A grain depot intelligent sampling quality inspection system and method

Abstract

The application discloses a kind of intelligent sampling quality inspection system and method of grain depot, it is related to intelligent grain depot detection technical field, including, collection environment data, three-dimensional point cloud data and acoustic surface wave group velocity data, using Love wave equation inversion calculation, obtain three-dimensional density distribution diagram;According to three-dimensional density distribution diagram, the vertical direction density gradient is calculated, and the stratified sampling parameter table is obtained;According to stratified sampling parameter table, stratified puncture is carried out to grain pile, and actual sampling depth data is generated, and actual sampling depth data is detected using three-way sample valve sample distribution.This application realizes the accurate detection of moisture, protein and heavy metal content by stratified detection of three-way sample valve and near-infrared X-ray combined analysis, and generates quality safety index by matching the detection results with the density distribution diagram using the constrained kriging interpolation method.

Description

Technical Field

[0001] This invention relates to the field of intelligent grain depot testing technology, and in particular to an intelligent sampling and quality inspection system and method for grain depots. Background Technology

[0002] Traditional sampling methods lack precise measurement of the density distribution inside the grain pile, resulting in insufficient sample representativeness and an inability to fully reflect grain quality. Secondly, existing technologies mostly use single detection methods, making it difficult to simultaneously obtain the physical characteristics (such as density) and chemical components (such as moisture, protein, and heavy metal content) of grain, thus limiting the comprehensiveness and accuracy of the test results.

[0003] Existing technologies have not effectively integrated surface acoustic wave group velocity data with three-dimensional point cloud data and environmental data, resulting in limited accuracy and efficiency in density distribution calculation. In addition, existing technologies mostly rely on single detection methods and lack the ability to comprehensively evaluate food quality and safety indicators. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent sampling and quality inspection system and method for grain depots, which solves the problems of insufficient accuracy in density distribution calculation and lack of comprehensive evaluation capability of grain quality and safety indicators in the prior art.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a smart sampling and quality inspection method for grain depots, which includes collecting environmental data, three-dimensional point cloud data and surface acoustic wave group velocity data, and using the Love wave equation to invert and calculate to obtain a three-dimensional density distribution map;

[0008] The vertical density gradient is calculated based on the three-dimensional density distribution map to obtain the stratified sampling parameter table;

[0009] The grain pile was punctured in layers according to the stratified sampling parameter table to generate actual sampling depth data. A three-way sampling valve was used to perform sample allocation and detection on the actual sampling depth data.

[0010] Near-infrared spectroscopy and X-ray fluorescence analysis were used to analyze the moisture, protein and heavy metal content in the grain pile. The analysis results were matched with the three-dimensional density distribution map to obtain quality and safety indicators.

[0011] As a preferred embodiment of the intelligent grain depot sampling and quality inspection system and method described in this invention, the collection of environmental data, three-dimensional point cloud data, and surface acoustic wave group velocity data includes the following steps:

[0012] Three-dimensional point cloud data is generated by scanning the surface of the grain pile with lidar;

[0013] By emitting surface acoustic waves and measuring the propagation time difference between adjacent sensors, surface acoustic wave group velocity data can be obtained from a sensor array on the surface of a grain pile.

[0014] As a preferred embodiment of the intelligent grain depot sampling and quality inspection system and method described in this invention, the method for obtaining a three-dimensional density distribution map using the Love wave equation inversion includes the following steps.

[0015] Based on surface acoustic wave group velocity data, the grain pile density is inverted using the Love wave equation to generate a three-dimensional density distribution.

[0016] By using a grid interpolation method, the 3D density distribution is combined with the 3D point cloud data to obtain a 3D density distribution map.

[0017] As a preferred embodiment of the intelligent grain depot sampling and quality inspection system and method of the present invention, the following steps are included in obtaining the stratified sampling parameter table by calculating the vertical density gradient based on the three-dimensional density distribution map:

[0018] The density data was aligned with the lidar point cloud coordinates using the grid alignment method, and the vertical density gradient of the grain pile was calculated using the central difference method.

[0019] Based on the density gradient of the grain pile in the vertical direction, a threshold for the density abrupt change layer is set. When the density gradient is greater than the threshold for the density abrupt change layer, the boundary edge of the grain pile is defined.

[0020] The grain pile is divided into N layers based on the boundary lines, resulting in a parameter table for the stratified sampling grain pile.

[0021] As a preferred embodiment of the intelligent grain storage sampling and quality inspection system and method of the present invention, the step of performing stratified puncture on the grain pile according to the stratified sampling parameter table to generate actual sampling depth data includes the following steps.

[0022] The hierarchical sampling parameter table is prioritized by a max-heap data structure, high-risk areas are dynamically parsed out, and the puncture speed is dynamically adjusted according to the density gradient intensity descending order.

[0023] The Terfenol-D magnetostrictive actuator was used to vertically penetrate the grain pile at a dynamically adjusted puncture speed, and the actual sampling depth data was recorded in real time.

[0024] As a preferred embodiment of the intelligent grain depot sampling and quality inspection system and method described in this invention, the following steps are included in the process of using a three-way sampling valve to perform sample allocation and detection on the actual sampling depth data:

[0025] Based on the overall humidity of the grain pile, set the surface humidity threshold and deep humidity threshold of the grain pile.

[0026] A three-way sampling valve was used to perform sample allocation and detection on the actual sampling depth data.

[0027] Mold detection is performed when the actual sampling depth data is less than the surface humidity threshold.

[0028] Moisture detection is performed when the surface humidity threshold is less than or equal to the actual sampling depth data, and the actual sampling depth data is less than or equal to the deep humidity threshold.

[0029] Heavy metal detection is performed when the actual sampling depth data is greater than the deep humidity threshold.

[0030] As a preferred embodiment of the intelligent grain storage sampling and quality inspection system and method described in this invention, the following steps are included: analyzing the moisture, protein, and heavy metal content in the grain pile using near-infrared spectroscopy and X-ray fluorescence, and matching the analysis results with a density distribution map to obtain quality and safety indicators.

[0031] Based on the stratification parameter table, grains from the surface, middle, and depth layers are extracted, crushed to the required particle size, pressed into tablets, and evenly spread in a quartz sample cup to produce near-infrared spectroscopy samples. The grains are then ground to the required particle size, pressed into tablets again, and covered with a polyester film to produce X-ray fluorescence samples.

[0032] By combining near-infrared spectroscopy with a PLS regression model, the moisture and protein content in near-infrared spectral samples in quartz sample cups were retrieved. The heavy metal content was quantitatively detected using an X-ray fluorescence analyzer combined with FP spectral interpretation method, generating quantitative analysis results of moisture, protein and heavy metal content in grain piles.

[0033] Constrained Kriging interpolation was used to spatially align the analysis results of moisture, protein and heavy metal content in the grain pile with the three-dimensional density distribution map, generating a three-dimensional thermal map of quality and safety that integrates multiphysics fields. Quality and safety indicators were calculated based on the kernel function combined with density gradient, temperature and humidity.

[0034] Secondly, the present invention provides an intelligent sampling and quality inspection system for grain depots, including a data collection module that collects environmental data, three-dimensional point cloud data and surface acoustic wave group velocity data, and uses the Love wave equation to invert and calculate to obtain a three-dimensional density distribution map;

[0035] The sampling parameter module calculates the vertical density gradient based on the three-dimensional density distribution map to obtain the stratified sampling parameter table;

[0036] The sample allocation and detection module performs stratified puncture on the grain pile according to the stratified sampling parameter table, generates actual sampling depth data, and uses a three-way sampling valve to perform sample allocation and detection on the actual sampling depth data.

[0037] The quality and safety module uses near-infrared spectroscopy and X-ray fluorescence to analyze the moisture, protein, and heavy metal content in the grain pile. The analysis results are then matched with the density distribution map to obtain quality and safety indicators.

[0038] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the intelligent grain depot sampling and quality inspection system and method as described in the first aspect of the present invention.

[0039] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the intelligent grain depot sampling and quality inspection system and method as described in the first aspect of the present invention.

[0040] The beneficial effects of this invention are as follows: This invention achieves high-precision mapping of the three-dimensional density distribution of grain piles through hexagonal SAW sensor array and Love wave equation inversion, with a spatial resolution of 15cm and an inversion error of ≤3.5%. It solves the shortcomings of traditional detection methods in blind zone coverage and density decoupling. Combined with the dynamic puncture mechanism of Terfenol-D magnetostrictive actuator, the sampling path is optimized through the maximum pile algorithm, and the speed is intelligently adjusted to penetrate the hard agglomerate layer, improving puncture efficiency. Through the layered detection of the three-way sample valve and the analysis of near-infrared X-ray, the accurate detection of moisture, protein and heavy metal content is achieved. The detection results are matched with the density distribution map by constrained kriging interpolation to generate quality and safety indicators. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart of the intelligent sampling and quality inspection process for grain depots in Example 1;

[0043] Figure 2 This is a data flow diagram of the intelligent sampling and quality inspection system for grain depots in Example 1;

[0044] Figure 3 This is a diagram of the intelligent sampling and quality inspection system for grain depots in Example 1;

[0045] Figure 4 This is a schematic diagram of the intelligent sampling and quality inspection system module and process in Example 1. Detailed Implementation

[0046] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0047] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0049] Example 1, referring to Figure 1 , Figure 2 , Figure 3 and Figure 4 This is the first embodiment of the present invention, which provides a grain depot intelligent sampling and quality inspection system and method, including the following steps:

[0050] S1. Collect environmental data, 3D point cloud data, and surface acoustic wave group velocity data.

[0051] S1.1. Scan the surface of the grain pile with lidar to generate three-dimensional point cloud data.

[0052] Furthermore, a dynamic scan was constructed based on the RIEGL VZ-4000 three-dimensional lidar, using a 5mm point spacing and a 10Hz repetition rate scanning mode. An adaptive surface fitting algorithm was used to eliminate particle scattering noise on the grain pile surface, generating structured point cloud data containing normal vector fields. The scanning process achieved millimeter-level positioning accuracy through GNSS / INS integrated navigation, and a point cloud registration algorithm was used to generate three-dimensional point cloud data.

[0053] S1.2. A hexagonal 64-channel SAW sensor array is deployed on the surface of the grain pile. By emitting surface acoustic waves at 50-150kHz and measuring the propagation time difference between adjacent sensors, surface acoustic wave group velocity data is obtained.

[0054] Furthermore, a 64-element piezoelectric ceramic SAW sensor array is deployed using a hexagonal close-packed topology, with the node spacing set to 30cm according to the wavelength compression criterion. A 50-150kHz linear frequency modulated signal is generated by an AD9833 signal generator, and waveform data is captured by an AD7768 high-speed acquisition module at a sampling rate of 1MS / s. Based on the cross-correlation algorithm, the propagation time difference between adjacent nodes is calculated (with an accuracy of 0.1μs) to obtain the surface acoustic wave group velocity data.

[0055] S1.3 Collect environmental data, including humidity and temperature.

[0056] Furthermore, humidity parameters of the surface and deep layers (1m depth interval) of the grain pile are collected at a frequency of 1Hz using SHT85 temperature and humidity sensors, while temperature data is collected layer by layer at a sampling rate of 1Hz using distributed SHT85 digital temperature and humidity sensors (±0.1℃ accuracy).

[0057] S2. Using the Love wave equation for inversion calculation, a three-dimensional density distribution map is obtained.

[0058] S2.1. Based on the obtained surface acoustic wave group velocity data, the grain pile density is inverted using the Love wave equation to generate a three-dimensional density distribution, expressed as follows:

[0059] ;

[0060] in, displacement The second derivative in the vertical direction In time The second derivative under the given condition, This is the infinitesimal change of the second derivative in the vertical direction. For group velocity, For humidity, For temperature, The identifier for group velocity.

[0061] Furthermore, It is usually a real number, which can be positive, negative, or zero. Usually real numbers, A value not equal to 0 indicates a tiny change in spatial location. Usually real numbers Not equal to zero indicates a tiny change in time. It is usually a positive value. The range is 0≤ C ≤100%, Positive values ​​are expressed in Kelvin (K) or Celsius (°C). It is a constant;

[0062] A full waveform inversion framework is adopted, and a density sensitivity kernel function is constructed based on the adjoint state method. A GPU-accelerated conjugate gradient algorithm is then used. The solution is iteratively solved at the voxel scale, and finally a three-dimensional distribution map containing density anomaly regions is generated.

[0063] S2.2. Using the grid interpolation method, the three-dimensional density distribution is combined with the three-dimensional point cloud data to obtain a three-dimensional density distribution map.

[0064] Furthermore, based on the multi-scale data fusion framework, an improved unstructured grid interpolation algorithm is used to achieve sub-voxel level registration of the density field and the point cloud. First, the density inversion grid (5cm resolution) and the laser point cloud (2mm accuracy) are spatially aligned using the Iterative Closest Point (ICP) algorithm to obtain a three-dimensional density distribution map.

[0065] S3. Calculate the vertical density gradient based on the three-dimensional density distribution map to obtain the stratified sampling parameter table.

[0066] S3.1 Align the density data with the lidar point cloud coordinates using the grid alignment method, and calculate the vertical density gradient of the grain pile layer by layer using the central difference method.

[0067] Furthermore, the expression for calculating the layer-by-layer density gradient in the vertical direction of the grain pile is as follows:

[0068] ;

[0069] in, Density gradient The first derivative in the vertical direction The vertical depth of the grain pile The space, The spatial step size in the vertical direction. For the depth index of the grain pile;

[0070] It is usually a positive value and greater than zero. It is usually a positive value and greater than zero. It is usually a positive value and greater than zero. It is usually an integer.

[0071] S3.2. Set a threshold for the humidity abrupt change layer based on the density gradient layer by layer in the vertical direction of the grain pile. When the density gradient is greater than the threshold for the humidity abrupt change layer, divide the grain pile boundary.

[0072] Furthermore, density is measured layer by layer along the height of the grain pile, and a density abrupt change threshold is set to determine whether there is a significant density change between two adjacent layers. When the density gradient exceeds the preset density abrupt change threshold, it means that there is a significant humidity difference between the two layers, and thus the two layers can be divided into different grain pile boundaries.

[0073] S3.3. Divide the grain pile into N layers according to the boundary of the grain pile to obtain the parameter table of the layered sampling grain pile.

[0074] Furthermore, based on the grain pile boundary determined through density gradient analysis, the entire grain pile is precisely divided into N distinct layers vertically. Each layer represents an area with relatively consistent density and moisture conditions. Detailed sampling is then conducted for each of these N layers, resulting in a stratified sampling grain pile parameter table. This parameter table records the specific measurement data for each layer in detail.

[0075] S4. Use the stratified sampling parameter table to perform stratified puncture on the grain pile to generate actual sampling depth data.

[0076] S4.1 Prioritize the hierarchical sampling parameter table using a max-heap data structure, dynamically parse out high-risk areas, and dynamically adjust the puncture speed according to the density gradient intensity descending order.

[0077] Furthermore, the maximum pile dynamic sorting method is used to analyze the density gradient intensity in the parameter table of the stratified sampled grain pile, and the puncture speed of the Terfenol-D magnetostrictive actuator is dynamically adjusted.

[0078] The layers are sorted in descending order based on the magnitude of their density gradients. For layers with larger density gradients, the puncture speed will be automatically slowed down to improve the accuracy of data collection, as there may be more complex structures or state changes. For layers with smaller density gradients, the puncture speed will be appropriately increased to improve efficiency.

[0079] S4.2. Use a Terfenol-D magnetostrictive actuator to vertically penetrate the grain pile at a dynamically adjusted piercing speed, and record the actual sampling depth data in real time.

[0080] Furthermore, based on the dynamically adjusted puncture speed, the Terfenol-D magnetostrictive actuator will vertically pierce the corresponding layer of the grain pile at the optimal speed. During this process, the specific position and puncture depth of the actuator will be monitored and recorded in real time to generate actual sampling depth data.

[0081] The Terfenol-D magnetostrictive actuator ensures that each puncture reaches the predetermined depth precisely, maintaining high accuracy even in grain piles with uneven density. These actual sampling depth data verify the effectiveness of the pre-defined stratification.

[0082] S5. Use a three-way sample valve to perform sample allocation and detection on the actual sampling depth data.

[0083] S5.1 Set the surface humidity threshold and deep humidity threshold of the grain pile based on the overall humidity of the grain pile.

[0084] Furthermore, based on the overall humidity of the grain pile, the sliding window method was used to obtain the humidity distribution of the surface layer (0-0.5m) and the deep layer (>3m).

[0085] S5.2 uses a three-way sample valve to perform sample allocation and detection on the actual sampling depth data.

[0086] Furthermore, the valve core angle is fed back in real time through a three-way sampling valve and an integrated Hall encoder (accuracy ±0.05°). Based on the depth data from the pressure sensor built into the sampling rod (range 0-50kPa, accuracy ±0.1kPa), a PID control algorithm drives a stepper motor (step angle 1.8°) to switch the flow channels. Shallow samples (<0.5m) enter the mold detection channel (flow rate 2L / min), medium samples (0.5-3m) flow to the moisture detection chamber (flow rate 1.5L / min), and deep samples (>3m) are introduced into the heavy metal detection module (flow rate 0.8L / min). A self-cleaning flow channel design (compressed air pulse cycle 30s) is adopted to avoid cross-contamination, and the sampling error rate is <0.8%.

[0087] S5.3 Mold detection shall be performed when the actual sampling depth data is less than the surface humidity threshold.

[0088] Furthermore, surface samples were subjected to high-throughput mold detection using a microfluidic chip (channel width 200 μm). Quantitative colony counts were achieved by integrating qPCR (temperature control accuracy ±0.3℃) to amplify the aflatoxin synthesis gene, combined with a fluorescent probe (excitation wavelength 485 nm) (sensitivity 10). 2 The results of mold detection (CFU / g) are obtained, and a red warning signal is triggered when the toxin concentration is >5 μg / kg.

[0089] S5.4 When the surface humidity threshold is less than or equal to the actual sampling depth data, and the actual sampling depth data is less than or equal to the deep humidity threshold, moisture detection shall be performed.

[0090] Furthermore, the mid-layer samples were rapidly detected for moisture content using near-infrared spectroscopy (wavelength 900-1700nm, resolution 3nm) combined with a PLS regression model (principal components = 8). The spectral probe was equipped with a self-focusing lens (focal length 15mm) and entered the grating spectrometer via fiber optic coupling (integration time 100ms), achieving a detection accuracy of ±0.15%. The data was processed using Kalman filtering to eliminate transmission vibration noise, and the three-dimensional moisture content distribution heatmap was updated every 60 seconds. Samples exceeding the standard (moisture content >14.5%) were automatically marked with a yellow warning label.

[0091] S5.5 When the actual sampling depth data is greater than the deep humidity threshold, heavy metal detection shall be performed.

[0092] Furthermore, after microwave digestion (1200W power, heating rate 15℃ / s), the deep samples were analyzed for heavy metal content such as lead and cadmium using ICP-MS (argon plasma temperature 8000K). A collision reaction cell (He flow rate 4.3mL / min) was used to eliminate mass spectrometry interference, achieving a detection limit as low as 0.01μg / kg (RSD<5%). Data was uploaded to the quality traceability system via the Modbus protocol. When Pb>0.2mg / kg or Cd>0.1mg / kg, a tiered control mechanism (isolation, ventilation, alarm) was triggered.

[0093] S6. Near-infrared spectroscopy and X-ray fluorescence analysis were used to analyze the moisture, protein and heavy metal content in the grain pile. The analysis results were matched with the density distribution map to obtain quality and safety indicators.

[0094] S6.1 Based on the layer parameter table, take out the grain from the surface, middle and depth layers, crush the grain to the particle size, press it into tablets, spread it evenly in a quartz sample cup to make a near-infrared spectral sample, grind the grain to the particle size again, press it into tablets again, cover the surface with a polyester film to make an X-ray fluorescence sample.

[0095] Furthermore, based on the stratification parameter table, representative grain samples are taken from the surface, middle and deep layers, crushed to a suitable particle size, pressed into shape and evenly spread in a quartz sample cup to prepare samples suitable for near-infrared spectroscopy analysis. The same or different grain samples are further ground to a finer particle size, pressed again and covered with a polyester film to prepare samples suitable for X-ray fluorescence analysis.

[0096] S6.2. By combining near-infrared spectroscopy with the PLS regression model, the moisture and protein content in the near-infrared spectral samples in the quartz sample cup are inverted. The heavy metal content is quantitatively detected by using an X-ray fluorescence analyzer combined with the FP spectral interpretation method, and quantitative analysis results of moisture, protein and heavy metal content in the grain pile are generated.

[0097] Furthermore, near-infrared spectroscopy is used to analyze the samples placed in quartz sample cups to determine their moisture and protein content, while X-ray fluorescence analysis can detect the heavy metal content in the samples, thus obtaining detailed information about the moisture, protein, and potentially harmful heavy metal content in the grain pile.

[0098] S6.3. Using constrained kriging interpolation, the analysis results of moisture, protein and heavy metal content in the grain pile are spatially aligned with the three-dimensional density distribution map to generate a three-dimensional thermal map of quality and safety that integrates multiple physics fields. Based on the kernel function combined with density gradient, temperature and humidity, the quality and safety indicators are calculated.

[0099] Furthermore, the quality and safety indicators are calculated using the following expression:

[0100] ;

[0101] in, In the grain pile Quality and safety indicators at the site For the depth of the grain pile Moisture content weighting coefficient at the location, For the depth of the grain pile Moisture content at that location This is the weighting coefficient for protein content. For the depth of the grain pile The weighting coefficient for protein content. For the depth of the grain pile Protein content value, This represents the weighting coefficient for heavy metal content. For the depth of the grain pile The weighting coefficient for heavy metal content. For the depth of the grain pile The heavy metal content value, For position density value, Critical density, For kernel function, As a sample, The total number of samples, This is the location index within the grain pile;

[0102] Usually real numbers, and ≥0, It is usually a real number, which can be positive, negative, or zero. Usually real numbers, and ≥0, For are usually real numbers, ≥0, It is usually a real number, which can be positive, negative, or zero. Usually real numbers, and ≥0, For are usually real numbers, ≥0, It is usually a real number, which can be positive, negative, or zero. It is usually a real number, which can be positive, negative, or zero. Usually a positive value. Greater than zero, It is usually a real number and is greater than zero.

[0103] Constrained kriging interpolation is used to predict data values ​​at unknown points. This involves matching the analysis results of moisture, protein, and heavy metal content with the density distribution map of the grain pile. Through effective processing of spatial data, a comprehensive quality and safety index is finally generated.

[0104] Furthermore, constrained kriging interpolation is employed, combining the analysis results of moisture, protein, and heavy metal content with the three-dimensional density distribution map of the grain pile, to refine the spatial data and predict the data values ​​of unknown points. This achieves a high-precision mapping of the internal quality characteristics of the grain pile. By introducing constraints, the accuracy of the interpolation results is optimized, ensuring a high degree of matching between the spatial distribution of moisture, protein, and heavy metal content and the density distribution map. Through weighted fusion of multidimensional data, a comprehensive quality and safety indicator is generated.

[0105] This embodiment also provides a grain depot intelligent sampling and quality inspection system, including: a data collection module that collects environmental data, three-dimensional point cloud data and surface acoustic wave group velocity data, and uses the Love wave equation to invert and calculate to obtain a three-dimensional density distribution map;

[0106] The sampling parameter module calculates the vertical density gradient based on the three-dimensional density distribution map to obtain the stratified sampling parameter table;

[0107] The sample allocation and detection module performs stratified puncture on the grain pile according to the stratified sampling parameter table, generates actual sampling depth data, and uses a three-way sampling valve to perform sample allocation and detection on the actual sampling depth data.

[0108] The quality and safety module uses near-infrared spectroscopy and X-ray fluorescence to analyze the moisture, protein, and heavy metal content in the grain pile. The analysis results are then matched with the density distribution map to obtain quality and safety indicators.

[0109] This embodiment also provides a computer device applicable to the intelligent grain depot sampling and quality inspection system and method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the intelligent grain depot sampling and quality inspection system and method proposed in the above embodiment.

[0110] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0111] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the intelligent grain depot sampling and quality inspection system and method proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0112] In summary, this invention achieves high-precision mapping of the three-dimensional density distribution of grain piles through a hexagonal SAW sensor array and Love wave equation inversion, with a spatial resolution of 15cm and an inversion error of ≤3.5%. It solves the shortcomings of traditional detection methods in terms of blind zone coverage and density decoupling. Combined with the dynamic puncture mechanism of the Terfenol-D magnetostrictive actuator, the sampling path is optimized through the maximum pile algorithm, and the speed is intelligently adjusted to penetrate the hard agglomerate layer, improving puncture efficiency. Through the layered detection of the three-way sample valve and the analysis of near-infrared X-rays, accurate detection of moisture, protein and heavy metal content is achieved. The detection results are matched with the density distribution map by constrained kriging interpolation to generate quality and safety indicators.

[0113] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for intelligent sampling and quality inspection in grain depots, characterized in that: Comprising, Collecting environmental data, three-dimensional point cloud data and acoustic surface wave group velocity data, using Love wave equation inversion calculation to obtain three-dimensional density distribution map, including the following steps, Based on the acoustic surface wave group velocity data, using Love wave equation inversion of grain bulk density, generate three-dimensional density distribution; Using grid interpolation combined method, combine three-dimensional density distribution with three-dimensional point cloud data, obtain three-dimensional density distribution map; According to the three-dimensional density distribution map, calculate the vertical direction density gradient, get the layered sampling parameter table, including the following steps, Through the grid alignment method, align the density data with the laser radar point cloud coordinates, use the central difference method to calculate the vertical direction of the grain pile layer by layer density gradient; Based on the vertical direction of the grain pile layer by layer density gradient, set the density mutation layer threshold, when the density gradient is greater than the density mutation layer threshold, divide the grain pile boundary edge; According to the grain pile boundary edge, divide the grain pile into N layers, get the layered sampling grain pile parameter table; According to the layered sampling parameter table, the grain pile is divided into layers, the actual sampling depth data is generated, including the following steps, Through the maximum heap data structure, the priority of the layered sampling parameter table is sorted, and the high risk area is dynamically analyzed, and the piercing speed is dynamically adjusted in descending order of density gradient intensity; Using Terfenol-D magnetostrictive actuator to vertically pierce into the grain pile at the dynamically adjusted piercing speed, real-time record the actual sampling depth data, using three-way sample valve to sample allocation detection of actual sampling depth data; Adopting near infrared spectroscopy and X-ray fluorescence analysis of moisture, protein and heavy metal content in grain pile, matching the analysis results with three-dimensional density distribution map, obtaining quality safety index.

2. The intelligent sampling and quality inspection method for grain depot according to claim 1, characterized in that: Collecting environmental data, three-dimensional point cloud data and acoustic surface wave group velocity data includes the following steps, Scan the surface of the grain pile by laser radar, generate three-dimensional point cloud data; On the surface of the grain pile sensor array, by emitting acoustic surface wave and measuring the propagation time difference between adjacent sensors, get the acoustic surface wave group velocity data.

3. The intelligent sampling and quality inspection method for grain depot according to claim 1, characterized in that: Using three-way sample valve to sample allocation detection of actual sampling depth data includes the following steps, According to the overall humidity of the grain pile, set the surface layer humidity threshold and the deep layer humidity threshold of the grain pile; Using three-way sample valve to sample allocation detection of actual sampling depth data; When the actual sampling depth data is less than the surface layer humidity threshold, mold detection is carried out; When the surface layer humidity threshold is less than or equal to the actual sampling depth data, and the actual sampling depth data is less than or equal to the deep layer humidity threshold, moisture detection is carried out; When the actual sampling depth data is greater than the deep layer humidity threshold, heavy metal detection is carried out.

4. The intelligent sampling and quality inspection method for grain depot according to claim 1, characterized in that: Adopting near infrared spectroscopy and X-ray fluorescence analysis of moisture, protein and heavy metal content in grain pile, matching the analysis results with density distribution map, obtaining quality safety index includes the following steps, Based on the layered parameter table, take out the surface layer, middle layer and deep layer depth of grain, crush the grain to particle size, tablet forming, uniform paving in quartz sample cup, make near infrared spectroscopy sample, then grind the grain to particle size, tablet again, surface covered with polyester film, make X-ray fluorescence sample; The moisture and protein content in the near-infrared spectrum sample in the quartz sample cup is inversed by near-infrared spectroscopy combined with a PLS regression model, the heavy metal content is quantitatively detected by using an X-ray fluorescence analyzer combined with FP spectral resolution, and quantitative analysis results of the moisture, protein and heavy metal content of the grain pile are generated; The analysis results of the moisture, protein and heavy metal content in the grain pile are spatially aligned with the three-dimensional density distribution map by using a constrained kriging interpolation method, a quality and safety three-dimensional thermodynamic map of fused multi-physical fields is generated, and a quality and safety index is calculated according to a kernel function combined with a density gradient, temperature and humidity.

5. A grain depot intelligent sampling and quality inspection system based on the grain depot intelligent sampling and quality inspection method of any one of claims 1-4, characterized in that: It comprises, A data collection module collects environmental data, three-dimensional point cloud data and surface acoustic wave group velocity data, and obtains a three-dimensional density distribution map by using Love wave equation inversion calculation; A sampling parameter module calculates a vertical direction density gradient according to the three-dimensional density distribution map, and obtains a layered sampling parameter table; A sample allocation and detection module performs layered puncture on the grain pile according to the layered sampling parameter table, generates actual sampling depth data, and performs sample allocation and detection on the actual sampling depth data by using a three-way sample valve; A quality and safety module analyzes the moisture, protein and heavy metal content in the grain pile by using near-infrared spectroscopy and X-ray fluorescence, matches the analysis results with the density distribution map, and obtains a quality and safety index. 6.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The processor executes the computer program to realize the steps of the grain depot intelligent sampling and quality inspection method of any one of claims 1-4.

7. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the grain depot intelligent sampling and quality inspection method of any one of claims 1-4.

Images