Phase change ejection intelligent control method based on genetic algorithm

Abstract

The invention discloses a phase change ejection intelligent control method based on a genetic algorithm. The method comprises the following steps: acquiring an initial parameter of a phase change ejection system and a deorbit speed of an ejected object; calculating a deorbit speed range under the current quality specification, if the target deorbit speed is within the deorbit speed range, performing parameter optimization on the phase change number, otherwise, ending the parameter optimization; whether the ratio of the target deorbit speed to the minimum deorbit speed value is smaller than a set threshold value or not is judged, if yes, the initial phase change number serves as the optimal phase change number value to be stored, then parameter optimization is conducted on the time interval, and if not, the phase change number is optimized based on a genetic algorithm to obtain the optimal phase change number value; optimizing the time interval based on a genetic algorithm to obtain an optimal value of the time interval; and outputting the phase change number and the time interval optimal value. According to the invention, multi-target intelligent optimization control and hierarchical step-by-step optimization control are carried out based on the genetic algorithm according to the priority of the parameters, and the accuracy and efficiency of phase change ejection intelligent control are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of power launch, and in particular relates to a phase change ejection intelligent control method based on genetic algorithm. Background Art

[0002] The new energy phase change ejection technology represented by supercritical carbon dioxide has the advantages of clean working fluid, fast reaction, low product temperature, low launch characteristics, and strong adaptability. It is a hot topic in the research of ejection power sources for weapon systems. When controlling phase change ejection, the ejection speed is usually used as the target. However, the internal ballistic characteristics and ejection power characteristics of the phase change ejection system are affected by many factors. How to use the initial parameters of the phase change ejection and the state parameters of the ejection as input variables, establish a multi-target control model, and achieve accurate and efficient control of the phase change ejection is a problem that needs to be solved urgently. Summary of the invention

[0003] The purpose of the present invention is to provide a phase change ejection intelligent control method based on genetic algorithm which can improve the accuracy and efficiency of phase change ejection control.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] A phase change ejection intelligent control method based on genetic algorithm comprises the following steps:

[0006] Step S1, obtaining initial parameters of the phase change ejection system and the de-orbit speed of the ejection object, the initial parameters including initial mass specification, initial number of phase changes, initial time interval, and taking the de-orbit speed of the ejection object as the target de-orbit speed;

[0007] Step S2, quality specification determination; calculating the derailment speed range under the current quality specification, if the target derailment speed is within the derailment speed range, further optimizing the number of phase changes; if the target derailment speed is less than the minimum derailment speed or the target derailment speed is greater than the maximum derailment speed, then ending the parameter optimization;

[0008] Step S3, optimizing the number of phase changes; judging whether the ratio of the target off-track speed to the minimum off-track speed is less than a set threshold value, if so, saving the initial number of phase changes as the optimal number of phase changes, and then further optimizing the time interval parameters; otherwise, optimizing the number of phase changes based on a genetic algorithm to obtain the optimal number of phase changes;

[0009] Step S4, time interval optimization: optimizing the time interval based on a genetic algorithm to obtain an optimal time interval value;

[0010] Step S5, outputting the optimal value of the number of phase changes and the optimal value of the time interval, and performing phase change ejection control according to the optimal value of the number of phase changes and the optimal value of the time interval.

[0011] In some embodiments, in step S3, the steps of optimizing the number of phase changes using a genetic algorithm are as follows:

[0012] S01, randomly generate M individuals as the initial population P1(0) of phase transition;

[0013] S02, calculate the fitness of each individual in the phase change population P1(t), where t is the evolutionary generation, t=0, 1, 2, ..., and the population at t=0 is the initial population P1(0) of the phase change number;

[0014] S03, performing selection operation, crossover operation and mutation operation on the population P1(t) after fitness evaluation in sequence, obtaining the next generation population P1(t+1), and updating the evolutionary generation t to t+1;

[0015] S04. If the evolutionary generation t is less than the maximum evolutionary generation T, return to S02; otherwise, the individual corresponding to the maximum fitness value obtained during the evolution process is output as the optimal value of the phase transition number.

[0016] In some embodiments, in step S4, the steps of optimizing the time interval using a genetic algorithm are as follows:

[0017] S01, randomly generate M individuals as the time interval initial population P2(0), in which the latter time is greater than the former time;

[0018] S02, calculate the fitness of each individual in the time interval population P2(t);

[0019] S03, performing selection operation, crossover operation and mutation operation on the population P2(t) after fitness evaluation in sequence, obtaining the next generation population P2(t+1), and updating the evolutionary generation t to t+1;

[0020] S04. If the evolutionary generation t is less than the maximum evolutionary generation T, return to S02; otherwise, the individual corresponding to the maximum value of the fitness value obtained during the evolution process is output as the optimal time interval.

[0021] In some embodiments, the steps S3 and S4 use an improved genetic algorithm to optimize the number of phase changes and the time interval, and the steps are as follows:

[0022] S001, population initialization; according to the upper and lower limits of the parameters to be optimized, Np individuals are randomly generated as the initial population f(0); the parameters to be optimized are the number of phase changes or the time interval;

[0023] S002, first fitness evaluation; calculate the fitness value of each individual in the population f(g), the population when the evolutionary generation g=0,1,2,……, g=0 is the initial population f(0);

[0024] S003, selection operation; sorting the fitness values ​​calculated for each individual in the population f(g) in ascending order, taking the individual with the smallest fitness value as the optimal individual, and saving it;

[0025] S004, crossover operation: cross the best individual with the other even-numbered individuals sorted in ascending order, and each crossover generates two new individuals to form a new population f'(g);

[0026] S005, mutation operation: perform multi-point mutation on f'(g) to generate offspring population ff(g);

[0027] S006, secondary fitness evaluation; calculate the fitness value of each individual in the offspring population ff(g), and sort them in ascending order according to the fitness values ​​calculated for each individual in the population ff(g);

[0028] S007, cross-generation optimization, merge the reordered offspring population ff(g) and the initial population f(0), and sort the merged individuals in ascending order according to the fitness value, take the first Np individuals as the next generation population f(g+1), and update the evolutionary generation g to g+1;

[0029] S008. If g>G, the individual with the smallest fitness value in all generations is output as the optimal individual and the calculation is terminated, otherwise return to step S002.

[0030] Furthermore, the fitness value is the absolute value of the difference between the calculated value of the de-orbit velocity and the target parameter value.

[0031] It can be seen from the above technical solutions that the present invention uses a genetic algorithm to optimize the control parameters in the phase change ejection control process. Aiming at the problem of accurate control of phase change ejection parameters, the method of quality specification determination, intelligent optimization of the number of phase changes based on genetic algorithms, and intelligent optimization of interval time is proposed with the derailment speed of the ejected object of phase change ejection as the task, so as to realize the intelligent control of the control parameters such as the phase change quality, number of phase changes, and interval time of the phase change ejection, and the hierarchical and step-by-step control improves the accuracy and efficiency of the intelligent control of the phase change ejection. In some embodiments, an improved genetic algorithm is used for parameter optimization, and the standard genetic algorithm is improved by performing parameter design strategy, fitness encoding mechanism, selection strategy, crossover operator, secondary evaluation, and father-son cross-generation optimization, etc., which has the characteristics of dynamic parameter adjustment, efficient optimal solution determination, focused selection of crossover operation, and doubling of father-son cross-generation optimization, which can effectively avoid falling into a local mechanism, improve the efficiency, accuracy and stability of the algorithm, and realize multi-objective parameter intelligent optimization of different ejection speeds. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 This is the flow chart of the standard genetic algorithm;

[0034] Figure 2 is a flow chart of the method of the present invention;

[0035] Figure 3 A flowchart of the improved genetic algorithm of the present invention;

[0036] Figure 4 This is a curve diagram showing the change of fitness with evolutionary generations when the phase change ejection intelligent control method based on improved genetic algorithm is used for simulation;

[0037] Figure 5 The curve diagram of the fitness changing with the evolutionary generation number when the phase change ejection intelligent control method based on the improved genetic algorithm is used for simulation at different target de-orbit speeds;

[0038] Figure 6 This is the error distribution diagram of the calculated de-orbit velocity and the target de-orbit velocity when the phase change ejection intelligent control method based on the improved genetic algorithm is used for simulation;

[0039] Figure 7 This is the interval time distribution diagram obtained by multiple simulations using the phase change ejection intelligent control method based on the improved genetic algorithm;

[0040] Figure 8 This is a comparison chart of the ejection velocity curves of the ejected object when multiple simulations are performed using the phase change ejection intelligent control method based on the improved genetic algorithm.

[0041] The specific implementation modes of the present invention are further described in detail below with reference to the accompanying drawings. DETAILED DESCRIPTION

[0042] The present invention is described in detail below in conjunction with the accompanying drawings. When describing the embodiments of the present invention in detail, for the convenience of explanation, the drawings representing the device structure will not be partially enlarged according to the general proportion, and the schematic diagram is only an example, which should not limit the scope of protection of the present invention. It should be noted that the drawings are simplified in form and use non-precise proportions, which are only used to facilitate and clearly assist in explaining the purpose of the embodiments of the present invention. At the same time, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated; the terms "positive", "negative", "bottom", "upper", "lower", etc. indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention.

[0043] The control target of the phase change ejection control system is the ejection speed of the ejection object (also called the ejection speed). The ejection speed of the ejection object is related to the internal ballistic characteristics and ejection dynamic characteristics of the phase change ejection. The internal ballistic characteristics and ejection dynamic characteristics of the phase change ejection are affected by many factors, such as the initial parameters of the phase change ejection and the state parameters of the ejection object. These parameters are all variables in the phase change ejection control process. How to realize multi-parameter intelligent control is the key to phase change ejection control.

[0044] Genetic algorithms have the characteristics of powerful global optimal solution search ability, opposition of problem domain, parallelism of information processing, robustness of application and simplicity of operation, and can play a good role in multi-parameter intelligent control. Based on this, the present invention proposes a phase change ejection intelligent control method based on genetic algorithm, which uses genetic algorithm to optimize control parameters to achieve multi-objective parameter intelligent optimization of different ejection speeds, and improves the accuracy and efficiency of phase change ejection intelligent control through hierarchical and step-by-step control.

[0045] Figure 1 This is the flowchart of the standard genetic algorithm. Figure 1 The steps of the standard genetic algorithm are briefly described. For a detailed description of the genetic algorithm, please refer to the Intelligent Optimization Algorithm and Its MATLAB Example published by the Electronic Industry Press. Figure 1As shown, the standard genetic algorithm includes the following steps:

[0046] S01, population initialization; set the evolutionary generation counter t = 0, set the maximum evolutionary generation T, and randomly generate M individuals as the initial population P(0);

[0047] S02, fitness evaluation; calculate the fitness FIT of each individual in the population P(t), t is the evolutionary generation, t=0, 1, 2, ..., the population P(0) at t=0 is the first generation population, that is, the initial population P(0) is the first generation population, the population P(1) at t=1 is the second generation population, and so on; the present invention takes the absolute value of the difference between the de-orbit velocity calculation value and the target parameter value as the fitness value FIT;

[0048] S03, operation; the group P(t) after fitness evaluation is subjected to selection operation, crossover operation and mutation operation in sequence to obtain the next generation group P(t+1), and the evolutionary generation t is updated to t+1; the purpose of selection operation and crossover operation is to directly inherit the optimized individuals to the next generation or to generate new individuals through pairing and crossover and then inherit them to the next generation; the mutation operation is to change the gene values ​​at certain gene loci of the individual strings in the group;

[0049] Specifically, the selection operation is based on the problem requirements. If the requirement is the largest, the individual with the largest fitness in the group is selected; if the requirement is the smallest, the individual with the smallest fitness in the group is selected; the crossover operation is to randomly cross all individuals in the group according to probability. In this random crossover process, the sample set does not change, only the position changes; the mutation operation is to mutate according to the mutation probability; the specific implementation of the selection operation, crossover operation and mutation operation of the standard genetic algorithm can be found in the book "Intelligent Optimization Algorithm and Its MATLAB Example";

[0050] S04, determine the termination condition; determine whether the evolutionary generation t is less than the maximum evolutionary generation T. If so, return to step S02; otherwise, take the individual corresponding to the maximum value of the fitness value obtained during the evolution process as the optimal value output and terminate the calculation.

[0051] Aiming at the problem of accurate control of phase change ejection parameters, the present invention takes the de-orbit speed of the ejected object of phase change ejection as the task, and proposes a phase change ejection intelligent control method based on genetic algorithm, which optimizes and controls the control parameters such as phase change quality, number of phase changes, interval time, etc., adopts a hierarchical and step-by-step optimization strategy, first optimizes the quality specifications, then optimizes the number of phase changes, and finally optimizes the interval time, and uses genetic algorithms to optimize the number of phase changes and interval time to achieve intelligent control of phase change ejection. Figure 2 As shown, the phase change ejection intelligent control method of the present invention comprises the following steps:

[0052] Step S1, obtaining initial parameters of the phase change ejection system and the de-orbit speed of the ejection object, the initial parameters including initial mass specification, initial number of phase changes, initial time interval, taking the de-orbit speed of the ejection object as the target de-orbit speed, and the de-orbit speed of the ejection object is the control object;

[0053] Step S2, quality specification determination; calculate the derailment speed range under the current quality specification, that is, calculate the maximum and minimum values ​​of the derailment speed under the current quality specification; if the target derailment speed is within the range of the maximum and minimum values ​​of the derailment speed, further perform parameter optimization on the number of phase changes; if the target derailment speed is less than the minimum value of the derailment speed or the target derailment speed is greater than the maximum value of the derailment speed, then end the parameter optimization; in specific application, if the target derailment speed is greater than the maximum value of the derailment speed, a prompt "quality specification exceeds the maximum value, reduce the quality specification" may be given, and then the process ends; if the target derailment speed is less than the minimum value of the derailment speed, a prompt "quality specification is lower than the minimum value, increase the quality specification" may be given, and then the process ends, to avoid unnecessary calculations;

[0054] Specifically, the maximum and minimum de-orbit speeds under a certain mass specification are calculated according to the phase change number range and interval time range of the phase change ejection system. The maximum de-orbit speed is calculated according to the maximum number of phase changes and the minimum time interval of the phase change ejection system under the mass specification, and the minimum de-orbit speed is calculated according to the minimum number of phase changes of the phase change ejection system under the mass specification. For example, if the phase change ejection system has 7 launchers, the phase change number range is 1 to 7, the time interval range is 0 to 0.2s, the maximum de-orbit speed is the speed when 7 launchers act at the same time (time interval is 0), and the minimum de-orbit speed is the speed when 1 launcher acts; the time interval is the time interval between launches of different launchers;

[0055] The de-orbit velocity is calculated based on the internal ballistic mathematical model and is a calculated value. Specifically, the de-orbit velocity calculated value Where m is the mass of the ejected object, l is the length of the launcher's trajectory, and F(t) is the internal thrust of the launcher. The internal thrust of the launcher is related to the number of phase changes and the time interval of the phase change ejection system, and is a function that changes with time t.

[0056] Step S3, optimizing the number of phase changes; judging whether the ratio of the target off-track speed to the minimum off-track speed is less than a set threshold value; if so, there is no need to optimize the number of phase changes, and the initial number of phase changes is saved as the optimal number of phase changes, and then the time interval is further optimized to improve the operation efficiency; otherwise, the number of phase changes is optimized based on a genetic algorithm to obtain the optimal number of phase changes;

[0057] The threshold is set as an empirical value. The threshold is related to the quality specification and the number of transmitters. After the maximum and minimum values ​​of the off-track speed are calculated, corresponding adjustments can be made to improve the search efficiency. The threshold set in this embodiment is 1.15. In this step, the number of phase changes is dynamically adjusted according to the ratio of the target off-track speed to the minimum off-track speed, so that when the genetic algorithm is used for parameter optimization later, the upper and lower limits of the random number selection can be adjusted, and the initial population of the number of phase changes is randomly generated to further focus the range, avoid searching some unnecessary points, and improve the search of more points in the possible domain, thereby improving the search efficiency and quality of the optimal solution.

[0058] Step S4, time interval optimization: optimizing the time interval based on a genetic algorithm to obtain an optimal time interval value;

[0059] Step S5, outputting the optimal value of the number of phase changes and the optimal value of the time interval, and performing phase change ejection control according to the optimal value of the number of phase changes and the optimal value of the time interval.

[0060] Specifically, in step S3, when the ratio of the target off-track speed to the minimum off-track speed is greater than or equal to the set threshold, the specific steps of optimizing the number of phase changes using the genetic algorithm are as follows:

[0061] S01, set the evolutionary generation counter t=0 and the maximum evolutionary generation T, and randomly generate M individuals as the initial population P1(0) of phase change number;

[0062] S02, calculate the fitness of each individual in the phase transition population P1(t);

[0063] S03, performing selection operation, crossover operation and mutation operation on the population P1(t) after fitness evaluation in sequence, obtaining the next generation population P1(t+1), and updating the evolutionary generation t to t+1;

[0064] S04. If the evolutionary generation t is less than the maximum evolutionary generation T, return to step S02 and recalculate the fitness of each individual in the phase change population P1(t). Otherwise, the individual corresponding to the maximum fitness value obtained during the evolution process is output as the optimal value of the phase change number.

[0065] In step S3, the steps for optimizing the time interval based on the genetic algorithm are the same as the steps for optimizing the number of phase changes based on the genetic algorithm, that is, after generating the initial population P2(0) of the time interval, the fitness calculation is performed, and then the selection, crossover, and mutation operations are performed to obtain the next generation population P2(t+1). Each step can refer to the steps for optimizing the number of phase changes, which will not be repeated here. When the genetic algorithm is used to optimize the time interval, when the initial population of the time interval is randomly generated, according to the irreversibility of time, the latter time must be greater than the previous time.

[0066] Although genetic algorithms have many advantages such as powerful global optimal solution search capabilities, opposition of problem domains, parallelism of information processing, robustness of applications, and simplicity of operation, the inventors have found through extensive practice and research that standard genetic algorithms have defects such as poor search capabilities and "premature maturity" in specific applications, and cannot guarantee rapid convergence of the algorithm. There is still room for improvement in the accuracy and efficiency of phase change ejection intelligent control. To this end, the inventors have made improvements to the standard genetic algorithm to enhance the efficiency, accuracy, and stability of the genetic algorithm when applied to phase change ejection control.

[0067] like Figure 3 As shown, the improved genetic algorithm of this embodiment includes the following steps:

[0068] S001, population initialization; set the evolutionary generation counter g = 0, set the maximum evolutionary generation G, and randomly generate Np individuals as the initial population f(0) according to the upper and lower limits of the parameters to be optimized; the parameters to be optimized are the number of phase changes or the time interval; in specific applications, according to the upper and lower limits of the parameters to be optimized, a random number function can be used to randomly generate the number of individuals Np, such as running in MATLAB software:

[0069] For i=1:1:NP

[0070] f(i) = rand() * (upper limit - lower limit) + lower limit

[0071] end

[0072] Wherein, rand() represents a random number between 0 and 1, and each cycle can obtain an arbitrary number between the lower limit and the upper limit, and Np individuals are obtained after Np cycles; this is a conventional operation method for random numbers, which is not the innovation of the present invention, and therefore will not be described in detail here;

[0073] S002, first fitness evaluation; calculate the fitness of each individual in the population f(g), the evolutionary generation g = 0, 1, 2, ..., the population when g = 0 is the initial population f(0), the present invention calculates the de-orbit speed value V and the target parameter value V MB The absolute value of the difference is taken as the fitness value FIT, FIT = |VV MB |; The absolute value of the difference between the calculated value of the off-orbit velocity and the target parameter value is used as the fitness. The closer the fitness is to 0, the better. The target parameter value V MB It is related to the design speed of the projectile. It is an empirical value set by the user and is not limited here.

[0074] S003, selection operation; sorting the fitness values ​​calculated for each individual in the population f(g) in ascending order, taking the individual with the smallest fitness value as the optimal individual, and saving it; the standard genetic algorithm does not sort the individuals in the population according to the fitness value;

[0075] S004, crossover operation; cross the best individual with the individuals in other even-numbered positions after ascending sorting, and generate two new individuals each time to form a new population f'(g); different from the crossover operation step of the standard genetic algorithm, this step crosses the best individual with the other even-numbered positions after sorting, so that the even-numbered positions become the optimal solution, and removing the samples of the even-numbered positions can focus more on the range;

[0076] S005, mutation operation; multi-point mutation is performed on the new population f'(g) to generate a child population ff(g), the parent population of ff(g) is f(g); this step is the same as the mutation operation step of the standard genetic algorithm;

[0077] S006, secondary fitness evaluation; calculating the fitness of each individual in the offspring population ff(g), the fitness calculation is the same as the fitness calculation in step S002, and the fitness values ​​calculated for each individual in the population ff(g) are sorted in ascending order;

[0078] S007, cross-generation optimization, merge the offspring population ff(g) reordered in step S006 and the initial population f(0), and sort the merged individuals in ascending order according to the fitness value, take the first Np individuals as the next generation population f(g+1), and update the evolutionary generation g to g+1;

[0079] S008, if g>G (termination criterion), the individual with the smallest fitness value in all generations is output as the optimal individual, and the calculation is terminated, otherwise return to step S002. When outputting the optimal individual, the fitness values ​​of all generations of phase change numbers or time intervals are sorted in ascending order, and the individual ranked first is output.

[0080] This embodiment improves the standard genetic algorithm by performing parameter design strategy, fitness encoding mechanism, selection strategy, crossover operator, secondary evaluation, and parent-child cross-generation optimization. In the phase change number optimization step, a parameter dynamic adjustment strategy is adopted to dynamically adjust the upper and lower limits, narrow the search range, and improve the search accuracy. When optimizing the number and time interval of UI phase changes, the fitness is determined by the deviation value (the absolute value of the difference between the calculated value of the objective function and the target parameter value), and the smallest ranked solution is the optimal solution for this iteration, thereby improving the accuracy and efficiency of the determination. The optimal solution of the parent generation is selected and crossover operations are performed, and the selection operation is more efficient and accurate in ascending order. When crossing, the selected optimal solution is crossed with the even-numbered bits to further focus the range and improve the convergence of the algorithm. Adding secondary evaluation is an evaluation of the offspring, calculating the fitness value, and adding cross-generation optimization, so that the fitness values ​​of the parent and offspring can be sorted together to select the optimal solution, thereby avoiding falling into a local mechanism and improving the efficiency, accuracy, and stability of the algorithm.

[0081] The phase change ejection intelligent control method based on genetic algorithm of the present invention can realize multi-objective intelligent optimization control according to the priority of parameters according to different ejection speed requirements, and hierarchical and step-by-step optimization control, and give the optimal solution of the optimal phase change quality, number of phase changes, and interval time parameters, thereby improving the accuracy and efficiency of the phase change ejection intelligent control.

[0082] In order to verify the effect of the method of the present invention, a control method using a standard genetic algorithm and a control method using an improved genetic algorithm are simulated and compared. The simulation test is performed using MATLAB software. The basic parameters of the phase change ejection system are shown in Table 1.

[0083] Table 1 Basic parameters

[0084]

[0085] The number of phase changes and the interval time are optimized based on the target deorbit speed. The population size of the improved genetic algorithm is Np=200, the number of chromosomes in the population is D=3, the crossover rate Pc is 0.8, the mutation rate Pm is 0.1, and the maximum evolutionary generation G is 100.

[0086] 1. Convergence Verification

[0087] When the target de-orbit speed is 30m / s, the change law of fitness obtained by the intelligent control method based on the improved genetic algorithm with the evolutionary generation is as follows: Figure 4 As shown. Figure 4 It can be seen that after iterative optimization, the error between the calculated de-orbit velocity and the target de-orbit velocity approaches zero.

[0088] Figure 5This is the law of change of fitness with evolutionary generations obtained by the intelligent control method based on the improved genetic algorithm when the target de-orbit speed is 20-80m / s. Figure 5 It can be seen that the fitness evolution curves at different speeds converge rapidly. When the number of evolutions is greater than 78 times, the fitness approaches 0, which verifies the rapid convergence of the intelligent control method based on the improved genetic algorithm.

[0089] The intelligent control method using the standard genetic algorithm requires more than 160 evolution times to reduce the error to 0.1%, which is not as fast as the intelligent control method based on the improved genetic algorithm in terms of convergence.

[0090] 2. Accuracy Verification

[0091] The error distribution law between the de-orbit speed calculated by the intelligent control method based on the improved genetic algorithm and the target de-orbit speed at different target de-orbit speeds is statistically analyzed as follows: Figure 6 As shown. Figure 6 It can be seen that the maximum error of the intelligent control of different target de-orbit speeds does not exceed 0.1%, which verifies the accuracy of the intelligent control method.

[0092] 3. Stability Verification

[0093] Taking the target de-orbit speed of 30m / s as an example, the intelligent control method based on the improved genetic algorithm is used to simulate the intelligent optimization control of multiple phase change ejection. When the mass specification is 3kg and the ejection is controlled three times, the optimal number of phase changes obtained by multiple simulations is [1,1,1], and the optimal interval time distribution is as follows: Figure 7 shown.

[0094] According to the phase change projectile internal ballistic mathematical model, after multiple intelligent control calculations, the velocity curve of the projectile is obtained. Figure 8 As shown. Figure 8 It can be seen that after multiple simulation optimizations, the optimal number of phase changes recommended by the intelligent control method based on the improved genetic algorithm is highly stable, the phase change interval time deviation is small, and the velocity curve of the ejected object is smooth, reflecting that the overload of the ejected object is small, which improves the efficiency of phase change ejection. The error between the de-orbit speed and the target speed calculated by multiple simulations does not exceed 0.013%, which not only verifies the accuracy of the intelligent control method based on the improved genetic algorithm, but also verifies its stability.

[0095] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technician familiar with this profession can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A phase change ejection intelligent control method based on genetic algorithm, characterized in that: The following steps are involved: Step S1, obtaining initial parameters of the phase change ejection system and the de-orbit speed of the ejection object, the initial parameters including initial mass specification, initial number of phase changes, initial time interval, and taking the de-orbit speed of the ejection object as the target de-orbit speed; Step S2, quality specification determination; calculating the derailment speed range under the current quality specification, if the target derailment speed is within the derailment speed range, further optimizing the number of phase changes; if the target derailment speed is less than the minimum derailment speed or the target derailment speed is greater than the maximum derailment speed, then ending the parameter optimization; Step S3, optimizing the number of phase changes; judging whether the ratio of the target off-track speed to the minimum off-track speed is less than a set threshold value, if so, saving the initial number of phase changes as the optimal number of phase changes, and then further optimizing the time interval parameters; otherwise, optimizing the number of phase changes based on a genetic algorithm to obtain the optimal number of phase changes; Step S4, time interval optimization: optimizing the time interval based on a genetic algorithm to obtain an optimal time interval value; Step S5, outputting the optimal value of the number of phase changes and the optimal value of the time interval, and performing phase change ejection control according to the optimal value of the number of phase changes and the optimal value of the time interval.

2. The phase change ejection intelligent control method according to claim 1, characterized in that: In step S3, the steps of optimizing the number of phase changes using a genetic algorithm are as follows: S01, randomly generate M individuals as the initial population P1(0) of phase transition; S02, calculate the fitness of each individual in the phase change population P1(t), where t is the evolutionary generation, t=0, 1, 2, ..., and the population at t=0 is the initial population P1(0) of the phase change number; S03, performing selection operation, crossover operation and mutation operation on the population P1(t) after fitness evaluation in sequence, obtaining the next generation population P1(t+1), and updating the evolutionary generation t to t+1; S04. If the evolutionary generation t is less than the maximum evolutionary generation T, return to S02; otherwise, the individual corresponding to the maximum fitness value obtained during the evolution process is output as the optimal value of the phase transition number.

3. The phase change ejection intelligent control method according to claim 1, characterized in that: In step S4, the steps of optimizing the time interval using a genetic algorithm are as follows: S01, randomly generate M individuals as the time interval initial population P2(0), in which the latter time is greater than the former time; S02, calculate the fitness of each individual in the time interval population P2(t); S03, performing selection operation, crossover operation and mutation operation on the population P2(t) after fitness evaluation in sequence, obtaining the next generation population P2(t+1), and updating the evolutionary generation t to t+1; S04. If the evolutionary generation t is less than the maximum evolutionary generation T, return to S02; otherwise, the individual corresponding to the maximum value of the fitness value obtained during the evolution process is output as the optimal time interval.

4. The phase change ejection intelligent control method according to claim 1, characterized in that: The improved genetic algorithm is used to optimize the number and time interval of phase changes. The steps are as follows: S001, population initialization; according to the upper and lower limits of the parameters to be optimized, Np individuals are randomly generated as the initial population f(0); the parameters to be optimized are the number of phase changes or the time interval; S002, first fitness evaluation; calculate the fitness value of each individual in the population f(g), the population when the evolutionary generation g=0,1,2,……, g=0 is the initial population f(0); S003, selection operation; sorting the fitness values ​​calculated for each individual in the population f(g) in ascending order, taking the individual with the smallest fitness value as the optimal individual, and saving it; S004, crossover operation: cross the best individual with the other even-numbered individuals sorted in ascending order, and each crossover generates two new individuals to form a new population f'(g); S005, mutation operation: perform multi-point mutation on f'(g) to generate offspring population ff(g); S006, secondary fitness evaluation; calculate the fitness value of each individual in the offspring population ff(g), and sort them in ascending order according to the fitness values ​​calculated for each individual in the population ff(g); S007, cross-generation optimization, merge the reordered offspring population ff(g) and the initial population f(0), and sort the merged individuals in ascending order according to the fitness value, take the first Np individuals as the next generation population f(g+1), and update the evolutionary generation g to g+1; S008. If g>G, the individual with the smallest fitness value in all generations is output as the optimal individual and the calculation is terminated, otherwise return to step S002.

5. The phase change ejection intelligent control method according to claim 2, 3 or 4, characterized in that: The fitness value is the absolute value of the difference between the calculated de-orbit velocity and the target parameter value.

Images