CN118821813A - A reader-writer deployment method and system for unmanned aerial vehicle intelligent hangar - Google Patents

Abstract

The invention discloses a reader/writer deployment method and system for an unmanned aerial vehicle (UAV) intelligent hangar, the method comprising: performing environmental mapping on the intelligent hangar to create a radio frequency identification virtual model; identifying the radio frequency identification virtual model to obtain the electronic tag position of the UAV in the intelligent hangar; calculating the tag coverage and the reader/writer load based on the electronic tag position and the initial position of the reader/writer, and constructing a reader/writer deployment optimization function based on the tag coverage and the reader/writer load; solving the reader/writer deployment optimization function by using a particle swarm algorithm and a genetic algorithm, and outputting an optimal reader/writer deployment strategy; the invention takes into account the load balance between readers/writers, avoids overloading of some readers/writers while other readers/writers are idle, thereby improving the reliability of reader/writer deployment, combining the advantages of the genetic algorithm and the particle swarm algorithm, and having better robustness and adaptability.

Description

A reader-writer deployment method and system for unmanned aerial vehicle intelligent hangar

Technical Field

The present invention belongs to the field of reader/writer deployment, and in particular relates to a reader/writer deployment method and system for an unmanned aerial vehicle intelligent hangar.

Background Art

In recent years, drone technology has made significant progress in both civil and military fields. At present, some power companies use drones to inspect power lines, substations, etc., to promptly discover and deal with potential safety hazards, improve the stability and safety of the power system, and at the same time, drone smart hangars for storing drones have been established at different data collection sites.

In the prior art, a radio frequency identification system is configured in the drone smart hangar, and the radio frequency identification system is usually composed of a reader and an electronic tag. The drone with the electronic tag is identified and tracked by radio waves, realizing the automatic and real-time management of drone information.

However, the communication ranges of RFID readers and tags vary, resulting in uneven signal coverage and possible blind spots in certain areas. The lack of an effective deployment strategy may lead to an excessive number of readers and writers, resulting in a waste of resources.

Summary of the invention

The present invention provides a reader/writer deployment method and system for an unmanned aerial vehicle intelligent hangar, which realizes more efficient and accurate reader/writer deployment by comprehensively considering coverage and load balancing factors.

In order to achieve the above object, the technical solution adopted by the present invention is:

The first aspect of the present invention provides a reader-writer deployment method for a drone intelligent hangar, comprising:

Perform environmental mapping of the smart hangar to create a RFID virtual model; identify the RFID virtual model to obtain the electronic tag location of the drone in the smart hangar;

Calculate the tag coverage and reader load based on the electronic tag position and the reader initial position, and build a reader deployment optimization function based on the tag coverage and reader load;

The process of solving the reader-writer deployment optimization function using particle swarm optimization and genetic algorithm includes:

The initial position and speed of the particle swarm are randomly generated. The particles represent the reader deployment plan. The global optimal solution in the particle swarm is found. The historical optimal solution of the reader deployment plan is updated using the global optimal solution.

Based on the historical optimal solution, the speed and position of the particles are iteratively updated, and the particle swarm is selectively cross-operated and mutated according to the number of iterations to re-search the global optimal solution in the particle swarm; the iteration is repeated until the maximum number of iterations is reached to output the optimal deployment strategy of the reader/writer.

Furthermore, crossover and mutation operations are selectively performed on the particle swarm according to the number of iterations, including:

Determine whether the number of iterations of the particle swarm is less than the set threshold;

When the number of iterations of the particle swarm is less than the set threshold, after iteratively updating the particle speed and position based on the historical optimal solution, the particle swarm is subjected to crossover and mutation operations to search for the global optimal solution in the particle swarm again;

When the number of iterations of the particle swarm is greater than or equal to the set threshold, after iteratively updating the particle speed and position based on the historical optimal solution, the global optimal solution in the particle swarm is directly sought.

Furthermore, a reader deployment optimization function is constructed based on tag coverage and reader load, including:

;

;

In the formula, It is represented as the comprehensive evaluation parameter of reader-writer deployment. Expressed as label coverage; Expressed as reader load; Expressed as the weight of label coverage; Expressed as the weight of the reader load.

Furthermore, the tag coverage is calculated based on the electronic tag position and the initial position of the reader, including:

The electronic tag position and the reader initial position calculate the distance between the electronic tag and the reader , according to the distance The coverage rate of electronic tags is calculated using the following formula:

;

;

;

In the formula, It is expressed as the coverage of the i-th electronic tag; It is represented by the number of readers/writers that cover the ith electronic tag through radio frequency; It is represented as the distance between the i-th electronic tag and the j-th reader; It is expressed as the distance of the reader's radio frequency coverage; represents the jth reader/writer; N represents the reader/writer set; m represents the number of readers/writers in the smart hangar.

Furthermore, the reader load is calculated based on the electronic tag position and the reader initial position, including:

;

In the formula, n represents the number of electronic tags in the smart hangar; Represents the reader/writer that reads the i-th electronic tag.

Furthermore, the particle swarm is subjected to crossover operations, including:

Two particles are randomly selected from the particle swarm as the parent particles of the crossover operation, and are denoted as parent particles and parent particle ;

For parent particles and parent particle Perform crossover operation to obtain offspring particles, the expression formula is:

;

In the formula, is a random number in [0,1]; and Represented as descendant particles;

Repeat the crossover operation on the particle swarm until the ratio of the offspring particles generated by the crossover operation to the total number of particles in the particle swarm reaches the preset crossover probability Pc.

Furthermore, the particle swarm is subjected to mutation operations, including:

Randomly select G particles from the particle swarm as the first generation particles for mutation operation, and perform mutation operation on the first generation particles to obtain mutated particles. The expression formula is:

;

;

In the formula, Represents the position of the first generation particle; is represented as the position of the mutant particle; It is expressed as the amount of positional variation; It is represented as the velocity of the first generation of particles; Expressed as the velocity of the mutant particle; Expressed as speed variation;

Repeat the mutation operation on the particle swarm until the ratio of the mutated particles to the total number of particles in the particle swarm reaches the preset mutation probability Pm.

The second aspect of the present invention provides a reader-writer deployment system for an unmanned aerial vehicle intelligent hangar, characterized in that it includes:

The mapping module maps the environment of the smart hangar and creates a RFID virtual model; the RFID virtual model is identified to obtain the electronic tag location of the drone in the smart hangar;

The processing and analysis module calculates the tag coverage and reader load based on the electronic tag position and the reader initial position, and builds a reader deployment optimization function based on the tag coverage and reader load;

The optimization solution module is used to randomly generate the initial position and speed of the particle swarm. The particles represent the reader deployment plan and find the global optimal solution in the particle swarm. The global optimal solution is used to update the historical optimal solution of the reader deployment plan. The particle speed and position are iteratively updated based on the historical optimal solution. The particle swarm is selectively cross-operated and mutated according to the number of iterations.

The output module is used to re-find the global optimal solution in the particle swarm; iterates repeatedly until the maximum number of iterations is reached and outputs the optimal deployment strategy of the reader/writer.

Furthermore, the electronic tag includes a tag power supply, a high-frequency interface, a microcontroller, a first EEPROM memory and a RAM memory; the tag power supply is electrically connected to the first EEPROM memory, the first EEPROM memory and the RAM memory are electrically connected to the microcontroller, and the microcontroller is electrically connected to the tag antenna through the high-frequency interface.

Furthermore, the reader/writer includes a logic control unit; the logic control unit is electrically connected to a second EEPROM memory and a ROM memory; the second EEPROM memory is electrically connected to a voltage regulator; a demodulator is electrically connected to the logic control unit; and the logic control unit is electrically connected to the reader/writer antenna through the modulator.

In a third aspect, the present invention provides an electronic device, comprising a storage medium and a processor; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the reader/writer deployment method described in the first aspect of the present invention.

Compared with the prior art, the present invention has the following beneficial effects:

The present invention calculates the tag coverage and reader load based on the electronic tag position and the initial position of the reader, and constructs a reader deployment optimization function based on the tag coverage and reader load; the load balance between readers is taken into account to avoid overloading of some readers while other readers are idle, thereby improving the reliability of reader deployment.

The present invention uses particle swarm algorithm and genetic algorithm to solve the reader/writer deployment optimization function and obtain the optimal reader/writer deployment strategy; in the early stage of iteration, crossover and mutation operations are used to prevent the particle swarm from falling into the local optimal solution, and in the later stage of iteration, these operations are reduced to ensure the stability and convergence of the solution; the advantages of genetic algorithm and particle swarm algorithm are combined to make the reader/writer deployment method have better robustness and adaptability.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a flow chart of a reader-writer deployment method for a drone smart hangar provided by Embodiment 1 of the present invention;

FIG2 is a flow chart of a reader-writer deployment method for a drone smart hangar provided by Embodiment 2 of the present invention;

FIG3 is a reader/writer deployment distribution diagram after optimization by the GA-PSO group algorithm provided in Example 2 of the present invention;

FIG4 is a line graph of the fitness value after optimization by the GA-PSO group algorithm provided in Example 2 of the present invention;

FIG5 is a reader/writer deployment distribution diagram after GA algorithm optimization provided in Example 2 of the present invention;

FIG6 is a line graph of fitness values after optimization by the GA algorithm provided in Example 2 of the present invention;

FIG7 is a reader/writer deployment distribution diagram after PSO algorithm optimization provided in Example 2 of the present invention;

FIG8 is a line graph of the fitness value after the PSO algorithm is optimized according to Embodiment 2 of the present invention;

FIG9 is a structural diagram of an electronic tag provided in Embodiment 3 of the present invention;

FIG10 is a structural diagram of a reader/writer provided in Embodiment 3 of the present invention.

DETAILED DESCRIPTION

The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

The horizontal direction of the drone hangar is set as the x-axis, the longitudinal direction of the drone hangar is set as the z-axis; the vertical direction of the drone hangar is set as the y-axis.

Example 1

As shown in FIG1 , this implementation provides a reader-writer deployment method for a drone smart hangar, including:

Step 1: Create an RFID virtual model by mapping the smart hangar to the virtual environment, and simulate different reader deployment strategies by mapping the smart hangar to the virtual environment; identify the RFID virtual model to obtain the electronic tag position of the drone in the smart hangar; calculate the tag coverage and reader load based on the electronic tag position and the initial position of the reader, and build a reader deployment optimization function based on the tag coverage and reader load;

Step 2: The process of solving the reader-writer deployment optimization function using the particle swarm algorithm and the genetic algorithm includes:

Step 21, randomly generate the initial position and speed of the particle swarm, the particle represents the reader deployment plan, and find the global optimal solution in the particle swarm; use the global optimal solution to update the historical optimal solution of the reader deployment plan, including:

Calculate the fitness value of the global optimal solution in the tth iteration, recorded as the fitness value When the number of iterations is 1, the global optimal solution is directly set as the historical optimal solution; when the number of iterations is not 1, the fitness value With fitness value For comparison, the reader deployment strategy with a larger fitness value is selected as the historical optimal solution stored after the tth iteration; the fitness value It is expressed as the fitness value of the historical optimal solution stored after the t-1th iteration.

Step 22, iteratively updating the speed and position of the particles based on the historical optimal solution, and determining whether the number of iterations of the particle swarm is less than a set threshold;

Step 23, when the number of iterations of the particle swarm is less than the set threshold, after iteratively updating the speed and position of the particles based on the historical optimal solution, the particle swarm is subjected to crossover and mutation operations, and the process jumps to step 25;

Step 24, when the number of iterations of the particle swarm is greater than or equal to the set threshold, after iteratively updating the speed and position of the particles based on the historical optimal solution, jump to step 25.

Step 25, re-search the global optimal solution in the particle swarm; repeat the iteration until the maximum number of iterations is reached to output the optimal deployment strategy of the reader/writer. The optimal deployment strategy of the reader/writer is the best deployment position for each reader/writer. The reader/writer is deployed to the UAV intelligent hangar according to the optimal deployment strategy of the reader/writer.

This implementation prevents the particle swarm from falling into the local optimal solution through crossover and mutation operations in the early stage of iteration, and ensures the stability and convergence of the solution by reducing these operations in the later stage of iteration; it combines the advantages of genetic algorithm and particle swarm algorithm to make the reader deployment method more robust and adaptable.

Example 2

As shown in FIG2 , this implementation provides a reader-writer deployment method for a drone smart hangar, including:

Step 1: Perform environmental mapping of the smart hangar to create an RFID virtual model; identify the RFID virtual model to obtain the electronic tag position of the drone in the smart hangar; calculate the tag coverage and reader load based on the electronic tag position and the initial position of the reader, and build a reader deployment optimization function based on the tag coverage and reader load, including:

;

;

In the formula, It is represented as the comprehensive evaluation parameter of reader-writer deployment. Expressed as label coverage; Expressed as reader load; Expressed as the weight of label coverage; Expressed as the weight of the reader load.

Calculate the tag coverage based on the electronic tag position and the reader initial position, including:

The electronic tag position and the reader initial position calculate the distance between the electronic tag and the reader , according to the distance The coverage rate of electronic tags is calculated using the following formula:

;

;

;

In the formula, It is expressed as the coverage of the i-th electronic tag; It is represented by the number of readers/writers that cover the ith electronic tag through radio frequency; It is represented as the distance between the i-th electronic tag and the j-th reader; It is expressed as the distance of the reader's radio frequency coverage; represents the jth reader/writer; N represents the reader/writer set; m represents the number of readers/writers in the smart hangar.

Calculate the reader load based on the electronic tag position and the reader initial position, including:

;

In the formula, n represents the number of electronic tags in the smart hangar; Represents the reader/writer that reads the i-th electronic tag.

Step 2: The process of solving the reader-writer deployment optimization function using the particle swarm algorithm and the genetic algorithm includes:

Step 21, randomly generate the initial position and speed of the particle swarm, the particle represents the reader deployment plan, find the global optimal solution in the particle swarm; use the global optimal solution to update the historical optimal solution of the reader deployment plan; including:

Calculate the fitness value of the global optimal solution in the tth iteration, recorded as the fitness value When the number of iterations is 1, the global optimal solution is directly set as the historical optimal solution; when the number of iterations is not 1, the fitness value With fitness value For comparison, the reader deployment strategy with a larger fitness value is selected as the historical optimal solution stored after the tth iteration; the fitness value It is expressed as the fitness value of the historical optimal solution stored after the t-1th iteration.

Step 22, iteratively updating the speed and position of the particles based on the historical optimal solution, and determining whether the number of iterations of the particle swarm is less than a set threshold;

Step 23, when the number of iterations of the particle swarm is less than the set threshold, after iteratively updating the particle speed and position based on the historical optimal solution, the particle swarm is crossover and mutation operated, and the process jumps to step 25; the optimal deployment strategy of the reader/writer is the optimal deployment position for each reader/writer, and the reader/writer is deployed in the UAV intelligent hangar according to the optimal deployment strategy of the reader/writer.

Among them, the crossover operation on the particle swarm includes:

Two particles are randomly selected from the particle swarm as the parent particles of the crossover operation, and are denoted as parent particles and parent particle ;

For parent particles and parent particle Perform crossover operation to obtain offspring particles, the expression formula is:

;

In the formula, is a random number in [0,1]; and Represented as descendant particles;

Repeat the crossover operation on the particle swarm until the ratio of the offspring particles generated by the crossover operation to the total number of particles in the particle swarm reaches the preset crossover probability Pc.

Among them, the mutation operation on the particle swarm includes:

Randomly select G particles from the particle swarm as the first generation particles for mutation operation, and perform mutation operation on the first generation particles to obtain mutated particles. The expression formula is:

;

;

In the formula, Represents the position of the first generation particle; is represented as the position of the mutant particle; It is expressed as the amount of positional variation; It is represented as the velocity of the first generation of particles; Expressed as the velocity of the mutant particle; Expressed as speed variation;

Repeat the mutation operation on the particle swarm until the ratio of the mutated particles to the total number of particles in the particle swarm reaches the preset mutation probability Pm.

Step 24, when the number of iterations of the particle swarm is greater than or equal to the set threshold, after iteratively updating the speed and position of the particles based on the historical optimal solution, jump to step 25.

Step 25, re-search the global optimal solution in the particle swarm; repeat the iteration until the maximum number of iterations is reached to output the optimal deployment strategy of the reader/writer.

In order to further verify the effectiveness of the improved particle swarm optimization algorithm (GA-PSO algorithm) in the present invention, the algorithm is compared with the genetic algorithm (GA algorithm) and the particle swarm optimization algorithm (PSO algorithm).

As shown in Figures 3, 5 and 7, the reader deployment distribution diagrams after optimization by GA-PSO algorithm, GA algorithm and PSO algorithm. Among them, "circle" represents the coverage of the reader, and "meter" represents the electronic tag; the reader deployment distribution diagrams after optimization by GA algorithm and PSO algorithm have two electronic tags that are not within the coverage of the reader; the reader deployment distribution diagram after optimization by GA-PSO algorithm has a single electronic tag that is not within the coverage of the reader; As shown in Figures 4, 6 and 8, the fitness value line graphs of the optimal deployment strategy of the reader after optimization by GA-PSO algorithm, GA algorithm and PSO algorithm; the fitness value of the optimal deployment strategy of the reader after optimization by GA-PSO algorithm is 0.686; the fitness value of the optimal deployment strategy of the reader after optimization by GA algorithm is 0.672; the fitness value of the optimal deployment strategy of the reader after optimization by PSO algorithm is 0.672; by comparison, it can be judged that GA-PSO algorithm can prevent particle swarm from falling into local optimal solution through crossover and mutation operations in the early stage of iteration, thereby improving the reliability of reader deployment.

The number of iterations required for the GA algorithm and the PSO algorithm to obtain the optimal reader deployment strategy are 102 and 80 respectively; the number of iterations required for the GA-PSO algorithm to obtain the optimal reader deployment strategy is 77; by comparison, it can be judged that the GA-PSO algorithm can ensure the stability and convergence of the solution by reducing these operations in the later stage of iteration; combining the advantages of genetic algorithm and particle swarm algorithm, the reader deployment method has better robustness and adaptability.

The number of readers is set to 9, 12 and 15 respectively; the GA-PSO algorithm, GA algorithm and PSO algorithm are run 20 times respectively to output the optimal deployment strategy of readers and writers, and the average optimal fitness value is obtained, as shown in Table 1.

Table 1, Average optimal fitness values of GA-PSO algorithm, GA algorithm and PSO algorithm;

From the test results, we can see that under the same conditions, the GA-PSO algorithm has the largest fitness value or the least number of iterations, that is, the improved particle swarm algorithm has the best optimization effect. Gradually decreases, so that the particles inherit less speed in the original direction, so that they fly closer and have better exploration ability. However, the search ability of the particle swarm decreases, and it is easy to fall into the local optimal solution as the number of iterations increases. The improved particle swarm algorithm selects a certain number of particles from the particle swarm according to a certain probability in each iteration, so that they reproduce randomly in pairs, produce a corresponding number of offspring particles, and replace the parent particles with offspring particles to keep the population size unchanged. The crossover operation can benefit the particles from both parents, enhance the search ability, and easily jump out of the local optimal solution; the mutation operation of the improved particle swarm algorithm (GA-PSO algorithm) changes the positions of some particles with a certain mutation probability, thereby enhancing the optimization ability of the GA-PSO algorithm.

Example 3

This embodiment provides a reader/writer deployment system for a drone intelligent hangar. The reader/writer deployment system described in this embodiment can apply the reader/writer deployment method described in Embodiment 1 and Embodiment 2. The reader/writer deployment system includes:

The mapping module maps the environment of the smart hangar and creates a RFID virtual model; the RFID virtual model is identified to obtain the electronic tag location of the drone in the smart hangar;

The processing and analysis module calculates the tag coverage and reader load based on the electronic tag position and the reader initial position, and builds a reader deployment optimization function based on the tag coverage and reader load;

The optimization solution module is used to randomly generate the initial position and speed of the particle swarm. The particles represent the reader deployment plan and find the global optimal solution in the particle swarm. The global optimal solution is used to update the historical optimal solution of the reader deployment plan. The particle speed and position are iteratively updated based on the historical optimal solution. The particle swarm is selectively cross-operated and mutated according to the number of iterations.

The output module is used to re-find the global optimal solution in the particle swarm; iterates repeatedly until the maximum number of iterations is reached and outputs the optimal deployment strategy of the reader/writer.

As shown in Figure 9, the electronic tag includes a tag power supply, a high-frequency interface, a microcontroller, a first EEPROM memory and a RAM memory; the tag power supply is electrically connected to the first EEPROM memory, the first EEPROM memory and the RAM memory are electrically connected to the microcontroller, and the microcontroller is electrically connected to the tag antenna through the high-frequency interface.

As shown in Figure 10, the reader/writer includes a logic control unit; the logic control unit is electrically connected to a second EEPROM memory and a ROM memory; the second EEPROM memory is electrically connected to a voltage regulator; a demodulator is electrically connected to the logic control unit; and the logic control unit is electrically connected to the reader/writer antenna through the modulator.

The optimization solution module selectively performs crossover and mutation operations on the particle swarm according to the number of iterations, including:

Determine whether the number of iterations of the particle swarm is less than the set threshold;

When the number of iterations of the particle swarm is less than the set threshold, after iteratively updating the particle speed and position based on the historical optimal solution, the particle swarm is subjected to crossover and mutation operations to search for the global optimal solution in the particle swarm again;

When the number of iterations of the particle swarm is greater than or equal to the set threshold, after iteratively updating the particle speed and position based on the historical optimal solution, the global optimal solution in the particle swarm is directly sought.

Example 4

In a third aspect, the present invention provides an electronic device, comprising a storage medium and a processor; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the reader/writer deployment method described in Example 1 and Example 2.

Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD- ROM , optical storage, etc.) containing computer-usable program codes.

The present application is described with reference to the flowcharts and/or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and/or box in the flowchart and/or block diagram, as well as the combination of the processes and/or boxes in the flowchart and/or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the functions specified in one process or multiple processes in the flowchart and/or one box or multiple boxes in the block diagram.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims (10)

1. A reader-writer deployment method for a drone smart hangar, comprising: Perform environmental mapping of the smart hangar to create a RFID virtual model; identify the RFID virtual model to obtain the electronic tag location of the drone in the smart hangar; Calculate the tag coverage and reader load based on the electronic tag position and the reader initial position, and build a reader deployment optimization function based on the tag coverage and reader load; The process of solving the reader-writer deployment optimization function using particle swarm optimization and genetic algorithm includes: The initial position and speed of the particle swarm are randomly generated. The particles represent the reader deployment plan. The global optimal solution in the particle swarm is found. The historical optimal solution of the reader deployment plan is updated using the global optimal solution. Based on the historical optimal solution, the speed and position of the particles are iteratively updated, and the particle swarm is selectively cross-operated and mutated according to the number of iterations to re-search the global optimal solution in the particle swarm; the iteration is repeated until the maximum number of iterations is reached to output the optimal deployment strategy of the reader/writer. 2. The reader-writer deployment method according to claim 1 is characterized in that the crossover operation and mutation operation are selectively performed on the particle swarm according to the number of iterations, comprising: Determine whether the number of iterations of the particle swarm is less than the set threshold; When the number of iterations of the particle swarm is less than the set threshold, after iteratively updating the particle speed and position based on the historical optimal solution, the particle swarm is subjected to crossover and mutation operations to search for the global optimal solution in the particle swarm again; When the number of iterations of the particle swarm is greater than or equal to the set threshold, after iteratively updating the particle speed and position based on the historical optimal solution, the global optimal solution in the particle swarm is directly sought. 3. The reader/writer deployment method according to claim 1, characterized in that a reader/writer deployment optimization function is constructed based on tag coverage and reader/writer load, comprising: ; ; In the formula, It is represented as the comprehensive evaluation parameter of reader-writer deployment. Expressed as label coverage; Expressed as reader load; Expressed as the weight of label coverage; Expressed as the weight of the reader load. 4. The reader-writer deployment method according to claim 3, characterized in that the tag coverage is calculated based on the electronic tag position and the reader-writer initial position, comprising: The electronic tag position and the reader initial position calculate the distance between the electronic tag and the reader , according to the distance The coverage rate of electronic tags is calculated using the following formula: ; ; ; In the formula, It is expressed as the coverage of the i-th electronic tag; It is represented by the number of readers/writers that cover the ith electronic tag through radio frequency; It is represented as the distance between the i-th electronic tag and the j-th reader; It is expressed as the distance of the reader's radio frequency coverage; represents the jth reader/writer; N represents the reader/writer set; m represents the number of readers/writers in the smart hangar. 5. The reader/writer deployment method according to claim 3, characterized in that the reader/writer load is calculated based on the electronic tag position and the reader/writer initial position, comprising: ; In the formula, n represents the number of electronic tags in the smart hangar; Represents the reader/writer that reads the i-th electronic tag. 6. The reader-writer deployment method according to claim 1 or 2, characterized in that the cross operation on the particle swarm comprises: Two particles are randomly selected from the particle swarm as the parent particles of the crossover operation, and are denoted as parent particles and parent particle ; For parent particles and parent particle Perform crossover operation to obtain offspring particles, the expression formula is: ; In the formula, is a random number in [0,1]; and Represented as descendant particles; Repeat the crossover operation on the particle swarm until the ratio of the offspring particles generated by the crossover operation to the total number of particles in the particle swarm reaches the preset crossover probability Pc. 7. The reader-writer deployment method according to claim 1 or 2, characterized in that the mutation operation on the particle swarm comprises: Randomly select G particles from the particle swarm as the first generation particles for mutation operation, and perform mutation operation on the first generation particles to obtain mutated particles. The expression formula is: ; ; In the formula, Represents the position of the first generation particle; is represented as the position of the mutant particle; It is expressed as the amount of positional variation; It is represented as the velocity of the first generation of particles; Expressed as the velocity of the mutant particle; Expressed as speed variation; Repeat the mutation operation on the particle swarm until the ratio of the mutated particles to the total number of particles in the particle swarm reaches the preset mutation probability Pm. 8. A reader-writer deployment system for a drone smart hangar, comprising: The mapping module maps the environment of the smart hangar and creates a RFID virtual model; the RFID virtual model is identified to obtain the electronic tag location of the drone in the smart hangar; The processing and analysis module calculates the tag coverage and reader load based on the electronic tag position and the reader initial position, and builds a reader deployment optimization function based on the tag coverage and reader load; The optimization solution module is used to randomly generate the initial position and speed of the particle swarm. The particles represent the reader deployment plan and find the global optimal solution in the particle swarm. The global optimal solution is used to update the historical optimal solution of the reader deployment plan. The particle speed and position are iteratively updated based on the historical optimal solution. The particle swarm is selectively cross-operated and mutated according to the number of iterations. The output module is used to re-find the global optimal solution in the particle swarm; iterates repeatedly until the maximum number of iterations is reached and outputs the optimal deployment strategy of the reader/writer. 9. The reader-writer deployment system according to claim 8, characterized in that the electronic tag comprises a tag power supply, a high-frequency interface, a microcontroller, a first EEPROM memory and a RAM memory; the tag power supply is electrically connected to the first EEPROM memory, the first EEPROM memory and the RAM memory are electrically connected to the microcontroller, and the microcontroller is electrically connected to the tag antenna through the high-frequency interface; The reader/writer includes a logic control unit; the logic control unit is electrically connected to a second EEPROM memory and a ROM memory; the second EEPROM memory is electrically connected to a voltage regulator; a demodulator is electrically connected to the logic control unit; and the logic control unit is electrically connected to the reader/writer antenna through the modulator. 10. An electronic device comprising a storage medium and a processor; the storage medium is used to store instructions; and the processor is used to operate according to the instructions to execute the reader/writer deployment method according to any one of claims 1 to 7.