Ultra-wideband coal mine underground positioning method based on improved star-graffiti optimization algorithm

Abstract

The invention discloses an ultra wide band coal mine underground positioning method based on an improved star-graffiti optimization algorithm, and the method comprises the steps: arranging UWB base stations in a coal mine underground positioning region, receiving a signal transmitted by a label through a UWB receiver, and correspondingly obtaining the linear distance between each base station and the label; measuring and acquiring coordinate information of the UWB base station by using a measuring instrument to obtain coordinates of the base station; constructing an equation set according to the coordinates of the base stations and the linear distance between each base station and the label, and constructing a fitness function based on a positioning model; and a Chan algorithm is utilized to determine the search upper and lower bounds of the star-graffiti optimization algorithm, the number of populations is defined, after the populations are initialized by adopting a good point set method, the iterative optimization process of the improved star-graffiti optimization algorithm is executed, and a positioning result is obtained. According to the invention, by improving the star-graffiti optimization algorithm, the interference problem of the complex environment under the coal mine to the UWB signal is effectively solved, and the positioning precision is significantly improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of ultra-wideband positioning, and particularly relates to an ultra-wideband underground coal mine positioning method based on an improved starling optimization algorithm. Background Art

[0002] At present, coal mines are an essential energy source in China. Although the production capacity of coal mines has decreased with the adjustment of the energy structure, their proportion in energy consumption is still relatively high. Coal mine resources in China are widely distributed, and there are problems such as large differences in the national coal mine mining technology level and safety conditions, weak awareness of coal mine safety control, and insufficient risk intelligent assessment and early warning technology capabilities, resulting in frequent coal mine accidents, causing casualties and economic losses, and seriously affecting the economic benefits and reputation of coal mines. Therefore, the research on mine personnel positioning technology is of extremely important significance.

[0003] Ultra-wideband (UWB) technology is a technology that uses broadband signals for communication and positioning. UWB technology uses short pulse signals with a large bandwidth for data transmission and positioning, and has advantages such as high-speed transmission, strong anti-interference ability, and high-precision positioning. In indoor positioning, UWB technology calculates the distance between the target object and the receiver by sending short pulse signals and using the multipath effect, thereby achieving positioning. Compared with other indoor positioning technologies, UWB technology is not sensitive to channel fading, has lower energy consumption, lower interception ability, and is relatively simple to install and deploy. Because of the high-precision and high-stability characteristics of UWB technology, it is applied in many fields. In addition to indoor positioning, UWB technology can also be used for object tracking, wireless communication, indoor navigation, and intelligent building management. UWB technology can accurately locate people's positions, thereby providing personalized services.

[0004] UWB positioning technology has multiple positioning modes, mainly including TDOA (Time Difference of Arrival), AOA (Angle of Arrival), and TOA (Time of Arrival) and other methods. TDOA (Time Difference of Arrival) positioning is a classic ranging technology that obtains the distance difference by measuring the time difference of the tag arriving at different sensors, and then determines the position of the tag. The TDOA positioning method does not depend on the propagation time of the signal, but locates through the time difference, so it has high stability and accuracy. AOA (Angle of Arrival) positioning determines the position of the target object by using the incident angle of the wireless signal arriving at the receiver. This method receives signals through multiple antenna arrays and calculates the direction of signal arrival to estimate the target position. TOA (Time of Arrival) positioning determines the distance by measuring the propagation time of the tag to the base station, and calculates the position of the tag using geometric methods (such as circular positioning method).

[0005] However, indoor positioning in coal mines faces challenges in complex environments. No matter which traditional positioning mode is adopted, the data obtained based on UWB ranging is inevitably affected by systematic errors and usually also contains various random errors. In summary, the existing UWB positioning methods in coal mines mainly have the following defects:

[0006] Signal attenuation and interference: The complex geological environment in coal mines causes severe attenuation of UWB signals during propagation. At the same time, phenomena such as reflection, scattering, and absorption by ore bodies will further affect the stability and accuracy of the signals.

[0007] Insufficient positioning accuracy: Traditional positioning modes (such as TDOA, AOA, TOA) are difficult to achieve high-precision positioning in complex environments. Especially in the deep part of the mine, the instability of the signal propagation path increases the positioning error.

[0008] Limited error compensation ability: Existing intelligent optimization algorithms often struggle to balance global search and local optimization when dealing with non-line-of-sight errors, resulting in limited improvement in positioning accuracy. Summary of the Invention

[0009] The present invention aims to provide a UWB positioning method for coal mines based on an improved starling optimization algorithm to solve problems such as signal attenuation and interference, insufficient positioning accuracy, and limited error compensation ability existing in the prior art.

[0010] To achieve the above object, the present invention provides a UWB coal mine underground positioning method based on an improved starling optimization algorithm, including:

[0011] Deploy UWB base stations within the coal mine underground positioning area, and receive the signals emitted by the tags through UWB receivers to obtain the straight-line distances between each base station and the tag correspondingly.

[0012] Measure and obtain the coordinate information of the UWB base stations using measuring instruments to obtain the base station coordinates.

[0013] Construct an equation system based on the base station coordinates and the straight-line distances between each base station and the tag, and construct a fitness function based on the positioning model.

[0014] Use the Chan algorithm to determine the search upper and lower bounds of the starling optimization algorithm, define the population size, and after initializing the population using the good point set method, perform the iterative optimization process of the improved starling optimization algorithm to obtain the positioning result.

[0015] Preferably, the number of deployed UWB base stations is 6.

[0016] Preferably, the positions of the tags are randomly distributed within the coal mine underground positioning area.

[0017] Preferably, the process of constructing the fitness function based on the positioning model includes:

[0018] Based on the basic positioning model, convert the straight-line distance difference from the tag to each base station into a non-linear equation, and construct the fitness function by minimizing the mean square error between the actual measurement value and the theoretical value.

[0019] Preferably, the process of using the Chan algorithm to determine the search upper and lower bounds of the starling optimization algorithm, defining the population size, and initializing the population using the good point set method includes:

[0020] First, use the Chan algorithm to solve and obtain the preliminary coordinate values;

[0021] Determine the search space centered on the preliminary coordinate values, and within the search space, use the good point set method to create an initial population and uniformly generate initial population individuals.

[0022] Preferably, the iterative optimization process of executing the improved starling optimization algorithm includes: a foraging stage and a storage stage;

[0023] Among them, the foraging stage is based on the Levy flight strategy and random individual selection for global exploration and local exploitation to update the population position;

[0024] The storage stage conducts in-depth exploitation through cache search and random radian strategy, combines the optimal individual and the random individual to adjust the population position, and finally solves the accurate coordinates of the tag.

[0025] Preferably, the global exploration based on the Levy flight strategy and random individual selection includes a first-stage exploration and a second-stage exploration;

[0026] The first-stage exploration is described as:

[0027]

[0028] The second-stage exploration is described as:

[0029]

[0030] Among them, represents the position vector of the i-th starling individual at the current iteration t + 1, represents the position vector of the i-th starling individual at the current iteration t, represents the average position of the starling individual in the j dimension, represents the coordinate vector of the A starling individual randomly selected from the population in the j dimension at the current iteration t, Denote the coordinate vector of the Nuthatch individual randomly selected from the population in the j - dimension at the current iteration t. μ represents a scaling factor, usually a random number between [0, 1], and U j Denote the upper bound of the j - dimension, and L j Denote the lower bound of the j - dimension, and T max Denote the maximum number of iterations, Denote the position vector of the i - th Nuthatch individual in the j - dimension at the current iteration t + 1, Denote the position vector of the i - th Nuthatch individual in the j - dimension at the current iteration t, Denote the position of the current optimal individual in the j - dimension, Denote the cached position of the i - th Nuthatch individual at the current iteration t, Denote the coordinate vector of the Nuthatch individual C randomly selected from the population in the j - dimension at the current iteration t. γ is a random number generated according to the Levy flight function, is the optimal individual position of the current population. A, B, and C are three different Nuthatch individuals randomly selected from the population, x m is the average position of all Nuthatches, r1, r2, τ i , (i = 1, 2, 3, 4, 5, 6, 7, 8) are all random numbers between [0, 1]. τ4 is a random number subject to a normal distribution, τ5 is a random number generated by Levy flight, t is the current iteration number, and δ is a constant; is the optimal individual of the current population, C is a Nuthatch individual randomly selected from the population, r1, r2, τ i , (i = 1, 2, 3, 4, 5, 6, 7, 8) are all random numbers between [0, 1].

[0031] Preferably, local exploitation based on the Levy flight strategy and random individual selection is described by the formula expression as follows:

[0032]

[0033] In the formula, Denote the new position vector of the i - th Nuthatch individual at the current iteration t + 1, Denote the position vector of the i - th Nuthatch individual at the current iteration t, Denote the optimal individual of the current population, Denote the position vector of the i - th Nuthatch individual at the current iteration t, λ represents the number generated by Levy flight, Denote the coordinate vector of the Nuthatch individual A randomly selected from the population at the current iteration t, Denote the coordinate vector of the Nuthatch individual B randomly selected from the population at the current iteration t, and l represents a factor that linearly decreases from 1 to 0.

[0034] Preferably, the cache search and random radian recovery strategy is described by a formula expression as follows:

[0035]

[0036]

[0037] In the formula, represents the cache position of the i-th nutcracker individual at the current iteration t, represents the position vector of the i-th nutcracker individual at the current iteration t, α represents a scaling factor, a random number between [0, 1], represents the coordinate vector of the randomly selected A nutcracker individual in the population at the current iteration t, represents the coordinate vector of the randomly selected B nutcracker individual in the population at the current iteration t, represents the compensation coefficient, RP represents the reference point parameter, represents the upper bound of the search space, represents the lower bound of the search space, T max represents the maximum number of iterations, represents a uniformly distributed random number, represents a random vector between [0, 1], P rp represents the probability threshold, θ is a random radian between [0, π], A and B are two different randomly selected nutcracker individuals from the population, r1, r2, τ3 are random numbers between [0, 1], is a random vector between [0, 1].

[0038] Preferably, the in-depth development of the cache search and random radian recovery strategy is described by a formula expression as follows:

[0039]

[0040] In the formula, represents the position vector of the i-th nutcracker individual at the current iteration t + 1, represents the position vector of the i-th nutcracker individual at the current iteration t, represents the cache position of the i-th nutcracker individual at the current iteration t.

[0041] Compared with the prior art, the present invention has the following advantages and technical effects:

[0042] By introducing the Levy flight strategy, the present invention enhances the global search ability, can more effectively explore the search space, avoid falling into local optimal solutions, and thus improve the positioning accuracy.

[0043] The present invention combines the initialization of good-point sets to optimize the population distribution, ensuring the diversity and coverage of the population, and further enhancing the global search ability of the algorithm.

[0044] The present invention utilizes an adaptive mechanism (foraging and storage stages) to dynamically balance the exploration and development processes, effectively suppressing the influence of random errors, so that high-precision positioning can still be maintained in a complex underground environment.

[0045] The present invention uses an improved starling optimization algorithm to achieve a better balance between global search and local optimization, and can accurately model and compensate for non-line-of-sight errors, effectively solving the problems of insufficient adaptability and robustness of existing intelligent optimization algorithms in complex environments.

[0046] The present invention conducts in-depth development through cache search and random radian strategies, further optimizing the population position, improving the algorithm's ability to suppress random errors, and making the positioning results more stable and reliable.

[0047] The present invention has been optimized for the complex underground environment of coal mines, and can effectively address problems such as signal attenuation, reflection, scattering, and absorption, ensuring the stability and reliability of the positioning system. In complex environments such as deep in the mine, this method can still exhibit high robustness and adaptability, providing a reliable positioning solution for coal mine safety monitoring and emergency rescue.

[0048] In summary, through the improved starling optimization algorithm, the present invention effectively solves the problems existing in the existing UWB underground coal mine positioning technology, such as signal attenuation and interference, insufficient positioning accuracy, and limited error compensation ability, and has high practical value and broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings constituting a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0050] Figure 1 is a schematic flowchart of the method according to an embodiment of the present invention;

[0051] Figure 2 is a schematic diagram of the site according to an embodiment of the present invention;

[0052] Figure 3 is a schematic diagram of two-dimensional error analysis according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will refer to the drawings and combine the embodiments to detail this application.

[0054] Note that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0055] The environment underground in coal mines is complex, and factors such as geological structures, rock strata, and ores will cause significant attenuation of UWB signals. Especially deep in the mine, the signal propagation process will be affected by the reflection, scattering, and absorption of ore bodies, resulting in a reduction in positioning accuracy. The high-density rock and ore materials have a large blocking effect on the signal, causing the UWB signal propagation path to be unstable and affecting the measurement accuracy.

[0056] As Figures 1-3 shown, in this embodiment, a UWB underground coal mine positioning method based on an improved starling optimization algorithm is provided, aiming to obtain more accurate position information. It includes the following steps:

[0057] Step S1: Deploy UWB base stations in the underground coal mine positioning area, receive the signals emitted by the tags through UWB receivers, and obtain the straight-line distances between each base station and the tags.

[0058] Step S2: Use measuring instruments to measure the coordinate information of the base stations, construct an equation set by combining the base station coordinates and the straight-line distances from the tags to each base station, and define a fitness function based on the positioning model.

[0059] Step S3: Use the Chan algorithm to determine the search upper and lower bounds of the starling optimization algorithm, define the population size, and initialize the population using the good point set method.

[0060] Step S4: After initialization, enter the next stage and execute the iterative optimization process of the improved starling optimization algorithm, including the following two stages:

[0061] The first stage (foraging stage): Based on the Levy flight strategy and random individual selection, conduct global exploration and local development, and update the population position.

[0062] The second stage (storage stage): Conduct in-depth development through cache search and random radian strategy, adjust the population position by combining the optimal individual and the random individual, and finally solve the accurate coordinates of the tag.

[0063] Furthermore, in step S1, the number of deployed UWB base stations is 6, and the base station coordinates are obtained by measuring with high-precision measuring instruments. The positions of the tags are randomly distributed within the positioning area.

[0064] Further, in the step S2, the construction method of the fitness function is as follows: Based on the basic positioning model, the linear distance difference from the tag to each base station is converted into a non - linear equation, and the fitness function is defined by minimizing the mean square error between the actual measurement value and the theoretical value.

[0065] Further, in the step S3, first, the preliminary coordinate values are solved by using the Chan algorithm, and the search space is determined with this as the center. In the search space, the method of good - point set is used to create the initial population, and the initial population individuals are uniformly generated to ensure the diversity and coverage of the population distribution.

[0066] Further, in the step S4, this mechanism can be divided into two main stages: foraging and storing, which are specifically described as follows:

[0067] 4.1. The first - stage exploration;

[0068]

[0069] In the public, represents the position vector of the i - th nutcracker individual at the current iteration t + 1, represents the position vector of the i - th nutcracker individual at the current iteration t, represents the average position of the nutcracker individual in the j - dimension, represents the coordinate vector of the A - th nutcracker individual randomly selected from the population in the j - dimension at the current iteration t, represents the coordinate vector of the B - th nutcracker individual randomly selected from the population in the j - dimension at the current iteration t, μ represents a scaling factor, usually a random number between [0,1], U j represents the upper bound of the j - dimension, L j represents the lower bound of the j - dimension, T max represents the maximum number of iterations, represents the position vector of the i - th nutcracker individual in the j - dimension at the current iteration t + 1, represents the position vector of the i - th nutcracker individual in the j - dimension at the current iteration t, represents the current optimal individual position in the j - dimension, represents the cached position of the i - th nutcracker individual at the current iteration t, represents the coordinate vector of the C - th nutcracker individual randomly selected from the population in the j - dimension at the current iteration t, γ is a random number generated according to the Levy flight function, is the optimal individual of the current population, A, B, C are three different nutcracker individuals randomly selected from the population, x mis the average position of all nutcrackers. τ1, τ2, τ3, r1, r2 are all random numbers between [0, 1]. τ4 is a random number following a normal distribution. τ5 is a random number generated by a Lévy flight. t is the current iteration number, and δ is set to 0.05.

[0070] 4.2. First-stage development;

[0071]

[0072] represents the new position vector of the i-th nutcracker individual at the current iteration t + 1. represents the position vector of the i-th nutcracker individual at the current iteration t. represents the optimal individual of the current population. represents the position vector of the i-th nutcracker individual at the current iteration t. λ represents a random number generated by the Lévy flight function. represents the coordinate vector of the randomly selected A nutcracker individual in the population at the current iteration t. represents the coordinate vector of the randomly selected B nutcracker individual in the population at the current iteration t. l represents a factor linearly decreasing from 1 to 0.

[0073] Proceed to the next stage. This mechanism is a cache search and retrieval strategy, which is described as follows:

[0074]

[0075] In the formula, represents the cache position of the i-th nutcracker individual at the current iteration t. represents the position vector of the i-th nutcracker individual at the current iteration t. α represents a scaling factor, a random number between [0, 1]. represents the coordinate vector of the randomly selected A nutcracker individual in the population at the current iteration t. represents the coordinate vector of the randomly selected B nutcracker individual in the population at the current iteration t. represents the compensation coefficient. RP represents the reference point parameter. represents the upper bound of the search space. represents the lower bound of the search space. T max represents the maximum number of iterations. represents a uniformly distributed random number. represents a random vector between [0, 1]. P rp represents the probability threshold. θ is a random radian between [0, π]. A and B are two different nutcracker individuals randomly selected from the population. r1, r2, τ3 are random numbers between [0, 1]. is a random vector between [0, 1]. T is the maximum number of iterations.

[0076] 4.3. Second-stage exploration;

[0077]

[0078] is the optimal individual of the current population, C is a nutcracker individual randomly selected from the population, r1, r2, τ i , (i = 1, 2, 3, 4, 5, 6, 7, 8) are all random numbers between [0, 1].

[0079] 4.4. Second-stage development;

[0080]

[0081] In the formula, represents the position vector of the i-th nutcracker individual at the current iteration t + 1, represents the position vector of the i-th nutcracker individual at the current iteration t, represents the cache position of the i-th nutcracker individual at the current iteration t.

[0082] More specifically, in this embodiment, a site with a length of 5 m and a width of 5 m is selected, and data is collected using 6 UWB base stations, a UWB tag, and a set of metric lenses;

[0083] The UWB base stations are arranged according to the required positioning area, and the signals emitted by the tag are received by the UWB receiver to obtain the straight-line distances between each base station and the tag;

[0084] The coordinate information of the base stations is obtained using metric instruments, and a system of equations is constructed based on the base station coordinates and the straight-line distances between each base station and the tag, and a fitness function is constructed based on the positioning model;

[0085] The search upper and lower bounds of the nutcracker optimization algorithm are determined using the Chan algorithm, the population size is defined, and after initializing the population using the good point set method, the iterative optimization process of the improved nutcracker optimization algorithm is executed to calculate the tag coordinates and obtain the positioning result.

[0086] For a further optimized solution, the placement positions of the UWB base stations are as Figure 2 shown, and the position of the tag randomly appears inside the positioning system, and the coordinate information of the base stations is measured using metric instruments.

[0087] For a further optimized solution, after obtaining the distance data, the upper and lower bound parameters of the algorithm are initially calculated using the Chan algorithm, the population size is defined, then an initial population is generated, and finally the tag coordinates are calculated and obtained.

[0088] In this embodiment, the Levy flight strategy is introduced to enhance the global search ability, the population distribution is optimized by combining the good point set initialization, and the exploration and exploitation process is dynamically balanced by using an adaptive mechanism (foraging and storage phases), effectively suppressing the influence of random errors. As Figure 3 shown, the experimental results show that in the simulated scenario, the average two-dimensional positioning error is 7 cm, and the proposed algorithm shows high robustness and adaptability in the complex underground coal mine environment, providing a reliable positioning solution for coal mine safety monitoring and emergency rescue.

[0089] In this embodiment, by improving the starling optimization algorithm, the problem of interference of the UWB signal caused by the complex underground coal mine environment is effectively solved, and the positioning accuracy is significantly improved.

[0090] The improved starling optimization algorithm proposed in this embodiment achieves a better balance between global search and local optimization, and can accurately model and compensate the non-line-of-sight error.

[0091] This embodiment performs excellently in the complex underground coal mine environment, can effectively cope with problems such as signal attenuation, reflection, scattering and absorption, and ensures the stability and reliability of the positioning system.

[0092] In summary, in this embodiment, by improving the starling optimization algorithm, the problems existing in the existing UWB underground coal mine positioning technology are effectively solved, and it has high practical value and broad application prospects.

[0093] The above is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An ultra-wideband underground coal mine positioning method based on an improved nutcracker optimization algorithm, characterized in that Including: Deploy UWB base stations within the positioning area in the coal mine underground. Receive the signals transmitted by the tags through UWB receivers, and correspondingly obtain the straight-line distances between each base station and the tags. Use measuring instruments to measure and obtain the coordinate information of the UWB base stations to get the base station coordinates. Construct an equation set based on the base station coordinates and the straight-line distances between each base station and the tags, and construct a fitness function based on the positioning model. Use the Chan algorithm to determine the search upper and lower bounds of the starling optimization algorithm, define the population size, and after initializing the population using the good point set method, execute the iterative optimization process of the improved starling optimization algorithm to obtain the positioning result.

2. The method according to claim 1, wherein The number of deployed UWB base stations is 6.

3. The method according to claim 1, wherein The positions of the tags are randomly distributed within the positioning area in the coal mine underground.

4. The method according to claim 1, wherein The process of constructing the fitness function based on the positioning model includes: Based on the basic positioning model, convert the difference in straight-line distances from the tag to each base station into a non-linear equation, and construct the fitness function by defining and minimizing the mean square error between the actual measurement value and the theoretical value.

5. The method according to claim 1, wherein The process of using the Chan algorithm to determine the search upper and lower bounds of the starling optimization algorithm, defining the population size, and initializing the population using the good point set method includes: First, use the Chan algorithm to solve and obtain the preliminary coordinate values. Determine the search space centered on the preliminary coordinate values, and within the search space, use the good point set method to create an initial population and uniformly generate initial population individuals.

6. The method according to claim 1, wherein The iterative optimization process of executing the improved starling optimization algorithm includes: a foraging stage and a storage stage; Among them, in the foraging stage, global exploration and local development are carried out based on the Levy flight strategy and random individual selection to update the population position. In the storage stage, in-depth development is carried out through cache search and random radian strategy, and the population position is adjusted by combining the optimal individual and the random individual to finally solve the accurate coordinates of the tag.

7. The method according to claim 6, wherein Global exploration based on the Levy flight strategy and random individual selection includes the first-stage exploration and the second-stage exploration; The description of the first-stage exploration is: The description of the second-stage exploration is: Among them, represents the position vector of the i-th nutcracker individual at the current iteration t + 1, represents the position vector of the i-th nutcracker individual at the current iteration t, represents the average position of the nutcracker individual in the j-th dimension, γ is a random number generated according to the Levy flight function, represents the coordinate vector of the A nutcracker individual randomly selected from the population in the j-th dimension at the current iteration t, represents the coordinate vector of the B nutcracker individual randomly selected from the population in the j-th dimension at the current iteration t, μ represents a scaling factor, usually a random number between [0, 1], U j represents the upper bound of the j-th dimension, L j represents the lower bound of the j-th dimension, T max represents the maximum number of iterations, represents the position vector of the i-th nutcracker individual in the j-th dimension at the current iteration t + 1, represents the position vector of the i-th nutcracker individual in the j-th dimension at the current iteration t, represents the current optimal individual position in the j-th dimension, represents the cached position of the i-th nutcracker individual at the current iteration t, represents the coordinate vector of the C nutcracker individual randomly selected from the population in the j-th dimension at the current iteration t, is the optimal individual of the current population, A, B, C are three different nutcracker individuals randomly selected from the population, x m is the average position of all nutcrackers, r1, r2, τ i , (i = 1, 2, 3, 4, 5, 6, 7, 8) are all random numbers between [0, 1], τ4 is a random number subject to a normal distribution, τ5 is a random number generated by Lewy flight, t is the current number of iterations, and δ is a constant; is the optimal individual of the current population, C is a nutcracker individual randomly selected from the population, r1, r2, τ i , (i = 1, 2, 3, 4, 5, 6, 7, 8) are all random numbers between [0, 1].

8. The method according to claim 6, wherein Local development based on the Levy flight strategy and random individual selection is described by a formula expression as: Wherein, represents the new position vector of the i-th nutcracker individual at the current iteration t + 1, represents the position vector of the i-th nutcracker individual at the current iteration t, represents the optimal individual of the current population, represents the position vector of the i-th nutcracker individual at the current iteration t, and λ represents a random number generated by the Levy flight function, represents the coordinate vector of the randomly selected A nutcracker individual in the population at the current iteration t, represents the coordinate vector of the randomly selected B nutcracker individual in the population at the current iteration t, and l represents a factor that linearly decreases from 1 to 0.

9. The method according to claim 6, wherein The cache search and random radian retrieval strategy is described by a formula expression as: Wherein, represents the caching position of the i-th nutcracker individual at the current iteration t, represents the position vector of the i-th nutcracker individual at the current iteration t, α represents a scaling factor, a random number between [0, 1], represents the coordinate vector of the randomly selected A nutcracker individual in the population at the current iteration t, represents the coordinate vector of the randomly selected B nutcracker individual in the population at the current iteration t, represents the compensation coefficient, RP represents the reference point parameter, represents the upper bound of the search space, represents the lower bound of the search space, T max represents the maximum number of iterations, represents a uniformly distributed random number, represents a random vector between [0, 1], P rp represents the probability threshold, θ is a random radian between [0, π], A and B are two different randomly selected nutcracker individuals from the population, r1, r2, τ3 are random numbers between [0, 1], is a random vector between [0, 1].

10. The method according to claim 6, wherein In-depth development by the cache search and random radian retrieval strategy is described by a formula expression as: In the formula, represents the position vector of the i-th nutcracker individual at the current iteration t + 1, represents the position vector of the i-th nutcracker individual at the current iteration t, represents the cached position of the i-th nutcracker individual at the current iteration t.

Images