Positioning algorithm numerical simulation method based on genetic algorithm and application

Abstract

The invention relates to the technical field of safety helmet positioning and ranging, and provides a genetic algorithm-based positioning algorithm numerical simulation method and application thereof, and the method comprises the steps: constructing a genetic algorithm-based nonlinear optimization positioning model; performing precision simulation analysis on the nonlinear optimization positioning model based on the genetic algorithm; and performing simulation comparison analysis on the nonlinear optimization positioning model based on the genetic algorithm and a Taylor positioning algorithm. According to the method, simulation analysis of positioning accuracy and stability of the nonlinear optimization positioning model based on the genetic algorithm can be realized, and data reference and support are provided for application of the nonlinear optimization positioning model based on the genetic algorithm in positioning and ranging of the intelligent safety helmet.

Description

Technical Field

[0001] The invention relates to the technical field of helmet positioning and ranging, and in particular to a positioning algorithm numerical simulation method based on a genetic algorithm and an application thereof. Background Art

[0002] As the most basic protective equipment for protecting the human head, the main function of the hard hat is to cushion shock and disperse stress, thereby protecting the head from injuries caused by falling objects and other specific factors. It is widely used in various workplaces, especially in high-risk industries such as construction, mining, petroleum, chemical industry, and electricity, and is one of the important equipment to ensure the safety of workers. When facing some complex and sudden situations, the function of traditional hard hats may appear to be relatively simple.

[0003] At present, most of the domestic research on the application of smart helmets is concentrated in the fields of underground coal mines, the construction of smart construction sites, emergency firefighting and power workplaces, and there are very few smart helmets developed for hazardous chemical workplaces. In terms of functional requirements, various smart helmet terminal design schemes have different functions due to their different application scenarios, but basically have emergency alarm, data transmission and personnel positioning functions. However, there is little detailed research on the accuracy and stability of smart helmet positioning technology, and it is unknown whether its positioning performance can meet the positioning accuracy requirements of related fields. There is a lack of discussion on positioning technology in complex environments or special environments. Although most of the currently developed smart helmets can meet multiple intelligent expansion functions in one, they have not taken into account the actual problems of hardware and software system costs and the weight of the helmet body, and the positioning performance needs to be evaluated and analyzed.

[0004] The existing positioning algorithms lack an in-depth and effective simulation implementation process in simulation analysis, which makes the simulation analysis data not comprehensive and scientific, affecting the actual application effect of the positioning algorithm.

[0005] Therefore, it is necessary to provide a numerical simulation method and application of a positioning algorithm based on a genetic algorithm. Summary of the invention

[0006] The present invention provides a numerical simulation method and application of a positioning algorithm based on a genetic algorithm. By constructing a nonlinear optimization positioning model based on a genetic algorithm; performing precision simulation analysis on the nonlinear optimization positioning model based on a genetic algorithm; and performing simulation comparative analysis on the nonlinear optimization positioning model based on a genetic algorithm and a Taylor positioning algorithm, simulation analysis of the positioning accuracy and stability of the nonlinear optimization positioning model based on a genetic algorithm can be achieved, and data reference and support can be provided for the application of the nonlinear optimization positioning model based on a genetic algorithm in the positioning and ranging of an intelligent helmet.

[0007] The present invention provides a positioning algorithm numerical simulation method based on a genetic algorithm, comprising:

[0008] Construct a nonlinear optimization positioning model based on genetic algorithm;

[0009] Conduct precision simulation analysis on the nonlinear optimization positioning model based on genetic algorithm;

[0010] A simulation comparison and analysis was conducted between the nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm.

[0011] Furthermore, a nonlinear optimization positioning model based on genetic algorithm is constructed, including:

[0012] A certain number of individuals are randomly generated as the initial population of the genetic algorithm, and several individuals with better performance are selected from the initial population as the initial solution;

[0013] Select the ranking function in the MATLAB software as the fitness function, distribute the fitness through the sorting mechanism, and sort the individuals in the initial population from the perspective of minimizing the objective function value;

[0014] Select the parameters for genetic algorithm evolution;

[0015] According to the positioning problem, a cost function is constructed based on the mean square error equation to quantify the difference between the position estimated by the genetic algorithm and the actual position;

[0016] The initial position point provided by the genetic algorithm is used as the starting point, and the LM algorithm is used for iterative optimization;

[0017] According to the preset termination conditions, it is determined whether the iterative optimization has converged. If so, the optimal individual is output. If not, the parameters of the genetic algorithm evolution are reselected and the algorithm's cycle operation continues.

[0018] Furthermore, the parameters for the genetic algorithm evolution are selected, including:

[0019] The selection operation is as follows: according to the fitness function value, through equal distance screening, excellent individuals are selected from the current population to be inherited to the next generation of population;

[0020] Crossover operation, specifically: for the selected excellent individuals, combine some of their genes through the crossover probability to generate new individuals to increase the diversity of the population, where the crossover probability value is 0.9;

[0021] The mutation operation is as follows: the mutation operator mutbga in the genetic algorithm breeder is selected to perform mutation operation on the new individuals generated after the crossover operation to introduce new genetic information.

[0022] Furthermore, the accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out, including:

[0023] Under different noise level variances, the accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out;

[0024] The accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out under different numbers of base stations.

[0025] Furthermore, under different noise level variances, the accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out, including:

[0026] Under the condition that the ranging error follows a Gaussian distribution with a mean of zero, the ranging error is increased from 0.01m to 0.1m in steps of 0.01m;

[0027] Randomly generate 50 test points in the space consisting of the x-axis range of [25, 75], the y-axis range of [25, 75], and the z-axis range of [0, 10];

[0028] The number of individuals in the initial population of the genetic algorithm is set to 50, the crossover probability is set to 0.9, the mutbga mutation operator is selected, the damping coefficient in the LM algorithm is set to 10, and the initial damping factor is 0.001;

[0029] Based on the set base station layout, the optimization algorithm positioning results under different noise level variances are simulated and obtained.

[0030] Furthermore, under different numbers of base stations, the accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out, including:

[0031] Under the condition that the ranging error follows a Gaussian distribution with a mean of zero, the ranging error is increased from 0.01m to 0.1m in steps of 0.01m;

[0032] Randomly generate 50 test points in the space consisting of the x-axis range of [25, 75], the y-axis range of [25, 75], and the z-axis range of [0, 10];

[0033] The number of individuals in the initial population of the genetic algorithm is set to 50, the crossover probability is set to 0.9, the mutbga mutation operator is selected, the damping coefficient in the LM algorithm is set to 10, and the initial damping factor is 0.001;

[0034] Based on the set base station layout, the positioning accuracy of the optimization algorithm under different numbers of base stations is simulated, and the mean square error value is used as the evaluation index of positioning accuracy to obtain the simulation results of the positioning accuracy of the optimization algorithm under different numbers of base stations; among which the number of base stations is 6, or 7, or 8, or 9, or 10.

[0035] Furthermore, a simulation comparison analysis is conducted between the nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm, including:

[0036] A nonlinear optimization positioning model based on a genetic algorithm is simulated and compared with a Taylor positioning algorithm in terms of positioning accuracy to obtain a first comparison result;

[0037] The nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm are simulated and compared in terms of operation time to obtain a second comparison result.

[0038] Furthermore, the nonlinear optimization positioning model based on the genetic algorithm is simulated and compared with the Taylor positioning algorithm in terms of positioning accuracy to obtain a first comparison result, including:

[0039] The mean square error value is set as the ordinate, and the ranging error is set as the abscissa, and the first coordinate schematic diagrams of the mean square error values ​​of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm under the conditions of several base station numbers varying with the noise level are drawn respectively; the base station number condition is: the number of base stations is 6, or 7, or 8, or 9, or 10; according to the first coordinate schematic diagram, the first comparison result of the mean square error values ​​of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm varying with the noise level is obtained by analysis;

[0040] The nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm are simulated and compared in terms of operation time to obtain the second comparison results, including:

[0041] The positioning operation time is set as the vertical axis, and the ranging error is set as the horizontal axis, and the second coordinate schematic diagrams of the positioning operation time of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm under the conditions of several base station numbers varying with the noise level are drawn respectively; the base station number conditions are: the number of base stations is 6, or 7, or 8, or 9, or 10; according to the second coordinate schematic diagram, the second comparison result of the positioning operation time of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm varying with the noise level is analyzed and obtained.

[0042] Furthermore, the method further includes evaluating the positioning stability and positioning performance of the nonlinear optimization positioning model based on the genetic algorithm based on the first comparison result and the second comparison result, and arranging the number of base stations in the positioning application scenario according to the evaluation result; specifically,

[0043] Based on the first comparison result and the second comparison result, the positioning stability and positioning performance of the nonlinear optimization positioning model based on the genetic algorithm are evaluated and calculated to obtain evaluation results under conditions of different numbers of base stations;

[0044] According to the evaluation results, the comprehensive performance evaluation value of the nonlinear optimization positioning model based on the genetic algorithm under the conditions of different base station numbers is obtained; the comprehensive performance evaluation value is: the weighted accumulation of the positioning stability evaluation value and the positioning performance evaluation value;

[0045] According to the comprehensive performance evaluation value, filter and obtain the optimal comprehensive performance evaluation value, and obtain the number of matching base stations corresponding to the optimal comprehensive performance evaluation value;

[0046] A positioning application scenario is obtained, and the number of base stations is arranged in the positioning application scenario based on the number of matching base stations, so as to be used for positioning implementation of a nonlinear optimization positioning model based on a genetic algorithm.

[0047] A numerical simulation method of positioning algorithm based on genetic algorithm is applied in the positioning and ranging of safety helmets.

[0048] Compared with the prior art, the present invention has the following advantages and beneficial effects: by constructing a nonlinear optimization positioning model based on a genetic algorithm; performing precision simulation analysis on the nonlinear optimization positioning model based on a genetic algorithm; performing simulation comparative analysis on the nonlinear optimization positioning model based on a genetic algorithm and a Taylor positioning algorithm, the simulation analysis of the positioning accuracy and stability of the nonlinear optimization positioning model based on a genetic algorithm can be realized, and data reference and support can be provided for the application of the nonlinear optimization positioning model based on a genetic algorithm in the positioning and ranging of an intelligent helmet.

[0049] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0050] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0052] Figure 1 A schematic diagram of the method steps for numerical simulation of a positioning algorithm based on a genetic algorithm;

[0053] Figure 2 A schematic diagram of the method steps for performing precision simulation analysis on a nonlinear optimization positioning model based on a genetic algorithm;

[0054] Figure 3 Schematic diagram of the method steps for simulation comparison and analysis of the nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm. DETAILED DESCRIPTION

[0055] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0056] The present invention provides a numerical simulation method of positioning algorithm based on genetic algorithm, such as Figure 1 As shown, including:

[0057] Construct a nonlinear optimization positioning model based on genetic algorithm;

[0058] Conduct precision simulation analysis on the nonlinear optimization positioning model based on genetic algorithm;

[0059] A simulation comparison and analysis was conducted between the nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm.

[0060] The working principle of the above technical solution is: in order to realize the numerical simulation method of the positioning algorithm based on the genetic algorithm, the present invention first constructs a nonlinear optimization positioning model based on the genetic algorithm; then performs precision simulation analysis on the nonlinear optimization positioning model based on the genetic algorithm; finally, the nonlinear optimization positioning model based on the genetic algorithm is simulated and compared with the Taylor positioning algorithm.

[0061] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, it is possible to realize the simulation analysis of the positioning accuracy and stability of the nonlinear optimization positioning model based on the genetic algorithm, and provide data reference and support for the application of the nonlinear optimization positioning model based on the genetic algorithm in the positioning and ranging of the smart helmet.

[0062] In one embodiment, a nonlinear optimization positioning model based on a genetic algorithm is constructed, including:

[0063] A certain number of individuals are randomly generated as the initial population of the genetic algorithm, and several individuals with better performance are selected from the initial population as the initial solution;

[0064] Select the ranking function in the MATLAB software as the fitness function, distribute the fitness through the sorting mechanism, and sort the individuals in the initial population from the perspective of minimizing the objective function value;

[0065] Select the parameters for genetic algorithm evolution;

[0066] According to the positioning problem, a cost function is constructed based on the mean square error equation to quantify the difference between the position estimated by the genetic algorithm and the actual position;

[0067] The initial position point provided by the genetic algorithm is used as the starting point, and the LM algorithm is used for iterative optimization;

[0068] According to the preset termination conditions, it is determined whether the iterative optimization has converged. If so, the optimal individual is output. If not, the parameters of the genetic algorithm evolution are reselected and the algorithm's cycle operation continues.

[0069] The working principle of the above technical solution is as follows: in order to construct a nonlinear optimization positioning model based on a genetic algorithm, the present invention first randomly generates a certain number of individuals as the initial population of the genetic algorithm, and selects a number of individuals with better performance from the initial population as the initial solution; then, the ranking function in the mat lab software is selected as the fitness function, and the fitness is allocated through the sorting mechanism, and the individuals in the initial population are sorted from the perspective of minimizing the value of the objective function; then, the parameters of the genetic algorithm evolution are selected; then, according to the positioning problem, a cost function is constructed based on the mean square error equation, and the difference between the position estimated by the genetic algorithm and the actual position is quantified; finally, the initial position point provided by the genetic algorithm is used as the starting point, and the LM algorithm is used for iterative optimization; according to the preset termination condition, it is judged whether the iterative optimization converges, if so, the optimal individual is output, if not, the parameters of the genetic algorithm evolution are reselected, and the algorithm cycle operation is continued.

[0070] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, a nonlinear optimization positioning model based on a genetic algorithm is constructed to provide a basis for subsequent simulation analysis.

[0071] In one embodiment, the parameters for genetic algorithm evolution are selected, including:

[0072] The selection operation is as follows: according to the fitness function value, through equal distance screening, excellent individuals are selected from the current population to be inherited to the next generation of population;

[0073] Crossover operation, specifically: for the selected excellent individuals, combine some of their genes through the crossover probability to generate new individuals to increase the diversity of the population, where the crossover probability value is 0.9;

[0074] The mutation operation is as follows: the mutation operator mutbga in the genetic algorithm breeder is selected to perform mutation operation on the new individuals generated after the crossover operation to introduce new genetic information.

[0075] The working principle of the above technical solution is: in order to select the parameters for the evolution of the genetic algorithm, the present invention first performs a selection operation, specifically: according to the fitness function value, through equidistant screening, select excellent individuals from the current population to be inherited to the next generation group; then perform a crossover operation, specifically: for the selected excellent individuals, combine some genes of the individuals through the crossover probability to generate new individuals to increase the diversity of the population, wherein the crossover probability value is 0.9; then perform a mutation operation, specifically: select the mutation operator mutbga in the genetic algorithm breeder, and perform a mutation operation on the new individuals generated after the crossover operation to introduce new genetic information.

[0076] The beneficial effect of the above technical solution is: by adopting the solution provided by this embodiment, by executing three operations, the scientific nature of the selection of the parameters for the evolution of the genetic algorithm can be guaranteed.

[0077] In one embodiment, Figure 2 As shown, the accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out, including:

[0078] Under different noise level variances, the accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out;

[0079] The accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out under different numbers of base stations.

[0080] The working principle of the above technical solution is: in order to realize the precision simulation analysis of the nonlinear optimization positioning model based on the genetic algorithm, the present invention first performs precision simulation analysis on the nonlinear optimization positioning model based on the genetic algorithm under different noise level variances; and then performs precision simulation analysis on the nonlinear optimization positioning model based on the genetic algorithm under different numbers of base stations.

[0081] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, the accuracy simulation analysis of the nonlinear optimization positioning model based on the genetic algorithm is performed based on different noise level variances and different numbers of base stations, which can provide comprehensive simulation analysis.

[0082] In one embodiment, under different noise level variances, the accuracy simulation analysis of the nonlinear optimization positioning model based on the genetic algorithm is performed, including:

[0083] Under the condition that the ranging error follows a Gaussian distribution with a mean of zero, the ranging error is increased from 0.01m to 0.1m in steps of 0.01m;

[0084] Randomly generate 50 test points in the space consisting of the x-axis range of [25, 75], the y-axis range of [25, 75], and the z-axis range of [0, 10];

[0085] The number of individuals in the initial population of the genetic algorithm is set to 50, the crossover probability is set to 0.9, the mutbga mutation operator is selected, the damping coefficient in the LM algorithm is set to 10, and the initial damping factor is 0.001;

[0086] Based on the set base station layout, the optimization algorithm positioning results under different noise level variances are simulated and obtained.

[0087] The working principle of the above technical solution is as follows: in order to realize the precision simulation analysis of the nonlinear optimization positioning model based on the genetic algorithm under different noise level variances, the present invention first increases the ranging error from 0.01m to 0.1m in a step of 0.01m under the condition that the ranging error is set to obey the Gaussian distribution with a mean of zero; then, 50 points to be measured are randomly generated in a space composed of an x-axis range of [25, 75], a y-axis range of [25, 75], and a z-axis range of [0, 10]; then, the number of individuals in the initial population in the genetic algorithm is set to 50, the crossover probability is set to 0.9, the mutbga mutation operator is selected, the damping coefficient in the LM algorithm is set to 10, and the initial damping factor is 0.001; finally, based on the set base station layout, the optimization algorithm positioning results under different noise level variances are obtained by simulation.

[0088] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, the accuracy of the precision simulation analysis of the nonlinear optimization positioning model based on the genetic algorithm can be guaranteed by performing precision simulation analysis on the nonlinear optimization positioning model based on the genetic algorithm under different noise level variances.

[0089] In one embodiment, under different numbers of base stations, the accuracy simulation analysis of the nonlinear optimization positioning model based on the genetic algorithm is performed, including:

[0090] Under the condition that the ranging error follows a Gaussian distribution with a mean of zero, the ranging error is increased from 0.01m to 0.1m in steps of 0.01m;

[0091] Randomly generate 50 test points in the space consisting of the x-axis range of [25, 75], the y-axis range of [25, 75], and the z-axis range of [0, 10];

[0092] The number of individuals in the initial population of the genetic algorithm is set to 50, the crossover probability is set to 0.9, the mutbga mutation operator is selected, the damping coefficient in the LM algorithm is set to 10, and the initial damping factor is 0.001;

[0093] Based on the set base station layout, the positioning accuracy of the optimization algorithm under different numbers of base stations is simulated, and the mean square error value is used as the evaluation index of positioning accuracy to obtain the simulation results of the positioning accuracy of the optimization algorithm under different numbers of base stations; among which the number of base stations is 6, or 7, or 8, or 9, or 10.

[0094] The working principle of the above technical solution is as follows: in order to realize the precision simulation analysis of the nonlinear optimization positioning model based on the genetic algorithm under different numbers of base stations, the present invention first increases the ranging error from 0.01m to 0.1m in a step of 0.01m under the condition that the ranging error is set to obey the Gaussian distribution with a mean of zero; then, 50 points to be measured are randomly generated in a space composed of an x-axis range of [25, 75], a y-axis range of [25, 75], and a z-axis range of [0, 10]; then, the number of individuals in the initial population in the genetic algorithm is set to 50, the crossover probability is set to 0.9, the mutbga mutation operator is selected, the damping coefficient in the LM algorithm is set to 10, and the initial damping factor is 0.001; finally, based on the set base station layout, the positioning accuracy of the optimization algorithm under different numbers of base stations is simulated, and the mean square error value is used as the evaluation index of the positioning accuracy to obtain the simulation results of the positioning accuracy of the optimization algorithm under different numbers of base stations; wherein the number of base stations is 6, or 7, or 8, or 9, or 10.

[0095] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, by performing precision simulation analysis on the nonlinear optimization positioning model based on the genetic algorithm under different numbers of base stations, the accuracy of the analysis of the nonlinear optimization positioning model based on the genetic algorithm can be guaranteed.

[0096] In one embodiment, a nonlinear optimization positioning model based on a genetic algorithm is simulated and compared with the Taylor positioning algorithm. Figure 3 As shown, including:

[0097] A nonlinear optimization positioning model based on a genetic algorithm is simulated and compared with a Taylor positioning algorithm in terms of positioning accuracy to obtain a first comparison result;

[0098] The nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm are simulated and compared in terms of operation time to obtain a second comparison result.

[0099] The working principle of the above technical solution is: in order to realize the simulation comparison analysis between the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm, the present invention first performs a simulation comparison of the positioning accuracy of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm to obtain a first comparison result; then performs a simulation comparison of the operation time of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm to obtain a second comparison result.

[0100] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, the accuracy of the simulation comparison can be guaranteed by performing simulation comparison between the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm.

[0101] In one embodiment, a nonlinear optimization positioning model based on a genetic algorithm is simulated and compared with a Taylor positioning algorithm in terms of positioning accuracy to obtain a first comparison result, including:

[0102] The mean square error value is set as the ordinate, and the ranging error is set as the abscissa, and the first coordinate schematic diagrams of the mean square error values ​​of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm under the conditions of several base station numbers varying with the noise level are drawn respectively; the base station number condition is: the number of base stations is 6, or 7, or 8, or 9, or 10; according to the first coordinate schematic diagram, the first comparison result of the mean square error values ​​of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm varying with the noise level is obtained by analysis;

[0103] The nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm are simulated and compared in terms of operation time to obtain the second comparison results, including:

[0104] The positioning operation time is set as the vertical axis, and the ranging error is set as the horizontal axis, and the second coordinate schematic diagrams of the positioning operation time of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm under the conditions of several base station numbers varying with the noise level are drawn respectively; the base station number conditions are: the number of base stations is 6, or 7, or 8, or 9, or 10; according to the second coordinate schematic diagram, the second comparison result of the positioning operation time of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm varying with the noise level is analyzed and obtained.

[0105] The working principle of the above technical solution is: in order to realize the simulation comparison of the positioning accuracy of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm, the present invention sets the mean square error value as the ordinate, sets the ranging error as the abscissa, and draws the first coordinate schematic diagrams of the mean square error values ​​of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm under the conditions of several base station numbers changing with the noise level; the base station number condition is: the number of base stations is 6, or 7, or 8, or 9, or 10; according to the first coordinate schematic diagram, the first comparison result of the mean square error values ​​of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm changing with the noise level is analyzed and obtained;

[0106] In order to realize the simulation comparison of the operation time of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm, so as to evaluate the operation efficiency of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm, the present invention sets the positioning operation time as the vertical coordinate, sets the ranging error as the horizontal coordinate, and draws the second coordinate schematic diagrams of the positioning operation time of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm under the conditions of several base station numbers under which the noise level changes; the base station number condition is: the number of base stations is 6, or 7, or 8, or 9, or 10; according to the second coordinate schematic diagram, the second comparison result of the positioning operation time of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm changing with the noise level is analyzed and obtained.

[0107] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, the accuracy of the simulation comparison analysis can be guaranteed by comparing the positioning accuracy and positioning operation time of the nonlinear optimization positioning model based on the genetic algorithm with the Taylor positioning algorithm.

[0108] In one embodiment, the method further includes evaluating the positioning stability and positioning performance of the nonlinear optimization positioning model based on the genetic algorithm based on the first comparison result and the second comparison result, and arranging the number of base stations in the positioning application scenario according to the evaluation result; specifically,

[0109] Based on the first comparison result and the second comparison result, the positioning stability and positioning performance of the nonlinear optimization positioning model based on the genetic algorithm are evaluated and calculated to obtain evaluation results under conditions of different numbers of base stations;

[0110] According to the evaluation results, the comprehensive performance evaluation value of the nonlinear optimization positioning model based on the genetic algorithm under the conditions of different base station numbers is obtained; the comprehensive performance evaluation value is: the weighted accumulation of the positioning stability evaluation value and the positioning performance evaluation value;

[0111] According to the comprehensive performance evaluation value, filter and obtain the optimal comprehensive performance evaluation value, and obtain the number of matching base stations corresponding to the optimal comprehensive performance evaluation value;

[0112] A positioning application scenario is obtained, and the number of base stations is arranged in the positioning application scenario based on the number of matching base stations, so as to be used for positioning implementation of a nonlinear optimization positioning model based on a genetic algorithm.

[0113] The working principle of the above technical solution is: in order to better apply the nonlinear optimization positioning model based on the genetic algorithm to the actual scene, the present invention also includes evaluating the positioning stability and positioning performance of the nonlinear optimization positioning model based on the genetic algorithm based on the first comparison result and the second comparison result, and arranging the number of base stations in the positioning application scene according to the evaluation result; specifically: firstly, based on the first comparison result and the second comparison result, the positioning stability and positioning performance of the nonlinear optimization positioning model based on the genetic algorithm are evaluated and calculated to obtain the evaluation results under the conditions of different numbers of base stations; then, according to the evaluation results, the comprehensive performance evaluation value of the nonlinear optimization positioning model based on the genetic algorithm under the conditions of different numbers of base stations is obtained; the comprehensive performance evaluation value is: the weighted accumulation of the positioning stability evaluation value and the positioning performance evaluation value; finally, according to the comprehensive performance evaluation value, the optimal comprehensive performance evaluation value is screened and obtained, and the number of matching base stations corresponding to the optimal comprehensive performance evaluation value is obtained; the positioning application scene is obtained, and the number of base stations is arranged in the positioning application scene based on the number of matching base stations, so as to be used for the positioning implementation of the nonlinear optimization positioning model based on the genetic algorithm.

[0114] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, the positioning stability and positioning performance of the nonlinear optimization positioning model based on the genetic algorithm are evaluated based on the first comparison result and the second comparison result, and the number of base stations in the positioning application scenario is arranged according to the evaluation results, which can improve the scientific nature of the arrangement and is conducive to improving the positioning efficiency of the nonlinear optimization positioning model based on the genetic algorithm.

[0115] The application of a numerical simulation method of a positioning algorithm based on a genetic algorithm in the positioning and ranging of a helmet can improve the application efficiency of the positioning and ranging of a helmet.

[0116] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A numerical simulation method for positioning algorithm based on genetic algorithm, characterized in that: include: Construct a nonlinear optimization positioning model based on genetic algorithm; Conduct precision simulation analysis on the nonlinear optimization positioning model based on genetic algorithm; A simulation comparison and analysis was conducted between the nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm.

2. The method for numerical simulation of positioning algorithm based on genetic algorithm according to claim 1, characterized in that: Construct a nonlinear optimization positioning model based on genetic algorithm, including: A certain number of individuals are randomly generated as the initial population of the genetic algorithm, and several individuals with better performance are selected from the initial population as the initial solution; Select the ranking function in the MATLAB software as the fitness function, distribute the fitness through the sorting mechanism, and sort the individuals in the initial population from the perspective of minimizing the objective function value; Select the parameters for genetic algorithm evolution; According to the positioning problem, a cost function is constructed based on the mean square error equation to quantify the difference between the position estimated by the genetic algorithm and the actual position; The initial position point provided by the genetic algorithm is used as the starting point, and the LM algorithm is used for iterative optimization; According to the preset termination conditions, it is determined whether the iterative optimization has converged. If so, the optimal individual is output. If not, the parameters of the genetic algorithm evolution are reselected and the algorithm's cycle operation continues.

3. The method for numerical simulation of positioning algorithm based on genetic algorithm according to claim 2, characterized in that: Select the parameters for genetic algorithm evolution, including: The selection operation is as follows: according to the fitness function value, through equal distance screening, excellent individuals are selected from the current population to be inherited to the next generation of population; Crossover operation, specifically: for the selected excellent individuals, combine some of their genes through the crossover probability to generate new individuals to increase the diversity of the population, where the crossover probability value is 0.9; The mutation operation is as follows: the mutation operator mutbga in the genetic algorithm breeder is selected to perform mutation operation on the new individuals generated after the crossover operation to introduce new genetic information.

4. The method for numerical simulation of positioning algorithm based on genetic algorithm according to claim 1, characterized in that: The accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out, including: Under different noise level variances, the accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out; The accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out under different numbers of base stations.

5. The method for numerical simulation of positioning algorithm based on genetic algorithm according to claim 4, characterized in that: Under different noise level variances, the accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out, including: Under the condition that the ranging error follows a Gaussian distribution with a mean of zero, the ranging error is increased from 0.01m to 0.1m in steps of 0.01m; Randomly generate 50 test points in the space consisting of the x-axis range of [25, 75], the y-axis range of [25, 75], and the z-axis range of [0, 10]; The number of individuals in the initial population of the genetic algorithm is set to 50, the crossover probability is set to 0.9, the mutbga mutation operator is selected, the damping coefficient in the LM algorithm is set to 10, and the initial damping factor is 0.001; Based on the set base station layout, the optimization algorithm positioning results under different noise level variances are simulated and obtained.

6. The method for numerical simulation of positioning algorithm based on genetic algorithm according to claim 4, characterized in that: Under different numbers of base stations, the accuracy simulation analysis of the nonlinear optimization positioning model based on genetic algorithm is carried out, including: Under the condition that the ranging error follows a Gaussian distribution with a mean of zero, the ranging error is increased from 0.01m to 0.1m in steps of 0.01m; Randomly generate 50 test points in the space consisting of the x-axis range of [25, 75], the y-axis range of [25, 75], and the z-axis range of [0, 10]; The number of individuals in the initial population of the genetic algorithm is set to 50, the crossover probability is set to 0.9, the mutbga mutation operator is selected, the damping coefficient in the LM algorithm is set to 10, and the initial damping factor is 0.001; Based on the set base station layout, the positioning accuracy of the optimization algorithm under different numbers of base stations is simulated, and the mean square error value is used as the evaluation index of positioning accuracy to obtain the simulation results of the positioning accuracy of the optimization algorithm under different numbers of base stations; among which the number of base stations is 6, or 7, or 8, or 9, or 10.

7. The method for numerical simulation of positioning algorithm based on genetic algorithm according to claim 1, characterized in that: The nonlinear optimization positioning model based on genetic algorithm and Taylor positioning algorithm are simulated and compared, including: A nonlinear optimization positioning model based on a genetic algorithm is simulated and compared with a Taylor positioning algorithm in terms of positioning accuracy to obtain a first comparison result; The nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm are simulated and compared in terms of operation time to obtain a second comparison result.

8. The method for numerical simulation of positioning algorithm based on genetic algorithm according to claim 7, characterized in that: The nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm are simulated and compared in terms of positioning accuracy to obtain the first comparison results, including: The mean square error value is set as the ordinate, and the ranging error is set as the abscissa, and the first coordinate schematic diagrams of the mean square error values ​​of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm under the conditions of several base station numbers varying with the noise level are drawn respectively; the base station number condition is: the number of base stations is 6, or 7, or 8, or 9, or 10; according to the first coordinate schematic diagram, the first comparison result of the mean square error values ​​of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm varying with the noise level is obtained by analysis; The nonlinear optimization positioning model based on genetic algorithm and the Taylor positioning algorithm are simulated and compared in terms of operation time to obtain the second comparison results, including: The positioning operation time is set as the vertical axis, and the ranging error is set as the horizontal axis, and the second coordinate schematic diagrams of the positioning operation time of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm under the conditions of several base station numbers varying with the noise level are drawn respectively; the base station number conditions are: the number of base stations is 6, or 7, or 8, or 9, or 10; according to the second coordinate schematic diagram, the second comparison result of the positioning operation time of the nonlinear optimization positioning model based on the genetic algorithm and the Taylor positioning algorithm varying with the noise level is analyzed and obtained.

9. The method for numerical simulation of positioning algorithm based on genetic algorithm according to claim 7, characterized in that: The method further includes evaluating the positioning stability and positioning performance of the nonlinear optimization positioning model based on the genetic algorithm based on the first comparison result and the second comparison result, and arranging the number of base stations in the positioning application scenario according to the evaluation result; specifically: Based on the first comparison result and the second comparison result, the positioning stability and positioning performance of the nonlinear optimization positioning model based on the genetic algorithm are evaluated and calculated to obtain evaluation results under conditions of different numbers of base stations; According to the evaluation results, the comprehensive performance evaluation value of the nonlinear optimization positioning model based on the genetic algorithm under the conditions of different numbers of base stations is obtained; The comprehensive performance evaluation value is: the weighted accumulation of the positioning stability evaluation value and the positioning performance evaluation value; According to the comprehensive performance evaluation value, filter and obtain the optimal comprehensive performance evaluation value, and obtain the number of matching base stations corresponding to the optimal comprehensive performance evaluation value; A positioning application scenario is obtained, and the number of base stations is arranged in the positioning application scenario based on the number of matching base stations, so as to be used for positioning implementation of a nonlinear optimization positioning model based on a genetic algorithm.

10. Application of the positioning algorithm numerical simulation method based on genetic algorithm as claimed in any one of claims 1 to 9 in the positioning and ranging of safety helmets.

Images