Temperature sensor radio frequency antenna adjusting method and system

Abstract

The invention relates to the technical field of temperature sensor radio frequency antennas, in particular to a temperature sensor radio frequency antenna adjusting method and system, and the method comprises the steps: determining the structure of a radio frequency antenna through building a learning model according to the installation scene of the radio frequency antenna and the polarization characteristics of a radio frequency temperature sensor; and the transmitting power and the antenna gain of the radio frequency antenna are adjusted according to requirements, so that the radio frequency antenna can adaptively adjust the transmitting power and the polarization mode under different application scenes and requirements, and the applicability is higher.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature sensor radio frequency antennas, and in particular to a temperature sensor radio frequency antenna adjustment method and system. Background Art

[0002] Adjusting the RF antenna can ensure that the RFID temperature sensor can receive a stable and strong enough RF signal. The increase in signal strength helps ensure accurate data transmission and avoids data loss or errors caused by signal attenuation or interruption. At the same time, by adjusting the RF antenna, the operating frequency and range of the RFID temperature sensor can be optimized to adapt it to different application scenarios and needs. Adjusting the RF antenna can also help optimize the energy efficiency of the RFID temperature sensor. By reasonably adjusting the parameters and performance of the antenna, the energy consumption of the sensor can be reduced, its service life can be extended, and the impact on the environment can be reduced. However, the commonly used RF antennas cannot be adaptively adjusted when the demand changes, and their applicability is poor. Summary of the invention

[0003] In view of the shortcomings of the prior art described above, an object of the present invention is to provide a temperature sensor RF antenna adjustment method and system, which is used to solve the problem that the RF antenna in the prior art cannot be adaptively adjusted when the application scenario and requirements change, and has poor applicability.

[0004] To achieve the above-mentioned object and other related objects, the present invention provides a method for adjusting a temperature sensor radio frequency antenna, the method comprising:

[0005] Collecting the absorbed power and communication frequency of the radio frequency temperature sensor, performing data mining on the absorbed power and the communication frequency, and obtaining potential laws and basic characteristics of the data;

[0006] Establishing a learning model based on the historical data of the radio frequency temperature sensor, and optimizing the learning model to improve the accuracy and reliability of the learning model prediction;

[0007] Determining the structure of the radio frequency antenna according to the installation scenario of the radio frequency antenna and the polarization characteristics of the radio frequency temperature sensor;

[0008] The transmission power and antenna gain of the radio frequency antenna are adjusted to optimize the effective omnidirectional radiated power of the radio frequency antenna.

[0009] Optionally, the step of performing data mining on the absorbed power and the communication frequency to obtain potential rules and basic characteristics of the data includes:

[0010] Preprocessing the data of the absorbed power and the communication frequency to obtain basic characteristics of the data;

[0011] Performing cluster analysis to determine the distribution characteristics of the absorbed power and the communication frequency, and obtaining the potential rules of the data;

[0012] Association rule mining is performed, support and confidence thresholds are set to screen strong association rules, and an association rule algorithm is applied to mine association rules between the absorption power and the communication frequency.

[0013] Optionally, the step of preprocessing the data of the absorbed power and the communication frequency to obtain basic characteristics of the data includes:

[0014] Perform data cleaning to remove duplicate, erroneous or abnormal data information;

[0015] Normalize the data to eliminate the influence of different dimensions and units on the data and normalize the data;

[0016] Feature extraction is performed to extract basic features of the absorbed power and the communication frequency according to the required conditions.

[0017] Optionally, the step of performing cluster analysis to determine the distribution characteristics of the absorbed power and the communication frequency to obtain the potential regularity of the data includes:

[0018] Determine a clustering algorithm, wherein the clustering algorithm is K-means, hierarchical clustering or DBSCAN;

[0019] Determine the number of clusters and determine the optimal number of clusters by the elbow rule or silhouette coefficient method;

[0020] Performing clustering, applying the clustering algorithm to cluster the absorbed power and the communication frequency;

[0021] The distribution characteristics of the absorbed power and the communication frequency in different clusters are analyzed to obtain the underlying laws and patterns of the data.

[0022] Optionally, the learning model is a neural network learning model, and the method of optimizing the learning model is to optimize it using a particle swarm optimization algorithm or a genetic algorithm.

[0023] Optionally, the step of optimizing using a particle swarm optimization algorithm includes:

[0024] Perform weight optimization and find the optimal weight value by simulating the flight and velocity update process of particles in the search space;

[0025] Regularization term optimization, adjusting the regularization term parameters in the neural network to control the complexity of the model and prevent overfitting;

[0026] Perform activation function optimization, optimize the activation function type and parameters of the neural network, and improve the nonlinear fitting ability of the model;

[0027] The step of optimizing by using genetic algorithm comprises:

[0028] Perform weight optimization by encoding the weights of the neural network as chromosomes of the genetic algorithm, and then use the selection, crossover and mutation operations of the genetic algorithm to search for the optimal weight combination;

[0029] Perform structural optimization by encoding the number of neural network layers, number of neurons and other structural parameters as chromosomes, and use genetic algorithms to search for the optimal network structure;

[0030] Perform learning rule optimization to optimize the learning rules of the neural network to accelerate the training process of the neural network and improve the convergence speed and accuracy.

[0031] The present invention also provides a temperature sensor radio frequency antenna adjustment system, the system comprising:

[0032] A big data collection and analysis module is used to collect the absorption power and communication frequency of the radio frequency temperature sensor, perform data mining on the absorption power and the communication frequency, and obtain the potential laws and basic characteristics of the data;

[0033] A network model building module, used to build a neural network learning model based on the historical data of the radio frequency temperature sensor, and optimize the neural network learning model through a particle swarm optimization algorithm or a genetic algorithm to improve the accuracy and reliability of the prediction of the neural network learning model;

[0034] An antenna structure determination module, used to determine the structure of the radio frequency antenna according to the installation scenario of the radio frequency antenna and the polarization characteristics of the radio frequency temperature sensor, to ensure that the polarization mode of the radio frequency antenna matches that of the radio frequency temperature sensor;

[0035] The radiation power optimization module is used to adjust the transmission power and antenna gain of the radio frequency antenna, optimize the effective omnidirectional radiation power of the radio frequency antenna, and increase the absorption power of the radio frequency temperature sensor.

[0036] Optionally, the big data collection and analysis module includes:

[0037] A basic feature determination unit, used for preprocessing the absorbed power and the communication frequency data to obtain basic features of the data;

[0038] A potential law determination unit, used for performing cluster analysis, determining the distribution characteristics of the absorption power and the communication frequency, and obtaining the potential law of the data;

[0039] The association rule mining unit is used to perform association rule mining, set support and confidence thresholds, screen strong association rules, apply association rule algorithms, mine association rules between the absorption power and the communication frequency, and obtain mutual influence and dependency between the absorption power and the communication frequency.

[0040] Optionally, the basic feature determination unit includes:

[0041] The data cleaning subunit is used to clean the data and remove duplicate, erroneous or abnormal data information;

[0042] The normalization subunit is used to normalize the data, eliminate the influence of different dimensions and units on the data, and normalize the data;

[0043] The feature extraction subunit is used to perform feature extraction and extract the basic features of the absorption power and the communication frequency according to the required conditions.

[0044] Optionally, the potential rule determination unit includes:

[0045] A clustering algorithm subunit, used to determine a clustering algorithm, wherein the clustering algorithm is K-means, hierarchical clustering or DBSCAN;

[0046] The cluster number subunit is used to determine the number of clusters and determine the optimal number of clusters by the elbow rule or the silhouette coefficient method;

[0047] A clustering execution subunit, used to execute clustering, and apply the clustering algorithm to cluster the absorbed power and the communication frequency;

[0048] The distribution characteristics subunit is used to analyze the distribution characteristics of the absorbed power and the communication frequency in different clusters to obtain the potential laws and patterns of the data.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] By establishing a learning model, the structure of the RF antenna is determined according to the installation scenario of the RF antenna and the polarization characteristics of the RF temperature sensor, and the transmission power and antenna gain of the RF antenna are adjusted as needed. This allows the RF antenna to adaptively adjust the transmission power and polarization mode in different application scenarios and requirements, making it more applicable. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flow chart of a method for adjusting a temperature sensor radio frequency antenna according to an embodiment of the present invention;

[0052] Figure 2is a flow chart of performing data mining on absorbed power and communication frequency in one embodiment of the present invention;

[0053] Figure 3 is a flow chart of data preprocessing of absorbed power and communication frequency in one embodiment of the present invention;

[0054] Figure 4 is a flow chart of performing cluster analysis to determine the distribution characteristics of absorbed power and communication frequency in one embodiment of the present invention;

[0055] Figure 5 is a flow chart of optimization using a particle swarm optimization algorithm in one embodiment of the present invention;

[0056] Figure 6 is a flow chart of optimization using a genetic algorithm in one embodiment of the present invention;

[0057] Figure 7 It is a principle block diagram of a temperature sensor radio frequency antenna adjustment system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] Refer to the following Figures 1 to 7 To describe a temperature sensor RF antenna adjustment method and system of the present invention. In the description of this embodiment, it should be understood that although the various steps in the flowcharts of the various embodiments of the present invention are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least part of the steps in each embodiment may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternating with other steps or at least part of the sub-steps or stages of other steps.

[0059] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0060] In the description of the present embodiment, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0061] like Figure 1 As shown, an embodiment of the present invention provides a method for adjusting a temperature sensor radio frequency antenna, comprising:

[0062] Step S100, collecting the absorption power and communication frequency of the radio frequency temperature sensor, performing data mining on the absorption power and communication frequency, and obtaining potential laws and basic characteristics of the data.

[0063] Step S200, establish a learning model based on the historical data of the radio frequency temperature sensor, and optimize the learning model to improve the accuracy and reliability of the learning model prediction. Optionally, the learning model is a neural network learning model. The learning model can be optimized by a particle swarm optimization algorithm or a genetic algorithm.

[0064] Step S300: determining the structure of the radio frequency antenna according to the installation scenario of the radio frequency antenna and the polarization characteristics of the ultra-high frequency radio frequency temperature sensor, so as to ensure that the polarization modes of the radio frequency antenna and the temperature sensor match.

[0065] Step S400, adjusting the transmission power and antenna gain of the radio frequency antenna, optimizing the effective omnidirectional radiation power of the radio frequency antenna, and increasing the absorption power of the radio frequency temperature sensor.

[0066] In this embodiment of the present invention, by collecting the absorbed power and communication frequency of the RF temperature sensor and performing data mining on the absorbed power and communication frequency of the RF temperature sensor, the basic characteristics of the absorbed power and communication frequency can be obtained. Then, based on data mining, a traditional machine learning algorithm is used for modeling. And training is performed based on the historical data of the RF temperature sensor to establish a learning model, and by continuously adjusting the parameters of the learning model, the prediction accuracy of the learning model is continuously improved. At the same time, the learning model is optimized to improve the accuracy and reliability of the learning model prediction. In practical applications, there are many installation scenarios for RF antennas. It can be set inside the ring network cabinet, or inside the switch cabinet, box transformer and energy storage booster of a new energy project. In addition, the internal metal structure of each specification of the ring network cabinet, the switch cabinet, box transformer and energy storage booster is also different. The installation scenario of the RF antenna is different, and the structure of the corresponding RF antenna will also change. When designing the RF antenna, the installation scenario should be fully considered. For example, the shell of the ring network cabinet is usually made of high-quality cold-rolled steel plate or stainless steel, which has good corrosion resistance and aging resistance. The RF antenna structure is designed by utilizing the conductivity of these metal materials, so that the RF antenna forms electromagnetic coupling with the metal structure of the ring main unit, thereby improving the radiation efficiency of the RF antenna. The internal structure of the ring main unit is compact and the equipment layout is reasonable. When designing the RF antenna, it is necessary to consider the installation position and direction of the RF antenna to avoid electromagnetic interference with other equipment, while ensuring that the RF antenna can effectively cover the entire internal space of the ring main unit. The switch cabinet of a new energy project may contain core components such as high-voltage switchgear and transformers, and the electromagnetic environment of these components is complex. Therefore, when designing the RF antenna, it is necessary to fully consider the electromagnetic characteristics of these devices to ensure that the RF antenna can work stably in this environment. Using the metal frame or partition of the switch cabinet of the new energy project, the bracket or reflective surface of the RF antenna can be designed to improve the directivity and gain of the RF antenna, thereby increasing the absorbed power of the RF temperature sensor. The box transformer and the energy storage booster usually have a sealed metal casing, which will affect the radiation performance of the RF antenna to a certain extent. Therefore, it is necessary to design a penetrating RF antenna structure to ensure that the RF signal can penetrate the metal casing and be effectively received by the RF temperature sensor. Consider opening a special antenna window on the casing of the box-type transformer or energy storage booster, or replace part of the metal casing with a transparent electromagnetic window material without affecting the performance of the equipment, so as to improve the radiation efficiency of the RF antenna. Therefore, when the installation scenario of the RF antenna changes, in order to ensure that the polarization mode of the RF antenna matches that of the RF temperature sensor (such as horizontal polarization, vertical polarization or circular polarization), it is necessary to determine the structure of the RF antenna according to the installation scenario of the RF antenna and the polarization characteristics of the RF temperature sensor. This can reduce the loss caused by polarization mismatch and improve the transmission efficiency of the RF signal.At the same time, when the demand changes, the effective isotropic radiated power (EIRP) of the RF antenna can be optimized by adjusting the transmit power and antenna gain of the antenna. Appropriate EIRP can improve the coverage and strength of the RF signal, thereby increasing the absorbed power of the RF temperature sensor. Using the above adjustment method, the RF antenna can adaptively adjust the transmit power and polarization mode to cope with different application scenarios and needs.

[0067] Optionally, the radio frequency temperature sensor is an ultra-high frequency radio frequency temperature sensor.

[0068] Furthermore, if Figure 2 As shown in FIG. 1 , the steps of performing data mining on the absorbed power and communication frequency to obtain the potential laws and basic characteristics of the data include:

[0069] Step S110, pre-processing the data of absorbed power and communication frequency to obtain basic characteristics of the data.

[0070] Step S120, performing cluster analysis to determine the distribution characteristics of the absorbed power and the communication frequency, and obtaining the potential rules of the data.

[0071] Step S130, performing association rule mining, setting support and confidence thresholds to screen strong association rules, applying association rule algorithms, mining association rules between absorbed power and communication frequency, and obtaining mutual influence and dependency between absorbed power and communication frequency.

[0072] In this embodiment of the present invention, the basic characteristics and potential laws of the data are obtained by preprocessing and clustering the data. The basic characteristics and potential laws of the data are then used to mine association rules. When mining association rules, it is necessary to set support and confidence thresholds, which are used to screen strong association rules, and then apply association rule algorithms, such as Apriori or FP-Growth algorithms, to mine the association rules between absorbed power and communication frequency. Then, the results are analyzed to analyze the mined association rules to obtain the mutual influence and dependency between absorbed power and communication frequency. Preferably, factor analysis can be performed later: by using methods such as Bartlett test and KMO test, determine whether the data is suitable for factor analysis; extract common factors, use principal component analysis or other methods to extract common factors, these factors represent the common variation between the original variables; according to the factor loading matrix and the rotated factor matrix, explain the meaning of each factor and their relationship with absorbed power and communication frequency.

[0073] Furthermore, if Figure 3 As shown, the steps of preprocessing the data of absorbed power and communication frequency to obtain the basic characteristics of the data include:

[0074] Step S111, perform data cleaning to remove duplicate, erroneous or abnormal data information.

[0075] Step S112, normalize the data to eliminate the influence of different dimensions and units on the data, and normalize the data.

[0076] Step S113, performing feature extraction, extracting basic features of the absorbed power and the communication frequency according to the required conditions.

[0077] Furthermore, if Figure 4 As shown, the steps of cluster analysis, determining the distribution characteristics of absorbed power and communication frequency, and obtaining the potential laws of the data include:

[0078] Step S121, determining a clustering algorithm, the clustering algorithm is K-means, hierarchical clustering or DBSCAN.

[0079] Step S122, determining the number of clusters, and determining the optimal number of clusters by the elbow rule or the silhouette coefficient method.

[0080] Step S123, performing clustering, applying the clustering algorithm to cluster the absorbed power and the communication frequency.

[0081] Step S124, analyzing the distribution characteristics of the absorbed power and communication frequency in different clusters to obtain the potential laws and patterns of the data.

[0082] Furthermore, if Figure 5 As shown in FIG. 1 , the steps of optimizing by using the particle swarm optimization algorithm include:

[0083] Step S211, weight optimization is performed to find the optimal weight value by simulating the flight and speed update process of particles in the search space.

[0084] Step S212, regularization term optimization, adjusting the regularization term parameters in the neural network to control the complexity of the model and prevent overfitting.

[0085] Step S213, performing activation function optimization, optimizing the activation function type and parameters of the neural network, and improving the nonlinear fitting ability of the model.

[0086] In this embodiment of the present invention, when the particle swarm optimization algorithm is applied in the optimization of the neural network model, it includes three major steps: weight optimization, regularization term optimization and activation function optimization. Weight optimization: The particle swarm optimization algorithm can also be used to optimize the weights of the neural network. Each particle represents a weight combination, and the optimal weight value is found by simulating the flight and speed update process of the particle in the search space. The particle swarm optimization algorithm has the advantages of fast convergence speed and simple parameter adjustment. Regularization term optimization: The particle swarm optimization algorithm can be used to adjust the regularization term parameters in the neural network to control the complexity of the learning model and prevent overfitting. By optimizing the regularization term parameters, the complexity of the model can be reduced while ensuring the performance of the model and the generalization ability can be improved. Activation function optimization: The particle swarm optimization algorithm can also be used to optimize the activation function type and parameters of the neural network. Different activation functions have a great influence on the performance of the model. By selecting appropriate activation functions and parameters, the nonlinear fitting ability of the learning model can be improved.

[0087] Furthermore, if Figure 6 As shown, the step of optimizing by using genetic algorithm includes:

[0088] Step S221, weight optimization is performed by encoding the weights of the neural network as chromosomes of the genetic algorithm, and then using the selection, crossover and mutation operations of the genetic algorithm to search for the optimal weight combination;

[0089] Step S222, performing structural optimization, encoding structural parameters such as the number of layers and the number of neurons of the neural network as chromosomes, and using a genetic algorithm to search for the optimal network structure;

[0090] Step S223, performing learning rule optimization, optimizing the learning rule of the neural network to accelerate the training process of the neural network and improve the convergence speed and accuracy.

[0091] In this embodiment of the present invention, when the genetic algorithm is used for optimization, three major steps are included: weight optimization, structure optimization, and learning rule optimization. Weight optimization: Genetic algorithms can be used to optimize the weights of neural networks. By encoding the weights of the neural network as chromosomes of the genetic algorithm, and then using the selection, crossover, and mutation operations of the genetic algorithm to search for the optimal weight combination. This method can effectively avoid falling into the local optimal solution and find the global optimal weight value. Structure optimization: In addition to weight optimization, genetic algorithms can also be used to optimize the structure of neural networks. By encoding structural parameters such as the number of layers and the number of neurons of the neural network as chromosomes, genetic algorithms are used to search for the optimal network structure. This helps to find the network structure that best suits a specific task and improves the performance of the model. Learning rule optimization: Genetic algorithms can also be used to optimize the learning rules of neural networks, such as parameters such as learning rate and momentum. By adjusting these parameters, the training process of the neural network can be accelerated and the convergence speed and accuracy can be improved.

[0092] like Figure 7 As shown, the present invention also provides a temperature sensor radio frequency antenna adjustment system, the system comprising:

[0093] The big data collection and analysis module 100 is used to collect the absorption power and communication frequency of the radio frequency temperature sensor, perform data mining on the absorption power and communication frequency, and obtain the potential laws and basic characteristics of the data;

[0094] A network model building module 200 is used to build a neural network learning model based on the historical data of the radio frequency temperature sensor, and optimize the neural network learning model through a particle swarm optimization algorithm or a genetic algorithm to improve the accuracy and reliability of the neural network learning model prediction;

[0095] The antenna structure determination module 300 is used to determine the structure of the RF antenna according to the installation scenario of the RF antenna and the polarization characteristics of the RF temperature sensor, so as to ensure that the polarization modes of the RF antenna and the RF temperature sensor match;

[0096] The radiation power optimization module 400 is used to adjust the transmission power and antenna gain of the radio frequency antenna, optimize the effective omnidirectional radiation power of the radio frequency antenna, and increase the absorption power of the radio frequency temperature sensor.

[0097] Furthermore, the big data collection and analysis module 100 includes:

[0098] A basic feature determination unit, used for preprocessing the absorbed power and communication frequency data to obtain the basic features of the data;

[0099] A potential law determination unit is used to perform cluster analysis, determine the distribution characteristics of absorbed power and communication frequency, and obtain the potential law of the data;

[0100] The association rule mining unit is used to mine association rules, set support and confidence thresholds, screen strong association rules, apply association rule algorithms, mine association rules between absorbed power and communication frequency, and obtain mutual influence and dependency between absorbed power and communication frequency.

[0101] Furthermore, the basic feature determination unit includes:

[0102] The data cleaning subunit is used to clean the data and remove duplicate, erroneous or abnormal data information;

[0103] The normalization subunit is used to normalize the data, eliminate the influence of different dimensions and units on the data, and normalize the data;

[0104] The feature extraction subunit is used to perform feature extraction and extract the basic features of the absorbed power and communication frequency according to the required conditions.

[0105] Furthermore, the potential rule determination unit includes:

[0106] The clustering algorithm subunit is used to determine the clustering algorithm, which can be K-means, hierarchical clustering or DBSCAN;

[0107] The cluster number subunit is used to determine the number of clusters and determine the optimal number of clusters by the elbow rule or the silhouette coefficient method;

[0108] A clustering execution subunit, used for executing clustering, applying a clustering algorithm to cluster the absorbed power and the communication frequency;

[0109] The distribution characteristics subunit is used to analyze the distribution characteristics of absorbed power and communication frequency in different clusters to obtain the underlying laws and patterns of the data.

[0110] In summary, the above adjustment system can be used to adaptively adjust the RF antenna to cope with different application scenarios and requirements.

[0111] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for adjusting a temperature sensor radio frequency antenna, characterized in that: The adjustment method comprises: Collecting the absorbed power and communication frequency of the radio frequency temperature sensor, performing data mining on the absorbed power and the communication frequency, and obtaining potential laws and basic characteristics of the data; Establishing a learning model based on the historical data of the radio frequency temperature sensor, and optimizing the learning model to improve the accuracy and reliability of the learning model prediction; Determining the structure of the radio frequency antenna according to the installation scenario of the radio frequency antenna and the polarization characteristics of the radio frequency temperature sensor; The transmission power and antenna gain of the radio frequency antenna are adjusted to optimize the effective omnidirectional radiated power of the radio frequency antenna.

2. The temperature sensor radio frequency antenna adjustment method according to claim 1, characterized in that: The step of performing data mining on the absorbed power and the communication frequency to obtain the potential laws and basic characteristics of the data includes: Preprocessing the data of the absorbed power and the communication frequency to obtain basic characteristics of the data; Performing cluster analysis to determine the distribution characteristics of the absorbed power and the communication frequency, and obtaining the potential rules of the data; Association rule mining is performed, support and confidence thresholds are set to screen strong association rules, and an association rule algorithm is applied to mine association rules between the absorption power and the communication frequency.

3. The temperature sensor radio frequency antenna adjustment method according to claim 2, characterized in that: The step of preprocessing the data of the absorbed power and the communication frequency to obtain the basic characteristics of the data includes: Perform data cleaning to remove duplicate, erroneous or abnormal data information; Normalize the data to eliminate the influence of different dimensions and units on the data and normalize the data; Feature extraction is performed to extract basic features of the absorbed power and the communication frequency according to the required conditions.

4. The temperature sensor radio frequency antenna adjustment method according to claim 2, characterized in that: The step of performing cluster analysis to determine the distribution characteristics of the absorbed power and the communication frequency and obtaining the potential regularity of the data includes: Determine a clustering algorithm, wherein the clustering algorithm is K-means, hierarchical clustering or DBSCAN; Determine the number of clusters and determine the optimal number of clusters by the elbow rule or silhouette coefficient method; Performing clustering, applying the clustering algorithm to cluster the absorbed power and the communication frequency; The distribution characteristics of the absorbed power and the communication frequency in different clusters are analyzed to obtain the underlying laws and patterns of the data.

5. The temperature sensor radio frequency antenna adjustment method according to claim 1, characterized in that: The learning model is a neural network learning model, and the method of optimizing the learning model is to use a particle swarm optimization algorithm or a genetic algorithm to optimize it.

6. The temperature sensor radio frequency antenna adjustment method according to claim 5, characterized in that: The step of optimizing by using the particle swarm optimization algorithm comprises: Perform weight optimization and find the optimal weight value by simulating the flight and velocity update process of particles in the search space; Regularization term optimization, adjusting the regularization term parameters in the neural network to control the complexity of the model and prevent overfitting; Perform activation function optimization, optimize the activation function type and parameters of the neural network, and improve the nonlinear fitting ability of the model; The step of optimizing by using genetic algorithm comprises: Perform weight optimization by encoding the weights of the neural network as chromosomes of the genetic algorithm, and then use the selection, crossover and mutation operations of the genetic algorithm to search for the optimal weight combination; Perform structural optimization by encoding the number of neural network layers, number of neurons and other structural parameters as chromosomes, and use genetic algorithms to search for the optimal network structure; Perform learning rule optimization to optimize the learning rules of the neural network to accelerate the training process of the neural network and improve the convergence speed and accuracy.

7. A temperature sensor radio frequency antenna adjustment system, characterized in that: The system comprises: A big data collection and analysis module is used to collect the absorption power and communication frequency of the radio frequency temperature sensor, perform data mining on the absorption power and the communication frequency, and obtain the potential laws and basic characteristics of the data; A network model building module, used to build a neural network learning model based on the historical data of the radio frequency temperature sensor, and optimize the neural network learning model through a particle swarm optimization algorithm or a genetic algorithm to improve the accuracy and reliability of the prediction of the neural network learning model; An antenna structure determination module, used to determine the structure of the radio frequency antenna according to the installation scenario of the radio frequency antenna and the polarization characteristics of the radio frequency temperature sensor, to ensure that the polarization mode of the radio frequency antenna matches that of the radio frequency temperature sensor; The radiation power optimization module is used to adjust the transmission power and antenna gain of the radio frequency antenna, optimize the effective omnidirectional radiation power of the radio frequency antenna, and increase the absorption power of the radio frequency temperature sensor.

8. The temperature sensor radio frequency antenna adjustment system according to claim 7, characterized in that: The big data collection and analysis module includes: A basic feature determination unit, used for preprocessing the absorbed power and the communication frequency data to obtain basic features of the data; A potential law determination unit, used for performing cluster analysis, determining the distribution characteristics of the absorption power and the communication frequency, and obtaining the potential law of the data; The association rule mining unit is used to perform association rule mining, set support and confidence thresholds, screen strong association rules, apply association rule algorithms, mine association rules between the absorption power and the communication frequency, and obtain mutual influence and dependency between the absorption power and the communication frequency.

9. The temperature sensor radio frequency antenna adjustment system according to claim 1, characterized in that: The basic feature determination unit comprises: The data cleaning subunit is used to clean the data and remove duplicate, erroneous or abnormal data information; The normalization subunit is used to normalize the data, eliminate the influence of different dimensions and units on the data, and normalize the data; The feature extraction subunit is used to perform feature extraction and extract the basic features of the absorption power and the communication frequency according to the required conditions.

10. The temperature sensor radio frequency antenna adjustment system according to claim 1, characterized in that: The potential rule determination unit comprises: A clustering algorithm subunit, used to determine a clustering algorithm, wherein the clustering algorithm is K-means, hierarchical clustering or DBSCAN; The cluster number subunit is used to determine the number of clusters and determine the optimal number of clusters by the elbow rule or the silhouette coefficient method; A clustering execution subunit, used to execute clustering, and apply the clustering algorithm to cluster the absorbed power and the communication frequency; The distribution characteristics subunit is used to analyze the distribution characteristics of the absorbed power and the communication frequency in different clusters to obtain the potential laws and patterns of the data.

Images