;
and 7: and outputting the optimizing result, and finishing the algorithm.
Further, the migration behavior in step 3 is implemented by the following calculation formula:
Ds(t)＝|Cs(t)+Ms(t)|
wherein, Cs(t)＝A×Ps(t)，Cs(t) indicates a new position, P, which does not conflict with the positions of other seagullss(t) represents the current position of the seagull, t represents the current iteration number, and a ═ fc-(t×(fcT)), a represents the motion behavior of the gull in a given search space, wherein fcThe frequency of variable a can be controlled to decrease its value linearly from 2 to 0, Ms(t)＝B×(Pbs(t)-Ps(t))，Ms(t) indicates the direction in which the best position is located, B is the random number responsible for balancing the global and local searches, and B is 0.5 × rd，rdIs [0, 1 ]]Random numbers within a range.
The attack behavior in step 4 is implemented by the following calculation formula:
Ps(t)＝Ds(t)×x×y×z+Pbs(t)
where x is r × cos (θ), y is r × sin (θ), z is r × θ, and xyz represents the spiral-shaped motion performed in the air when the gull attacks the prey, θ is a random angle value in the range of [0, 2 pi ], and r is the radius of each spiral.
The foraging behavior in the step 5 is realized by the following calculation formula:
Ls(t)＝Ps(t)+Rand×step
wherein Rand is [ -1, 1 [ ]]Random number in the range, step being the maximum step size of movement, gull being at Ps(t) selecting a position with a radius of step as the center of the circle and a position with a higher food concentration than the current position in the circle to carry out foraging, namely the concentration value Y of the polluted gasLs(t)>YPs(t) if Y (t) is YLs(t)。
The invention has the beneficial effects that:
the invention creatively combines the improved gull algorithm with the unmanned aerial vehicle group to realize the quick and efficient positioning of the gas leakage source.
In the migration behavior of the original gull algorithm, the value of the balance operator B is limited by the variable A, so that the algorithm greatly prolongs the distance between the current individual and the optimal individual, and the individual can approach the optimal individual in a larger step length in the next step of position updating, the overall convergence speed is higher, but the optimal value is easy to miss in the iteration process. Aiming at the problem, the method simulates the setting idea of a balance operator in the Woofer algorithm, reduces the value range of the balance operator, greatly reduces the step length and greatly improves the global search capability.
In the attack behavior of the original gull algorithm, the random value of the spiral radius r can cause the moving direction of an individual to be disordered, so the spiral radius r is set as a fixed value, and the stability of the algorithm is improved.
In the original gull algorithm, the random exploration process of individuals is lacked, so that other individuals can unconditionally follow the current optimal individuals in the iteration process, and the local optimal individual is easy to fall into. Aiming at the problem, the invention simulates the idea of foraging behavior in an artificial fish swarm algorithm, so that other individuals can perform own exploration behavior while following the optimal individual, and the situation that the individual falls into local optimal is avoided.
Drawings
FIG. 1 is a flow chart of a method for locating a source of a gas leak from multiple drones based on an improved gull algorithm;
FIG. 2 is a flow chart of an improved gull algorithm;
FIG. 3 is a simulation route diagram of an improved gull algorithm under a Gaussian steady-state smoke plume concentration field artificially built in MATLAB software;
FIG. 4 is a graph comparing the optimizing efficiency of the improved gull algorithm with that of the standard gull algorithm in a Gaussian steady-state plume concentration field;
the specific implementation mode is as follows:
the invention is implemented as follows:
step 1: detecting that the concentration value of the gas pollutant obviously exceeds the daily monitoring range in a downwind area of a gas leakage source, preliminarily judging that enterprise steal behavior possibly exists, and starting an emergency tracing program;
step 2: setting 5 unmanned aerial vehicles in an area to be monitored, and setting the initial positions of the unmanned aerial vehicles;
and step 3: searching a gas leakage source by adopting an improved seagull algorithm;
and 4, step 4: updating the position of each unmanned aerial vehicle;
and 5: judging whether the gas leakage source is successfully positioned, if so, executing the step 6, otherwise, returning to the step 3;
step 6: unmanned aerial vehicle finds the gas leakage source, and emergent tracing to the source is finished, and output gas leaks the source position.
The improved gull algorithm provided in the step 3 comprises the following steps:
step 1: initialization setting, including population number popsize, dimension D of solution space, maximum iteration number T of algorithm, and variable fcMaximum trial times try _ number, maximum moving step length and group initial position;
step 2: calculating the fitness value of each individual of the initial population to obtain the position P of the current optimal individualbs(t)；
And step 3: performing global search according to migration behavior in improved gull algorithm, and utilizing position P of current optimal individualbs(t) obtaining the new position D of the seagulls(t)；
The migration behavior is realized by the following calculation formula:
Ds(t)＝|Cs(t)+Ms(t)|
and 4, step 4: local search is carried out according to the attack behavior in the improved gull algorithm, and the new position D of the gull is utilizeds(t) obtaining the attack position P of the gulls(t)；
The attack behavior is implemented with the following calculation:
Ps(t)＝Ds(t)×x×y×z+Pbs(t)
and 5: according to the foraging behavior of the sea gull, using the attack position P of the sea gulls(t), maximum number of trials try _ number, and maximum step size of movement update position L of gulls(t) and a contaminant gas concentration value Y (t);
foraging behavior is achieved using the following computational formula:
Ls(t)＝Ps(t)+Rand×step
step 6: judging whether the iteration times are reached, if so, turning to a step 7, otherwise, returning to the step 2;
and 7: and outputting the optimizing result, and finishing the algorithm.
As shown in fig. 4, in the gaussian steady-state plume concentration field simulation experiment, because the value range of the balance operator B of the standard gull algorithm is large and the algorithm lacks a random exploration process of an individual as a whole, the gull algorithm is trapped into local optimality and cannot jump out until iteration is finished, the value range of the balance operator B is narrowed by improving the gull algorithm, the step length is greatly reduced, and foraging behavior is added into the algorithm, so that other individuals can randomly explore along with the optimal individual, and the trapping into local optimality is avoided.
The above is a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to change or replace the technical solution of the present invention within the technical scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (5)
1. A multi-unmanned aerial vehicle gas leakage source positioning method based on an improved gull algorithm is characterized by comprising the following steps:
step 1: detecting that the concentration value of the gas pollutant obviously exceeds the daily monitoring range in a downwind area of a gas leakage source, preliminarily judging that enterprise steal behavior possibly exists, and starting an emergency tracing program;
step 2: setting N unmanned aerial vehicles in an area to be monitored, and setting initial positions of the unmanned aerial vehicles;
and step 3: searching a gas leakage source by adopting an improved seagull algorithm;
and 4, step 4: updating the position of each unmanned aerial vehicle;
and 5: judging whether the gas leakage source is successfully positioned, if so, executing the step 6, otherwise, returning to the step 3;
step 6: unmanned aerial vehicle finds the gas leakage source, and emergent tracing to the source is finished, and output gas leaks the source position.
2. The method of claim 1, wherein the improved gull algorithm provided in step 3 comprises the following steps:
step 1: initialization setting, including population number popsize, dimension D of solution space, maximum iteration number T of algorithm, and variable fcMaximum trial times try _ number, maximum moving step length and group initial position;
step 2: calculating the fitness value of each individual of the initial population to obtain the position P of the current optimal individualbs(t)；
And step 3: performing global search according to migration behavior in improved gull algorithm, and utilizing position P of current optimal individualbs(t) obtaining the new position D of the seagulls(t)；
And 4, step 4: local search is carried out according to the attack behavior in the improved gull algorithm, and the new position D of the gull is utilizeds(t) obtaining the attack position P of the gulls(t)；
And 5: according to the foraging behavior of the sea gull, using the attack position P of the sea gulls(t), maximum number of trials try _ number, and maximum step size of movement update position L of gulls(t) and a contaminant gas concentration value Y (t);
step 6: judging whether the iteration times are reached, if so, turning to a step 7, otherwise, returning to the step 2;
and 7: and outputting the optimizing result, and finishing the algorithm.
3. The improved gull algorithm of claim 2, wherein D in step 3s(t) the equation for which the operator B, B is 0.5 × rd，rdIs [0, 1 ]]Random numbers in the range reduce the value range of the balance operator B, greatly reduce the step length and greatly improve the global search capability.
4. The improved gull algorithm of claim 2, wherein P in step 4 issAnd (t) setting the spiral radius r as a fixed value in the calculation formula of the invention, ensuring that individuals do not have a disordered moving direction in the iteration process, and improving the stability of the algorithm.
5. The improved gull algorithm of claim 2, wherein L in step 5 iss(t) the calculation formula:
Ls(t)＝Ps(t)+Rand×step
wherein Rand is [ -1, 1 [ ]]Random number in the range, step being the maximum step size of movement, gull being at Ps(t) selecting a position with a radius of step as the center of the circle and a position with a higher food concentration than the current position in the circle to carry out foraging, namely the concentration value Y of the polluted gasLs(t)>YPs(t) if Y (t) is YLsAnd (t), other individuals can randomly explore themselves while following the optimal individuals, and the situation that the individuals fall into local optimal conditions is avoided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111594830.8A CN114279636A (en) | 2021-12-24 | 2021-12-24 | Multi-unmanned aerial vehicle gas leakage source positioning method based on improved seagull algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111594830.8A CN114279636A (en) | 2021-12-24 | 2021-12-24 | Multi-unmanned aerial vehicle gas leakage source positioning method based on improved seagull algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114279636A true CN114279636A (en) | 2022-04-05 |
Family
ID=80875500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111594830.8A Withdrawn CN114279636A (en) | 2021-12-24 | 2021-12-24 | Multi-unmanned aerial vehicle gas leakage source positioning method based on improved seagull algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114279636A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116128330A (en) * | 2022-11-18 | 2023-05-16 | 中国人民解放军陆军装甲兵学院 | Air-ground unmanned system combat effectiveness evaluation method based on machine learning |
-
2021
- 2021-12-24 CN CN202111594830.8A patent/CN114279636A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116128330A (en) * | 2022-11-18 | 2023-05-16 | 中国人民解放军陆军装甲兵学院 | Air-ground unmanned system combat effectiveness evaluation method based on machine learning |
| CN116128330B (en) * | 2022-11-18 | 2024-04-26 | 中国人民解放军陆军装甲兵学院 | Air-ground unmanned system combat effectiveness evaluation method based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fu et al. | Pollution source localization based on multi-UAV cooperative communication | |
| CN112507622B (en) | Anti-unmanned aerial vehicle task allocation method based on reinforcement learning | |
| CN113867368B (en) | Robot path planning method based on improved gull algorithm | |
| CN110062390B (en) | Wireless sensor network node optimization deployment method based on improved wolf colony algorithm | |
| CN111751502B (en) | Multi-unmanned-aerial-vehicle cooperative pollutant tracing method based on improved simulated annealing | |
| CN113885536B (en) | Mobile robot path planning method based on global gull algorithm | |
| Liu et al. | A Survey on Particle Swarm Optimization Algorithms for Multimodal Function Optimization. | |
| Xue et al. | Path planning of mobile robot based on improved ant colony algorithm for logistics | |
| CN109063938A (en) | Air Quality Forecast method based on PSODE-BP neural network | |
| CN110401958B (en) | Node dynamic coverage enhancement method based on virtual force | |
| CN115509239B (en) | Unmanned vehicle route planning method based on air-ground information sharing | |
| CN112327876B (en) | Robot path planning method based on terminal distance index | |
| CN114279636A (en) | Multi-unmanned aerial vehicle gas leakage source positioning method based on improved seagull algorithm | |
| CN110928357A (en) | Maximum power point tracking method of photovoltaic array under time-varying shadow condition | |
| CN105652952A (en) | Maximum power point tracking method for photovoltaic power generation system based on fireworks algorithm | |
| CN115407784A (en) | Unmanned vehicle route planning method based on air-ground information complementation | |
| CN115113628A (en) | Routing method of inspection robot based on improved wolf algorithm | |
| CN113867369A (en) | Robot path planning method based on alternating current learning seagull algorithm | |
| CN115437386A (en) | Unmanned vehicle route planning method based on air-ground information fusion | |
| CN113495564A (en) | Ground unmanned platform path planning method based on evolutionary drosophila algorithm | |
| CN115657694A (en) | Unmanned vehicle route planning method based on air-ground information interaction | |
| CN108445894A (en) | A kind of secondary paths planning method considering unmanned boat movenent performance | |
| CN114995390A (en) | Mobile robot path planning method based on dynamic adaptive parameter adjustment dayflies algorithm | |
| CN116772880B (en) | Unmanned aerial vehicle path planning method based on unmanned aerial vehicle vision | |
| Gao et al. | A multiobjective hybrid optimization algorithm for path planning of coal mine patrol robot |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220405 |