Grain moisture monitoring method, device and equipment based on detection wave analysis and medium

Abstract

The invention discloses a grain moisture monitoring method, device and equipment based on detection wave analysis and a medium, and the method comprises the steps: controlling a driver to drive a detection radar to scan stored grains through a scanning instruction, receiving echo signals obtained through scanning, and carrying out the preprocessing of the echo signals to obtain corresponding processing signals, and performing feature extraction on the processed signal by combining the distance value and the air pressure value to obtain a corresponding signal feature, calibrating the signal feature according to the temperature value to obtain a calibration feature, and performing feature analysis to obtain a corresponding moisture monitoring value. According to the grain moisture monitoring method based on detection wave analysis, the stored grains can be scanned through the detection radar, and the echo signals are analyzed and processed to accurately obtain the moisture content in the grains, so that the moisture monitoring efficiency and reliability are greatly improved, and meanwhile, the accuracy of detecting the moisture in the grains is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of warehouse management, and in particular to a grain moisture monitoring method, device, equipment and medium based on detection wave analysis. Background Art

[0002] To facilitate grain storage, it can be piled together and placed in large granaries. Changes in grain moisture content can affect its quality, so reliable grain storage requires monitoring its moisture content. Traditional methods typically insert a probe into the grain to detect local moisture levels. However, this moisture detection method requires frequent movement of the probe, resulting in low efficiency. Furthermore, it can only detect a localized area on the grain surface. When grain is piled high, it is impossible to accurately measure the moisture content within the grain. Consequently, existing methods suffer from low grain moisture detection efficiency. Summary of the Invention

[0003] The embodiments of the present invention provide a grain moisture monitoring method, device, equipment and medium based on detection wave analysis, aiming to solve the problem of low efficiency of grain moisture detection in existing technical methods.

[0004] In a first aspect, an embodiment of the present invention provides a grain moisture monitoring method based on detection wave analysis, wherein the method is applied to a monitoring terminal, the monitoring terminal establishes a communication connection with a detection radar, a temperature sensor, an air pressure sensor, a distance sensor, and a driver, the driver is provided on a slide rail, and the distance sensor and the detection radar are both fixedly provided on the driver, the method comprising:

[0005] Sending a scanning instruction to the driver to control the driver to drive the detection radar to scan the stored grain;

[0006] receiving an echo signal obtained by scanning the detection radar, and preprocessing the echo signal according to the signal processing rule to obtain a corresponding processed signal;

[0007] Extract features from the processed signal according to preset signal feature extraction rules, the distance value detected by the distance sensor, and the air pressure value detected by the air pressure sensor to obtain corresponding signal features;

[0008] Calibrate the signal feature according to a preset feature calibration strategy and the temperature value monitored by the temperature sensor to obtain a corresponding calibration feature;

[0009] The calibration feature is analyzed according to a preset standard moisture monitoring model to obtain a corresponding moisture monitoring value.

[0010] In a second aspect, an embodiment of the present invention further provides a grain moisture monitoring device based on detection wave analysis, wherein the device is configured in a monitoring terminal, the monitoring terminal establishes a communication connection with a detection radar, a temperature sensor, an air pressure sensor, a distance sensor, and a driver, the driver is set on a slide rail, the distance sensor and the detection radar are both fixedly set on the driver, and the device is used to perform the grain moisture monitoring method based on detection wave analysis as described in the first aspect above, and the device includes:

[0011] a scanning unit, configured to send a scanning instruction to the driver to control the driver to drive the detection radar to scan the stored grain;

[0012] a signal preprocessing unit, configured to receive the echo signal obtained by scanning the detection radar, and preprocess the echo signal according to the signal processing rule to obtain a corresponding processed signal;

[0013] a feature extraction unit, configured to extract features from the processed signal according to a preset signal feature extraction rule, the distance value detected by the distance sensor, and the air pressure value detected by the air pressure sensor, to obtain corresponding signal features;

[0014] a calibration unit, configured to calibrate the signal feature according to a preset feature calibration strategy and a temperature value monitored by the temperature sensor to obtain a corresponding calibration feature;

[0015] The feature analysis unit is used to perform feature analysis on the calibration feature according to a preset standard moisture monitoring model to obtain a corresponding moisture monitoring value.

[0016] In a third aspect, an embodiment of the present invention further provides a computer device, wherein the device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0017] Memory for storing computer programs;

[0018] The processor is used to implement the steps of the grain moisture monitoring method based on detection wave analysis described in the first aspect when executing the program stored in the memory.

[0019] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the grain moisture monitoring method based on detection wave analysis as described in the first aspect above are implemented.

[0020] Embodiments of the present invention provide a method, device, equipment, and medium for monitoring grain moisture based on detection wave analysis. The method includes: controlling a driver to drive a detection radar to scan stored grain using a scanning instruction, receiving the echo signal obtained by the scan and performing preprocessing to obtain a corresponding processed signal, extracting features from the processed signal in combination with the distance value and the air pressure value to obtain corresponding signal features, calibrating the signal features according to the temperature value to obtain calibration features, and then performing feature analysis to obtain corresponding moisture monitoring values. The above-mentioned grain moisture monitoring method based on detection wave analysis can scan stored grain using the detection radar and analyze and process the echo signal to accurately obtain the moisture content within the grain, greatly improving the efficiency and reliability of moisture monitoring, while also improving the accuracy of detecting moisture within the grain. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A flow chart of a method for monitoring grain moisture based on detection wave analysis provided by an embodiment of the present invention;

[0023] Figure 2 A schematic diagram of an application scenario of a grain moisture monitoring method based on detection wave analysis provided by an embodiment of the present invention;

[0024] Figure 3 This is an application effect diagram of the grain moisture monitoring method based on detection wave analysis provided by an embodiment of the present invention;

[0025] Figure 4 Another application effect diagram of the grain moisture monitoring method based on detection wave analysis provided by an embodiment of the present invention;

[0026] Figure 5 A schematic block diagram of a grain moisture monitoring device based on detection wave analysis provided by an embodiment of the present invention;

[0027] Figure 6 It is a schematic block diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0029] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0030] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0031] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0032] The embodiment of the present invention provides a method for monitoring grain moisture based on detection wave analysis. The method is applied to a monitoring terminal, and the monitoring terminal executes a stored software program to implement the above-mentioned method for monitoring grain moisture based on detection wave analysis. Figure 2 and Figure 3As shown, the monitoring terminal 10 can be a monitor or server configured in a grain storage enterprise or institution. The monitoring terminal 10 establishes a communication connection with the detection radar 20, the temperature sensor 30, the air pressure sensor 40, the distance sensor 50, and the driver 60. The driver 60 is set on a slide rail 61, and the driver 60 can slide along the slide rail 61. The slide rail 61 can be set on the top of the grain silo. At the same time, the distance sensor 50 and the detection radar 20 are fixedly set on the driver 60. Then, when the driver 60 moves horizontally on the plane, it can drive the distance sensor 50 and the detection radar 20 to move synchronously, so as to realize vertical scanning of the grain below the detection radar 20. The detection radar 20 acquires the echo signal, the temperature sensor 30 acquires the temperature inside the granary, the pressure sensor 40 acquires the pressure inside the granary, and the distance sensor 50 detects the distance between the distance sensor 50 and the top surface of the grain during the vertical scanning process. The echo signal, temperature value, pressure value, and distance value are then transmitted to the monitoring terminal 10. The monitoring terminal 10 analyzes and processes the detection information to obtain the corresponding moisture monitoring value. The moisture monitoring value is the value obtained by monitoring the overall moisture content of the grain stored in the granary. The monitoring terminal 10 can be configured with a corresponding display screen to display the acquired moisture monitoring information on the display screen for management personnel to view. At the same time, the monitoring terminal 10 can establish a network connection with the detectors installed in multiple granaries, thereby enabling simultaneous moisture monitoring of multiple granaries through the monitoring terminal 10. The grain moisture monitoring method in the specific embodiment of the present application can be applied to granaries with circular cross-sections, rectangular cross-sections, or other cross-sectional shapes.

[0033] like Figure 1 As shown, the method includes steps S110 to S150.

[0034] S110 , sending a scanning instruction to the driver to control the driver to drive the detection radar to scan the stored grain.

[0035] Send a scanning instruction to the driver, and control the driver to drive the detection radar to scan the stored grain through the scanning instruction. Among them, the frequency of the detection radar is preferably selected as 300MHz-1GHz, so as to achieve deep penetration of the grain. At the same time, the radar signal in this frequency band is more sensitive to the moisture content of the grain and is suitable for detecting the moisture content of the grain. Preferably, the center frequency of the detection radar can be set to 500MHz, the bandwidth is 200MHz, and the detection distance resolution is about 0.3m; since a single detection radar is used, there is no need to consider the problem of mutual interference between detection radars. In order to achieve accurate detection, the power of the detection wave emitted by the detection radar can be set to 0.2-10W.

[0036] Specifically, the scanning command specifies the scanning points and the number of scans. The driver then drives the detection radar to each scanning point, performing a single scan. If the number of scans is set to 1, only one scan is performed. If the number of scans is set to multiple, the same scanning point is scanned multiple times. Data from these multiple scans is then averaged to minimize detection errors. For example, if the spacing between adjacent scanning points along the x- or y-axis is set to 0.3m, a stepper motor is configured on the driver to power the movement, controlling the driver's translational speed at 0.5-1m / s.

[0037] S120: Receive the echo signal obtained by the detection radar scanning, and pre-process the echo signal according to the signal processing rule to obtain a corresponding processed signal.

[0038] The detection wave penetrates the grain and bounces back, forming an echo signal. The detection radar detects this reflected echo signal. To improve detection accuracy, the sampling frequency of the echo signal can be set to 5-10 times the center frequency of the detection radar. The acquired echo signal can be pre-processed to obtain a processed signal that accurately reflects the moisture detection characteristics.

[0039] In a specific embodiment, step S120 includes sub-steps: filtering the echo signal according to the filtering algorithm in the signal processing rule to obtain a corresponding filtered signal; and enhancing the filtered signal according to the signal enhancement function in the signal processing rule to obtain a corresponding processed signal.

[0040] Specifically, the echo signal can be filtered by the filtering algorithm set in the signal processing rules. The filtering algorithm can be a filtering algorithm based on the Butterworth high-pass filter. The core of the filtering algorithm is to remove DC drift by attenuating low-frequency components and retaining high-frequency useful signals. The signal of each scanning point in the echo signal can be first subjected to a fast Fourier transform to convert the time domain signal into a frequency domain signal for filtering. Afterwards, the sampling frequency, cutoff frequency, order and attenuation requirements are determined. The sampling frequency is the sampling frequency when the echo signal is detected. The cutoff frequency of the high-pass filter is the "3dB attenuation point", such as the cutoff frequency f c It can be set to 0.15-0.5 times the center frequency f of the detection radar. The attenuation requirement can be set to no more than 3dB (retaining more than 90% of the energy). The order of the Butterworth filter determines the steepness of the transition band (the higher the order, the steeper the transition band, but the higher the computational complexity), which needs to be calculated using the amplitude-frequency characteristic formula:

[0041] The amplitude-frequency characteristic of the Butterworth filter is shown in formula (1):

[0042]

[0043] Where, ω=2πf (angular frequency), ω c =2πf c (3dB cut-off frequency), n is the order. For the stopband frequency f stop , must satisfy the attenuation Rs = 10log 10 [1+(ω c / ω stop ) 2n ]≥40dB (In high-pass filters, the stopband frequency is lower than the cutoff frequency, so ω is used c / ω stop ),ω stop That is, f stop The corresponding stopband angular frequency, such as setting the stopband frequency f stop The order n is calculated as 0.1 times the center frequency of the detection radar. The higher the order n, the better the filtering effect; however, the larger n is, the more computing power is required for filtering.

[0044] Computation and ω c Corresponding normalized cutoff frequency: f c / (f s / 2), where f s is the sampling frequency; and calculate the stop Corresponding normalized stopband frequency: f stop / (f s / 2). The calculated normalized cutoff frequency, normalized stopband frequency, and order n are used to configure the core parameters of the filtering algorithm. The frequency domain signal is filtered using the parameter-configured filtering algorithm to obtain a corresponding filtered signal.

[0045] The obtained filtered signal can be further enhanced by the signal enhancement function configured in the signal processing rule to obtain the corresponding processed signal. The signal enhancement function can be a function based on the wavelet transform algorithm, and the filtered signal is subjected to wavelet transform by the signal enhancement function. According to the type of grain in the granary, a suitable wavelet basis function (such as Daubechies wavelet, 3-layer decomposition) can be selected, and the filtered signal can be subjected to multi-layer wavelet decomposition to obtain coefficients of different frequency sub-bands; characteristic coefficients are screened to obtain coefficients that can reflect the effective signal characteristics for amplification processing, and noise-related coefficients are thresholded by setting soft thresholds or hard thresholds; finally, the signal is reconstructed by inverse wavelet transform and the frequency domain signal is reconverted into the corresponding time domain signal to achieve signal enhancement and obtain a processed signal corresponding to the filtered signal. The obtained processed signal can highlight the reflection signal characteristics related to the moisture detection of a specific type of grain.

[0046] S130 , performing feature extraction on the processed signal according to a preset signal feature extraction rule, the distance value detected by the distance sensor, and the air pressure value detected by the air pressure sensor to obtain corresponding signal features.

[0047] The monitoring terminal can obtain the distance value detected by the distance sensor and the pressure value detected by the pressure sensor simultaneously. The signal feature extraction rules, distance value, and pressure value are used to extract features from the processed signal obtained in the above steps, thereby obtaining signal characteristics. Among them, the signal characteristics include the reflection coefficient and dielectric constant corresponding to each scanning point. Specifically, according to the propagation law of electromagnetic waves in a medium, when the moisture content of a certain area in the medium changes, the ability to absorb electromagnetic waves also changes. The higher the moisture content in the grain, the greater the dielectric constant εr and the greater the reflection coefficient Γ. The dielectric constant and reflection coefficient of the grain can be obtained by analyzing the processed signal, thereby analyzing the moisture content of the grain.

[0048] In a specific embodiment, step S130 includes sub-steps: extracting corresponding key information from a group of signals corresponding to each distance value in the processed signal according to the extraction parameters set in the signal feature extraction rule and the distance value; parsing each key information and the corresponding distance value according to the reflection coefficient analytical expression and the air pressure value in the signal feature extraction rule to obtain the reflection coefficient corresponding to each distance value; parsing each key information and the corresponding distance value according to the dielectric constant analytical expression and the air pressure value in the signal feature extraction rule to obtain the dielectric constant corresponding to each distance value; combining the reflection coefficient and the dielectric constant of each distance value to obtain the corresponding signal feature.

[0049] Each scanning point can correspond to a distance value detected by the distance sensor, and each distance value corresponds to a set of signals of a scanning point. The corresponding key information can be extracted from each set of signals in the processed signal. Specifically, a set of time domain signals in the processed signal is as follows: Figure 4 As shown in the figure, the incident interval time can be calculated according to the distance value. The incident interval time is the interval time between the emission of the detection wave and the incident time of the detection wave (the time point when the detection wave is incident from the grain surface). The incident interval time t1 = h / c, where c is the propagation speed of the electromagnetic wave signal in vacuum (c = 3×10 8 m / s), h is the distance value; here we only need to roughly obtain the incident time interval, so the propagation speed of the electromagnetic wave signal in the air can be directly taken as a rough value of 3×10 8m / s. The corresponding incident time interval can be determined according to the incident interval time. The incident time interval is also the interval of the electromagnetic wave reflected from the grain surface in the echo signal. For example, the incident time interval can be determined to be 1.8t1-2.2t1. Figure 4 The corresponding mark is in the time domain signal, and a signal value with the highest amplitude in the corresponding set of signals is obtained as the incident signal amplitude. The corresponding rebound time point is further determined according to the extraction parameters. The electromagnetic wave signal passes through the grain and contacts the bottom of the warehouse, which will also produce a strong reflection signal, and the intensity of the reflection signal will increase sharply at this time. The extraction parameters are configured with a bottoming amplitude threshold and a bottoming slope threshold. The signal after the incident signal amplitude can be judged, and whether the slope of the signal curve between the previous moment and the current moment in the signal is greater than the bottoming slope threshold is judged. If the slope of the signal curve between the previous moment and the current moment is greater than the bottoming slope threshold, and the signal strength at the current moment is greater than the bottoming amplitude threshold, then the current moment can be used as the rebound time point (such as Figure 4 (Time t2 in the figure is the rebound time point). The highest signal value between the rebound time point and the signal after the rebound time point is obtained as the bottoming signal amplitude. By combining the incident signal amplitude, the rebound time point, and the bottoming signal amplitude as corresponding key information, each group of processed signals can be corresponding to a set of key information.

[0050] In a specific embodiment, before extracting the corresponding key information from a group of signals corresponding to each distance value in the processed signal according to the extraction parameters set in the signal feature extraction rule and the distance value, it also includes: organizing the signals located at the same scanning point in the processed signal according to the scanning point set in the scanning instruction; and associating and combining a group of signals at the same scanning point with a corresponding distance value according to the correspondence between the scanning point and the distance value.

[0051] Before obtaining key information, the signals at the same scanning point can be sorted according to the scanning point set in the scanning instruction. If the same scanning point contains multiple groups of signals, the multiple groups of signals can be averaged to obtain the signal curves corresponding to the multiple groups of signals and used as the following example: Figure 4Key information is extracted from the time domain signal shown. Each scanning point corresponds to one or more distance values. If the same scanning point is scanned multiple times, multiple distance values ​​can be obtained. Based on the correspondence between the scanning points and the distance values, the average of the multiple distance values ​​for the same scanning point is calculated, and the calculated average distance value is associated with a group of signals at the same scanning point. This association ensures that the same scanning point corresponds to a distance value (the distance value here can also be the average of multiple distance values) and a group of signals (the signal here can be the signal curve obtained by averaging multiple groups of signals at the same scanning point).

[0052] In a specific embodiment, each of the key information and the corresponding distance value is analyzed according to the reflection coefficient analytical expression in the signal feature extraction rule and the air pressure value to obtain the reflection coefficient corresponding to each of the distance values, including: calculating the ratio between the air pressure value and the standard atmospheric pressure to obtain the air pressure ratio; inputting the air pressure ratio, the signal amplitude in the key information and the corresponding distance value into the reflection coefficient analytical expression for analysis to obtain the corresponding reflection coefficient.

[0053] Further, according to the reflection coefficient analytical expression and air pressure value in the signal feature extraction rule, each of the key information and the distance value corresponding to the key information is analyzed to obtain the reflection coefficient corresponding to each distance value. Specifically, the greater the air pressure value, the greater the air density. The greater the air density, the slower the propagation speed of the electromagnetic wave and the stronger the scattering of the electromagnetic wave. The smaller the air pressure value, the faster the propagation speed of the electromagnetic wave and the weaker the scattering of the electromagnetic wave. The ratio P / P0 between the air pressure value and the standard atmospheric pressure can be calculated, where P is the air pressure value and P0 is the standard atmospheric pressure. The air pressure ratio, the signal amplitude in the key information and the corresponding distance value are further input into the reflection coefficient analytical expression to obtain the corresponding reflection coefficient. Then a distance value and the signal amplitude of a group of signals corresponding to the distance value can be correspondingly analyzed to obtain a reflection coefficient. The reflection coefficient analytical expression is shown in formula (2):

[0054]

[0055] Here, k is the basic scattering coefficient (the scattering coefficient of electromagnetic waves by air at standard atmospheric pressure), P is the air pressure, P0 is the standard atmospheric pressure, A1 is the incident signal amplitude in the signal amplitude, A2 is the transmitted signal amplitude of the detection wave (signal emission intensity), and Γ is the calculated reflection coefficient. The higher the moisture content in the grain, the greater the grain pile dielectric constant εr and the corresponding reflection coefficient Γ. The relationship between the reflection coefficient Γ and the dielectric constant εr is not linear.

[0056] In a specific embodiment, the key information and the corresponding distance value are analyzed according to the dielectric constant analytical formula in the signal feature extraction rule and the air pressure value to obtain the dielectric constant corresponding to each distance value, including: calculating the ratio between the air pressure value and the standard atmospheric pressure to obtain the air pressure ratio; calculating the interval time between the emission time of the detection wave and the echo reception time in the key information; inputting the air pressure ratio, the interval time and the corresponding distance value into the dielectric constant analytical formula for analysis to obtain the corresponding dielectric constant.

[0057] Furthermore, the interval between the emission time of the detection wave and the reception time of the echo is calculated, that is, the Figure 4 The interval between time t2 and the emission time of the detection wave; if the emission time of the detection wave is taken as the zero point, the time at time t2 can be directly obtained as the corresponding interval time. Inputting the air pressure ratio, interval time, and distance value into the dielectric constant analytical formula, the corresponding dielectric constant can be obtained analytically. Specifically, the change in the dielectric constant inside the grain directly affects the propagation speed of the electromagnetic wave inside the grain, and the increase in the moisture content of the grain will correspondingly increase the dielectric constant inside the grain. The dielectric constant analytical formula is shown in formula (3):

[0058]

[0059] Where c is the propagation speed of electromagnetic wave signals in vacuum, εr is the calculated dielectric constant of grain, L is the vertical distance between the installation position of the distance sensor and the bottom of the grain silo (since the distance sensor scans on a plane, the vertical distance between the distance sensor and the bottom of the grain silo is theoretically constant), t2 is the interval time, s p is the dielectric constant of air at pressure p. According to the principles of physics, s p It can be obtained by calculating the corresponding pressure ratio. The specific calculation formula is shown in formula (4):

[0060]

[0061] Where s0 is the dielectric constant of air at standard atmospheric pressure P0, and p is the measured air pressure value.

[0062] Each distance value can be calculated to obtain a reflection coefficient and a dielectric constant. The corresponding signal characteristics can be obtained by combining the reflection coefficient and the dielectric constant of each distance value.

[0063] S140: Calibrate the signal feature according to a preset feature calibration strategy and the temperature value monitored by the temperature sensor to obtain a corresponding calibration feature.

[0064] Furthermore, temperature changes have a certain impact on the dielectric constant and reflection coefficient of grain. To eliminate the impact of temperature changes on the measurement results, the above-mentioned signal characteristics can be calibrated using a feature calibration strategy and the actual measured temperature value, thereby obtaining a calibration feature corresponding to the signal characteristics. Specifically, the feature calibration strategy is based on the corresponding configuration of the reference temperature. By calibrating the signal characteristics, a calibration feature corresponding to the reference temperature is obtained, thereby accurately measuring the moisture content (water content) of the grain in the standard model corresponding to the reference temperature.

[0065] In a specific embodiment, step S140 includes sub-steps: inputting the temperature value into the feature calibration strategy to obtain a corresponding correction value; and calibrating the signal feature according to the correction value to obtain a calibration feature corresponding to the signal feature.

[0066] Specifically, the currently measured temperature value is input into the characteristic calibration strategy to obtain the correction value. Since the detection radar scan takes a certain amount of time, the temperature value can be continuously measured during the scanning process and the average value can be calculated for calibration, thereby further improving the accuracy of the calibration; the average value of the continuously measured temperature values ​​can be input into the above-mentioned characteristic calibration strategy. For example, the specific process of obtaining the correction value corresponding to the dielectric constant can be expressed by formula (5):

[0067] X = (T - T0) × Δε (5);

[0068] Where X is the calculated correction value, T is the currently measured temperature (or the average of continuously measured temperatures during the scan), T0 is the reference temperature (e.g., set T0 to 20°C), and Δε is the correction factor, such as Δε = -0.02. Based on these parameter settings, if T = 23.5°C, the corresponding correction value X for the dielectric constant is calculated to be -0.07.

[0069] Based on a similar principle, a correction value corresponding to the reflection coefficient can be calculated accordingly (the correction coefficient Δε corresponding to the reflection coefficient is different from the value in the above example).

[0070] The signal signature is calibrated using the correction value to obtain the corresponding calibration signature. For example, the dielectric constant of each distance value in the signal signature can be corrected using the correction value -0.07 corresponding to the dielectric constant. The original dielectric constant of each distance value is then added to the correction value to obtain the corrected dielectric constant. Based on the same principle, the reflection coefficient of each distance value in the signal signature can be added to the corresponding correction value to obtain the corrected reflection coefficient. The corrected dielectric constant and the corrected reflection coefficient are combined to form the calibrated calibration signature.

[0071] S150: Perform feature analysis on the calibration feature according to a preset standard moisture monitoring model to obtain a corresponding moisture monitoring value.

[0072] The calibration signature is analyzed using a standard moisture monitoring model corresponding to the grain type to obtain the corresponding moisture detection value. When using a standard moisture monitoring model, it is necessary to first select a model that corresponds to the grain type. The reflection coefficient and dielectric constant of each distance value in the calibration signature are analyzed to obtain a corresponding detection value. Each distance value corresponds to a scanning point, and this detection value can be used to reflect the moisture content of a scanning point in the grain.

[0073] In specific applications, a standard moisture monitoring model corresponding to each grain type can be constructed at a reference temperature T0. For example, at the reference temperature T0 and in the experimental environment, the reflectance coefficient and dielectric constant of the same grain type at different humidity levels are measured to construct a corresponding function model as the standard moisture monitoring model. In this constructed standard moisture monitoring model, the moisture content M is the dependent variable, and the reflectance coefficient and dielectric constant are the independent variables. The least squares method can be used to fit the moisture content corresponding to each variable.

[0074] For example, for the corresponding relationship between dielectric constant and grain moisture, a function model based on linear fitting can be constructed, as shown in formula (6):

[0075]

[0076] Where M is the water content at a certain scanning point, εr is the dielectric constant at a certain scanning point, and v1, v2, v3, b1, and b2 are all parameter values ​​in the formula. For example, when the center frequency of the probe wave is 500MHz, M ≥ 14%, and the experimentally measured function is M = 0.82 × εr - 3.15 (R 2 =0.97, R 2 is the function fitting consistency, R 2 The larger the value, the higher the consistency of the function fitting. The above steps can be used to obtain the water content corresponding to the dielectric constant. The water content corresponding to the reflection coefficient can be further obtained through the constructed similar function model. The water content of each of the two independent variables is fitted by the least squares method to obtain an accurate moisture monitoring value for a scanning site.

[0077] Furthermore, in other embodiments, a neural network model corresponding to the water content M, reflection coefficient, and dielectric constant can be constructed as the above-mentioned standard moisture monitoring model. The input layer in the neural network model is used to input the reflection coefficient and dielectric constant; the neural network model can be configured to include one or more hidden layers, and each hidden layer is configured to correspond to multiple hidden nodes; and the output layer of the neural network model is configured to correspond to the output of the water content M. The constructed neural network model is trained and tested using a test data set and a verification data set to ensure that it can efficiently analyze and accurately obtain the water content M. Based on the tested neural network model as the standard moisture monitoring model, the reflection coefficient and dielectric constant of each distance value are respectively correlated and analyzed, thereby obtaining the water content M corresponding to each distance value as the moisture monitoring value of the corresponding scanning position.

[0078] In the grain moisture monitoring method based on detection wave analysis disclosed in the above-mentioned embodiment, the method includes: controlling a driver to drive a detection radar to scan the stored grain through a scanning instruction, receiving the echo signal obtained by the scan and performing preprocessing to obtain a corresponding processed signal, extracting features from the processed signal in combination with the distance value and the air pressure value to obtain a corresponding signal feature, calibrating the signal feature according to the temperature value to obtain a calibration feature, and then performing feature analysis to obtain a corresponding moisture monitoring value. The above-mentioned grain moisture monitoring method based on detection wave analysis can scan the stored grain through the detection radar and analyze and process the echo signal to accurately obtain the moisture content within the grain, greatly improving the efficiency and reliability of moisture monitoring, while also improving the accuracy of detecting the moisture content within the grain.

[0079] The embodiment of the present invention further provides a grain moisture monitoring device based on detection wave analysis, which can be configured in a monitoring terminal and is used to execute any embodiment of the grain moisture monitoring method based on detection wave analysis. Figure 5 , Figure 5 A schematic block diagram of a grain moisture monitoring device based on detection wave analysis provided in an embodiment of the present invention.

[0080] like Figure 5 As shown, the grain moisture monitoring device 100 based on detection wave analysis includes a scanning unit 110, a signal preprocessing unit 120, a feature extraction unit 130, a calibration unit 140 and a feature analysis unit 150.

[0081] The scanning unit 110 is used to send a scanning instruction to the driver to control the driver to drive the detection radar to scan the stored grain.

[0082] The signal preprocessing unit 120 is used to receive the echo signal obtained by the detection radar scanning, and preprocess the echo signal according to the signal processing rule to obtain a corresponding processed signal.

[0083] The feature extraction unit 130 is used to extract features from the processed signal according to preset signal feature extraction rules, the distance value detected by the distance sensor, and the air pressure value detected by the air pressure sensor to obtain corresponding signal features.

[0084] The calibration unit 140 is configured to calibrate the signal feature according to a preset feature calibration strategy and the temperature value monitored by the temperature sensor to obtain a corresponding calibration feature.

[0085] The feature analysis unit 150 is configured to perform feature analysis on the calibration feature according to a preset standard moisture monitoring model to obtain a corresponding moisture monitoring value.

[0086] The grain moisture monitoring device based on detection wave analysis provided in an embodiment of the present invention applies the above-mentioned grain moisture monitoring method based on detection wave analysis. The scanning instruction controls the driver to drive the detection radar to scan the stored grain, receives the echo signal obtained by the scan, pre-processes it to obtain a corresponding processing signal, extracts the features of the processed signal in combination with the distance value and the air pressure value to obtain the corresponding signal feature, calibrates the signal feature according to the temperature value to obtain the calibration feature, and then performs feature analysis to obtain the corresponding moisture monitoring value. The above-mentioned grain moisture monitoring method based on detection wave analysis can scan the stored grain through the detection radar and analyze and process the echo signal to accurately obtain the moisture content inside the grain, greatly improving the efficiency and reliability of moisture monitoring, while also improving the accuracy of detecting the moisture inside the grain.

[0087] The grain moisture monitoring device based on detection wave analysis can be implemented in the form of a computer program. Figure 6 Runs on the computer equipment shown.

[0088] See also Figure 6 , Figure 6 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device may be a monitoring terminal for executing a grain moisture monitoring method based on detection wave analysis to monitor the moisture content of grain inside a granary.

[0089] See Figure 6 The computer device 500 includes a processor 502 , a memory, and a communication interface 505 connected via a communication bus 501 , wherein the memory may include a storage medium 503 and an internal memory 504 .

[0090] The storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute a grain moisture monitoring method based on detection wave analysis. The storage medium 503 can be a volatile storage medium or a non-volatile storage medium.

[0091] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500.

[0092] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the grain moisture monitoring method based on detection wave analysis.

[0093] The communication interface 505 is used for network communication, such as providing data information transmission. Those skilled in the art will understand that Figure 6 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0094] The processor 502 is configured to run a computer program 5032 stored in the memory to implement corresponding functions in the above-mentioned grain moisture monitoring method based on detection wave analysis.

[0095] Those skilled in the art will understand that Figure 6 The embodiment of the computer device shown in the figure does not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structure and function of the memory and processor are the same as those in the figure. Figure 6 The embodiments shown are consistent and will not be described again here.

[0096] It should be understood that in the embodiment of the present invention, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0097] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be volatile or non-volatile. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps included in the above-described grain moisture monitoring method based on detection wave analysis.

[0098] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0099] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, or units with the same function may be combined into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or units, or may be an electrical, mechanical or other form of connection.

[0100] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.

[0101] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0102] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a computer-readable storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0103] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A grain moisture monitoring method based on detection wave analysis, characterized in that: The method is applied to a monitoring terminal, wherein the monitoring terminal establishes a communication connection with a detection radar, a temperature sensor, an air pressure sensor, a distance sensor, and a driver, wherein the driver is arranged on a slide rail, and the distance sensor and the detection radar are both fixedly arranged on the driver. The method includes: Sending a scanning instruction to the driver to control the driver to drive the detection radar to scan the stored grain; receiving an echo signal obtained by scanning the detection radar, and preprocessing the echo signal according to the signal processing rule to obtain a corresponding processed signal; Extract features from the processed signal according to preset signal feature extraction rules, the distance value detected by the distance sensor, and the air pressure value detected by the air pressure sensor to obtain corresponding signal features; Calibrate the signal feature according to a preset feature calibration strategy and the temperature value monitored by the temperature sensor to obtain a corresponding calibration feature; The calibration feature is analyzed according to a preset standard moisture monitoring model to obtain a corresponding moisture monitoring value.

2. The grain moisture monitoring method based on detection wave analysis according to claim 1 is characterized in that: The preprocessing of the echo signal according to the signal processing rule to obtain a corresponding processed signal includes: Filtering the echo signal according to the filtering algorithm in the signal processing rule to obtain a corresponding filtered signal; The filtered signal is enhanced according to the signal enhancement function in the signal processing rule to obtain a corresponding processed signal.

3. The grain moisture monitoring method based on detection wave analysis according to claim 1 is characterized in that: The extracting features of the processed signal according to a preset signal feature extraction rule, the distance value detected by the distance sensor, and the air pressure value detected by the air pressure sensor to obtain corresponding signal features includes: Extracting corresponding key information from a group of signals corresponding to each distance value in the processed signal according to the extraction parameters set in the signal feature extraction rule and the distance value; Analyze each key information and the corresponding distance value according to the reflection coefficient analytical expression in the signal feature extraction rule and the air pressure value to obtain the reflection coefficient corresponding to each distance value; Analyze each key information and the corresponding distance value according to the dielectric constant analytical formula in the signal feature extraction rule and the air pressure value to obtain the dielectric constant corresponding to each distance value; The reflection coefficient and the dielectric constant of each distance value are combined to obtain a corresponding signal feature.

4. The grain moisture monitoring method based on detection wave analysis according to claim 3 is characterized in that: The step of parsing each key information and the corresponding distance value according to the reflection coefficient analytical expression in the signal feature extraction rule and the air pressure value to obtain the reflection coefficient corresponding to each distance value includes: Calculating the ratio between the air pressure value and the standard atmospheric pressure to obtain an air pressure ratio; The air pressure ratio, the signal amplitude in the key information and the corresponding distance value are input into the reflection coefficient analytical formula for analysis to obtain the corresponding reflection coefficient.

5. The grain moisture monitoring method based on detection wave analysis according to claim 3 is characterized in that: The step of parsing the key information and the corresponding distance value according to the dielectric constant analytical formula in the signal feature extraction rule and the air pressure value to obtain the dielectric constant corresponding to each distance value includes: Calculating the ratio between the air pressure value and the standard atmospheric pressure to obtain an air pressure ratio; Calculating the interval between the emission time of the detection wave and the echo reception time in the key information; The pressure ratio, the interval time, and the corresponding distance value are input into the dielectric constant analytical formula for analysis to obtain the corresponding dielectric constant.

6. The grain moisture monitoring method based on detection wave analysis according to any one of claims 3 to 5, characterized in that: Before extracting corresponding key information from a group of signals corresponding to each distance value in the processed signal according to the extraction parameters set in the signal feature extraction rule and the distance value, the method further includes: Arranging signals located at the same scanning point in the processed signals according to the scanning point set in the scanning instruction; According to the correspondence between the scanning points and the distance values, a group of signals of the same scanning point is associated and combined with a corresponding distance value.

7. The grain moisture monitoring method based on detection wave analysis according to any one of claims 1 to 5, characterized in that: The calibrating the signal feature according to a preset feature calibration strategy and the temperature value monitored by the temperature sensor to obtain a corresponding calibration feature includes: Inputting the temperature value into the characteristic calibration strategy to obtain a corresponding correction value; The signal feature is calibrated according to the correction value to obtain a calibration feature corresponding to the signal feature.

8. A grain moisture monitoring device based on detection wave analysis, characterized in that: The device is configured in a monitoring terminal, the monitoring terminal establishes a communication connection with a detection radar, a temperature sensor, an air pressure sensor, a distance sensor, and a driver, the driver is set on a slide rail, the distance sensor and the detection radar are fixedly set on the driver, and the device is used to perform the grain moisture monitoring method based on detection wave analysis according to any one of claims 1 to 7, and the device includes: a scanning unit, configured to send a scanning instruction to the driver to control the driver to drive the detection radar to scan the stored grain; a signal preprocessing unit, configured to receive the echo signal obtained by scanning the detection radar, and preprocess the echo signal according to the signal processing rule to obtain a corresponding processed signal; a feature extraction unit, configured to extract features from the processed signal according to a preset signal feature extraction rule, the distance value detected by the distance sensor, and the air pressure value detected by the air pressure sensor, to obtain corresponding signal features; a calibration unit, configured to calibrate the signal feature according to a preset feature calibration strategy and a temperature value monitored by the temperature sensor to obtain a corresponding calibration feature; The feature analysis unit is used to perform feature analysis on the calibration feature according to a preset standard moisture monitoring model to obtain a corresponding moisture monitoring value.

9. A computer device, characterized in that: The device includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; The processor is configured to implement the steps of the grain moisture monitoring method based on detection wave analysis described in any one of claims 1 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the grain moisture monitoring method based on detection wave analysis as described in any one of claims 1 to 7 are implemented.

Images