RFID signal completion and anti-interference method and system based on comparative learning in small-space dense storage environment

Abstract

The invention belongs to the radio frequency identification signal quality enhancement technology, and relates to an RFID signal completion and anti-interference method and system based on comparative learning in a small space dense storage environment, and the method comprises the steps: carrying out the optimization design of the automatic reading of an RFID signal, optimizing the radio frequency identification in real time according to the environment change, and achieving the self-adaptive reading of an RFID tag; rFID signals are separated and extracted, strong coupling parts in the read RFID signals are separated, and error data generated by mutual collision and coupling of the RFID signals are reduced; according to a spatial position relation between historical RFID signals and RFID tags, a contrast learning model based on a convolutional neural network is trained, so that the contrast learning model can learn modes and relation characteristics of the RFID signals, and incomplete RFID signals are complemented. According to the invention, the problem of data misreading and misreading caused by RFID signal collision in a small-space dense storage environment can be effectively solved.

Description

Technical Field

[0001] The present invention belongs to a radio frequency identification signal quality enhancement technology, and specifically relates to an RFID signal completion and anti-interference method and system based on comparative learning in a small space dense storage environment. Background Art

[0002] With the continuous development of modern logistics and warehousing management technology, smart warehousing has attracted much attention due to its high efficiency and high accuracy; as one of the key technologies in smart warehousing, radio frequency identification (RFID) technology realizes automatic identification and tracking of items through wireless communication, bringing revolutionary changes to the construction of smart warehousing. RFID tags have the advantages of wide reading range, non-contact identification, large information storage capacity, and high security, which can meet the needs of warehouse managers for material inventory, tracking, and refined management.

[0003] However, in a small space, multiple types, multiple materials, and small objects densely stored environment, the accurate reading of RFID signals will be interfered with, and the accuracy of information acquisition is still insufficient, with omissions and misreadings. In addition, outer packaging materials such as metal, tin foil, or liquid items can also cause significant interference to the accurate reading of information. Accurate reading of RFID signals in a small space and dense environment still faces the following challenges:

[0004] 1) Signal interference problem. In dense spaces, multiple RFID tags overlap with each other, causing signals to easily interfere with each other, resulting in reduced data reading accuracy and stability. Metal, tin foil, liquid, etc. will cause different degrees of reflection or attenuation of RFID signals, further exacerbating the signal interference problem.

[0005] 2) Multi-scale recognition problem. In a small space with dense storage, objects of different sizes and shapes are placed in a messy manner, which causes different angle deviations between the signal source and the read / write head, resulting in the signal being unable to be accurately read, making it difficult to accurately recognize signals at different angles in all directions.

[0006] 3) Data completion complexity: Due to factors such as the variety of tag types, uneven signal quality, and tag overlap, completing incomplete RFID data becomes particularly complex.

[0007] Existing technologies are unable to effectively address the above challenges, which affects the accuracy and reliability of RFID data acquisition.

[0008] Although some studies have attempted to solve the above problems, most of them are aimed at improving the storage environment of batch items in large warehouses. The RFID tag identification solution used in this kind of intelligent storage of bulk items is difficult to meet the needs of accurate signal reading in a small space and dense storage environment. Summary of the invention

[0009] In order to solve the problems existing in the prior art, the present invention proposes an RFID signal completion and anti-interference method and system based on comparative learning in a small space dense environment, which uses machine learning technology to perform pattern analysis and comparative learning on the collected multi-source data, enhances the signal recognition ability through pattern recognition and prediction models, completes missing signals and suppresses interference, thereby improving signal quality and reading accuracy, and effectively solves the problem of data omission and misreading caused by RFID signal collision in a small space dense storage environment, and realizes efficient management and precise tracking of small materials in small space multi-category dense storage conditions.

[0010] On the one hand, the technical solution adopted in the embodiment of the present invention is: a RFID signal completion and anti-interference method based on contrast learning in a small space dense storage environment, comprising the following steps:

[0011] S1. Optimize the design of automatic reading of RFID signals, so as to optimize radio frequency identification in real time according to environmental changes and realize adaptive reading of RFID tags;

[0012] S2, separating and extracting RFID signals, separating the strongly coupled parts of the read RFID signals, and reducing the erroneous data generated by the collision and coupling of RFID signals;

[0013] S3. According to the spatial position relationship between historical RFID signals and RFID tags, a contrastive learning model based on a convolutional neural network is trained so that the contrastive learning model can learn the pattern and relationship characteristics of RFID signals and complete the incomplete RFID signals.

[0014] Based on the same inventive concept, the RFID signal completion and anti-interference system based on comparative learning in a small space dense storage environment provided in an embodiment of the present invention includes the following units:

[0015] The reading optimization unit is used to optimize the automatic reading of RFID signals, thereby optimizing the radio frequency identification in real time according to environmental changes and realizing adaptive reading of RFID tags;

[0016] The separation and extraction unit is used to separate and extract the RFID signal, separate the strongly coupled part of the read RFID signal, and reduce the erroneous data generated by the collision and coupling of the RFID signals;

[0017] The completion unit is used to train the contrastive learning model based on the convolutional neural network according to the spatial position relationship between the historical RFID signals and the RFID tags, so that the contrastive learning model can learn the pattern and relationship characteristics of the RFID signals and complete the incomplete RFID signals.

[0018] The technical solution of the present invention adopts multi-source information fault-tolerant technology and data completion strategy as a whole, effectively overcoming the interference caused by signal overlap and improving the accuracy and reliability of RFID data reading in a small space dense storage environment. Compared with the prior art, the technical effects achieved by the present invention specifically include:

[0019] 1. Signal reading optimization design: The RFID system anti-collision module is used to manage multiple RFID tags communicating with readers at the same time to avoid signal conflicts and collisions. Its purpose is to ensure that each tag can be read accurately and quickly in a complex reading environment.

[0020] The anti-collision algorithms of existing RFID systems are mainly divided into three categories: ALOHA-based anti-collision algorithm, tree-based anti-collision algorithm and hybrid algorithm; these existing algorithms cannot adapt to the dynamic and complex changes of the environment.

[0021] The present invention proposes an RFID anti-collision optimization strategy based on MOPSO multi-objective optimization, which can optimize radio frequency identification in real time according to environmental changes and realize adaptive reading of tag data. When the environment is complex or the RFID signal is dense, the multi-objective particle swarm optimization (MOPSO) algorithm is used to intelligently process and analyze the acquired RFID data and adjust the reader radio frequency in real time.

[0022] 2. Signal separation and extraction algorithm: After the reader extracts the RFID signal, it is stored in the system's initial signal library. Due to tag overlap or signal collision, these signals contain mixed data that interfere with each other, and this part of the mixed signal needs to be separated.

[0023] Common signal separation algorithms include ICA, BSS, NMF, etc.; these algorithms can effectively separate mixed signals to a certain extent, but they usually rely on the assumption of statistical independence of mixed signals, which is not always true in practical applications. In addition, these algorithms may be sensitive to noise and outliers, resulting in poor separation results.

[0024] The present invention proposes a strong coupling relaxation decomposition technology, which uses a blind source separation (BSS) algorithm to decompose strongly coupled signals into independent signal sources, effectively solving the problem of incomplete separation in existing separation algorithms. In addition, graph theory and machine learning algorithms are further used to model RFID signals, where signals are regarded as nodes in a graph, and edges represent interactions between signals. By analyzing the correlation between signals, strongly coupled signals, i.e., signals that interfere with each other severely, are identified, and strongly coupled signals are decomposed into independent signal sources, thereby improving signal quality and readability and reducing interference between signals.

[0025] 3. Data feature learning and completion model based on contrastive learning: RFID transmits signals in the form of electromagnetic waves. Electromagnetic waves are a type of energy. Energy loss occurs during the transmission process. Therefore, there is energy loss during the transmission process of electromagnetic waves, which is also called signal attenuation. Electromagnetic waves propagate in the form of direct radiation, reflection, scattering, diffraction, etc., and will produce absorption effects when blocked by obstacles. This will cause problems such as missing and omitted signals read by the reader.

[0026] In order to solve the above-mentioned problems such as missing and omissions, the present invention trains a convolutional neural network comparative learning model to learn and complete the missing erroneous data; by collecting a large number of historical RFID data signals obtained by multiple experiments and decomposition technology, including tag reading intensity, timestamp, environmental noise, etc., and combining the spatial position relationship of RFID tags, including the distance, angle and relative position between tags, a convolutional neural network comparative learning model is trained to enable it to learn the patterns and trends in RFID data, and realize accurate completion of complex RFID signal data. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a flow chart of an RFID signal completion and anti-interference method based on comparative learning in an embodiment of the present invention;

[0028] Figure 2 1 is a flow chart of RFID anti-collision optimization reading based on MOPSO algorithm in an embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of the RFID signal completion principle in an embodiment of the present invention;

[0030] Figure 4 It is a schematic diagram of the system architecture in an application example of the present invention. DETAILED DESCRIPTION

[0031] The present invention is further described in detail below in conjunction with embodiments and drawings, but the embodiments of the present invention are not limited thereto.

[0032] Example

[0033] This embodiment provides an RFID signal completion and anti-interference method based on contrast learning in a small space dense storage environment, which is suitable for smart warehousing based on RFID technology in a small space multi-category dense storage environment, such as Figure 1 As shown, the specific implementation steps include:

[0034] S1. Optimize the design of automatic reading of RFID signals, so as to optimize radio frequency identification in real time according to environmental changes and realize adaptive reading of RFID tags.

[0035] This embodiment optimizes the design of automatic reading of RFID signals. According to the change of reading angle, the reading and writing radio frequency is adjusted through the MOPSO algorithm to minimize signal leakage.

[0036] The RFID system anti-collision module is used to manage multiple RFID tags communicating with the reader at the same time to avoid signal conflicts and collisions. Its goal is to ensure that each tag can be read accurately and quickly in a complex reading environment. This embodiment adopts an RFID anti-collision optimization strategy based on multi-objective particle swarm optimization MOPSO, which can optimize radio frequency identification in real time according to environmental changes and realize adaptive reading of RFID tags. When the RFID signal is dense, the multi-objective particle swarm optimization MOPSO algorithm is used to intelligently process and analyze the acquired RFID signal and adjust the reader radio frequency in real time.

[0037] The RFID anti-collision optimization reading process based on the MOPSO algorithm is as follows Figure 2 As shown, the specific algorithm execution process is described as follows:

[0038] S11. Define the objective function of the optimization strategy to represent the transmit power optimization reading accuracy, as shown in formula (1):

[0039] min{f 0 (y,z),f 1 (y,z),...,f m (y,z)} (1)

[0040] Among them, f 0 is the main objective function, which indicates the improvement rate of RFID signal reading accuracy; f i represents the i-th auxiliary objective function, 1≤i≤m, which represents optimizing the transmission power or frequency of the RFID tag reader to reduce signal interference and improve the data acquisition accuracy of specific types of materials.

[0041] S12. Define decision variables, including y and z:

[0042] y={y 1 ,y 2 ,...,y n},z={z 1 ,z 2 ,...,z n}(2)

[0043] Among them, y represents the configuration parameters of the RFID system in a densely packed small space, including the layout of the RFID tag reader, the angle and position of the antenna; z represents the variables related to different types of materials or storage areas, including the type of materials, tag characteristics, location in a small space and other information.

[0044] S13. Define the constraints of the decision variables, as shown in formulas (3) and (4), to ensure that the decision variables meet the necessary constraints:

[0045] g j ′(y,z)≤0,j=1,…,r(3)

[0046] h j ′(y,z)≤0,j=1,…,s(4)

[0047] S14. By performing weighted summation on the characteristic functions of the signal sources, the read RFID signal is approximately represented to achieve effective multi-source extraction of the signal. The specific expression is shown in formula (6):

[0048]

[0049] Where N represents the number of signal sources, w i is the weight of the i-th signal source, Φ i represents the characteristic function of the i-th signal source, and x represents the read RFID signal.

[0050] RFID tags are deployed on items, and the tag layout strategy needs to ensure that all storage units are covered. In this embodiment, RFID tags of type NXPucode8 / ImpimjR6 are deployed in the items in the warehouse, with a size of 50x25mm and a chip power of 10dbm. The reading head configuration method is: 4 RFID reading heads with a model of MTK6763-8 core are installed, which are installed at the entrance, exit and two corners of the warehouse respectively to ensure that the RFID reading head covers the warehouse in all directions; the reading head angle is set to 30 degrees to achieve the best reading effect. The data reading mechanism is: the system acquisition frequency is once per second, and the collection points are evenly laid out to ensure that each storage unit can be covered. The synchronization mechanism between the RFID reading head and the database adopts real-time synchronization, and the data format is unified as JSON.

[0051] S2. Separate and extract the RFID signal, separate the strongly coupled part of the read RFID signal, and reduce the erroneous data generated by the collision and coupling of RFID signals.

[0052] This embodiment specifically uses a strong coupling relaxation decomposition technology and a blind source separation (BSS) algorithm to decompose the strongly coupled part of the read RFID signal into independent signal sources, effectively solving the problem of incomplete separation in the prior art.

[0053] When separating and extracting RFID signals, this embodiment uses graph theory and machine learning algorithms to model RFID signals, treating signals as nodes and edges as interactions between signals. By analyzing the correlation between RFID signals, strongly coupled signals, i.e., signals that interfere with each other severely, are identified and decomposed into independent signal sources, thereby improving signal quality and readability and reducing interference between signals. The specific algorithm flow is as follows:

[0054] S21. Assume that the blind source separation (BSS) algorithm is independent component analysis (ICA). The objective function of the independent component analysis can be expressed as:

[0055]

[0056] Where W is the separation filter matrix, w i is the weight of the ith signal source, represents the column vector of the separation filter matrix, and S is the covariance matrix of the RFID signal. In a small space multi-category dense storage environment, this objective function is used to separate independent source signals from RFID signals and reduce interference between signals.

[0057] S22. Short-time Fourier transform (STFT) is used to extract the time-frequency characteristics of the RFID signal, and the correlation between the RFID signals is obtained based on the extracted time-frequency characteristics.

[0058] The time-frequency features are specifically expressed as follows:

[0059]

[0060] Among them, X(t,f) is the time-frequency representation of the RFID signal, x RFID (τ) is the original RFID signal, w(t-τ) is the window function, t represents the time variable, and f represents the frequency variable.

[0061] Feature extraction is used to identify the unique properties of a signal. When processing RFID signals, short-time Fourier transform can be used to extract the signal's characteristics in the time and frequency domains, which helps to identify and separate strongly coupled signals.

[0062] S3. According to the spatial position relationship between historical RFID signals and RFID tags, a contrastive learning model based on a convolutional neural network is trained so that the contrastive learning model can learn the pattern and relationship characteristics of RFID signals and complete the incomplete RFID signals.

[0063] When data is missing or missed, analyze the pattern and cause of missing data, build a prediction model (linear regression, decision tree, neural network, etc.) to estimate the possible value of the missing data; use machine learning algorithms (k-nearest neighbor, SVM support vector machine, etc.) to predict missing values ​​and use them to fill in the missing values.

[0064] In this embodiment, in order to solve the problem of missed reading of RFID signals caused by storage media such as metal and liquid, a contrastive learning model based on convolutional neural network (CNN) is used to learn and complete the missing data. By collecting a large number of historical RFID signals, including tag reading intensity, timestamp, environmental noise, etc., combined with the spatial position relationship of RFID tags, including the distance, angle and relative position between tags, the contrastive learning model based on convolutional neural network is trained to enable it to learn the pattern and relationship characteristics of RFID signals, and realize accurate completion of complex RFID signals. Figure 3 The specific execution process is as follows:

[0065] S31. In the convolutional neural network (CNN), the convolution layer performs a convolution operation by applying a series of learnable filters to the input historical RFID signal. The convolution operation is expressed as:

[0066]

[0067] Among them, f represents the input historical RFID signal, including RFID tag reading strength, timestamp, environmental noise and other information, as well as the spatial position relationship data of RFID tags, such as the distance, angle and relative position between tags. g represents the learnable convolution kernel. By adjusting the parameters of the convolution kernel, the convolutional neural network CNN can learn the patterns and relationship features in the RFID data.

[0068] S32. Reduce the spatial size of the feature map of the RFID signal through the pooling layer, thereby reducing the number of parameters and the amount of calculation.

[0069] Among them, the maximum pooling can be expressed as:

[0070] maxpooling(x)=max i ∈Nx i (10)

[0071] When processing RFID signals, the pooling operation is used to reduce the spatial size of the feature map, reduce the number of parameters and the amount of calculation. For the input feature map, the maximum value is taken as the result after pooling in the element set N in the pooling window to extract the main features of the RFID signal and reduce the data dimension. In this embodiment, a nonlinear activation function (ReLU) is introduced in the convolutional neural network to enhance the expression ability of the model, which is specifically expressed as:

[0072] ReLU(x RFID )=max(0,x) (11)

[0073] For the input x RFID , if x RfID If it is greater than 0, then output x RFID itself; if x RFID If it is less than or equal to 0, then output 0. This allows CNN to learn more complex patterns and relationship features, and improve the ability to process and analyze RFID signals.

[0074] S33. Train a contrastive learning model based on convolutional neural networks.

[0075] When training the model, the mean square error (MSE) is used as the loss function to measure the difference between the model's predicted value and the actual value. The mean square error (MSE) is specifically expressed as:

[0076]

[0077] Where n represents the number of samples. When training the model for data completion, the MSE loss function is used to measure the model prediction value. and the true value y i By minimizing the MSE loss function, the model parameters are adjusted so that the model can more accurately predict the value of the missing data.

[0078] The back-propagation algorithm is used during training to calculate the gradient of the loss function with respect to the network parameters. Specifically, the gradient of each parameter with respect to the loss function is calculated using the chain rule. Then, combined with the gradient descent algorithm, the network weights are updated according to the direction and magnitude of the gradient, gradually optimizing the model performance. The trained model can predict the value of missing data. This usually involves an autoencoder structure, where the encoder part compresses the input into a low-dimensional representation, and the decoder part reconstructs this representation into the original data. The goal is to minimize the reconstruction error, including both the encoder and decoder parts. The encoder compresses the input into a low-dimensional representation as follows:

[0079] z=Encoder(x)(13)

[0080] Among them, x is the input RFID data and z is the low-dimensional representation.

[0081] The decoder reconstructs the low-dimensional representation into the original data as follows:

[0082]

[0083] The goal is to minimize the reconstruction error, which is usually measured using MSE or other related loss functions:

[0084]

[0085] By iteratively training the autoencoder, the model can learn the patterns and relational features in the RFID signal, thereby accurately completing the RFID signal data caused by metal or liquid.

[0086] The signal completion and interference resistance method of this embodiment firstly adopts a multi-dimensional signal acquisition method when reading signals to address the problems of dense distribution of RFID tags and signal overlap in a small space dense environment, optimizes the tag attachment medium, and performs radio frequency optimization in real time according to environmental changes; secondly, the strong coupling relaxation decomposition technology and blind source separation algorithm are used to model and separate the read RFID signals to improve signal quality and readability; finally, for incomplete data, a multi-scale linkage data fusion completion method based on MOPSO multi-objective optimization and contrast learning is used to train a convolutional neural network to learn data characteristics, thereby achieving data completion of incomplete RFID signals.

[0087] After performing signal completion and anti-interference processing, this embodiment can also perform intelligent data analysis and processing on the RFID data after data completion and fault tolerance processing to provide intelligent services.

[0088] The realization of intelligent services includes functions such as automatic classification, package location, usage prediction, and expiration date management; interacting with the user interface, such as providing search, screening, statistics and other operations. Specifically including:

[0089] Data hot backup technology: implement hot backup mechanism to ensure real-time replication and backup of data;

[0090] The database backup solution is regular backup, and the backup is triggered by data changes; the data storage solution includes local storage, remote data centers, and cloud storage data centers, with storage location performance optimization and cost balance;

[0091] Breakpoint recovery mechanism: detect hardware, software failures or network anomalies and switch to data backup;

[0092] During the fault handling process, minimize service interruption time. The entire process from fault state to normal state includes data synchronization, service restart, status verification, etc.

[0093] Easy-to-expand technology: Adopt modular design to implement new functions or upgrade existing functions without rebuilding the entire system; use microservice architecture to improve the flexibility and scalability of the system.

[0094] In actual applications, a system architecture including a front-end user interface, a back-end server, a database management system, an RFID reader, a sensor network, and a communication interface can be built first. The deployment process of the smart warehouse management system is as follows: First, evaluate the existing storage facilities and determine the location suitable for deploying RFID readers and tags. Ensure that the environmental factors such as light, temperature, and humidity in the warehouse are suitable to ensure the stable operation of the RFID system. Then, according to the type and quantity of materials, select the appropriate RFID tag configuration. For example, considering the particularity of the materials, the tags need to have strong anti-interference and waterproof properties. Subsequently, RFID readers are installed and deployed at the entrance, exit, and key storage areas of the warehouse to ensure that each storage unit can be covered; the installation height and angle of the reader must be carefully designed to achieve the best reading effect. Finally, the system is integrated to integrate the RFID reader with the warehouse management system (WMS) to ensure that data can be transmitted and processed in real time. An application example after actual deployment may include the access layer, application layer, service layer, and infrastructure layer in the system architecture, such as Figure 4 shown.

[0095] The actual operation process of the intelligent warehouse management system can include the following processes:

[0096] Materials entering the warehouse: After the materials arrive at the warehouse, the RFID reader scans the label and enters the material information into the system. The system automatically calculates the storage location and places the materials in place through automated equipment.

[0097] Storage management: The system regularly takes inventory of stored materials, reads tag information through RFID readers, and compares it with the records in the system to ensure the accuracy and completeness of the materials.

[0098] Material retrieval: When materials need to be shipped out of the warehouse, the operator can query the information of the required materials through the system. The system will automatically locate the location of the materials and deliver the materials to the shipping port through automated equipment.

[0099] Material outbound: When materials are outbound, the label is scanned again by the RFID reader, the system records the outbound information, and updates the inventory data.

[0100] The expected effects of the actual intelligent warehouse management system include:

[0101] Improve efficiency: Through automated equipment and intelligent management, reduce manual operations and improve the efficiency of material warehousing and outbound delivery.

[0102] Reduce costs: reduce the cost of manual inventory and management, and reduce the waste of storage space through refined management; enhance response speed: in an emergency, the system can quickly locate the required materials, improve the unit's response speed and preparation efficiency.

[0103] Safe and reliable: Through RFID technology, real-time monitoring and tracking of materials can be achieved to reduce the risk of material loss and damage. At the same time, the system adopts strict data encryption and authority management mechanisms to ensure the safety and reliability of material information.

[0104] Data-driven decision-making: By collecting and analyzing data on material storage, warehousing, and other aspects, the system can provide detailed data reports and analysis results to help decision makers better understand the material management situation and make more reasonable decisions.

[0105] Scalability: The system adopts a modular design, and its functions can be expanded and customized according to actual needs to meet the requirements of different application scenarios.

[0106] Based on the same inventive concept, this embodiment also provides an RFID signal completion and anti-interference system based on comparative learning in a small space dense storage environment, which specifically includes the following units:

[0107] The reading optimization unit is used to optimize the automatic reading of RFID signals, thereby optimizing the radio frequency identification in real time according to environmental changes and realizing adaptive reading of RFID tags;

[0108] The separation and extraction unit is used to separate and extract the RFID signal, separate the strongly coupled part of the read RFID signal, and reduce the erroneous data generated by the collision and coupling of the RFID signals;

[0109] The completion unit is used to train the contrastive learning model based on the convolutional neural network according to the spatial position relationship between the historical RFID signals and the RFID tags, so that the contrastive learning model can learn the pattern and relationship characteristics of the RFID signals and complete the incomplete RFID signals.

[0110] The completion unit can perform data completion and fault-tolerant processing, and perform data preprocessing and data cleaning on the read RFID signals, mainly including data completion and fault-tolerant processing. Specifically, it mainly includes removing duplicate records, filling in null values, removing invalid data, consistency alignment processing, data error correction, etc.

[0111] The reading optimization unit realizes the automatic reading of material information, including the design of anti-interference algorithms to improve the reading accuracy of RFID signals. The completion unit studies data completeness strategies to complete and correct data loss or missed reading caused by signal or material interference.

[0112] The system of this embodiment can also provide intelligent data analysis and services, develop data analysis models based on artificial intelligence, and provide intelligent services such as query, early warning, reminder and knowledge discovery; the system can set up high-availability and easy-to-expand maintenance modules, study data hot backup technology and breakpoint recovery mechanism, and ensure the continuous operation and adaptive expansion of the system.

[0113] It should be noted that the system of this embodiment corresponds to the aforementioned signal completion and anti-interference method, and each unit module of the system is respectively used to implement each step of the aforementioned signal completion and anti-interference method.

[0114] In general, this embodiment adopts multi-source information fault-tolerant technology and data completion strategy to effectively overcome signal interference and improve the accuracy and reliability of RFID data reading. First, in view of the dense distribution of RFID tags and signal overlap in a small space dense environment, a multi-dimensional signal acquisition method is adopted when reading the signal, the tag attachment medium is optimized, and the radio frequency optimization is performed in real time according to environmental changes; secondly, the strong coupling relaxation decomposition technology and blind source separation algorithm are used to model and separate the read RFID signals to improve signal quality and readability; finally, for incomplete data, a multi-scale linkage data fusion completion method based on MOPSO multi-objective optimization and contrast learning is used to train the convolutional neural network to learn data characteristics, and realize data completion of incomplete RFID signals, which can effectively solve the problem of data omission and misreading caused by RFID signal collision in a small space dense storage environment.

[0115] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

Claims

1. A RFID signal completion and anti-interference method based on contrastive learning in a small space dense storage environment, characterized in that: The following steps are involved: S1. Optimize the design of automatic reading of RFID signals, so as to optimize radio frequency identification in real time according to environmental changes and realize adaptive reading of RFID tags; S2, separating and extracting RFID signals, separating the strongly coupled parts of the read RFID signals, and reducing the erroneous data generated by the collision and coupling of RFID signals; S3. According to the spatial position relationship between historical RFID signals and RFID tags, a contrastive learning model based on a convolutional neural network is trained so that the contrastive learning model can learn the pattern and relationship characteristics of RFID signals and complete the incomplete RFID signals.

2. The RFID signal complement and anti-interference method according to claim 1, characterized in that: Step S1 adopts the RFID anti-collision optimization strategy based on multi-objective particle swarm optimization MOPSO, performs real-time radio frequency identification optimization according to environmental changes, and realizes adaptive reading of RFID tags; when the RFID signal is dense, the multi-objective particle swarm optimization MOPSO algorithm is used to intelligently process and analyze the acquired RFID signal, and adjust the reading and writing radio frequency in real time.

3. The RFID signal complement and anti-interference method according to claim 2, characterized in that: Step S1 includes: S11, defining the objective function of the optimization strategy to represent the transmission power optimization reading accuracy; S12. Define decision variables, including y and z: y={y1,y2,...,u n },z={z1,z2,...,z n } Among them, y represents the configuration parameters of the RFID system in a dense and small space, including the layout of the RFID tag reader, the angle and position of the antenna; z represents the variables related to different types of materials or storage areas, including the type of materials, tag characteristics, and location information in a dense and small space; S13. Define the constraints of decision variables: S14. By performing weighted summation on the characteristic functions of the signal sources, the read RFID signals are approximately represented to achieve effective multi-source extraction of the signals: Where N represents the number of signal sources, w i is the weight of the i-th signal source, Φ o represents the characteristic function of the i-th signal source, and x represents the read RFID signal.

4. The RFID signal complement and anti-interference method according to claim 1, characterized in that: Step S2 uses a blind source separation algorithm to decompose the strongly coupled part of the read RFID signal into independent signal sources; When separating and extracting RFID signals, graph theory and machine learning algorithms are used to model RFID signals, treating signals as nodes and edges as interactions between signals. By analyzing the correlation between RFID signals, strongly coupled signals are identified and decomposed into independent signal sources.

5. The RFID signal complement and anti-interference method according to claim 4, characterized in that: Step S2 includes: S21. Assume that the blind source separation algorithm is independent component analysis, and the objective function of independent component analysis is expressed as: Where W is the separation filter matrix, w o is the weight of the ith signal source, represents the column vector of the separation filter matrix, S is the covariance matrix of the RFID signal; S22. Short-time Fourier transform is used to extract time-frequency features of RFID signals, and the correlation between RFID signals is obtained based on the extracted time-frequency features.

6. The RFID signal complement and anti-interference method according to claim 5, characterized in that: The time-frequency characteristics of RFID signals are expressed as: Among them, X(t,f) is the time-frequency representation of the RFID signal, x RFID (τ) is the original RFID signal, w(t-τ) is the window function, t represents the time variable, and f represents the frequency variable.

7. The RFID signal complement and anti-interference method according to claim 1, characterized in that: Step S3 includes: S31. In a convolutional neural network, the convolution layer performs a convolution operation by applying a series of learnable filters to the input historical RFID signal; S32, reducing the spatial size of the feature graph of the RFID signal through a pooling layer; S33. Train a contrastive learning model based on convolutional neural networks.

8. The RFID signal complement and anti-interference method according to claim 1 or 7, characterized in that: In step S3, the historical RFID signal includes tag reading strength, timestamp, and environmental noise; the spatial position relationship of the RFID tags includes the distance, angle, and relative position between the tags.

9. An RFID signal completion and anti-interference system based on contrastive learning in a small space dense storage environment, characterized in that: The following units are included: The reading optimization unit is used to optimize the automatic reading of RFID signals, thereby optimizing the radio frequency identification in real time according to environmental changes and realizing adaptive reading of RFID tags; The separation and extraction unit is used to separate and extract the RFID signal, separate the strongly coupled part of the read RFID signal, and reduce the erroneous data generated by the collision and coupling of the RFID signals; The completion unit is used to train the contrastive learning model based on the convolutional neural network according to the spatial position relationship between the historical RFID signals and the RFID tags, so that the contrastive learning model can learn the pattern and relationship characteristics of the RFID signals and complete the incomplete RFID signals.

10. The RFID signal complement and anti-interference system according to claim 9, characterized in that: The reading optimization unit adopts an RFID anti-collision optimization strategy based on multi-objective particle swarm optimization MOPSO, performs real-time radio frequency identification optimization according to environmental changes, and realizes adaptive reading of RFID tags; when the RFID signal is dense, the multi-objective particle swarm optimization MOPSO algorithm is used to intelligently process and analyze the acquired RFID signal, and adjust the reading and writing radio frequency in real time.

Images