CN114444635A - Grain water content and temperature prediction method and system based on RFID (radio frequency identification) tag - Google Patents

Grain water content and temperature prediction method and system based on RFID (radio frequency identification) tag Download PDF

Info

Publication number
CN114444635A
CN114444635A CN202210118124.4A CN202210118124A CN114444635A CN 114444635 A CN114444635 A CN 114444635A CN 202210118124 A CN202210118124 A CN 202210118124A CN 114444635 A CN114444635 A CN 114444635A
Authority
CN
China
Prior art keywords
tag
impedance
grain
temperature
reflection coefficient
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210118124.4A
Other languages
Chinese (zh)
Other versions
CN114444635B (en
Inventor
杨卫东
沈二波
李智
朱春华
赵会义
段珊珊
李明星
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Henan University of Technology
Original Assignee
Henan University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Henan University of Technology filed Critical Henan University of Technology
Priority to CN202210118124.4A priority Critical patent/CN114444635B/en
Publication of CN114444635A publication Critical patent/CN114444635A/en
Application granted granted Critical
Publication of CN114444635B publication Critical patent/CN114444635B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
    • G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
    • G06K17/0029—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device the arrangement being specially adapted for wireless interrogation of grouped or bundled articles tagged with wireless record carriers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Abstract

The invention discloses a method and a system for predicting grain water content and temperature based on an RFID (radio frequency identification) tag, which relate to the technical field related to non-contact measurement, and specifically comprise the following steps: acquiring data: obtaining perception data; calculating the impedance of the tag: processing the sensing data by utilizing a multi-classification SVM method and a Fresnel reflection coefficient to obtain tag impedance; predicting the water content and temperature of the grain: predicting the water content of the grain by utilizing a linear regression method or a machine learning method according to the correlation between the tag impedance and the grain temperature and humidity; according to the method, the tag impedance is corrected through a multi-classification SVM method and a Fresnel reflection coefficient, so that the measured tag impedance can obtain stable measured values under different rotation angles and different distances, and the accuracy of the prediction results of the temperature and the humidity of the grains is ensured.

Description

Grain water content and temperature prediction method and system based on RFID (radio frequency identification) tag
Technical Field
The invention relates to the technical field of non-contact measurement, in particular to a grain water content and temperature prediction method and system based on an RFID tag.
Background
Grain storage is an effective way to meet future grain needs, prevent war, famine or other emergencies. Therefore, the grain storage has important significance. In particular, grain storage safety is becoming more and more important, and its key factors (i.e., temperature and humidity) have a great influence on grain storage safety. However, how to accurately and effectively measure and monitor these two factors becomes a challenging research problem between consumers and producers and at different stages of the food distribution chain.
The existing wheat moisture measurement technology can be divided into a drying method, a capacitance method, a resistance method, a microwave method and a neutron meter method. The temperature and humidity of the wheat heap are generally measured by adopting a multi-line series sensor method, and once a measuring node is damaged, the measuring node is not easy to replace. Therefore, conventional sensor-based measurement methods have failed to meet the needs of current social developments. Currently, wireless awareness is attracting widespread attention in internet of things (IOT) applications. In particular, several wireless technologies are used for contactless sensing applications, including tracking, health monitoring, and localization. In previous studies, Wi-Fi signals were used for non-contact wheat moisture and mold detection. However, Wi-Fi signals are susceptible to environmental changes (e.g., human ambulation), which greatly reduces the robustness of wheat moisture and mold detection systems.
More recently, RFID tags have been used in temperature measurement schemes. For example, a discharge period measurement scheme conforming to a standard is proposed by utilizing a volatile memory of a tag, and a mapping model between a discharge period and a temperature is established so as to improve the robustness. However, the accuracy of the system depends on the length of the discharge duration of the tag circuit, and its recognition accuracy is affected by the distance. Furthermore, the discharge duration is not linearly related to the temperature. Therefore, a passive RFID temperature sensor using a bimetal coil as a temperature sensing unit has been proposed. In addition, a system has been constructed that uses a pair of tags to counteract other environmental effects. However, this method uses many assumed parameters to calculate the tag impedance, ignoring the effect of frequency on impedance. In addition, obtaining the temperature using the phase difference is susceptible to the surrounding environment.
Although the RFID-based sensing techniques described above mostly use antenna gain or phase difference as features to sense location, material properties, health monitoring, and temperature. However, most of them are still affected by the distance and angle of the RFID system; therefore, it is an urgent problem to those skilled in the art to develop a measurement method that is not affected by the distance and angle of the RFID system.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for predicting moisture content and temperature of grain based on an RFID tag, which overcome the above disadvantages.
In order to achieve the above purpose, the invention provides the following technical scheme:
a grain water content and temperature prediction method based on an RFID tag comprises the following specific steps:
acquiring data: obtaining perception data;
calculating the impedance of the tag: processing the sensing data by utilizing a multi-classification SVM method and a Fresnel reflection coefficient to obtain tag impedance;
predicting the water content and temperature of the grain: and predicting the water content of the grain by utilizing a linear regression method or a machine learning method according to the correlation between the tag impedance and the grain temperature and humidity.
Optionally, the sensing data includes S-parameters and resonant frequency.
Optionally, the step of correcting the tag impedance by using the multi-classification SVM method includes:
simultaneously constructing a training data set and a test data set;
selecting a kernel function and parameters of a multi-classification support vector machine;
training the SVM model through samples in the training data set;
the trained SVM model is used for impedance classification with random angles.
Optionally, the kernel function is a gaussian radial basis function.
Optionally, based on the fresnel reflection coefficient, the expression of the S parameter is:
Figure BDA0003497302920000031
in the formula, gamma12Is the Fresnel reflection coefficient of the surfaces of the first medium and the second medium, i.e. the Fresnel reflection coefficient of the label, ZcRepresenting the impedance of the tag chip, ZdRepresenting the input impedance of the tag;
Figure BDA0003497302920000032
represents ZdConjugation of (1).
The expression of the reflection coefficient S11 of the first port is:
Figure BDA0003497302920000033
wherein d represents the thickness of the second medium; γ represents a propagation constant; e1rAnd E1iRespectively representing the reflected and incident waves, τ, at the interface of the first and second media1、τ2Respectively representing the transmission coefficients of the electromagnetic waves in a first medium and a second medium; gamma-shaped1、Γ2、Γ3Respectively representing Fresnel reflection coefficients of a first medium, a second medium and a third medium;
let τ be τ1τ2，C＝e-2γdThen, equation (3) is simplified as:
Figure BDA0003497302920000034
optionally, the step of correcting the tag impedance by using the fresnel reflection coefficient specifically includes:
step 21, when the gamma is1The Fresnel reflection coefficient of the air interface; tau is1The transmission coefficient from the air interface to the grain interface; gamma-shaped2The Fresnel reflection coefficient of the grain interface is obtained; tau is2The transmission coefficient from the grain interface to the air interface; epsilonairIs the dielectric constant of air; epsilonwheatThe dielectric constant of the grain is obtained according to the Fresnel reflection coefficient and the magnetic wave transmission line theory:
Figure BDA0003497302920000035
Figure BDA0003497302920000036
Figure BDA0003497302920000037
according to equations (5), (6) and (7), we obtain:
Figure BDA0003497302920000041
step 22, placing the metal plate in a target box, namely the gamma shape3-1; s is obtained by the formulas (3) and (4) after the metal plate is placed11Can be expressed as:
Figure BDA0003497302920000042
step 23, removing the metal plate; gamma may be obtained by definition1＝-Γ3According to formula (3), without metal sheet S11Can be expressed as:
Figure BDA0003497302920000043
step 24, obtaining a ternary equation system according to the expressions (8), (9) and (10):
Figure BDA0003497302920000044
step 25, solving the reflection coefficient gamma obtained by the formula (11)1And substituting the formula (2) to obtain a tag impedance value independent of the distance.
A system for recognizing moisture content and temperature of grain based on RFID tag, comprising: the system comprises a data sensing module, a data preprocessing module, a multi-classification support vector machine module and a temperature and humidity prediction module; wherein the content of the first and second substances,
the data perception module is used for reading the S parameter of the measurement target and the tag impedance;
the data preprocessing module is used for obtaining a tag impedance value irrelevant to the distance;
the multi-classification support vector machine module is used for obtaining the impedance of the tag antenna at an irrelevant angle;
and the temperature and humidity prediction module is used for predicting the temperature and the humidity of the grain by utilizing linear regression and machine learning respectively.
Optionally, the sensing module includes an RFID tag, the RFID tag is an RFID tag with a circuit chip removed, and the RFID tag is connected to the multi-class support vector machine module.
According to the technical scheme, compared with the prior art, the grain water content and temperature prediction method and system based on the RFID tag are provided, the tag impedance is corrected through a multi-classification SVM method and a Fresnel reflection coefficient, so that the measured tag impedance can obtain stable measured values under different rotation angles and different distances, and the accuracy of the prediction results of the grain temperature and humidity is guaranteed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is an architecture diagram of a prediction system of the present invention;
FIG. 2 is a schematic diagram illustrating the impedance variation of the tag according to the present invention at different distances and different angles;
FIG. 3 is a graph showing the relationship between the moisture content of wheat and the impedance (real part) of a label according to the present invention;
FIG. 4 is a graph showing the relationship between wheat temperature and tag impedance (real part) according to the present invention;
FIG. 5 is a schematic view of a wheat temperature fit curve of the present invention for different moisture contents;
FIG. 6 is a flow chart of the method of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a method and a system for predicting grain water content and temperature based on an RFID (radio frequency identification) tag, wherein a VNA (vector network analyzer) device and an RFID antenna are used for acquiring a reflected signal of the tag by taking wheat as an example; in the preprocessing module, a distance-independent algorithm and a multi-angle method based on Fresnel reflection coefficients are designed, so that distance-independent and angle-independent tag impedance is obtained. For the temperature and humidity estimation modules, linear regression and machine learning were used to predict the temperature and humidity of wheat, respectively.
Example 1
A prediction system of grain moisture content and temperature based on RFID tags, as shown in FIG. 1, comprises a data sensing module, a data preprocessing module, a multi-classification support vector machine module, and a temperature and humidity prediction module, wherein:
the data perception module is used for reading S parameters and other information of a measurement target;
the data preprocessing module is used for obtaining a tag impedance value irrelevant to the distance;
the multi-classification support vector machine module is used for obtaining the impedance of the tag antenna at an irrelevant angle;
a temperature and humidity prediction module to predict temperature and humidity of wheat using linear regression and machine learning, respectively.
The steps of a grain moisture content and temperature prediction method based on an RFID tag are shown in fig. 6, and specifically include:
step 1, acquiring data
Placing the target with wheat in a sensing area, and emitting electromagnetic waves to the periphery in the area by an RFID antenna; if the tag gets enough energy, it will reflect the signal back to the antenna, and the system can then read the S parameters and other information through the VNA device; wherein the other information comprises a resonant frequency of the tag when operating; the frequency sweep range of the VNA is set to 860MHz to 960MHz and the sensed data is sent to the PC for pre-processing.
The S parameter is called Scatter parameter, i.e. scattering parameter. The S parameter describes the frequency domain characteristic of the transmission channel, and when the serial link SI analysis is carried out, the accurate S parameter of the channel is an important link, and almost all the characteristics of the transmission channel can be seen through the S parameter.
Step 2, calculating the impedance of the label
Step 21, in order to make the system face practical application and realize any effective and accurate identification of moisture and temperature of wheat, the present embodiment provides a distance-independent impedance algorithm based on fresnel reflection coefficient and electromagnetic wave transmission line theory.
Fresnel reflection coefficient: the S parameter of the system can be described as the definition of the Fresnel reflection coefficient
Figure BDA0003497302920000071
In the formula, gamma12Expressing the Fresnel reflection coefficient of the surfaces of the media 1 and 2, i.e. the Fresnel reflection coefficient of the label, ZcRepresenting the impedance of the tag chip, ZdRepresenting the input impedance of the tag.
The reflection coefficient S11 of port 1 is defined by:
Figure BDA0003497302920000072
wherein d represents the thickness of the wheat (medium 2) in meters, γ represents the propagation constant, usually complex, E1rAnd E1iRespectively representing the reflected wave and the incident wave, τ, at the interface between the medium 1 and the medium 21、τ2Respectively represents the transmission coefficients of electromagnetic waves in the medium 1 and the medium 2; gamma-shaped1、Γ2、Γ3Respectively, the fresnel reflection coefficients of the media.
Let τ be τ1τ2，C＝e-2γd(ii) a Then equation (3) is simplified to:
Figure BDA0003497302920000073
in the formula, gamma1Representing the fresnel reflection coefficient at the interface, can be used to obtain the input impedance of the tag. From equation (4), the reflection coefficient Γ of the tag is independent of the distance from the antenna to the tag, and is only dependent on the thickness of the wheat sample. In this example, the thickness of the sample cartridge (i.e., 18cm) is known.
Therefore, the specific steps of the distance-independent impedance algorithm in this embodiment are as follows:
step 211, assuming the Fresnel reflection coefficient and transmission coefficient of the electromagnetic wave incident on the air interface air → wheat and wheat → air are respectively Γ1、τ1And Γ2、τ2. If epsilonairAnd εwheatRepresenting the dielectric constants of air and wheat, and is obtained according to the theory of electromagnetic wave transmission line in medium
Figure BDA0003497302920000074
Figure BDA0003497302920000081
Also for the transmission coefficient tau2Can obtain
Figure BDA0003497302920000082
For equations (5), (6), and (7), the following relationships can be obtained by the following equations:
Γ1 2＝τ1τ2+1 (8)；
according to gamma1And Γ2Definition of (f)1Denotes the reflection coefficient from air to wheat, and Γ2Denotes the reflection coefficient from wheat to air, hence Γ1＝-Γ2。
Step 212, placing a metal plate behind the target box; total reflection when electromagnetic waves are incident on the metal plate, i.e. Γ3Is-1. As can be seen from the formulas (3) and (4), S after the metal plate is placed11Can be expressed as:
Figure BDA0003497302920000083
step 213, remove the metal plate. According to definition Γ1＝-Γ3According to formula (2), without metal sheet S11Can be expressed as:
Figure BDA0003497302920000084
step 214, obtaining the following ternary equation system according to expressions (8), (9) and (10)
Figure BDA0003497302920000085
Wherein, S parameter S'11And S "11Can be obtained from VNA, and the reflection coefficient gamma can be obtained by solving the formula (11)1Then, the tag impedance value independent of the distance is obtained by formula (2).
Wherein, the method also comprises the following steps of:
first, the circuit chip of the RFID tag is removed, and both ports of the tag antenna are connected to the VNA device, and the S-parameter of the VNA device is observed to obtain the impedance of the tag antenna.
Generally, the input impedance refers to the equivalent impedance of the input of the circuit. The current I can be observed by adding a voltage source to the input port. The derivation process of the tag antenna input impedance is based on the S parameter, which is defined as follows:
Figure BDA0003497302920000091
wherein S is11And S21Respectively representing the reflection coefficient of port 1 and the transmission coefficient from port 1 to port 2, S11And S21Readable from a vector network analyzer, Z0Is the characteristic impedance of the transmission line, which in this embodiment is 50 (ohms). Tag antenna impedance Zd0Can be obtained from equation (1).
And verifying the sensitivity of the tag antenna to the wheat temperature and humidity through the relevance of the impedance of the tag antenna and the wheat temperature and humidity.
Step 22, tag impedance regardless of angle
For the wheat moisture and temperature sensing system, it is not practical to require that the target to be measured is always placed at the same position or angle. In order to make the system more practical, the influence of placing the object to be measured at different angles is reduced according to a multi-angle method.
Two steps are used to solve:
1) a circularly polarized antenna: antenna polarization may describe the spatial direction of the antenna radiation electromagnetic wave vector. It regards the spatial direction of the electric field vector as the polarization direction of the electromagnetic wave radiated by the antenna. Another characteristic of an antenna is the direction angle, which determines the direction in which electromagnetic waves are scattered. Therefore, the antenna polarization with a large directional angle can well reduce the directional sensitivity of the tag. The circularly polarized antenna deployed by the system has a 65-degree direction, so that the influence caused by multiple angles is reduced.
2) Multi-classification support vector machine: the idea of sensing the temperature and the humidity of the label is to map the impedance of the label to the moisture and the temperature of the wheat. Therefore, it is critical to obtain a stable tag impedance value. However, in reality the accuracy of the impedance values is affected by the angle at which the tag is placed. Therefore, a multi-classification SVM method is used to obtain stable impedance, and the steps are as follows:
step 221, measuring to obtain tag impedance values of-90 degrees to +90 degrees (impedance values are recorded every 5 degrees), constructing a data set, and normalizing the data to be in a range of [0, 1 ];
step 222, establishing a training and testing data set, and simultaneously constructing and randomly extracting; taking the impedance value corresponding to the label at 0 degrees as a training target;
step 223, selecting kernel functions and parameters of the multi-classification support vector machine. In the present embodiment, a gaussian Radial Basis Function (RBF) is used as a kernel function;
224, training the SVM model by using the wheat samples in the training data set, wherein the LIBSVM tool box is used for realizing multi-angle impedance classification;
the trained models in step 225, step 224 may be used for classification of new impedances with random angles.
Step 3, predicting the temperature and the humidity
Measuring the change condition of the electronic tag impedance value of the sample of the wheat in the temperature change process and fitting by utilizing a linear regression mode to obtain a fitting curve; the relation between the real part and the imaginary part of the impedance of the label and the temperature and the humidity can be obtained according to the fitting curve; thus, the temperature and humidity of the wheat are predicted.
Example 2
The equipment used in this example: a sample box (dimensions 31.5cm x 18cm), a passive RFID tag (Alien 9640 to Higgs 3 chip), an RFID reader antenna (Laird 2S 9028 PCR), a vector network analyzer (tack TTR506A, power 10dB), a tablet computer and a metal plate (copper, 1 mm). The label is attached to the wheat sample box, and the sample box is located in the sensing area. The reading antenna is connected to a VNA device that can send and receive electromagnetic waves. The measurement signal can be displayed on the tablet computer. In addition, a total reflection experiment was also performed using the metal plate.
Measurements of different samples were performed in a chamber with a temperature of 20 ℃. Rotating the wheat box with the label from-90 degrees to +90 degrees, then recording the impedance value of the label once every 5 degrees, and setting the sweep frequency range to 860MHz to 960 MHz. Verification of the "distance independent" algorithm was performed over a 100cm range, 2cm each time, and the value of the tag impedance was recorded, ranging from 3cm to 100 cm.
From the above values, fig. 2 can be obtained, in fig. 2, it can be seen that the tag impedance remains constant at different distances and remains around 86 ohms. It will fluctuate only if the distance exceeds 80 cm. This means that when the distance is greater than 80cm, the system becomes unstable. Fig. 2 also shows the change of the impedance of the tag at different rotation angles. It can be seen that there are more crossover points for the impedance values for different water cut as the angle of rotation increases. Nevertheless, the system is able to achieve 98.6% accuracy over a distance of 80cm, with a rotation angle in the range-30 ° to +30 °.
When the sample to be measured was wheat having moisture contents of 7.7%, 9.5%, 10.6%, 14.0%, 16.0%, 17.2%, respectively, the room temperature was 20 ℃. The resonance frequency was found to be 942.5 MHz. The plot of the tag impedance and moisture content is shown in fig. 3. It can be seen that the tag impedance (real part) increases with increasing water content.
Freezing wheat with water content of 14.0% in refrigerator to-10 deg.C, taking out, placing in sensing region, observing the change of label impedance at room temperature with temperature rise, as shown in FIG. 4, it is easy to see that there is a good linear relationship between temperature and label impedance, wherein R2＝0.9968。
Table 1 shows the identification accuracy of the moisture content of six types of wheat rotated at different angles based on the multi-classification support vector machine method, and it can be seen that the identification accuracy reaches 100% when the rotation angle is 0 °. Table 2 shows the R of the best-fit curve2And relative error rates, where M represents different moisture content, R2Indicating the proximity between the fitted curve and the test data. Fig. 5 shows 6 wheat with different moisture contents, and the fitting curves of the temperature and the label impedance are shown, and it can be easily found that the slopes of the temperature-impedance curves with different moisture contents are similar, and the temperature is increased along with the increase of the impedance.
Table 1: accuracy rate of system for identifying moisture content of wheat at different angles
Figure BDA0003497302920000111
Table 2: fitting curve R of temperature and impedance of wheat under different moisture contents2Error rate
Figure BDA0003497302920000121
From fig. 5 and table 2, it can be concluded that the tag impedance can well represent the change of temperature (i.e., the temperature and the impedance (real part) can be well fitted by a linear function), so that the temperature and the humidity of the grain can be predicted by using linear regression and machine learning, respectively, and the accuracy of the prediction result is ensured.
In the embodiment, firstly, the temperature and humidity sensing system is designed, and comprises a data basis data sensing, distance-independent tag impedance algorithm and a multi-classification SVM algorithm, so that the influence of sensing distance and sensing angle on a measurement result is respectively solved. The measurement result shows that the system can obtain higher humidity and temperature sensing precision under different rotation angles and different distances.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (8)

1. A grain water content and temperature prediction method based on an RFID tag is characterized by comprising the following specific steps:
acquiring data: obtaining perception data;
calculating the impedance of the tag: processing the sensing data by utilizing a multi-classification SVM method and a Fresnel reflection coefficient to obtain tag impedance;
predicting the water content and temperature of the grain: and predicting the water content of the grain by utilizing a linear regression method or a machine learning method according to the correlation between the tag impedance and the grain temperature and humidity.
2. The RFID tag-based grain water content and temperature prediction method according to claim 1, wherein the sensing data includes S parameter and resonant frequency.
3. The RFID tag-based grain moisture content and temperature prediction method according to claim 1, wherein the step of correcting the tag impedance by using the multi-classification SVM method comprises the steps of:
simultaneously constructing a training data set and a test data set;
selecting a kernel function and parameters of a multi-classification support vector machine;
training the SVM model through samples in the training data set;
the trained SVM model is used for impedance classification with random angles.
4. The RFID tag-based grain water content and temperature prediction method according to claim 3, wherein the kernel function is a Gaussian radial basis function.
5. The method as claimed in claim 2, wherein the expression of the S parameter based on the fresnel reflection coefficient is as follows:
Figure FDA0003497302910000011
in the formula, gamma12Is the Fresnel reflection coefficient of the surfaces of the first medium and the second medium, i.e. the Fresnel reflection coefficient of the label, ZcRepresenting the impedance of the tag chip, ZdRepresenting the input impedance of the tag;
Figure FDA0003497302910000012
represents ZdConjugation of (1);
the expression of the reflection coefficient S11 of the first port is:
Figure FDA0003497302910000021
wherein d represents the thickness of the second medium; γ represents a propagation constant; e1rAnd E1iRespectively representing the reflected and incident waves, τ, at the interface of the first and second media1、τ2Respectively representing the transmission coefficients of the electromagnetic waves in a first medium and a second medium; gamma-shaped1、Γ2、Γ3Respectively representing Fresnel reflection coefficients of a first medium, a second medium and a third medium;
let τ be τ1τ2，C＝e-2γd(ii) a Then equation (3) is simplified to:
Figure FDA0003497302910000022
6. the method for predicting the moisture content and the temperature of the grain based on the RFID tag as claimed in claim 5, wherein the step of correcting the tag impedance by using the Fresnel reflection coefficient specifically comprises the following steps:
step 21, when the gamma is1The Fresnel reflection coefficient of the air interface; tau is1The transmission coefficient from the air interface to the grain interface; gamma-shaped2The Fresnel reflection coefficient of the grain interface is obtained; tau is2The transmission coefficient from the grain interface to the air interface; epsilonairIs the dielectric constant of air; epsilonwheatThe dielectric constant of the grain is obtained according to a Fresnel reflection coefficient and a magnetic wave transmission line theory:
Figure FDA0003497302910000023
Figure FDA0003497302910000024
Figure FDA0003497302910000025
according to equations (5), (6) and (7), we obtain:
Figure FDA0003497302910000026
step 22, placing the metal plate in the target box, namely, the L shape3-1; is represented by the formula (3) andformula (4) S after placing the metal plate11Expressed as:
Figure FDA0003497302910000031
step 23, removing the metal plate; according to definition1＝-Γ3According to formula (3), without metal sheet S11Expressed as:
Figure FDA0003497302910000032
and 24, obtaining a ternary equation system according to the expressions (8), (9) and (10):
Figure FDA0003497302910000033
step 25, solving the reflection coefficient gamma obtained by the formula (11)1And substituting the formula (2) to obtain a tag impedance value independent of the distance.
7. A system for recognizing grain moisture content and temperature based on RFID tags, comprising: the system comprises a data sensing module, a data preprocessing module, a multi-classification support vector machine module and a temperature and humidity prediction module; wherein the content of the first and second substances,
the data perception module is used for reading the S parameter of the measurement target;
the data preprocessing module is used for obtaining a tag impedance value irrelevant to the distance;
the multi-classification support vector machine module is used for obtaining the impedance of the tag antenna at an irrelevant angle;
and the temperature and humidity prediction module is used for predicting the temperature and the humidity of the grain by utilizing linear regression and machine learning respectively.
8. The system for identifying the water content and the temperature of the grain based on the RFID tag as claimed in claim 7, wherein the sensing module comprises an RFID antenna and a vector network analyzer, and the RFID antenna and the vector network analyzer are used for acquiring the reflected signal of the RFID tag.
CN202210118124.4A 2022-02-08 2022-02-08 Method and system for predicting grain water content and temperature based on RFID (radio frequency identification) tag Active CN114444635B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210118124.4A CN114444635B (en) 2022-02-08 2022-02-08 Method and system for predicting grain water content and temperature based on RFID (radio frequency identification) tag

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210118124.4A CN114444635B (en) 2022-02-08 2022-02-08 Method and system for predicting grain water content and temperature based on RFID (radio frequency identification) tag

Publications (2)

Publication Number Publication Date
CN114444635A true CN114444635A (en) 2022-05-06
CN114444635B CN114444635B (en) 2023-10-17

Family

ID=81371841

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210118124.4A Active CN114444635B (en) 2022-02-08 2022-02-08 Method and system for predicting grain water content and temperature based on RFID (radio frequency identification) tag

Country Status (1)

Country Link
CN (1) CN114444635B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2580438Y (en) * 2002-04-29 2003-10-15 长春工业大学 Electrical conductivity measurer
CN102759546A (en) * 2011-04-27 2012-10-31 航天信息股份有限公司 Device and method for detecting water content of grain in on-line manner on basis of radio frequency identification (RFID)
CN102759535A (en) * 2011-04-27 2012-10-31 航天信息股份有限公司 Device and method for detecting water content of grain on basis of radio frequency identification (RFID) technology
US20140091811A1 (en) * 2012-09-28 2014-04-03 General Electric Company Systems and methods for monitoring sensors
EP2808840A1 (en) * 2013-05-28 2014-12-03 Nxp B.V. RFID- enabled plant label, plant care system, plant care method and computer program product
US9916485B1 (en) * 2015-09-09 2018-03-13 Cpg Technologies, Llc Method of managing objects using an electromagnetic guided surface waves over a terrestrial medium
CN108985430A (en) * 2018-07-03 2018-12-11 永道无线射频标签(扬州)有限公司 A kind of RFID tag with humidity function
CN110458362A (en) * 2019-08-15 2019-11-15 中储粮成都储藏研究院有限公司 Grain quality index prediction technique based on SVM supporting vector machine model
CN110751000A (en) * 2019-09-24 2020-02-04 国网湖南省电力有限公司 Verification test method and device for ultrahigh frequency RFID (radio frequency identification) tag
CN113504251A (en) * 2021-08-13 2021-10-15 河南工业大学 Grain moisture rapid detection method and system based on radio frequency signals

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2580438Y (en) * 2002-04-29 2003-10-15 长春工业大学 Electrical conductivity measurer
CN102759546A (en) * 2011-04-27 2012-10-31 航天信息股份有限公司 Device and method for detecting water content of grain in on-line manner on basis of radio frequency identification (RFID)
CN102759535A (en) * 2011-04-27 2012-10-31 航天信息股份有限公司 Device and method for detecting water content of grain on basis of radio frequency identification (RFID) technology
US20140091811A1 (en) * 2012-09-28 2014-04-03 General Electric Company Systems and methods for monitoring sensors
EP2808840A1 (en) * 2013-05-28 2014-12-03 Nxp B.V. RFID- enabled plant label, plant care system, plant care method and computer program product
US9916485B1 (en) * 2015-09-09 2018-03-13 Cpg Technologies, Llc Method of managing objects using an electromagnetic guided surface waves over a terrestrial medium
CN108985430A (en) * 2018-07-03 2018-12-11 永道无线射频标签(扬州)有限公司 A kind of RFID tag with humidity function
CN110458362A (en) * 2019-08-15 2019-11-15 中储粮成都储藏研究院有限公司 Grain quality index prediction technique based on SVM supporting vector machine model
CN110751000A (en) * 2019-09-24 2020-02-04 国网湖南省电力有限公司 Verification test method and device for ultrahigh frequency RFID (radio frequency identification) tag
CN113504251A (en) * 2021-08-13 2021-10-15 河南工业大学 Grain moisture rapid detection method and system based on radio frequency signals

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
WEIDONG YANG.ETC: "Multi-Class Wheat Moisture Detection with 5GHz Wi-Fi: A Deep LSTM Approach", WEB OF SCIENCE *
万志强;杨磊;张晴晴;王晨: "几种常见粮食水分检测方法的分析与比较", 绿色科技, no. 14 *
李俊林;张元;廉飞宇: "微波检测储粮水分技术的研究", 粮油加工, no. 09 *

Also Published As

Publication number Publication date
CN114444635B (en) 2023-10-17

Similar Documents

Publication Publication Date Title
Fathi et al. Potential chipless RFID sensors for food packaging applications: A review
Bhattacharyya et al. RFID tag antenna based temperature sensing in the frequency domain
US11586872B2 (en) Metal fastener with embedded RFID tag and method of production
US7154283B1 (en) Method of determining performance of RFID devices
Zuo et al. RFID-based sensing in smart packaging for food applications: A review
Ennasar et al. Design and characterization of a broadband flexible polyimide RFID tag sensor for NaCl and sugar detection
Sharif et al. Inkjet‐printed UHF RFID tag based system for salinity and sugar detection
CN102759535B (en) Device and method for detecting water content of grain on basis of radio frequency identification (RFID) technology
Görtschacher et al. UHF RFID sensor system using tag signal patterns: Prototype system
Costa et al. Wireless detection of water level by using spiral resonators operating in sub-GHz range
Ahmadihaji et al. From chip-based to chipless rfid sensors: a review
CN114444635B (en) Method and system for predicting grain water content and temperature based on RFID (radio frequency identification) tag
Hasani et al. A novel enhanced-performance flexible RFID-enabled embroidered wireless integrated module for sensing applications
CN113504251A (en) Grain moisture rapid detection method and system based on radio frequency signals
CN110018351B (en) Non-contact antenna impedance measuring method and system
Barahona et al. Decoding of multiple same-coded in-line placed chipless RFID tags
US10929741B2 (en) Cross-registration for unclonable chipless RFID tags
de Alencar et al. Practical performance comparison of 1-D and 2-D decoding methods for a chipless RFID system in a real environment
Kapse et al. A non-invasive method for detection of freshness of packaged milk
Shen et al. TagSense: Robust wheat moisture and temperature sensing using a passive RFID tag
Radhakrishna et al. Design of A 20-Bit Chipless RFID Tag Utilizing Multiple Resonators in UWB Frequency Range
Jeong et al. A machine learning approach-based chipless RFID system for robust detection in real-world implementations
Shen et al. TagSense: Robust Wheat Moisture and Temperature Sensing Using RFID
Lu et al. Measurement method for RFID tags group sensitivity based on reading distance
Ouyang et al. Small conformal UHF RFID tag antenna for labelling fruits

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant