CN113407895B - Flash bird repelling optimal frequency selection method and system based on simulated annealing algorithm - Google Patents
Flash bird repelling optimal frequency selection method and system based on simulated annealing algorithm Download PDFInfo
- Publication number
- CN113407895B CN113407895B CN202110731551.5A CN202110731551A CN113407895B CN 113407895 B CN113407895 B CN 113407895B CN 202110731551 A CN202110731551 A CN 202110731551A CN 113407895 B CN113407895 B CN 113407895B
- Authority
- CN
- China
- Prior art keywords
- frequency
- flashing
- flash
- simulated annealing
- solution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M29/00—Scaring or repelling devices, e.g. bird-scaring apparatus
- A01M29/06—Scaring or repelling devices, e.g. bird-scaring apparatus using visual means, e.g. scarecrows, moving elements, specific shapes, patterns or the like
- A01M29/10—Scaring or repelling devices, e.g. bird-scaring apparatus using visual means, e.g. scarecrows, moving elements, specific shapes, patterns or the like using light sources, e.g. lasers or flashing lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Optics & Photonics (AREA)
- Algebra (AREA)
- Birds (AREA)
- Insects & Arthropods (AREA)
- Pest Control & Pesticides (AREA)
- Wood Science & Technology (AREA)
- Zoology (AREA)
- Environmental Sciences (AREA)
- Catching Or Destruction (AREA)
Abstract
The application discloses a flash bird repelling optimal frequency selection method and system based on a simulated annealing algorithm.
Description
Technical Field
The application relates to the technical field of flash bird repelling, in particular to a flash bird repelling optimal frequency selection method and system based on a simulated annealing algorithm.
Background
Because birds frequently move on the power transmission line to bring certain harm to the safe operation of the power transmission line, the line fault frequency brought by the birds is higher and higher.
Most of existing bird repelling equipment is installed on a transmission tower, and birds are repelled to be away from a transmission area through modes of flashing, sound, visual stimulation and the like. The flashing frequency of the existing flashing bird repelling device is fixed and unchanged, and birds have certain adaptability to the flashing frequency, so that the effectiveness of repelling the birds is greatly reduced, and line faults are easy to occur.
Disclosure of Invention
The application provides a method and a system for selecting optimal flashing bird-repelling frequency based on a simulated annealing algorithm, which are used for solving the technical problem that the effectiveness of bird repelling is greatly reduced due to the fact that the flashing frequency of the existing flashing bird-repelling equipment is fixed.
In view of this, the first aspect of the present application provides a method for selecting an optimal frequency for flashing bird repelling based on a simulated annealing algorithm, including the following steps:
s1, repelling birds based on a flash bird repelling device under a preset initial flash frequency, and acquiring a relative distance of the birds repelling under the preset initial flash frequency, wherein the relative distance is a difference between a distance of the birds relative to a position of the flash bird repelling device within a preset time after flash driving is started and a distance of the birds relative to the position of the flash bird repelling device before flash driving is started, and when the birds are successfully repelled, the relative distance is larger than 0;
s2, forming a pair of mapping data by the preset initial flashing frequency and the relative distance, and storing the mapping data into a mapping database;
s3, adjusting the preset initial flashing frequency, and repeating the steps S1-S2 until the logarithm of the mapping data in the mapping database reaches a preset logarithm;
s4, fitting the mapping data in the mapping database based on a least square method to form a fitting curve, so as to obtain a fitting curve function;
s5, calculating the fitted curve function based on a simulated annealing algorithm to obtain the optimal flash frequency;
and S6, replacing the preset initial flashing frequency with the optimal flashing frequency, applying the optimal flashing frequency to the flashing bird repelling device, and repeating the steps from S1 to S6 so as to continuously and iteratively replace the flashing frequency of the flashing bird repelling device.
Preferably, step S1 is preceded by: selecting the preset initial flashing frequency specifically comprises the following steps: the preset initial flashing frequency is selected according to a probability density function meeting normal distribution or selected according to historical flashing frequency data.
Preferably, the step of adjusting the preset initial flashing frequency in step S3 specifically includes:
updating the preset initial flashing frequency according to the following formula,
f1=f0+(-1) v γ(θ)
wherein f1 represents the flash frequency after update, f0 represents the flash frequency before update, v is a random number 1 or 2, and γ (θ) represents a value range of (f 0, θ) max -f0]Wherein θ is max Indicating the maximum flashing frequency of the flashing bird repellent device.
Preferably, the fitted curve function in step S4 is,
f(x)=a 1 α 1 (x)+a 2 α 2 (x)+...+a n α n (x)
in the formula, alpha k (x) k =1, 2.. N is a set of linearly independent functions, a k k =1, 2.., n denotes a pending coefficient;
suppose the mapped data point value to be fitted is y i i =1,2,. N, then the mapped data point values y to be fitted are fitted i The sum of the squares of the distances to the fitted curve function f (x) is the smallest, and the corresponding fitted curve function f (x) is the best fitted curve function.
Preferably, step S5 specifically includes:
s501, initializing parameters of a simulated annealing algorithm, assuming that the initial temperature of the simulated annealing is T, the lowest temperature of the simulated annealing is T _ min, and the maximum iteration number is L;
s502, randomly generating an initial solution theta in a solution space, and calculating a function value f (theta) of the fitting curve function according to the initial solution theta;
s503, applying disturbance to the initial solution to generate a new solution theta ', and calculating a function value f (theta ') of the fitted curve function according to the new solution theta ';
s504, calculating a difference between the function value f (θ) of the fitting curve function and the function value f (θ ') of the fitting curve function, that is, Δ f = f (θ) -f (θ'), Δ f representing the difference;
s505, judging whether the difference delta f is smaller than 0, if so, accepting the new solution theta ', and if not, judging whether accepting the new solution theta' according to Metropolis criterion;
s506, if the new solution theta ' is accepted, the new solution theta ' is taken as the current solution, and if the new solution theta ' is not accepted, the initial solution theta is taken as the current solution;
s507, according to the current solution serving as an initial solution of the next iteration, repeating the steps S502-S507 to perform iterative calculation, continuously iterating for N times in the iteration process, and if the generated new solutions are all accepted, reducing the current temperature of the simulated annealing, wherein N is less than L;
s508, judging whether an iteration ending condition is met, if not, reducing the current temperature of the simulated annealing until the current temperature of the simulated annealing reaches the lowest temperature T _ min of the simulated annealing and iteration is ended or until the iteration times reaches the maximum iteration times L, and outputting a new solution obtained by the last iteration as the optimal flash frequency, wherein the reduction of the current temperature of the simulated annealing meets a temperature attenuation function, and the temperature attenuation function is T k+1 =αT k ,T k Temperature at time k, T k+1 The temperature at time k +1, α, represents the temperature cooling coefficient, α ∈ (0.95, 0.99).
Preferably, the step of applying a perturbation to the initial solution in step S503 to generate a new solution θ' specifically includes:
s5031, taking the initial solution as an initial point, and generating a new solution along a gradient reverse direction by adopting a steepest descent method;
s5032, if the generated new solution is not accepted, decreasing the step size of the gradient descent returns to step S5031 for recalculation, wherein the step size may be determined by a one-dimensional optimization method.
Preferably, the step of judging whether to accept the new solution θ' according to the Metropolis criterion in step S505 specifically includes:
when the initial temperature of the simulated annealing is T, calculating the internal energy of the initial solution and the new solution, and if E is satisfied j <E i Accepting the new solution, wherein E i 、E j Respectively representing the internal energy of the initial solution and the internal energy of the new solution; if not satisfying E j <E i According to a probability formulaWhether the solution is larger than the random number in the interval of [0, 1), if the judgment is yes, the new solution is accepted, and if the judgment is no, the new solution is not accepted, wherein p represents the solution of the probability formula, and K represents the self-defined parameter.
In a second aspect, the invention provides a flash bird repelling optimal frequency selection system based on a simulated annealing algorithm, which is used for executing the flash bird repelling optimal frequency selection method based on the simulated annealing algorithm, and comprises a relative distance module, a mapping module, a flash frequency adjusting module, a fitting module, a simulated annealing module and a frequency replacing module;
the relative distance module is used for acquiring the relative distance of birds driven under the preset initial flashing frequency based on the flashing bird driving equipment under the preset initial flashing frequency, the relative distance is the difference between the distance of the birds relative to the position of the flashing bird driving equipment in the preset time after the flashing driving is started and the distance of the birds relative to the position of the flashing bird driving equipment before the flashing driving is started, and when the birds are driven successfully, the relative distance is larger than 0;
the mapping module is used for forming a pair of mapping data by the preset initial flashing frequency and the relative distance and storing the mapping data into a mapping database;
the flash frequency adjusting module is used for adjusting the preset initial flash frequency;
the fitting module is used for fitting the mapping data in the mapping database based on a least square method to form a fitting curve so as to obtain a fitting curve function;
the simulated annealing module is used for calculating the fitted curve function based on a simulated annealing algorithm to obtain the optimal flashing frequency;
the frequency replacing module is used for replacing the preset initial flashing frequency with the optimal flashing frequency and applying the optimal flashing frequency to the flashing bird repelling device.
According to the technical scheme, the invention has the following advantages:
the invention utilizes the mapping relation between different flash frequencies and the corresponding relative distance of the driven birds to be fitted into a fitting curve function, forms the dynamic prediction relation between the dynamic flash frequencies and the corresponding relative distances of the driven birds, then obtains the optimal flash frequency by calculating the fitting curve function based on a simulated annealing algorithm, applies the optimal flash frequency to flash bird driving equipment, and obtains different optimal flash frequencies by continuous iteration processing, thereby ensuring that the optimal flash frequency can be dynamically changed and improving the effectiveness of bird driving.
Drawings
Fig. 1 is a flowchart of a flash bird repelling optimal frequency selection method based on a simulated annealing algorithm according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a flash bird repelling optimal frequency selection system based on a simulated annealing algorithm according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
Most of existing bird repelling equipment is installed on a transmission tower, and birds are repelled to be away from a power transmission area through modes of flashing, sound, visual stimulation and the like. The flashing frequency of the existing flashing bird repelling device is fixed and unchangeable, and birds have certain adaptability to the flashing bird repelling device, so that the effectiveness of repelling the birds is greatly reduced, and line faults are easy to occur.
Therefore, referring to fig. 1, the invention provides a flash bird repelling optimal frequency selection method based on a simulated annealing algorithm, which comprises the following steps:
s1, repelling birds based on flash bird repelling equipment under a preset initial flash frequency, acquiring a relative distance of the birds driven under the preset initial flash frequency, wherein the relative distance is a difference between a distance of the birds relative to the position of the flash bird repelling equipment within a preset time after the flash driving is started and a distance of the birds relative to the position of the flash bird repelling equipment before the flash driving is started, and when the birds are successfully driven, the relative distance is larger than 0;
s2, forming a pair of mapping data by the preset initial flashing frequency and the relative distance, and storing the mapping data into a mapping database;
s3, adjusting the preset initial flashing frequency, and repeating the steps S1-S2 until the logarithm of the mapping data in the mapping database reaches the preset logarithm;
s4, fitting the mapping data in the mapping database based on a least square method to form a fitting curve, so as to obtain a fitting curve function;
s5, calculating the fitted curve function based on a simulated annealing algorithm to obtain the optimal flashing frequency;
and S6, replacing the preset initial flashing frequency with the optimal flashing frequency, applying the optimal flashing frequency to the flashing bird repelling device, and repeating the steps from S1 to S6, thereby continuously and iteratively replacing the flashing frequency of the flashing bird repelling device.
In the embodiment, the mapping relation between different flashing frequencies and the corresponding relative distance of the repelled birds is fitted into a fitting curve function to form a dynamic prediction relation between the dynamic flashing frequencies and the corresponding relative distances of the repelled birds, the fitting curve function is operated based on a simulated annealing algorithm to obtain the optimal flashing frequency, the optimal flashing frequency is applied to flashing bird repelling equipment, and different optimal flashing frequencies are obtained through continuous iteration processing, so that the optimal flashing frequency can be dynamically changed, and the bird repelling effectiveness is improved.
The following is a detailed description of an embodiment of the method for selecting the optimal frequency for flashing bird repelling based on the simulated annealing algorithm.
The invention provides a flash bird repelling optimal frequency selection method based on a simulated annealing algorithm, which comprises the following steps of:
s100, selecting a preset initial flashing frequency, and specifically comprising the following steps: selecting preset initial flashing frequency according to a probability density function meeting normal distribution or selecting according to historical flashing frequency data;
it should be noted that, in an embodiment, the initial flashing frequency of the flashing bird repelling device may be selected according to historical flashing frequency data, or may be selected according to a probability density function satisfying normal distribution, where the probability density function is phi = phi + (-1) v f(s) phi, phi denotes the flashing frequency, v denotes the random number 1 or 2,is a value range of [0,1]In the formula, μ represents a mean value, and σ represents a variance.
S200, driving birds based on the flash bird driving equipment under the preset initial flash frequency, obtaining the relative distance of the birds driven under the preset initial flash frequency, wherein the relative distance is the difference between the distance of the birds relative to the position of the flash bird driving equipment in the preset time after the flash driving is started and the distance of the birds relative to the position of the flash bird driving equipment before the flash driving is started, and when the birds are driven successfully, the relative distance is larger than 0;
it should be noted that, under the action of the flashing frequency, the relative distance of the birds is the difference between the distance of the birds relative to the position of the flashing bird repelling device within the preset time after the flashing driving is started and the distance of the birds relative to the position of the flashing bird repelling device before the flashing driving is started; if the birds are successfully driven under the action of the flash frequency, the distance between the birds and the device is increased compared with that before the flash is started, the relative distance can be obtained through radar detection, and the relative distance larger than 0 represents the state of successful bird driving, which indicates that the flash bird driving equipment is effective in driving the birds under the flash frequency.
S300, forming a pair of mapping data by the preset initial flashing frequency and the relative distance, and storing the mapping data into a mapping database;
s400, adjusting the preset initial flashing frequency, and repeating the steps S200-S300 until the logarithm of the mapping data in the mapping database reaches the preset logarithm;
it should be noted that, when the preset initial flashing frequency is adjusted, the relative distance of the birds driven under the preset initial flashing frequency can be adjusted, so that the effectiveness of driving away the birds is ensured.
In one embodiment, the preset initial flashing frequency is updated according to,
f1=f0+(-1) v γ(θ)
wherein f1 represents the flash frequency after update, f0 represents the flash frequency before update, v is a random number of 1 or 2, and γ (θ) represents a value range of (f 0, θ) max -f0]Of (a) is generated randomly, wherein θ max Indicating the maximum flashing frequency of the flashing bird repellent device.
In addition, the preset logarithm may be based on the maximum storage capacity of the mapping database, and assuming that the maximum storage capacity of the mapping database is 10, only mapping data of 10 flashing frequencies and relative distances may exist.
S500, fitting the mapping data in the mapping database based on a least square method to form a fitting curve, so as to obtain a fitting curve function;
specifically, the fitted curve function in step S500 is,
f(x)=a 1 α 1 (x)+a 2 α 2 (x)+...+a n α n (x)
in the formula, alpha k (x) k =1, 2.. N is a set of linearly independent functions, a k k =1,2., n denotes a undetermined coefficient;
suppose the mapped data point value to be fitted is y i i =1, 2.. N, then the mapped data point values y to be fitted are fitted i And the square sum of the distances from the fitting curve function f (x) is minimum, so that the corresponding fitting curve function f (x) is the best fitting curve function, and the best fitting curve function is the curve target function obtained by final fitting.
S600, calculating the fitted curve function based on a simulated annealing algorithm to obtain the optimal flashing frequency;
specifically, step S600 specifically includes:
s601, initializing parameters of a simulated annealing algorithm, assuming that the initial temperature of the simulated annealing is T, the lowest temperature of the simulated annealing is T _ min, and the maximum iteration number is L;
it should be noted that the initial temperature T can be as high as possible to satisfyWhere θ is the initial solution, f (θ) is the fitted curve objective function value, and f (θ) = f (x).
The lowest temperature T _ min is the termination condition of algorithm iteration, and in order to obtain the optimal solution, the lowest temperature should be as low as possible; for each iteration of the temperature, the number of iterations is set to be in a decreasing trend as the temperature decreases.
S602, randomly generating an initial solution theta in a solution space, and calculating a function value f (theta) of a fitting curve function according to the initial solution theta;
s603, applying disturbance to the initial solution to generate a new solution theta ', and calculating a function value f (theta ') of the fitting curve function according to the new solution theta ';
it should be noted that the step of applying a perturbation to the initial solution to generate a new solution θ' in S503 specifically includes:
s6031, taking the initial solution as an initial point, and generating a new solution along the gradient reverse direction by adopting a steepest descent method;
s6032, if the generated new solution is not accepted, reducing the step length of the gradient descent, returning to the step S6031 for recalculation, wherein the step length can be determined by adopting a one-dimensional optimization method, and specifically, enabling the step length to be determined by adopting a one-dimensional optimization methodIn the formula (I), the compound is shown in the specification,is the function f at point x k The gradient of (d); so that f (x) k+1 ) The minimum t is the optimal step size.
S604, calculating a difference between the function value f (θ) of the fitted curve function and the function value f (θ ') of the fitted curve function, that is, Δ f = f (θ) -f (θ'), Δ f representing the difference;
s605, judging whether the difference delta f is smaller than 0, if yes, receiving a new solution theta ', and if not, judging whether to receive the new solution theta' according to Metropolis criteria;
it should be noted that the step of judging whether to accept the new solution θ' according to the Metropolis criterion specifically includes:
when the initial temperature of the simulated annealing is T, calculating the internal energy of the initial solution and the new solution, and if E is satisfied j <E i Then a new solution is accepted, wherein E i 、E j Respectively representing the internal energy of the initial solution and the internal energy of the new solution; if not satisfying E j <E i According to a probability formulaIs greater than the random number in the interval of [0, 1), if the judgment is yes, the new solution is accepted, if the judgment is no, the new solution is not accepted, wherein p represents the solution of the probability formula, and K represents the self-defined parameter.
S606, if the new solution theta ' is accepted, the new solution theta ' is taken as the current solution, and if the new solution theta ' is not accepted, the initial solution theta is taken as the current solution;
s607, repeating the steps S602-S607 for iterative calculation according to the current solution as the initial solution of the next iteration, continuously iterating for N times in the iterative process, and if the generated new solutions are all accepted, reducing the current temperature of the simulated annealing, wherein N is less than L;
s608, judging whether an iteration ending condition is met, if not, reducing the current temperature of the simulated annealing until the current temperature of the simulated annealing reaches the lowest temperature T _ min of the simulated annealing and iteration ends or until the iteration times reaches the maximum iteration times L, and outputting a new solution obtained by the last iteration as the optimal flash frequency, wherein the reduction of the current temperature of the simulated annealing meets a temperature attenuation function, and the temperature attenuation function is T k+1 =αT k ,T k Temperature at time k, T k+1 The temperature at the time k +1, α represents the temperature cooling coefficient, α ∈ (0.95, 0.99).
S700, replacing the preset initial flashing frequency with the optimal flashing frequency, applying the optimal flashing frequency to the flashing bird repelling device, and repeating the steps S200-S700, thereby continuously and iteratively replacing the flashing frequency of the flashing bird repelling device.
The invention further provides a selection system for executing the flash bird repelling optimal frequency selection method based on the simulated annealing algorithm according to the embodiment, and please refer to fig. 2 for easy understanding, the flash bird repelling optimal frequency selection system based on the simulated annealing algorithm provided by the invention comprises a relative distance module 100, a mapping module 200, a flash frequency adjusting module 300, a fitting module 400, a simulated annealing module 500 and a frequency replacing module 600:
the relative distance module 100 is configured to drive birds based on the flash bird repelling device at a preset initial flash frequency, obtain a relative distance of the birds driven at the preset initial flash frequency, where the relative distance is a difference between a distance of the birds from the position of the flash bird repelling device within a preset time after the flash driving is started and a distance of the birds from the position of the flash bird repelling device before the flash driving is started, and when the birds are successfully driven, the relative distance is greater than 0;
the mapping module 200 is configured to store a pair of mapping data, which is formed by a preset initial flashing frequency and a relative distance, in a mapping database;
a flash frequency adjusting module 300 for adjusting a preset initial flash frequency;
a fitting module 400, configured to fit the mapping data in the mapping database based on a least square method to form a fitting curve, so as to obtain a fitting curve function;
the simulated annealing module 500 is used for calculating the fitting curve function based on a simulated annealing algorithm to obtain the optimal flash frequency;
the frequency replacing module 600 is configured to replace the preset initial flashing frequency with an optimal flashing frequency, and further configured to apply the optimal flashing frequency to the flashing bird repelling device.
It should be noted that the working process in this embodiment is consistent with the working process of the method for selecting the optimal frequency for flashing and bird repelling based on the simulated annealing algorithm in the above embodiment, and details are not repeated here.
According to the system for selecting the optimal flashing bird-repelling frequency based on the simulated annealing algorithm, the mapping relation between different flashing frequencies and the corresponding relative distances of the birds to be repelled is utilized to be fitted into a fitting curve function, a dynamic prediction dynamic relation between the dynamic flashing frequencies and the corresponding relative distances of the birds to be repelled is formed, the fitting curve function is calculated based on the simulated annealing algorithm to obtain the optimal flashing frequencies, the optimal flashing frequencies are applied to flashing bird-repelling equipment, and different optimal flashing frequencies are obtained through continuous iteration processing, so that the optimal flashing frequencies can be dynamically changed, and the bird-repelling effectiveness is improved.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present application.
Claims (7)
1. The method for selecting the optimal frequency of the flash bird repelling based on the simulated annealing algorithm is characterized by comprising the following steps of:
s1, driving birds based on flash bird driving equipment under a preset initial flash frequency, obtaining a relative distance of the birds driven under the preset initial flash frequency, wherein the relative distance is the difference between the distance of the birds relative to the position of the flash bird driving equipment within a preset time after flash driving is started and the distance of the birds relative to the position of the flash bird driving equipment before flash driving is started, and when the birds are driven successfully, the relative distance is larger than 0;
s2, forming a pair of mapping data by the preset initial flashing frequency and the relative distance, and storing the mapping data into a mapping database;
s3, adjusting the preset initial flashing frequency, and repeating the steps S1-S2 until the logarithm of the mapping data in the mapping database reaches a preset logarithm;
the step of adjusting the preset initial flashing frequency in step S3 specifically includes:
the preset initial flashing frequency is updated according to the following formula,
f1=f0+(-1) v γ(θ)
wherein f1 represents the flash frequency after update, f0 represents the flash frequency before update, v is a random number of 1 or 2, and γ (θ) represents a value range of (f 0, θ) max -f0]Of (a) is generated randomly, wherein θ max Representing a maximum flashing frequency of the flashing bird repelling device;
s4, fitting the mapping data in the mapping database based on a least square method to form a fitting curve, so as to obtain a fitting curve function;
s5, calculating the fitted curve function based on a simulated annealing algorithm to obtain the optimal flash frequency;
and S6, replacing the preset initial flashing frequency with the optimal flashing frequency, applying the optimal flashing frequency to the flashing bird repelling device, and repeating the steps from S1 to S6 so as to continuously and iteratively replace the flashing frequency of the flashing bird repelling device.
2. The method for selecting the optimal frequency for flashing bird repelling based on the simulated annealing algorithm according to claim 1, wherein the step S1 comprises the following steps: selecting the preset initial flashing frequency specifically comprises the following steps: the preset initial flashing frequency is selected according to a probability density function meeting normal distribution or according to historical flashing frequency data.
3. The method for selecting the optimal frequency for flashing bird repelling based on the simulated annealing algorithm as claimed in claim 1, wherein the fitting curve function in step S4 is,
f(x)=a 1 α 1 (x)+a 2 α 2 (x)+…+a n α n (x)
in the formula, alpha k (x) k =1, 2.. N is a set of linearly independent functions, a k k =1, 2.., n denotes a pending coefficient;
assume that the mapped data point value to be fitted is y i i =1, 2.. N, then the mapped data point values y to be fitted are fitted i The sum of the squares of the distances to the fitted curve function f (x) is the smallest, and the corresponding fitted curve function f (x) is the best fitted curve function.
4. The method for selecting the optimal frequency for flashing bird repelling based on the simulated annealing algorithm according to claim 1, wherein the step S5 specifically comprises the following steps:
s501, initializing parameters of a simulated annealing algorithm, assuming that the initial temperature of the simulated annealing is T, the lowest temperature of the simulated annealing is T _ min, and the maximum iteration number is L;
s502, randomly generating an initial solution theta in a solution space, and calculating a function value f (theta) of the fitting curve function according to the initial solution theta;
s503, applying disturbance to the initial solution to generate a new solution theta ', and calculating a function value f (theta ') of the fitted curve function according to the new solution theta ';
s504, calculating a difference between the function value f (θ) of the fitting curve function and the function value f (θ ') of the fitting curve function, that is, Δ f = f (θ) -f (θ'), Δ f representing the difference;
s505, judging whether the difference delta f is smaller than 0, if so, accepting the new solution theta ', and if not, judging whether accepting the new solution theta' according to Metropolis criterion;
s506, if the new solution theta ' is accepted, the new solution theta ' is taken as the current solution, and if the new solution theta ' is not accepted, the initial solution theta is taken as the current solution;
s507, according to the current solution serving as an initial solution of the next iteration, repeating the steps S502-S507 to perform iterative calculation, continuously iterating for N times in the iteration process, and if the generated new solutions are all accepted, reducing the current temperature of the simulated annealing, wherein N is less than L;
s508, judging whether an iteration ending condition is met, if not, reducing the current temperature of the simulated annealing until the current temperature of the simulated annealing reaches the lowest temperature T _ min of the simulated annealing and iteration is ended or until the iteration times reaches the maximum iteration times L, and outputting a new solution obtained by the last iteration as the optimal flash frequency, wherein the reduction of the current temperature of the simulated annealing meets a temperature attenuation function, and the temperature attenuation function is T k+1 =αT k ,T k Temperature at time k, T k+1 The temperature at the time k +1, α represents the temperature cooling coefficient, α ∈ (0.95, 0.99).
5. The method for selecting the optimal frequency for flashing bird repelling based on the simulated annealing algorithm as claimed in claim 4, wherein the step of applying the perturbation to the initial solution in step S503 to generate a new solution θ' specifically comprises:
s5031, taking the initial solution as an initial point, and generating a new solution along a gradient reverse direction by adopting a steepest descent method;
s5032, if the generated new solution is not accepted, decreasing the step size of the gradient descent returns to step S5031 for recalculation, wherein the step size may be determined by a one-dimensional optimization method.
6. The method for selecting the optimal frequency for flashing bird repelling based on the simulated annealing algorithm as claimed in claim 4, wherein the step of judging whether to accept the new solution θ' according to Metropolis criterion in step S505 specifically comprises:
when the initial temperature of the simulated annealing is T, calculating the internal energy of the initial solution and the new solution, and if the internal energy satisfies E j <E i Accepting the new solution, wherein E i 、E j Respectively representing the internal energy of the initial solution and the internal energy of the new solution; if not satisfy E j <E i According to a probability formulaWhether the solution of (2) is larger than the [0, 1) regionAnd if the judgment is yes, accepting the new solution, and if the judgment is no, not accepting the new solution, wherein p represents the solution of the probability formula, and K represents the self-defined parameter.
7. The flash bird repelling optimal frequency selection system based on the simulated annealing algorithm is used for executing the flash bird repelling optimal frequency selection method based on the simulated annealing algorithm, and is characterized by comprising a relative distance module, a mapping module, a flash frequency adjusting module, a fitting module, a simulated annealing module and a frequency replacing module;
the relative distance module is used for acquiring the relative distance of birds driven under the preset initial flashing frequency based on the flashing bird driving equipment under the preset initial flashing frequency, the relative distance is the difference between the distance of the birds relative to the position of the flashing bird driving equipment in the preset time after the flashing driving is started and the distance of the birds relative to the position of the flashing bird driving equipment before the flashing driving is started, and when the birds are driven successfully, the relative distance is larger than 0;
the mapping module is used for forming a pair of mapping data by the preset initial flashing frequency and the relative distance and storing the mapping data into a mapping database;
the flash frequency adjusting module is used for adjusting the preset initial flash frequency; in particular for updating said preset initial flashing frequency according to the following formula,
f1=f0+(-1) v γ(θ)
wherein f1 represents the flash frequency after update, f0 represents the flash frequency before update, v is a random number 1 or 2, and γ (θ) represents a value range of (f 0, θ) max -f0]Of (a) is generated randomly, wherein θ max Representing a maximum flashing frequency of the flashing bird repelling device;
the fitting module is used for fitting the mapping data in the mapping database based on a least square method to form a fitting curve so as to obtain a fitting curve function;
the simulated annealing module is used for calculating the fitting curve function based on a simulated annealing algorithm to obtain the optimal flash frequency;
the frequency replacing module is used for replacing the preset initial flashing frequency with the optimal flashing frequency and applying the optimal flashing frequency to the flashing bird repelling device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110731551.5A CN113407895B (en) | 2021-06-29 | 2021-06-29 | Flash bird repelling optimal frequency selection method and system based on simulated annealing algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110731551.5A CN113407895B (en) | 2021-06-29 | 2021-06-29 | Flash bird repelling optimal frequency selection method and system based on simulated annealing algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113407895A CN113407895A (en) | 2021-09-17 |
CN113407895B true CN113407895B (en) | 2023-01-20 |
Family
ID=77680230
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110731551.5A Active CN113407895B (en) | 2021-06-29 | 2021-06-29 | Flash bird repelling optimal frequency selection method and system based on simulated annealing algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113407895B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5570321A (en) * | 1994-03-03 | 1996-10-29 | Atlantic Richfield Company | Seismic velocity model optimization method using simulated annearling to determine prestack travel-times |
CN212787168U (en) * | 2020-07-27 | 2021-03-26 | 华北电力大学 | Novel transmission line unmanned aerial vehicle intelligence drive bird device |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104082272A (en) * | 2014-07-07 | 2014-10-08 | 国家电网公司 | Telemetering type mixed frequency bird repelling device |
CN104115818B (en) * | 2014-08-10 | 2016-07-27 | 哈尔滨理工大学 | The acousto-optic compound bird-repeller system that a kind of vertical shaft fan is constituted |
CN205357935U (en) * | 2016-03-03 | 2016-07-06 | 哈尔滨理工大学 | Transmission line reputation combines bird repellent device |
CN106359364A (en) * | 2016-10-10 | 2017-02-01 | 深圳供电局有限公司 | Intelligent comprehensive bird expelling device |
CN106682682A (en) * | 2016-10-20 | 2017-05-17 | 北京工业大学 | Method for optimizing support vector machine based on Particle Swarm Optimization |
CN106945837A (en) * | 2017-04-14 | 2017-07-14 | 上海博历机械科技有限公司 | A kind of bird repellent unmanned plane of utilization high efficiency dye sensitization solar battery |
CN107027739A (en) * | 2017-04-21 | 2017-08-11 | 上海博历机械科技有限公司 | One kind contains the continuous type airport bird scaring system of LED light device |
CN108858198A (en) * | 2018-07-26 | 2018-11-23 | 西北工业大学 | A kind of robotic arm path planing method based on Genetic Simulated Annealing Algorithm |
CN111513054B (en) * | 2020-04-09 | 2022-08-02 | 国家电网有限公司 | Bird repelling method and bird repelling device based on ultrasonic waves |
CN111972394B (en) * | 2020-06-11 | 2022-01-21 | 广东电网有限责任公司 | DQN-based selection method for optimal frequency of ultrasonic bird repelling |
CN111860947B (en) * | 2020-06-11 | 2023-01-24 | 广东电网有限责任公司 | Transmission tower bird damage occurrence probability prediction method based on BP neural network |
-
2021
- 2021-06-29 CN CN202110731551.5A patent/CN113407895B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5570321A (en) * | 1994-03-03 | 1996-10-29 | Atlantic Richfield Company | Seismic velocity model optimization method using simulated annearling to determine prestack travel-times |
CN212787168U (en) * | 2020-07-27 | 2021-03-26 | 华北电力大学 | Novel transmission line unmanned aerial vehicle intelligence drive bird device |
Also Published As
Publication number | Publication date |
---|---|
CN113407895A (en) | 2021-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110809771B (en) | System and method for compression and distribution of machine learning models | |
CN107798379B (en) | Method for improving quantum particle swarm optimization algorithm and application based on improved algorithm | |
CN108476488B (en) | Determining the position of a wireless transmitter | |
JP2019197540A5 (en) | ||
CN111652863A (en) | Medical image detection method, device, equipment and storage medium | |
CN113407895B (en) | Flash bird repelling optimal frequency selection method and system based on simulated annealing algorithm | |
CN111972394B (en) | DQN-based selection method for optimal frequency of ultrasonic bird repelling | |
CN110149588A (en) | Determine the method, apparatus, equipment and storage medium of the position of unmanned plane base station | |
CN112996058A (en) | User QoE (quality of experience) optimization method based on multi-unmanned aerial vehicle network, unmanned aerial vehicle and system | |
CN109379747B (en) | Wireless network multi-controller deployment and resource allocation method and device | |
KR101659485B1 (en) | Apparatus and method for processing tactical datalink based on grid scheme | |
CN113676559B (en) | Information processing system and method for multi-device mobile edge calculation of Internet of things | |
CN107995027B (en) | Improved quantum particle swarm optimization algorithm and method applied to predicting network flow | |
Torre et al. | Fractal-based measure approximation with entropy maximization and sparsity constraints | |
CN110912283B (en) | Parameter adjusting method and device of wireless power transmission system | |
TW202243399A (en) | Method for flattening impedance of power deliver network | |
JP7393603B2 (en) | Antenna design support device, antenna design support program, and antenna design support method | |
CN114187462A (en) | Method, device and equipment for determining deployment position of service network point of operation machine | |
CN116644646B (en) | Method, device, equipment and storage medium for mesoscopic reconstruction of rock | |
CN115379386B (en) | Unmanned plane cluster electromagnetic spectrum monitoring method and device based on wolf's swarm algorithm | |
JP2020087148A (en) | Information processing device, information processing method and program | |
CN117726049B (en) | Regional walking time length determining method, electronic equipment and storage medium | |
Gandhi et al. | A novel Hénon map based adaptive PSO for wavelet shrinkage image denoising | |
CN116643868A (en) | Vehicle edge system task scheduling method based on location privacy awareness | |
CN117579655A (en) | Electric automobile charging demand sensing method and system based on edge server |
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 |