Automatic dust removal method and system for RFID high-frequency antenna surface based on air dust removal

By automatically identifying dust adhesion and gain, adjusting dust removal parameters, intelligent dust removal on the surface of RFID high-frequency antennas, solving the problem of dust in the air affecting signal quality and improving dust removal efficiency and cleanliness.

CN118371487BActive Publication Date: 2024-11-08JIANGSU KERUITAN ELECTRONICS TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410513895.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-26
Publication Date
2024-11-08
Estimated Expiration
2044-04-26

AI Technical Summary

Technical Problem

Dust in the air affects the transmission and reception quality of RFID high-frequency antenna signals, reducing identification accuracy.

Method used

An automated dust removal method and system based on air dust removal is adopted to collect basic antenna information through sensor components, identify dust adhesion and gain, adjust dust removal parameters, and automatically control the dust removal device for dust removal.

Benefits of technology

It improves the intelligence of dust removal on the surface of RFID high-frequency antennas, improves dust removal efficiency and cleanliness, and ensures the stability and accuracy of signal transmission.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118371487B_ABST
    Figure CN118371487B_ABST
Patent Text Reader

Abstract

The present invention discloses an automatic dust removal method and system for the surface of RFID high-frequency antennas based on air dust removal, and relates to the field of separation and adsorption. The method comprises: using a sensor component to obtain a set of basic information of multiple high-frequency antennas; performing dust adhesion identification and dust gain identification; judging whether the cleanliness of the surfaces of multiple antennas meets a preset cleaning threshold, and if so, triggering a dust removal instruction; calling a dust removal parameter analysis module according to the dust removal instruction, fine-tuning and optimizing the multiple first dust removal parameters, and obtaining multiple target dust removal parameters; and automatically controlling the dust removal device to remove dust from the surfaces of the multiple high-frequency antennas respectively. This method solves the technical problem that the presence of dust in the air causes antenna signal attenuation, affects the transmission and reception of radio frequency signals, and thus reduces the accuracy of identification, and achieves the technical effect of improving the intelligence level of dust removal on the surface of RFID high-frequency antennas, and improving dust removal efficiency and cleanliness.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of separation and adsorption technology, and in particular to the field of air dust removal, and specifically to an automatic dust removal method and system for the surface of an RFID high-frequency antenna based on air dust removal. Background Art

[0002] RFID high-frequency antennas are antennas used to ensure fast, contactless identification of objects. In order to make the antenna work properly and improve the stability and accuracy of the radio frequency identification system, the antenna surface needs to be dusted. Dust and impurities in the air may affect the performance of the antenna and the quality of signal transmission. In the RFID system, the stability and sensitivity of the antenna are crucial to the accuracy of tag identification. Dust in the air may cause antenna signal attenuation or uneven reflection, affecting the transmission and reception of radio frequency signals, thereby reducing the accuracy of identification, so air dust removal is required. At present, by regularly cleaning the antenna surface, keeping the surrounding environment clean, and using a dust cover, the aluminum chips on the antenna after the high-frequency antenna is riveted are mainly removed by dragging the material on the surface of the material with a brush.

[0003] In summary, the prior art has a technical problem that the presence of dust in the air causes antenna signal attenuation, affects the transmission and reception of radio frequency signals, and thus reduces recognition accuracy. Summary of the invention

[0004] Based on this, it is necessary to provide an automatic dust removal method and system for the surface of RFID high-frequency antennas based on air dust removal, which can improve the intelligence level of dust removal on the surface of RFID high-frequency antennas, and improve the dust removal efficiency and cleanliness, in response to the above technical problems.

[0005] In a first aspect, an automatic dust removal method for the surface of an RFID high-frequency antenna based on air dust removal is provided, the method comprising: using a sensor component to collect basic information of multiple high-frequency antennas to obtain multiple high-frequency antenna basic information sets, wherein the multiple high-frequency antenna basic information sets include multiple humidity monitoring data sets and multiple antenna surface image sets; traversing the multiple antenna surface image sets to perform dust adhesion identification and dust gain identification, to obtain multiple dust adhesion identification results and multiple dust gain coefficients; determining the cleanliness of multiple antenna surfaces based on the multiple dust adhesion identification results and the multiple dust gain coefficients; determining whether the cleanliness of the multiple antenna surfaces meets a preset cleaning threshold, and if so, triggering a dust removal instruction; and calling a dust removal parameter analysis according to the dust removal instruction. Module, input the surface cleanliness of the multiple antennas into the dust removal parameter analysis module, and obtain multiple first dust removal parameters and multiple fine-tuning thresholds; fine-tune and optimize the multiple first dust removal parameters according to the multiple humidity monitoring data, and constrain them according to the parameter constraints during the optimization process to obtain multiple target dust removal parameters, wherein the multiple target dust removal parameters include static electricity removal parameters, first air suction parameters, first air blowing parameters and second air suction parameters, and the parameter constraints are that the parameter values ​​of the multiple first dust removal parameters after fine-tuning must meet the multiple fine-tuning thresholds; based on the multiple target dust removal parameters, the static electricity removal module, the first air suction module, the first air blowing module and the second air suction module of the dust removal device are automatically controlled to remove dust from the surfaces of the multiple high-frequency antennas respectively.

[0006] In a second aspect, an automatic dust removal system for the surface of an RFID high-frequency antenna based on air dust removal is provided, the system comprising: a high-frequency antenna basic information set acquisition module, the high-frequency antenna basic information set acquisition module is used to use a sensor component to collect basic information of multiple high-frequency antennas, and obtain multiple high-frequency antenna basic information sets, wherein the multiple high-frequency antenna basic information sets include multiple humidity monitoring data sets and multiple antenna surface image sets; a dust recognition module, the dust recognition module is used to traverse the multiple antenna surface image sets to perform dust adhesion recognition and dust gain recognition, and obtain multiple dust adhesion recognition results and multiple dust gain coefficients; an antenna surface cleanliness determination module, the antenna surface cleanliness determination module is used to determine the cleanliness of multiple antenna surfaces according to the multiple dust adhesion recognition results and the multiple dust gain coefficients; a dust removal instruction triggering module, the dust removal instruction triggering module is used to determine whether the cleanliness of the surfaces of the multiple antennas meets a preset cleaning threshold, and if so, trigger a dust removal instruction; A dust removal parameter analysis module, the dust removal parameter analysis module is used to call the dust removal parameter analysis module according to the dust removal instruction, input the surface cleanliness of the multiple antennas into the dust removal parameter analysis module, and obtain multiple first dust removal parameters and multiple fine-tuning thresholds; a target dust removal parameter acquisition module, the target dust removal parameter acquisition module is used to fine-tune and optimize the multiple first dust removal parameters according to the multiple humidity monitoring data, and constrain them according to parameter constraints during the optimization process to obtain multiple target dust removal parameters, wherein the multiple target dust removal parameters include static electricity removal parameters, first air suction parameters, first air blowing parameters and second air suction parameters, and the parameter constraints are that the parameter values ​​of the multiple first dust removal parameters after fine-tuning must meet the multiple fine-tuning thresholds; an automation control module, the automation control module is used to automatically control the static electricity removal module, the first air suction module, the first air blowing module and the second air suction module of the dust removal device based on the multiple target dust removal parameters, and respectively remove dust from the surfaces of the multiple high-frequency antennas.

[0007] According to a third aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps according to the first aspect when executing the computer program.

[0008] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps described in the first aspect are implemented.

[0009] The above-mentioned automatic dust removal method and system for the surface of the RFID high-frequency antenna based on air dust removal adopts this method to solve the technical problem that the presence of dust in the air causes antenna signal attenuation, affects the transmission and reception of radio frequency signals, and thus reduces the recognition accuracy, and achieves the technical effect of improving the intelligence level of dust removal on the surface of the RFID high-frequency antenna, and enhancing the dust removal efficiency and cleanliness.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of a process of an automatic dust removal method for the surface of an RFID high-frequency antenna based on air dust removal in one embodiment;

[0012] Figure 2 A schematic diagram of a process for obtaining a dust gain coefficient in a method for automatic dust removal on the surface of an RFID high-frequency antenna based on air dust removal in one embodiment;

[0013] Figure 3 It is a structural block diagram of an automatic dust removal system for the surface of an RFID high-frequency antenna based on air dust removal in one embodiment;

[0014] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment.

[0015] Explanation of the reference numerals: high-frequency antenna basic information set acquisition module 11, dust identification module 12, antenna surface cleanliness determination module 13, dust removal instruction triggering module 14, dust removal parameter analysis module 15, target dust removal parameter acquisition module 16, automation control module 17. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0017] like Figure 1 As shown, the present application provides an automatic dust removal method for the surface of an RFID high-frequency antenna based on air dust removal, the method comprising:

[0018] Using the sensor assembly to collect basic information of the multiple high-frequency antennas to obtain multiple high-frequency antenna basic information sets, wherein the multiple high-frequency antenna basic information sets include multiple humidity monitoring data sets and multiple antenna surface image sets;

[0019] Air dust removal refers to the technology of removing dust, particulate matter and other impurities from the air through various technologies and equipment. The RFID high-frequency antenna is an antenna used to ensure fast, contactless identification of objects. Dust and impurities will adhere to the surface of the RFID high-frequency antenna, which will interfere with the antenna's electromagnetic wave transmission and reception. Dust and impurities may change the impedance matching of the antenna, causing electromagnetic waves to be reflected, scattered or attenuated during transmission, thereby affecting the communication distance and stability of the RFID high-frequency antenna. Therefore, in order to enable the RFID high-frequency antenna to work normally and improve the stability and accuracy of the radio frequency identification system, it is necessary to perform dust removal on the surface of the RFID high-frequency antenna. By providing an automatic dust removal method for the surface of the RFID high-frequency antenna based on air dust removal, the technical effect of improving the intelligence of dust removal on the surface of the RFID high-frequency antenna and improving the dust removal efficiency and cleanliness is achieved.

[0020] The sensor assembly includes a humidity sensor and an image sensor, which are used to collect humidity changes and surface detail changes of the multiple high-frequency antennas, such as dust accumulation, aluminum shavings distribution, etc., where multiple high-frequency antennas refer to a collection of high-frequency antennas in an area; the collected information is integrated to obtain multiple high-frequency antenna basic information sets, which include multiple humidity monitoring data sets and multiple antenna surface image sets; using the sensor assembly to collect basic information of multiple high-frequency antennas helps to monitor the status of the antennas in real time, predict potential problems, and optimize the performance of the antennas. By reasonably selecting sensors, designing collection plans, and effectively processing and analyzing data, effective management and maintenance of high-frequency antennas can be achieved.

[0021] Traversing the plurality of antenna surface image sets to perform dust adhesion recognition and dust gain recognition, and obtaining a plurality of dust adhesion recognition results and a plurality of dust gain coefficients;

[0022] The plurality of antenna surface image sets are accessed sequentially to perform dust adhesion recognition and dust gain recognition operations, wherein the dust adhesion recognition refers to analyzing the plurality of antenna surface image sets by image processing technology, thereby detecting the presence and distribution of dust and obtaining a plurality of dust adhesion recognition results; the dust gain recognition refers to obtaining the dust change in the environment where the plurality of antennas are located and obtaining a plurality of dust gain coefficients. By traversing the plurality of antenna surface image sets to perform dust adhesion recognition and dust gain recognition, a plurality of dust adhesion recognition results and a plurality of dust gain coefficients can be obtained, providing important reference information for the subsequent maintenance and management of high-frequency antennas.

[0023] Performing grayscale processing on the plurality of antenna surface image sets respectively to obtain a plurality of antenna surface grayscale image sets;

[0024] Dividing the plurality of antenna surface grayscale image sets into regions according to the structural features of the plurality of high-frequency antennas to obtain a plurality of antenna surface grayscale region image sets and a plurality of antenna surrounding grayscale region image sets, wherein the plurality of antenna surface grayscale region image sets and the plurality of antenna surrounding grayscale region image sets correspond to each other one by one;

[0025] Performing dust adhesion recognition on the plurality of antenna surface grayscale area image sets to obtain a plurality of dust adhesion recognition results;

[0026] Dust gain analysis is performed on the grayscale area image sets around the multiple antennas to obtain multiple dust gain coefficients.

[0027] The multiple antenna surface image sets are respectively subjected to grayscale processing. Grayscale processing is a process of converting a color image into a grayscale image, which reduces the color information of the image but retains the brightness information of the image. The multiple antenna surface image sets are processed and integrated by calculating the average values ​​of the three color channels of red, green and blue for each pixel in the image to obtain multiple antenna surface grayscale image sets. The multiple antenna surface grayscale image sets are divided into regions according to the structural features of the multiple high-frequency antennas, that is, the multiple antenna surface grayscale image sets are divided according to the high-frequency antennas and the areas near the high-frequency antennas, and the antenna surface area is accurately separated from the surrounding area according to the image segmentation technology, wherein the image segmentation technology can be an edge detection algorithm, an image segmentation algorithm, etc. By integrating the antenna surface area image and the surrounding area image, a plurality of antenna surface grayscale area image sets and a plurality of antenna surrounding grayscale area image sets are obtained, each antenna surface grayscale area image has a corresponding antenna surrounding grayscale area image, and the plurality of antenna surface grayscale area image sets are subjected to dust attachment identification, and the presence of dust attachment on the antenna surface is detected, and the degree and distribution of dust attachment are determined, and a plurality of dust attachment identification results are obtained, and dust gain analysis is performed on the plurality of antenna surrounding grayscale area image sets, that is, by comparing the antenna surrounding area grayscale image with the image in the standard or clean state, the dust condition of the surrounding area and a plurality of dust gain coefficients are determined. The dust attachment condition on the antenna surface and the degree of influence of dust on the antenna dust attachment are obtained, which provides important information and basis for the maintenance and management of high-frequency antennas.

[0028] respectively extracting images at the last moment from the plurality of antenna surface grayscale area image sets as a plurality of dust attachment recognition images;

[0029] Randomly selecting m pixel points from the plurality of dust attachment recognition images as m starting recognition points;

[0030] Taking the m starting recognition points as attachment recognition starting points, performing random iterations in the multiple dust attachment recognition images according to a preset recognition bandwidth to obtain m stage recognition points, wherein the m starting recognition points correspond to the m stage recognition points one by one;

[0031] Determine whether the difference between the grayscale values ​​of the m stage identification points and the grayscale values ​​of the m starting identification points meets a preset difference threshold, and if so, use the positions of the m stage identification points as m first dust attachment points;

[0032] Taking the m first dust attachment points as the attachment size identification starting point, random iteration is performed in the multiple dust attachment identification images according to a preset identification step length, until the difference between the grayscale values ​​of the m pixel points obtained after the iteration and the grayscale values ​​of the m first dust attachment points meets the preset difference threshold, and the preset identification step length is superimposed according to the number of iterations to obtain m first dust attachment sizes of the m first dust attachment points, wherein the preset identification step length is smaller than the preset identification bandwidth.

[0033] From the plurality of antenna surface grayscale area image sets, extract the image at the last moment of each set, the image represents the final state of dust adhesion on the antenna surface within a period of time, and therefore use it as a plurality of dust adhesion recognition images, randomly select m pixel points from each dust adhesion recognition image as starting recognition points, the starting recognition point will be used as the starting point of dust adhesion recognition for subsequent iterative recognition processes; take the m starting recognition points as the attachment recognition starting points, perform random iterations in the dust adhesion recognition images according to a preset recognition bandwidth, the preset recognition bandwidth refers to a specific range set by the staff, that is, a certain range around the starting recognition point, a pre-set step size for iteration, determine whether there is dust adhesion, randomly select new pixel points within the preset recognition bandwidth of the starting recognition point, as stage recognition points, and obtain m stage recognition points corresponding to the m starting recognition points through multiple iterations, wherein m refers to a positive integer greater than or equal to 1; After obtaining the stage identification point, it is determined whether the difference between the gray value of the stage identification point and the gray value of the corresponding starting identification point meets the preset difference threshold. The preset difference threshold is set by the staff and is used to determine whether the position of the stage identification point is a dust attachment area. If it is satisfied, it means that the position of the stage identification point is a dust attachment area, so the position of the stage identification point is taken as m first dust attachment points; the m first dust attachment points are taken as the attachment size identification starting point, and random iterations are performed in the multiple dust attachment identification images according to the preset identification step length. The preset identification step length is set by the staff. After determining the dust attachment point, the size of the dust is identified. During the iteration process, the difference between the gray value of the pixel point obtained after the iteration and the gray value of the first dust attachment point is continuously checked until the difference meets the preset difference threshold. In each iteration, the preset identification step length is superimposed according to the number of iterations to more finely identify the size of the dust attachment. Through the above method, the first dust attachment size of each first dust attachment point can be obtained. Since the dust size must be smaller than the dust attachment point, the preset identification step length should be smaller than the preset identification bandwidth to ensure the fineness and accuracy of the identification. Effectively identify the location and size of dust attached to the antenna surface, providing important reference information for subsequent antenna maintenance and performance optimization.

[0034] If not, taking the m stage recognition points as attachment recognition starting points, performing random iterations in the multiple dust attachment recognition images according to a preset recognition bandwidth until the iteration reaches the edge of the multiple dust attachment recognition images, and obtaining multiple dust attachment point sets and multiple dust attachment size sets;

[0035] The plurality of dust attachment point sets and the plurality of dust attachment size sets are taken as a plurality of dust attachment recognition results.

[0036] If the difference between the grayscale value of the m stage recognition points and the grayscale value of the corresponding starting recognition point does not meet the preset difference threshold, it means that the real dust attachment area has not been found, and the search range needs to be further expanded. The m stage recognition points are used as new attachment recognition starting points, and random iterations are performed in the dust attachment recognition image again according to the preset recognition bandwidth. The grayscale values ​​of the newly recognized pixels are continuously checked. If the grayscale value difference with the starting point or the stage recognition point still does not meet the preset difference threshold, we will continue to iterate until the edge of the dust attachment recognition image is reached, and multiple dust attachment point sets and multiple dust attachment size sets are obtained. The multiple dust attachment point sets include the positions of all possible dust attachment points recognized in the image, and the grayscale value changes of the recognition points during each iteration are recorded, so as to estimate the size of each dust attachment point and form multiple dust attachment size sets. The dust attachment point sets and the dust attachment size sets are output as multiple dust attachment recognition results. By obtaining the specific position of dust attachment and the size information of dust attachment, it provides help for the subsequent dust removal of the high-frequency antenna.

[0037] Performing dust suspension recognition on the grayscale area image sets around the multiple antennas to obtain multiple dust suspension recognition results;

[0038] Randomly selecting a first dust suspension recognition result from the plurality of dust suspension recognition results, wherein the first dust suspension recognition result includes a plurality of first dust suspension point sets and a plurality of first dust suspension size sets, each first dust suspension point set corresponds to a first antenna surrounding grayscale area image in the first antenna surrounding grayscale area image set;

[0039] Calculate the ratio of any first dust suspension size in a plurality of first dust suspension size sets to the sum of the suspension sizes in the corresponding first dust suspension size sets to obtain a plurality of first dust suspension coefficient sets;

[0040] Using the multiple first dust suspension coefficient sets, weighted calculation is performed on the grayscale values ​​corresponding to the suspension points of the multiple first dust suspension point sets to obtain multiple dust suspension grayscale values;

[0041] Perform dust gain analysis according to the plurality of dust suspension grayscale values ​​to obtain a first dust gain coefficient;

[0042] Dust gain analysis is performed according to the multiple dust suspension identification results to obtain multiple dust gain coefficients.

[0043] Dust suspension recognition is performed on the plurality of grayscale area image sets around the antennas, and dust particles suspended in the air around the antennas are detected and identified to obtain a plurality of dust suspension recognition results, which include the position and size information of all dust suspension points identified in the plurality of grayscale area images around the antennas. One of the plurality of dust suspension recognition results is randomly selected as the first dust suspension recognition result, and the first dust suspension recognition result includes a plurality of first dust suspension point sets and a plurality of first dust suspension size sets, each set corresponding to an image in the first grayscale area image set around the antennas. The ratio of each first dust suspension size to the sum of the suspension sizes in the corresponding set is calculated, i.e., the first dust suspension coefficient. This first dust suspension coefficient reflects the relative importance of dust suspension particles of different sizes in the overall suspension state. By calculating the ratio of each first dust suspension size to the sum of all suspension sizes in the corresponding set for all three months, a plurality of first dust suspension coefficient sets are obtained. The plurality of first dust suspension coefficient sets will be used for subsequent weighted calculations. Using the calculated first dust suspension coefficient set, the grayscale value corresponding to each suspension point in the first dust suspension point set is weightedly calculated to obtain the contribution of dust suspension particles of different sizes to the overall grayscale value and obtain the dust suspension grayscale value; dust gain analysis is performed based on the calculated dust suspension grayscale value to evaluate the impact of the dust suspension state on the dust on the antenna surface, and the first dust gain coefficient can be calculated by analyzing the relationship between the dust suspension grayscale value and the antenna performance parameters. Comprehensive analysis of the dust adhesion on the antenna surface and the dust suspension state around the antenna provides technical support for subsequent antenna dust removal.

[0044] like Figure 2 As shown, the difference between two dust suspension gray values ​​at adjacent moments of the plurality of dust suspension gray values ​​is calculated respectively to obtain a plurality of suspension gray value differences;

[0045] Determine whether the plurality of suspended gray value differences are all positive numbers, and if so, perform linear fitting to obtain the first dust gain coefficient;

[0046] If not, variance calculation is performed on the multiple dust suspension grayscale values ​​to obtain the first dust gain coefficient.

[0047] Traverse the difference list and check whether each element is greater than zero. If all the differences are positive, it means that the dust suspension state is continuously enhanced, due to the continuous accumulation of dust particles or the deterioration of environmental conditions; if all the suspension gray value differences are positive, it means that it is increasing, and linear fitting can be performed. The first dust gain coefficient is generated according to the slope after fitting. The first dust gain coefficient is obtained by linear fitting. Linear fitting is a method of finding the best function to match data by minimizing the sum of squares of errors; use a linear model to fit the change trend of dust suspension gray value over time, and estimate the dust gain coefficient by the slope of the fitting line. This coefficient will quantify the degree of influence of the enhancement of dust suspension state on antenna performance; if there are non-positive numbers in the suspension gray value difference, it means that the change of dust suspension state is not monotonically enhanced, and there may be fluctuations or unstable changes. Variance calculation is used to evaluate the discreteness of dust suspension gray value, and this is used as the first dust gain coefficient. Variance is a statistic that measures the degree of difference between a data point and its average value. It can reflect the degree of change and stability of the dust suspension state. According to the change of the dust suspension gray value, a suitable method is used to calculate the first dust gain coefficient, thereby evaluating the impact of the dust suspension state on the antenna performance.

[0048] determining a plurality of antenna surface cleanliness levels according to the plurality of dust attachment identification results and the plurality of dust gain coefficients;

[0049] It is necessary to collect the dust adhesion identification results and the corresponding dust gain coefficient of each antenna, and obtain them through professional detection equipment or technology, such as using a high-resolution camera to capture the image of the antenna surface, and then identify the dust adhesion through image processing technology; the dust gain coefficient can be obtained by comparing the performance difference of the antenna in the clean and dust-attached state; according to the collected dust adhesion identification results, analyze the dust distribution, density and size of each antenna surface, and quantify the degree of dust adhesion on the antenna surface, such as the number of dust particles and area proportion. The dust gain coefficient refers to the dust adhesion that changes over time; combined with the analysis of dust adhesion and dust gain coefficient, a cleanliness level is determined for each antenna surface. The cleanliness level can be a quantitative value or a qualitative description, such as very clean, lightly polluted, heavily polluted, etc., to obtain the cleanliness of multiple antenna surfaces. The cleanliness of multiple antenna surfaces can be determined based on multiple dust adhesion identification results and multiple dust gain coefficients, providing a data basis for subsequent automated dust removal.

[0050] Determine whether the surface cleanliness of the plurality of antennas meets a preset cleaning threshold, and if so, trigger a dust removal instruction;

[0051] According to the antenna's use requirements, performance standards, and actual working environment, one or more preset cleaning thresholds are set, which are set by the staff. The cleanliness of each antenna surface is compared with the preset cleaning threshold. According to the comparison result, it is judged whether the cleanliness of each antenna surface meets the preset cleaning threshold. If the cleanliness is higher than or equal to the threshold, it is considered that the antenna surface meets the cleaning requirements; if the cleanliness is lower than the threshold, it is considered that cleaning is required; for antennas whose cleanliness does not meet the preset threshold, the system automatically triggers the dust removal instruction, which can be a signal, command or notification to start the cleaning process of the antenna. By automatically judging the cleanliness of multiple antenna surfaces and triggering the dust removal instruction, the efficiency and accuracy of antenna maintenance are improved. This helps to ensure the stable performance of the antenna and reduce failures and losses caused by dust adhesion.

[0052] Calling a dust removal parameter analysis module according to the dust removal instruction, inputting the plurality of antenna surface cleanliness levels into the dust removal parameter analysis module, and obtaining a plurality of first dust removal parameters and a plurality of fine-tuning thresholds;

[0053] The dust removal parameter analysis module refers to a neural network model specifically used to analyze the cleanliness data of the antenna and calculate the appropriate dust removal parameters. The cleanliness data of multiple antenna surfaces are used as input and passed to the dust removal parameter analysis module. The dust removal parameter analysis module processes and analyzes the input cleanliness data, including comparing the cleanliness differences of different antennas, identifying areas with lower cleanliness, or determining the change trend of cleanliness, etc. According to the analysis results of the cleanliness data, multiple first dust removal parameters and multiple fine-tuning thresholds are calculated, such as the working mode, cleaning strength, cleaning time, etc. of the dust removal equipment; multiple fine-tuning thresholds refer to the range or limit of each parameter that can be adjusted when adjusting multiple first dust removal parameters, such as the adjustment range of cleaning strength, extension or shortening of cleaning time, etc. When adjusting according to the multiple humidity monitoring data, in order to be more in line with the actual environment of the antenna, it is necessary to fine-tune the multiple first dust removal parameters, and the fine-tuning range is the multiple fine-tuning thresholds. The dust removal parameter analysis module is called according to the dust removal instruction, and the appropriate dust removal parameters and fine-tuning thresholds are calculated according to the cleanliness data of the antenna surface. This will help to achieve more accurate and efficient dust removal operations.

[0054] Fine-tune and optimize the multiple first dust removal parameters according to the multiple humidity monitoring data, and constrain them according to parameter constraints during the optimization process to obtain multiple target dust removal parameters, wherein the multiple target dust removal parameters include static electricity removal parameters, first air suction parameters, first air blowing parameters, and second air suction parameters, and the parameter constraints are that the parameter values ​​of the multiple first dust removal parameters after fine-tuning must meet the multiple fine-tuning thresholds;

[0055] According to the multiple humidity monitoring data, the multiple first dust removal parameters are fine-tuned and optimized, and the humidity monitoring data is analyzed to understand the humidity conditions of the current environment, where high humidity may lead to enhanced dust adhesion and affect the dust removal effect; while low humidity may make dust easier to remove, and the dust removal parameters need to be adjusted according to the humidity conditions to optimize the dust removal effect. According to the humidity monitoring data, the multiple first dust removal parameters are fine-tuned and optimized, including adjusting the static electricity removal parameters, the first suction parameters, the first blowing parameters and the second suction parameters, wherein the static electricity removal module is activated for destatic treatment, and then the dust is removed by the cleaning head, which is the dust removal device in this application, with a structure of suction on both sides and air in the middle, adjusting the first suction parameter, the first blowing parameter and the second suction parameter. The purpose of the adjustment is to make the dust removal operation more adaptable to the current humidity environment and improve the dust removal efficiency. In the process of fine-tuning optimization, parameter constraints need to be applied, and the parameter constraints ensure that the fine-tuned parameter values ​​are within the fine-tuning threshold range set previously. After fine-tuning optimization and parameter constraints, multiple target dust removal parameters are obtained. These parameters are optimized based on the current humidity environment and the cleanliness of the antenna surface to achieve the best dust removal effect. Fine-tuning optimization is an iterative process that requires multiple adjustments based on the actual dust removal effect and environmental changes.

[0056] Optimizing and identifying the plurality of humidity monitoring data and the plurality of first dust removal parameters using a fine-tuning optimization identifier to obtain a plurality of sets of fine-tuning first dust removal parameters;

[0057] According to the parameter constraint condition, the fine-tuning first dust removal parameters that do not meet the constraint are eliminated from the plurality of fine-tuning first dust removal parameter sets to obtain a plurality of fine-tuning second dust removal parameter sets;

[0058] A fitness analysis is performed on the multiple sets of fine-tuning second dust removal parameters, and the fine-tuning second dust removal parameters corresponding to the maximum fitness values ​​are respectively used as multiple target dust removal parameters.

[0059] A plurality of humidity monitoring data and a plurality of first dust removal parameters are input into a fine-tuning optimization identifier, which is a neural network model used to identify the relationship between humidity data and dust removal parameters, and to fine-tune and optimize the dust removal parameters according to the current humidity conditions. Through the processing of the fine-tuning optimization identifier, a plurality of sets of fine-tuning first dust removal parameters can be obtained, each set being a combination of dust removal parameters optimized according to specific humidity monitoring data; the sets of fine-tuning first dust removal parameters are screened according to the parameter constraints to ensure that the adjusted parameter values ​​are within the fine-tuning threshold range to avoid adverse effects on the dust removal equipment or the antenna; for the fine-tuning first dust removal parameters that do not meet the constraints, they are removed from the set Eliminate, after screening, obtain multiple fine-tuning second dust removal parameter sets, and perform fitness analysis on multiple fine-tuning second dust removal parameter sets, that is, select experts with rich experience and professional knowledge in related fields, clarify the goals and evaluation criteria of fitness analysis, such as dust removal efficiency, energy consumption, ease of operation, equipment safety and other aspects, and provide multiple fine-tuning second dust removal parameter sets and related humidity monitoring data, antenna cleanliness and other information to the expert team. Experts independently evaluate each fine-tuning second dust removal parameter set based on the provided information and fitness evaluation criteria, such as providing feedback in the form of scoring, ranking or text description to explain the fitness of the multiple fine-tuning second dust removal parameter sets. According to the summary and analysis of the expert evaluation results, the fine-tuning second dust removal parameter set with the highest fitness is determined, and the fine-tuning second dust removal parameter corresponding to the maximum fitness value is used as multiple target dust removal parameters. These target dust removal parameters are obtained through optimization and screening under the current humidity environment, and have high fitness and practicality. Through the above method, the optimal dust removal parameter combination for a specific humidity environment is obtained, thereby improving the dust removal efficiency and effect.

[0060] Based on the multiple target dust removal parameters, the static electricity removal module, the first air suction module, the first air blowing module and the second air suction module of the dust removal device are automatically controlled to remove dust from the surfaces of the multiple high-frequency antennas respectively.

[0061] According to the design and function of the dust removal device, the static electricity removal module, the first suction module, the first blowing module and the second suction module are confirmed. The static electricity removal module is used to remove static electricity on the antenna surface. The suction module and the blowing module are the control modules of the cleaning head. The suction module is used to absorb dust, and the blowing module is used to blow away dust. According to the multiple target dust removal parameters obtained by the fine-tuning optimization identifier and fitness analysis, the corresponding control parameters are set for each module, including working voltage, working time, suction strength, blowing speed, etc. The various modules of the dust removal device are integrated with the automatic control system to ensure that the control system can accurately receive the target dust removal parameters and control the working status of each module in real time. According to the layout and cleanliness of multiple high-frequency antennas, the dust removal task is planned, the automatic control system is started, and the various modules of the dust removal device are controlled to start working according to the planned tasks and the set target dust removal parameters. The static electricity removal module works first to remove static electricity on the antenna surface; the first suction module and the second suction module work simultaneously to absorb dust; the first blowing module works to blow away the remaining dust. By automatically controlling the dust removal device based on multiple target dust removal parameters, efficient and accurate dust removal can be achieved on the surfaces of multiple high-frequency antennas. This can not only improve the performance and service life of the antenna, but also reduce the cost and difficulty of manual maintenance. This method solves the technical problem that the presence of dust in the air causes antenna signal attenuation, affects the transmission and reception of radio frequency signals, and thus reduces recognition accuracy, and achieves the technical effect of improving the intelligence level of dust removal on the surface of RFID high-frequency antennas, and improving dust removal efficiency and cleanliness.

[0062] In summary, the beneficial effects of this method include:

[0063] 1. This method reliably identifies the dust adhesion on the antenna surface and the dust gain around the antenna, then matches the corresponding dust removal parameters and fine-tunes the dust removal parameters according to the humidity environment, thereby achieving the technical effect of obtaining more accurate dust removal parameters.

[0064] 2. Improve dust removal efficiency and cleanliness by obtaining dust conditions that match the RFID high-frequency antenna and matching dust removal equipment parameters.

[0065] like Figure 3 As shown, the embodiment of the present application includes an automatic dust removal system for the surface of an RFID high-frequency antenna based on air dust removal, and the system includes:

[0066] A high-frequency antenna basic information set acquisition module 11, wherein the high-frequency antenna basic information set acquisition module 11 is used to collect basic information of multiple high-frequency antennas using a sensor component to obtain multiple high-frequency antenna basic information sets, wherein the multiple high-frequency antenna basic information sets include multiple humidity monitoring data sets and multiple antenna surface image sets;

[0067] A dust recognition module 12, the dust recognition module 12 is used to traverse the plurality of antenna surface image sets to perform dust adhesion recognition and dust gain recognition, and obtain a plurality of dust adhesion recognition results and a plurality of dust gain coefficients;

[0068] An antenna surface cleanliness determination module 13, the antenna surface cleanliness determination module 13 is used to determine multiple antenna surface cleanliness according to the multiple dust attachment identification results and the multiple dust gain coefficients;

[0069] A dust removal instruction triggering module 14, the dust removal instruction triggering module 14 is used to determine whether the surface cleanliness of the plurality of antennas meets a preset cleaning threshold, and if so, trigger a dust removal instruction;

[0070] A dust removal parameter analysis module 15, wherein the dust removal parameter analysis module 15 is used to call a dust removal parameter analysis module according to the dust removal instruction, input the plurality of antenna surface cleanliness levels into the dust removal parameter analysis module, and obtain a plurality of first dust removal parameters and a plurality of fine-tuning thresholds;

[0071] A target dust removal parameter acquisition module 16, the target dust removal parameter acquisition module 16 is used to fine-tune and optimize the multiple first dust removal parameters according to the multiple humidity monitoring data, and to constrain the multiple target dust removal parameters according to the parameter constraint conditions during the optimization process to obtain multiple target dust removal parameters, wherein the multiple target dust removal parameters include static electricity removal parameters, first air suction parameters, first air blowing parameters, and second air suction parameters, and the parameter constraint conditions are that the parameter values ​​of the multiple first dust removal parameters after fine-tuning must meet the multiple fine-tuning thresholds;

[0072] The automation control module 17 is used to automatically control the static electricity removal module, the first air suction module, the first air blowing module and the second air suction module of the dust removal device based on the multiple target dust removal parameters, so as to remove dust from the surfaces of the multiple high-frequency antennas respectively.

[0073] Furthermore, the embodiment of the present application also includes:

[0074] An antenna surface grayscale image set acquisition module, the antenna surface grayscale image set acquisition module is used to perform grayscale processing on the multiple antenna surface image sets respectively to obtain multiple antenna surface grayscale image sets;

[0075] A grayscale area image set acquisition module, wherein the grayscale area image set acquisition module is used to divide the plurality of antenna surface grayscale image sets into regions according to the structural characteristics of the plurality of high-frequency antennas, and obtain a plurality of antenna surface grayscale area image sets and a plurality of antenna surrounding grayscale area image sets, wherein the plurality of antenna surface grayscale area image sets and the plurality of antenna surrounding grayscale area image sets correspond to each other one by one;

[0076] A dust adhesion recognition result obtaining module, the dust adhesion recognition result obtaining module is used to perform dust adhesion recognition on the plurality of antenna surface grayscale area image sets to obtain a plurality of dust adhesion recognition results;

[0077] A dust gain coefficient acquisition module is used to perform dust gain analysis on the grayscale area image set around the multiple antennas to obtain multiple dust gain coefficients.

[0078] Furthermore, the embodiment of the present application also includes:

[0079] A dust attachment recognition image acquisition module, wherein the dust attachment recognition image acquisition module is used to respectively extract the images at the last moment in the plurality of antenna surface grayscale area image sets as a plurality of dust attachment recognition images;

[0080] A starting recognition point obtaining module, the starting recognition point obtaining module is used to randomly select m pixel points from the plurality of dust attachment recognition images as m starting recognition points;

[0081] a stage identification point acquisition module, the stage identification point acquisition module being used to take the m starting identification points as attachment identification starting points, and to perform random iterations in the plurality of dust attachment identification images according to a preset identification bandwidth, to obtain m stage identification points, wherein the m starting identification points correspond one to one to the m stage identification points;

[0082] a gray value difference judgment module, the gray value difference judgment module is used to judge whether the difference between the gray values ​​of the m stage identification points and the gray values ​​of the m starting identification points meets a preset difference threshold, and if so, the positions of the m stage identification points are used as m first dust attachment points;

[0083] A dust attachment module, wherein the dust attachment module is used to take the m first dust attachment points as attachment size identification starting points, perform random iterations in the multiple dust attachment identification images according to a preset identification step length, until the difference between the grayscale values ​​of the m pixel points obtained after the iteration and the grayscale values ​​of the m first dust attachment points meets the preset difference threshold, and superimpose the preset identification step length according to the number of iterations to obtain m first dust attachment sizes of the m first dust attachment points, wherein the preset identification step length is smaller than the preset identification bandwidth.

[0084] Furthermore, the embodiment of the present application also includes:

[0085] a random iteration module, wherein if no, the random iteration module is used to take the m stage recognition points as the attachment recognition starting points, perform random iterations in the multiple dust attachment recognition images according to a preset recognition bandwidth, until iterating to the edge of the multiple dust attachment recognition images, and obtain multiple dust attachment point sets and multiple dust attachment size sets;

[0086] The dust adhesion recognition result module is used to use the multiple dust adhesion point sets and the multiple dust adhesion size sets as multiple dust adhesion recognition results.

[0087] Furthermore, the embodiment of the present application also includes:

[0088] A dust suspension identification result obtaining module, the dust suspension identification result obtaining module is used to perform dust suspension identification on the grayscale area image set around the plurality of antennas to obtain a plurality of dust suspension identification results;

[0089] a dust suspension identification result inclusion module, the dust suspension identification result inclusion module being used to randomly select a first dust suspension identification result from the plurality of dust suspension identification results, wherein the first dust suspension identification result comprises a plurality of first dust suspension point sets and a plurality of first dust suspension size sets, each first dust suspension point set corresponding to a first antenna surrounding grayscale area image in the first antenna surrounding grayscale area image set;

[0090] A dust suspension coefficient set acquisition module, the dust suspension coefficient set acquisition module is used to respectively calculate the ratio of any first dust suspension size in a plurality of first dust suspension size sets to the sum of the suspension sizes in the corresponding first dust suspension size sets, to obtain a plurality of first dust suspension coefficient sets;

[0091] a dust suspension grayscale value obtaining module, the dust suspension grayscale value obtaining module being used to perform weighted calculation on grayscale values ​​corresponding to suspension points of the plurality of first dust suspension point sets using the plurality of first dust suspension coefficient sets to obtain a plurality of dust suspension grayscale values;

[0092] A dust gain coefficient obtaining module, the dust gain coefficient obtaining module is used to perform dust gain analysis according to the plurality of dust suspension gray values ​​to obtain a first dust gain coefficient;

[0093] A dust gain analysis module is used to perform dust gain analysis according to the multiple dust suspension identification results to obtain multiple dust gain coefficients.

[0094] Furthermore, the embodiment of the present application also includes:

[0095] A suspension gray value difference obtaining module, the suspension gray value difference obtaining module is used to respectively calculate the difference between two dust suspension gray values ​​of the plurality of dust suspension gray values ​​at adjacent moments to obtain a plurality of suspension gray value differences;

[0096] A linear fitting module, the linear fitting module is used to determine whether the plurality of suspension gray value differences are all positive numbers, and if so, perform linear fitting to obtain the first dust gain coefficient;

[0097] A variance calculation module is used to perform variance calculation on the multiple dust suspension grayscale values ​​to obtain the first dust gain coefficient.

[0098] Furthermore, the embodiment of the present application also includes:

[0099] An optimization recognition module, the optimization recognition module is used to optimize and recognize the plurality of humidity monitoring data and the plurality of first dust removal parameters by using a fine-tuning optimization identifier to obtain a plurality of fine-tuning first dust removal parameter sets;

[0100] a dust removal parameter elimination module, the dust removal parameter elimination module being used to eliminate the fine-tuning first dust removal parameters that do not meet the constraints from the plurality of fine-tuning first dust removal parameter sets according to the parameter constraint conditions, to obtain a plurality of fine-tuning second dust removal parameter sets;

[0101] A fitness analysis module is used to perform fitness analysis on the multiple sets of fine-tuning second dust removal parameters, and respectively use the fine-tuning second dust removal parameters corresponding to the maximum fitness values ​​as multiple target dust removal parameters.

[0102] The specific embodiment of the automatic dust removal system for the surface of the RFID high-frequency antenna based on air dust removal can be referred to the embodiment of the automatic dust removal method for the surface of the RFID high-frequency antenna based on air dust removal, which will not be repeated here. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0103] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store news data and data such as time attenuation factors. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement an automatic dust removal method for the surface of an RFID high-frequency antenna based on air dust removal.

[0104] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0105] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the method for automatic dust removal on the surface of an RFID high-frequency antenna based on air dust removal are implemented.

[0106] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for automatic dust removal on the surface of an RFID high-frequency antenna based on air dust removal are implemented.

[0107] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. Automatic dust removal method for the surface of RFID high-frequency antenna based on air dust removal, It is characterized in that The method comprises: Using the sensor assembly to collect basic information of the multiple high-frequency antennas to obtain multiple high-frequency antenna basic information sets, wherein the multiple high-frequency antenna basic information sets include multiple humidity monitoring data sets and multiple antenna surface image sets; Traversing the plurality of antenna surface image sets to perform dust adhesion recognition and dust gain recognition, and obtaining a plurality of dust adhesion recognition results and a plurality of dust gain coefficients; determining a plurality of antenna surface cleanliness levels according to the plurality of dust attachment identification results and the plurality of dust gain coefficients; Determine whether the surface cleanliness of the plurality of antennas meets a preset cleaning threshold, and if so, trigger a dust removal instruction; Calling a dust removal parameter analysis module according to the dust removal instruction, inputting the plurality of antenna surface cleanliness levels into the dust removal parameter analysis module, and obtaining a plurality of first dust removal parameters and a plurality of fine-tuning thresholds; Fine-tune and optimize the multiple first dust removal parameters according to the multiple humidity monitoring data, and constrain them according to parameter constraints during the optimization process to obtain multiple target dust removal parameters, wherein the multiple target dust removal parameters include static electricity removal parameters, first air suction parameters, first air blowing parameters, and second air suction parameters, and the parameter constraints are that the parameter values ​​of the multiple first dust removal parameters after fine-tuning must meet the multiple fine-tuning thresholds; Based on the multiple target dust removal parameters, the static electricity removal module, the first air suction module, the first air blowing module and the second air suction module of the dust removal device are automatically controlled to remove dust from the surfaces of the multiple high-frequency antennas respectively; Wherein, the method comprises: Performing grayscale processing on the plurality of antenna surface image sets respectively to obtain a plurality of antenna surface grayscale image sets; Dividing the plurality of antenna surface grayscale image sets into regions according to the structural features of the plurality of high-frequency antennas to obtain a plurality of antenna surface grayscale region image sets and a plurality of antenna surrounding grayscale region image sets, wherein the plurality of antenna surface grayscale region image sets and the plurality of antenna surrounding grayscale region image sets correspond to each other one by one; Performing dust adhesion recognition on the plurality of antenna surface grayscale area image sets to obtain a plurality of dust adhesion recognition results; Performing dust gain analysis on a set of grayscale area images around the plurality of antennas to obtain a plurality of dust gain coefficients; Wherein, performing dust gain analysis on the grayscale area image set around the plurality of antennas to obtain a plurality of dust gain coefficients includes: Performing dust suspension recognition on the grayscale area image sets around the multiple antennas to obtain multiple dust suspension recognition results; Randomly selecting a first dust suspension recognition result from the plurality of dust suspension recognition results, wherein the first dust suspension recognition result includes a plurality of first dust suspension point sets and a plurality of first dust suspension size sets, each first dust suspension point set corresponds to a first antenna surrounding grayscale area image in the first antenna surrounding grayscale area image set; Calculate the ratio of any first dust suspension size in a plurality of first dust suspension size sets to the sum of the suspension sizes in the corresponding first dust suspension size sets to obtain a plurality of first dust suspension coefficient sets; Using the multiple first dust suspension coefficient sets, weighted calculation is performed on the grayscale values ​​corresponding to the suspension points of the multiple first dust suspension point sets to obtain multiple dust suspension grayscale values; Perform dust gain analysis according to the plurality of dust suspension grayscale values ​​to obtain a first dust gain coefficient; Dust gain analysis is performed according to the multiple dust suspension identification results to obtain multiple dust gain coefficients.

2. The method according to claim 1, It is characterized in that Performing dust adhesion recognition on the plurality of antenna surface grayscale area image sets to obtain a plurality of dust adhesion recognition results, including: respectively extracting images at the last moment from the plurality of antenna surface grayscale area image sets as a plurality of dust attachment recognition images; Randomly selecting m pixel points from the plurality of dust attachment recognition images as m starting recognition points; Taking the m starting recognition points as attachment recognition starting points, performing random iterations in the multiple dust attachment recognition images according to a preset recognition bandwidth to obtain m stage recognition points, wherein the m starting recognition points correspond to the m stage recognition points one by one; Determine whether the difference between the grayscale values ​​of the m stage identification points and the grayscale values ​​of the m starting identification points meets a preset difference threshold, and if so, use the positions of the m stage identification points as m first dust attachment points; Taking the m first dust attachment points as the attachment size identification starting point, random iteration is performed in the multiple dust attachment identification images according to a preset identification step length, until the difference between the grayscale values ​​of the m pixel points obtained after the iteration and the grayscale values ​​of the m first dust attachment points meets the preset difference threshold, and the preset identification step length is superimposed according to the number of iterations to obtain m first dust attachment sizes of the m first dust attachment points, wherein the preset identification step length is smaller than the preset identification bandwidth.

3. The method according to claim 2, It is characterized in that The method comprises: If not, taking the m stage recognition points as attachment recognition starting points, performing random iterations in the multiple dust attachment recognition images according to a preset recognition bandwidth until the iteration reaches the edge of the multiple dust attachment recognition images, and obtaining multiple dust attachment point sets and multiple dust attachment size sets; The plurality of dust attachment point sets and the plurality of dust attachment size sets are taken as a plurality of dust attachment recognition results.

4. The method according to claim 1, It is characterized in that Performing dust gain analysis according to the plurality of dust suspension grayscale values ​​to obtain a first dust gain coefficient includes: respectively calculating the difference between two dust suspension grayscale values ​​of the plurality of dust suspension grayscale values ​​at adjacent moments to obtain a plurality of suspension grayscale value differences; Determine whether the plurality of suspended gray value differences are all positive numbers, and if so, perform linear fitting to obtain the first dust gain coefficient; If not, variance calculation is performed on the multiple dust suspension grayscale values ​​to obtain the first dust gain coefficient.

5. The method according to claim 1, It is characterized in that Fine-tuning and optimizing the plurality of first dust removal parameters according to the plurality of humidity monitoring data, and constraining the parameters according to the parameter constraint conditions during the optimization process to obtain a plurality of target dust removal parameters, including: Optimizing and identifying the plurality of humidity monitoring data and the plurality of first dust removal parameters using a fine-tuning optimization identifier to obtain a plurality of sets of fine-tuning first dust removal parameters; According to the parameter constraint condition, the fine-tuning first dust removal parameters that do not meet the constraint are eliminated from the plurality of fine-tuning first dust removal parameter sets to obtain a plurality of fine-tuning second dust removal parameter sets; A fitness analysis is performed on the multiple sets of fine-tuning second dust removal parameters, and the fine-tuning second dust removal parameters corresponding to the maximum fitness values ​​are respectively used as multiple target dust removal parameters.

6. RFID high frequency antenna surface automatic dust removal system based on air dust removal, It is characterized in that The system is used to perform the method according to any one of claims 1 to 5, and the system comprises: A high-frequency antenna basic information set acquisition module, the high-frequency antenna basic information set acquisition module is used to collect basic information of multiple high-frequency antennas using a sensor component to obtain multiple high-frequency antenna basic information sets, wherein the multiple high-frequency antenna basic information sets include multiple humidity monitoring data sets and multiple antenna surface image sets; A dust recognition module, the dust recognition module is used to traverse the plurality of antenna surface image sets to perform dust adhesion recognition and dust gain recognition, and obtain a plurality of dust adhesion recognition results and a plurality of dust gain coefficients; An antenna surface cleanliness determination module, the antenna surface cleanliness determination module being used to determine multiple antenna surface cleanliness according to the multiple dust attachment identification results and the multiple dust gain coefficients; A dust removal instruction triggering module, the dust removal instruction triggering module is used to determine whether the surface cleanliness of the plurality of antennas meets a preset cleaning threshold, and if so, trigger a dust removal instruction; a dust removal parameter analysis module, the dust removal parameter analysis module being used to call the dust removal parameter analysis module according to the dust removal instruction, input the plurality of antenna surface cleanliness levels into the dust removal parameter analysis module, and obtain a plurality of first dust removal parameters and a plurality of fine-tuning thresholds; A target dust removal parameter acquisition module, the target dust removal parameter acquisition module is used to fine-tune and optimize the multiple first dust removal parameters according to the multiple humidity monitoring data, and to constrain the multiple target dust removal parameters according to the parameter constraint conditions during the optimization process to obtain multiple target dust removal parameters, wherein the multiple target dust removal parameters include static electricity removal parameters, first air suction parameters, first air blowing parameters, and second air suction parameters, and the parameter constraint conditions are that the parameter values ​​of the multiple first dust removal parameters after fine-tuning must meet the multiple fine-tuning thresholds; An automation control module is used to automatically control the static electricity removal module, the first air suction module, the first air blowing module and the second air suction module of the dust removal device based on the multiple target dust removal parameters, so as to remove dust from the surfaces of the multiple high-frequency antennas respectively.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.