A method and system for monitoring grain conditions in a wharf granary

Abstract

The present invention relates to the field of grain storage monitoring technology, and specifically to a method and system for monitoring grain conditions in a wharf granary. The method comprises the following steps: obtaining data on the environmental characteristics of the wharf granary and the grain pile size characteristics, temperature characteristics, humidity characteristics, and gas concentration characteristics; constructing a spatiotemporal feature model based on the data, the spatiotemporal feature model comprising a temperature spatiotemporal feature model, a humidity spatiotemporal feature model, and a gas concentration spatiotemporal feature model; obtaining spatiotemporal feature data according to the spatiotemporal feature model; processing the spatiotemporal feature data to obtain optimized spatiotemporal feature data; constructing a food security risk assessment model through the optimized spatiotemporal feature data; and monitoring the grain conditions in the wharf granary according to the food security risk assessment model. The present invention greatly reduces the monitoring cost and achieves high-precision assessment of food security risks by performing internal sensorless monitoring of the temperature, humidity, and concentration of infinite space points inside the grain pile.

Description

Technical Field

[0001] The present invention relates to the technical field of grain storage monitoring, and in particular to a method and system for monitoring grain conditions in a wharf granary. Background Art

[0002] In the field of grain storage, especially in large storage facilities such as port grain silos, grain condition monitoring and management are the key to ensuring food safety, preventing losses, and improving operational efficiency. Traditional port grain silo grain condition monitoring mainly relies on manual inspections and simple environmental monitoring equipment such as thermometers and hygrometers. However, with the advancement of technology and the complexity of grain storage needs, this traditional method can no longer meet the needs of modern grain silo management.

[0003] In the prior art, multiple sensors are usually used to closely monitor key parameters such as temperature, humidity and gas concentration in the granary, and corresponding warning thresholds are set for these parameters according to actual needs and food safety standards. Once the data detected by the sensor exceeds or falls below the preset threshold, the system will immediately trigger the monitoring and warning mechanism, thereby realizing accurate and real-time monitoring and warning of the grain situation in the granary. This method has the following difficult problems: first, it is difficult to deploy a large number of temperature, humidity and gas concentration sensors inside the grain pile, so it is difficult to detect the temperature, humidity and gas concentration data at multiple points in the grain pile; second, it does not solve the problem of data loss caused by sensor failure, network instability, storage saturation, and power outage; third, it does not consider the influence of time variability and spatial correlation at different points in the grain pile; fourth, it does not consider the changes in temperature, humidity and gas concentration from the perspective of time and space at the same time; fifth, it does not consider the impact of changes in temperature, humidity and gas concentration on grain risk at the same time. The above problems will reduce the accuracy of monitoring data, resulting in inaccurate capture and analysis of key data, and may ignore major safety hazards of grain storage.

[0004] At present, there are not many studies on grain condition monitoring that consider both the internal data defects and spatiotemporal characteristics of grain piles in grain silos at docks. There is no specific method to realize the temperature, humidity and A grain condition monitoring method for grain silos at a port using real-time concentration data. Summary of the invention

[0005] In view of the defects in the prior art, the present invention provides a method and system for monitoring grain conditions in a wharf granary.

[0006] On the one hand, the monitoring method provided by the present invention includes the following steps: obtaining data on the environmental characteristics of the grain silo at the wharf and the size characteristics of the grain pile, temperature characteristics, humidity characteristics, and gas concentration characteristics; constructing a spatiotemporal characteristic model based on the data, the spatiotemporal characteristic model including a temperature spatiotemporal characteristic model, a humidity spatiotemporal characteristic model, and a gas concentration spatiotemporal characteristic model; obtaining spatiotemporal characteristic data according to the spatiotemporal characteristic model; processing the spatiotemporal characteristic data to obtain optimized spatiotemporal characteristic data; constructing a food security risk assessment model through the optimized spatiotemporal characteristic data; and monitoring the grain situation in the grain silo at the wharf according to the food security risk assessment model. The present invention obtains the temperature, humidity, and gas concentration inside the grain pile through the spatiotemporal characteristic model. The concentration data avoids the deployment of a large number of sensors in the grain pile, greatly reducing the monitoring cost; by processing the data of the spatiotemporal characteristic model, the high-precision data of the infinite space points inside the grain pile is effectively obtained, realizing the accurate monitoring of the grain condition in the grain warehouse at the terminal; through the food security risk assessment model, the comprehensive and real-time monitoring of the grain condition in the grain warehouse at the terminal is realized, which improves the safety and management efficiency of grain storage, which is of great significance for ensuring grain quality and reducing losses, and also provides a scientific basis and technical support for grain storage management.

[0007] Optionally, the data of obtaining the environmental characteristics of the grain warehouse at the wharf and the grain pile size characteristics, temperature characteristics, humidity characteristics, and gas concentration characteristics include: obtaining the average temperature, average humidity, and average concentration, maximum temperature change, maximum humidity change and maximum Data on the amplitude of concentration changes; obtain data on the maximum length, maximum width and maximum height of the grain pile in the wharf grain warehouse; obtain data on the fluctuation frequency, time attenuation coefficient and conduction influence coefficient of the temperature of the grain pile in the wharf grain warehouse; obtain data on the fluctuation frequency, time attenuation coefficient and conduction influence coefficient of the humidity of the grain pile in the wharf grain warehouse; obtain data on the maximum length, maximum width and maximum height of the grain pile in the wharf grain warehouse; obtain data on the fluctuation frequency, time attenuation coefficient and conduction influence coefficient of the humidity of the grain pile in the wharf grain warehouse The data of time decay coefficient of concentration and conduction influence coefficient. The present invention elaborates on the specific contents of obtaining multiple characteristic data of grain silo environment and grain pile at the wharf, which has the following effects: first, it reflects the comprehensiveness and meticulousness of data collection, which is essential for evaluating the stability of grain silo environment and the storage conditions of grain; second, it is conducive to a more accurate understanding of the scale of grain pile, providing a basis for the subsequent construction of spatiotemporal characteristic model; third, it reveals the changing laws and mutual influence relationships of the internal environmental parameters of grain pile, which helps to deeply understand the physical and chemical processes inside the grain pile.

[0008] Optionally, the temperature spatiotemporal characteristic model satisfies the following expression:

[0009] ,

[0010] in, is the spatial point position of the grain pile Department The temperature of the moment, is the average temperature of the environment around the grain pile, is the maximum variation of the ambient temperature around the grain pile, is the maximum height of the grain pile, for The frequency of fluctuations in direction, for The phase angle of the direction, is the maximum width of the grain pile, is the time attenuation coefficient, for Directional temperature conduction influence coefficient, for Directional temperature conduction influence coefficient, , , is the coordinate of the spatial point; the humidity spatiotemporal characteristic model satisfies the following expression:

[0011] ,

[0012] in, is the spatial point position of the grain pile Department Humidity at all times, is the average humidity of the environment around the grain pile, is the maximum change range of the ambient humidity around the grain pile, is the maximum height of the grain pile, for The frequency of fluctuations in direction, for The phase angle of the direction, is the maximum length of the grain pile, is the time attenuation coefficient, for Directional humidity conduction influence coefficient, for Directional humidity conduction influence coefficient, , , is the coordinate of the spatial point; the gas concentration spatiotemporal characteristic model satisfies the following expression:

[0013] ,

[0014] in, is the spatial point position of the grain pile Department The gas concentration at the time, is the average gas concentration around the grain pile, is the maximum variation range of the ambient gas concentration around the grain pile, is the maximum height of the grain pile, is the maximum length of the grain pile, is the maximum width of the grain pile, is the time attenuation coefficient, for Directional gas concentration conduction influence coefficient, is the depth weight coefficient, , , is the coordinate of a spatial point. The present invention provides expressions satisfied by the temperature space-time characteristic model, the humidity space-time characteristic model and the gas concentration space-time characteristic model, which enhances the scientificity and accuracy of model construction. The temperature space-time characteristic model expression can capture the fluctuation of temperature over time and space, which is helpful to evaluate the heat conduction and heat diffusion effects in the grain storage process; the humidity space-time characteristic model expression can reveal the impact of humidity changes on grain quality and storage stability, and provide a scientific basis for regulating the humidity of the granary; the gas concentration space-time characteristic model expression can reflect the distribution and change law of gas concentration in the granary, which is of great significance for evaluating grain respiration and preventing grain mildew.

[0015] Optionally, the spatiotemporal characteristic data obtained according to the spatiotemporal characteristic model includes: obtaining temperature data of multiple spatial points evenly distributed in the grain pile space at multiple times according to the temperature spatiotemporal characteristic model; obtaining humidity data of multiple spatial points evenly distributed in the grain pile space at multiple times according to the humidity spatiotemporal characteristic model; obtaining gas concentration data of multiple spatial points evenly distributed in the grain pile space at multiple times according to the gas concentration spatiotemporal characteristic model. The present invention obtains multi-dimensional data of the grain pile space through the spatiotemporal characteristic model, showing a high degree of accuracy. Through the temperature spatiotemporal characteristic model, the temperature changes of different spatial positions in the grain pile at multiple time points can be accurately captured, providing a reliable basis for temperature monitoring of the grain storage environment; through the humidity spatiotemporal characteristic model, the humidity data of each spatial point inside the grain pile can be fully obtained, which helps to timely discover and deal with potential humidity problems and ensure the safety of grain drying; through the gas concentration spatiotemporal characteristic model, the data dimension of the grain pile space is further enriched, and the gas concentration changes inside the grain pile can be monitored in real time, providing strong support for preventing problems such as grain mildew and insect pests.

[0016] Optionally, the processing of the spatiotemporal characteristic data to obtain optimized spatiotemporal characteristic data includes: using an anomaly detection model to perform anomaly detection on the spatiotemporal characteristic data of temperature, humidity and gas concentration; according to the anomaly detection, eliminating the abnormal data to obtain the spatiotemporal characteristic data with missing data points; using Newton interpolation formula to interpolate the spatiotemporal characteristic data with missing data points; according to the spatiotemporal characteristic data after the interpolation, obtaining optimized spatiotemporal characteristic data. The present invention describes in detail the processing flow of spatiotemporal characteristic data, aiming to optimize data quality through a series of steps. First, the spatiotemporal characteristic data of temperature, humidity and gas concentration are carefully screened by using an anomaly detection model, and the abnormal data are effectively identified and eliminated, which is crucial to ensure the accuracy and reliability of the data; second, for the missing data points generated after the abnormal data are eliminated, the Newton interpolation formula is used to perform scientific interpolation processing, and the missing values ​​are reasonably inferred based on the known data points, so as to maintain the integrity and continuity of the data; third, based on the spatiotemporal characteristic data after the interpolation processing, an optimized data set is obtained, which provides strong support for subsequent data analysis and decision-making.

[0017] Optionally, constructing a food security risk assessment model by optimizing the spatiotemporal feature data includes: determining parameters affecting food security risks by optimizing the spatiotemporal feature data; and constructing a food security risk assessment model according to the parameters, wherein the food security risk assessment model satisfies the following expression:

[0018] ,

[0019] in, is the food security risk assessment index, , , are the optimal values ​​of temperature and humidity and the set value of gas concentration, respectively. , , , , are the maximum and minimum values ​​of temperature, humidity and gas concentration respectively, , , , , , are the mean and standard deviation of temperature, humidity and gas concentration, respectively. is the temperature, For humidity, is the gas concentration, is the time trend function, is the spatial correlation function, , , , , , , , is the weight coefficient. The present invention utilizes optimized spatiotemporal feature data to construct a food security risk assessment model, demonstrating the concept of data-driven risk assessment. The specific effects are as follows: First, through in-depth analysis of the optimized spatiotemporal feature data, the key parameters affecting food security risks are accurately identified. These parameters cover multiple dimensions such as temperature, humidity, and gas concentration, providing a solid data foundation for the construction of the model; second, based on these key parameters, a food security risk assessment model is constructed. The model comprehensively considers the impact of various parameters on food security risks and realizes quantitative risk assessment; third, the scientificity and accuracy of risk assessment are improved, providing strong decision-making support for food storage management.

[0020] Optionally, the monitoring of grain conditions in grain warehouses at docks according to the food security risk assessment model includes the following steps: dividing the levels of food security risks through the food security risk assessment model, the levels including low risk level, medium risk level, medium-high risk level and high risk level; determining a threshold interval of a food security risk assessment index according to the level of food security risk, the threshold intervals of the food security risk assessment index corresponding to the medium risk level, the medium-high risk level and the high risk level are not continuous; judging, according to the threshold interval, whether the food security risk assessment indexes of multiple spatial points evenly distributed in the grain pile at multiple times fall into the threshold interval; determining a real-time food security risk level according to whether the food security risk assessment index falls into the threshold interval; determining the temperature, humidity and Abnormal concentration; through the real-time food security risk level and the abnormal situation, the grain condition in the grain warehouse at the terminal is monitored. The present invention describes the steps of monitoring the grain condition in the grain warehouse at the terminal based on the food security risk assessment model, and the effect is significant. First, the level of food security risk is divided through the model, and the threshold interval of the assessment index corresponding to each level is clarified, where the threshold interval above the medium risk level is discontinuous, which helps to define the risk status more accurately; second, based on the correspondence between the assessment index and the threshold interval, the risk level of the grain can be quickly judged, and the risk can be identified immediately; third, the risk level is combined with temperature, humidity, By monitoring abnormal concentrations, we can comprehensively assess the grain situation in the granary and promptly discover potential problems, providing a scientific basis for taking corresponding measures.

[0021] Optionally, the temperature, humidity, The abnormal situation of concentration includes the following steps: determining whether the grain situation is abnormal or normal according to the real-time grain safety risk level; determining the temperature, humidity, The present invention determines the temperature, humidity, Abnormal concentration reflects the risk-oriented monitoring strategy. The following results have been achieved: First, through the real-time food security risk level, it is directly judged whether the grain situation is abnormal, which helps to quickly identify the problem area; second, based on the confirmation of abnormal grain situation, further analysis of temperature, humidity, The specific abnormal conditions of concentration are conducive to accurately identifying the specific factors that cause risks; thirdly, it improves the targeted nature of monitoring, ensures the timely discovery and handling of abnormal conditions, and is conducive to providing strong guarantees for grain storage safety.

[0022] Optionally, the temperature, humidity, The abnormal concentration includes: according to the determination result of the abnormal grain condition, using temperature, humidity and The optimized spatiotemporal characteristic data of concentration are respectively related to the corresponding temperature, humidity and According to the comparison result, determine the temperature, humidity and The present invention describes in detail the method for judging the temperature, humidity and The specific method of detecting concentration anomalies has significant effects. First, by optimizing the comparison of spatiotemporal feature data with the baseline value, it can accurately capture the temperature, humidity and The difference between the actual state and the ideal state of concentration provides a reliable basis for judging abnormal situations; secondly, the direct application of the comparison results makes the temperature, humidity and Abnormal concentrations can be quickly identified, avoiding tedious troubleshooting processes and improving monitoring efficiency; thirdly, the core role of data in judging abnormal situations is strengthened, ensuring the timely discovery and accurate identification of abnormal situations, which is conducive to providing strong support for the optimization and adjustment of the grain storage environment.

[0023] In a second aspect, the present invention provides a terminal grain silo grain condition monitoring system, comprising an input device, a processor, an output device and a memory, wherein the input device, the processor, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the system uses the terminal grain silo grain condition monitoring method. The terminal grain silo grain condition monitoring system provided by the present invention has a high degree of integration, and can realize comprehensive, real-time and accurate monitoring of the terminal grain silo grain condition, which can not only improve management efficiency, but also reduce labor costs, and provide a strong guarantee for the intelligent supervision of grain storage. The specific effects are as follows: First, through high-precision sensors and Internet of Things technology, the system can monitor key parameters such as temperature, humidity, and gas concentration inside the granary in real time and comprehensively, ensuring that the grain storage environment is in the best state, effectively preventing problems such as grain heating and mildew caused by abnormal temperature and humidity, and significantly improving the safety and stability of grain storage; Second, the system has powerful data analysis functions, which can deeply mine and analyze historical data, help managers grasp the trends and laws of changes in the granary environment, and provide strong support for the formulation of more scientific and reasonable storage management strategies; Third, the system realizes remote monitoring and intelligent early warning. Once abnormal data is detected, it can immediately trigger the alarm mechanism and notify managers in a variety of ways to deal with it in a timely manner, effectively avoiding potential safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of a method for monitoring grain conditions in a grain silo at a wharf according to an embodiment of the present invention;

[0025] Figure 2 This is a schematic diagram of the structure of a grain condition monitoring system for a port grain silo according to an embodiment of the present invention;

[0026] Figure 3 The present invention is a flowchart of an algorithm executed by a grain condition monitoring system for a grain silo at a port according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0028] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0029] See also Figure 1 The embodiment of the present invention provides a method for monitoring grain conditions in a grain silo at a wharf, the method comprising the following steps:

[0030] S1. Obtain data on the environmental characteristics of the grain silo at the terminal and the grain pile size characteristics, temperature characteristics, humidity characteristics, and gas concentration characteristics.

[0031] Among them, S1 includes the following steps:

[0032] S11. Get the average temperature, average humidity, and average concentration, maximum temperature change, maximum humidity change, maximum Data on the magnitude of concentration changes.

[0033] In one embodiment, temperature sensors, humidity sensors, and gas concentration sensors are deployed at appropriate locations according to the size and shape of the granary to ensure that the sensors can cover every corner of the granary to reflect the overall temperature, humidity, and gas concentration distribution.

[0034] Furthermore, the data receiving and processing software is configured on the cloud server, and the data collection frequency and transmission method of the sensor are set.

[0035] Furthermore, the sensor is activated to collect the temperature, humidity and Concentration data, the data is transmitted to the data center or cloud server via wireless communication technology.

[0036] Furthermore, after receiving the data, the data center or cloud server performs preprocessing and cleaning to remove outliers and noise, and uses the big data analysis algorithm to calculate the average value of each sensor to obtain the average temperature, average humidity and average humidity of the granary. In addition, the big data analysis algorithm is used to filter out temperature, humidity, The maximum and minimum values ​​of the concentration are calculated, and the minimum value is subtracted from the maximum value to obtain the maximum temperature change range, the maximum humidity change range and the maximum gas concentration change range of the granary.

[0037] S12. Obtain data on the maximum length, maximum width and maximum height of the grain pile in the port granary.

[0038] In one embodiment, a high-precision, remotely controllable 3D laser scanner is selected, such as the GoSLAM RS100 3D laser scanning system, which can quickly move and scan the walls inside the granary; it is also equipped with a wireless transmission module for transmitting the scan data in real time to a remote computer or monitoring center.

[0039] Specifically, inside the granary, the scanning route is planned according to the shape and position of the grain pile to ensure that the scanning range can fully cover the grain pile. In addition, safety warning signs are set to ensure the safety of personnel and equipment during the scanning process. Among them, the shape of the grain pile is mostly approximately conical or elliptical.

[0040] Furthermore, the 3D laser scanner is connected to the wireless transmission module to ensure stable and reliable data transmission. The remote access software is installed and configured on the remote computer to ensure remote access and data processing.

[0041] Furthermore, the three-dimensional laser scanner is remotely controlled to scan the grain pile according to the planned scanning route; during the scanning process, care is taken to maintain an appropriate distance between the scanner and the grain pile to avoid damage or contamination of the grain; the scanning data is transmitted to the remote computer in real time via a wireless transmission module.

[0042] Furthermore, on a remote computer, professional 3D data processing software is used to process the scanned data, including steps such as denoising, simplification, and fusion; a 3D model of the grain pile is generated based on the processed data; in the 3D model, the length, width, and height of the grain pile can be accurately measured. In this embodiment, the grain pile is approximately an elliptical cone.

[0043] It should be noted that for an irregular conical grain pile, the length of the grain pile is the longest radial length of the bottom of the grain pile, the width of the grain pile is the longest radial length of the bottom of the grain pile perpendicular to the length of the grain pile, and the height of the grain pile is the vertical distance from the highest point on the top of the grain pile to the bottom.

[0044] S13. Obtain data on the temperature fluctuation frequency, time attenuation coefficient and conduction influence coefficient of the grain pile in the grain silo at the terminal.

[0045] Specifically, the steps include:

[0046] S131. Obtain data on the frequency of temperature fluctuations of grain piles in the grain silo at the terminal.

[0047] In one embodiment, temperature sensors and transmitters based on GPRS / 4G transmission are selected. These devices have the characteristics of high precision, low power consumption, and strong anti-interference ability. They are suitable for use in granaries and have built-in large-screen LCD displays for easy on-site data viewing. They also support multiple upload methods, such as uploading collected data to a server via a wireless network base station.

[0048] Furthermore, monitoring equipment is arranged at different heights, different positions, and different grain piles in the granary to comprehensively reflect the overall temperature distribution of the granary. The arrangement of monitoring points should take into account factors such as the volume, height, span of the grain pile, as well as the impact of the external environment on the temperature of the grain pile.

[0049] Furthermore, the monitoring equipment is connected to the management cloud platform to achieve real-time synchronization and remote viewing of data. The cloud platform has functions such as data storage, analysis, and alarm to detect and handle abnormal situations in a timely manner.

[0050] Furthermore, the grain bin temperature data is continuously collected and automatically stored in the cloud platform, and the collected data is processed and analyzed using the data analysis function of the cloud platform to obtain the temperature fluctuation frequency of the grain pile. In this embodiment, the daily fluctuation frequency is taken, and the fluctuation is 1 or 2 times under normal circumstances, and the fluctuation is generally more than 5 times under abnormal circumstances.

[0051] It should be noted that the temperature fluctuation of the grain pile in the wharf granary, as an important facility for grain storage, has an important impact on the storage quality and safety of grain. Therefore, it is necessary to monitor and obtain the temperature fluctuation frequency of the grain pile in real time so as to take timely measures to maintain a suitable storage environment. By implementing a temperature monitoring program, the temperature fluctuation frequency of the grain pile in the wharf granary can be accurately obtained, providing a scientific basis for grain storage management.

[0052] S132. Obtain data on the temperature time attenuation coefficient of the grain pile in the port granary.

[0053] In one embodiment, a temperature and humidity sensor based on GPRS / 4G transmission is selected to ensure that the temperature change of the grain pile can be monitored in real time and accurately. Multiple sensors are arranged at different positions (such as the top, middle, and bottom) and at different heights in the granary to fully reflect the temperature distribution of the grain pile.

[0054] Furthermore, the frequency of sensor data collection is set to once per minute to ensure that the details of temperature changes can be captured, and the collected data is transmitted to the cloud platform in real time for storage and backup, so as to facilitate subsequent analysis.

[0055] Furthermore, an exponential decay model is used to fit the temperature data, and the exponential decay model satisfies the following expression:

[0056] ,

[0057] in, For time The temperature at is the initial temperature, is the temperature time attenuation coefficient.

[0058] Furthermore, the curve fitting tool MATLAB is used to estimate the parameters of the model. For the exponential decay model, it is usually necessary to estimate parameters such as the initial temperature value and the decay coefficient.

[0059] Furthermore, the accuracy of the model was verified by comparing the fitted model curve with the original data curve, and the residual error, determination coefficient and other indicators were calculated to evaluate the fitting effect of the model.

[0060] Furthermore, according to the model with better fitting effect, the data of grain pile temperature time attenuation coefficient are determined.

[0061] S133. Obtain data on the temperature conduction influence coefficient of the grain pile in the grain silo at the dock.

[0062] In one embodiment, data on the temperature conduction influence coefficient of a grain pile in a grain silo at a port are obtained by combining experimental measurement with numerical simulation.

[0063] Specifically, a certain amount of wheat was selected as the experimental grain pile material to ensure the uniformity of the wheat quality and moisture content; a simulated granary environment was constructed, including parameters such as the grain pile stacking method, density (bulk density), porosity, etc., to approach the conditions of an actual granary; and multiple temperature sensors were arranged inside the grain pile to monitor the temperature changes at different locations inside the grain pile in real time.

[0064] Furthermore, the initial temperature of the grain pile is recorded, and a target cooling temperature is set. At the same time, key parameters such as moisture content and density of the grain pile are recorded; cold air is sent into the grain pile through ventilation equipment to reduce the temperature of the grain pile. The stability and continuity of the ventilation equipment should be maintained during this process; the temperature change data of different positions inside the grain pile during the cooling process are recorded, and the temperature change trend over time is analyzed.

[0065] Furthermore, based on the theory of heat and mass transfer in porous media, a mathematical model of coupled heat and moisture transfer in a grain pile is established. The mathematical model should take into account the influence of parameters such as thermal conductivity, thermal diffusivity, moisture content, density, etc. of the grain pile on temperature conduction; the grain pile parameters in the experiment (such as density, porosity, initial temperature, etc.) are input into the mathematical model, and the boundary conditions and initial conditions of the simulation are set; the mathematical model is solved using numerical methods such as computational fluid dynamics to obtain the simulation results of the temperature distribution inside the grain pile.

[0066] Furthermore, the numerical simulation results were compared with the experimental data to verify the accuracy and reliability of the mathematical model; through comparison and analysis, key parameters such as the thermal conductivity and temperature diffusivity of the grain pile were extracted, which reflect the effect of temperature conduction in the grain pile.

[0067] Furthermore, the thermal conductivity and the temperature diffusivity are used in combination with the expression of the grain pile temperature conduction influence coefficient to calculate the data of the grain pile temperature conduction influence coefficient. The expression of the grain pile temperature conduction influence coefficient is as follows:

[0068] ,

[0069] in, is the influence coefficient of grain pile temperature conduction, is the weight factor, is the thermal conductivity, is the thermal conductivity coefficient.

[0070] S14. Obtain data on humidity fluctuation frequency, time attenuation coefficient and conduction influence coefficient of grain pile in the grain silo at the wharf.

[0071] Specifically, the steps include:

[0072] S141. Obtain data on the frequency of humidity fluctuations in the grain pile in the grain silo at the port.

[0073] In one embodiment, a humidity sensor and a wireless transmission device are installed in the grain silo to ensure that all devices are properly connected and working properly.

[0074] Furthermore, data collection parameters are set, monitoring equipment is started, and equipment status and data collection status are remotely monitored in real time.

[0075] Furthermore, the monitoring equipment automatically collects humidity data in the granary and transmits it to the management cloud platform in real time, ensuring stable and reliable data transmission and accurate data.

[0076] Furthermore, the collected humidity data is downloaded from the management cloud platform, and the data is cleaned and sorted to remove abnormal values ​​and duplicate data.

[0077] Furthermore, statistical analysis is performed on the humidity data using statistical software or data analysis tools to calculate the frequency of humidity fluctuations in the grain pile.

[0078] S142. Obtain data on the time attenuation coefficient of the humidity of the grain pile in the grain silo at the dock.

[0079] In one embodiment, humidity sensors are arranged at different heights and positions inside the grain pile to ensure that the distribution of the humidity in the grain pile can be fully reflected, and to ensure that the sensors are properly connected to the data collector and can transmit data in real time.

[0080] Furthermore, the data logger is started to record the real-time data of the humidity sensor, and the data is recorded at regular intervals (such as every hour, every half day or every day), and the data is continuously recorded for a period of time (such as several days, weeks or months) to obtain sufficient humidity change data.

[0081] Furthermore, the recorded humidity data are sorted in chronological order to form a graph showing the change of humidity over time.

[0082] Furthermore, according to the curve graph of humidity changing over time, an exponential decay model is used to describe the decay process of humidity, and the exponential decay model satisfies the following expression:

[0083]

[0084] in, For time The temperature at is the initial humidity, is the temperature time attenuation coefficient.

[0085] Furthermore, the data of the temperature-time attenuation coefficient are obtained by fitting the model parameters.

[0086] S143. Obtain data on the influence coefficient of moisture conduction of grain piles in the grain silo at the port.

[0087] In one embodiment, data on the moisture conduction influence coefficient of grain piles in a grain silo at a port are obtained through experimental measurement and data analysis.

[0088] Specifically, determine the key parameters of the experimental grain pile, such as type, moisture content, and density; arrange humidity sensors inside the grain pile to ensure that the distribution of humidity in the grain pile can be fully reflected; set the initial humidity value and record the time.

[0089] Furthermore, the data logger is started to record the real-time data of the humidity sensor; the data is recorded at regular intervals (such as every hour, every half day or every day) and continuously recorded for a period of time (such as several days, weeks or months) to obtain sufficient humidity change data.

[0090] Furthermore, during the experiment, by changing the ventilation conditions, temperature conditions or humidity source of the grain pile, the changes in humidity conduction are observed; and the humidity change data after the conditions are changed are recorded.

[0091] Furthermore, the recorded humidity data are sorted in chronological order to form a curve graph showing the change of humidity over time; the humidity data at different locations and time points are compared to analyze the law of humidity conduction.

[0092] Furthermore, according to the humidity change curve, the trend and rate of humidity conduction are analyzed; the mathematical model heat conduction equation and moisture migration model are used to describe the humidity conduction process; and the humidity conduction influence coefficient is calculated by fitting the model parameters.

[0093] It should be noted that the moisture conductivity coefficient reflects the ease with which moisture is conducted in the grain pile, and is related to the physical properties of the grain pile, environmental conditions and time factors.

[0094] S15. Obtain grain from the granary at the dock Data on concentration time decay coefficient and conduction influence coefficient.

[0095] Specifically, the steps include:

[0096] S151. Obtain grain piles in the dock granary Data on concentration time decay coefficient.

[0097] In one embodiment, the grain pile in the granary at the wharf is obtained by experimental measurement and data analysis. Data on concentration time decay coefficient.

[0098] Specifically, determine the type, moisture content, density and other key parameters of the experimental grain pile; arrange the grain pile inside Concentration sensor to ensure a comprehensive reflection of the grain pile The distribution of concentration; the arrangement of sensors should take into account factors such as the depth of the grain pile and the lateral distance to obtain more comprehensive data.

[0099] Furthermore, start the data logger and start recording Real-time data from concentration sensors; record data at set intervals and continue recording for a period of time (such as days, weeks or months) to obtain sufficient Concentration change data.

[0100] Furthermore, during the experiment, the ventilation and temperature conditions of the grain pile can be changed or external Source, etc., observe Changes in concentration; record the changes in conditions Concentration change data.

[0101] Furthermore, the recorded The concentration data are sorted in chronological order to form Plot of concentration versus time.

[0102] Furthermore, we compared the Concentration data, described by exponential decay model The exponential decay model of the concentration satisfies the following expression:

[0103] ,

[0104] in, It's time of concentration, For initial concentration, for Concentration time decay coefficient.

[0105] Furthermore, by fitting the model parameters, we can obtain Data on concentration time decay coefficient.

[0106] S152. Obtain grain piles in the dock granary Data on the concentration conduction influence coefficient.

[0107] In one embodiment, the grain pile in the granary at the wharf is obtained by experimental design, data collection and analysis. Data on the concentration conduction influence coefficient.

[0108] Specifically, multiple monitoring points are set up in the granary, including the top, middle and bottom of the grain pile, as well as the edge and center of the grain pile; concentration sensor and ensure that the sensor can accurately measure the Concentration; record initial concentration value and set the monitoring time interval (such as every hour, every half day or every day).

[0109] Furthermore, the data collector is started to record the Concentration data; data is continuously recorded at set intervals until sufficient data is collected for subsequent analysis.

[0110] Furthermore, the analysis of each monitoring point The concentration trend is determined Diffusion and conduction characteristics in grain piles; described using the diffusion equation in mathematical models The conduction process in the grain pile; by fitting the model parameters, we can calculate Concentration conduction influence coefficient.

[0111] S2. Based on the data, a spatiotemporal feature model is constructed.

[0112] In order to deeply understand and predict the temperature, humidity and The spatiotemporal distribution of concentration and its changing trend were analyzed, and three spatiotemporal characteristic models were constructed. These models integrate time series analysis with spatial distribution characteristics in order to achieve accurate simulation and prediction of granary environmental parameters.

[0113] In one embodiment, based on the data of the environmental characteristics of the grain silo at the wharf and the grain pile size characteristics, temperature characteristics, humidity characteristics, and gas concentration characteristics, a temperature spatiotemporal characteristic model, a humidity spatiotemporal characteristic model, and a gas concentration spatiotemporal characteristic model are constructed.

[0114] The temperature spatiotemporal characteristic model satisfies the following expression:

[0115] ,

[0116] in, is the spatial point position of the grain pile Department The temperature of the moment, is the average temperature of the environment around the grain pile, is the maximum variation of the ambient temperature around the grain pile, is the maximum height of the grain pile, for The frequency of fluctuations in direction, for The phase angle of the direction, is the maximum width of the grain pile, is the time attenuation coefficient, for Directional temperature conduction influence coefficient, for Directional temperature conduction influence coefficient, , , is the coordinate of the space point.

[0117] The humidity spatiotemporal characteristic model satisfies the following expression:

[0118] ,

[0119] in, is the spatial point position of the grain pile Department Humidity at all times, is the average humidity of the environment around the grain pile, is the maximum change range of the ambient humidity around the grain pile, is the maximum height of the grain pile, for The frequency of fluctuations in direction, for The phase angle of the direction, is the maximum length of the grain pile, is the time attenuation coefficient, for Directional humidity conduction influence coefficient, for Directional humidity conduction influence coefficient, , , is the coordinate of the space point.

[0120] It should be noted that and The spatial point coordinates represent the coordinates of points in two vertical directions in the horizontal direction. The spatial point coordinates represent the point coordinates perpendicular to the horizontal direction; the horizontal phase angle or vertical phase angle mentioned above is used to describe the phase difference of the periodic change of the temperature field or humidity field in the horizontal direction or vertical direction relative to a reference point. This phase angle is usually used to analyze the fluctuation and propagation characteristics of the temperature field, especially in complex systems involving spatial and temporal changes. The temperature time series data is regarded as a signal and can be extracted using signal processing technology.

[0121] The gas concentration spatiotemporal characteristic model satisfies the following expression:

[0122] ,

[0123] in, is the spatial point position of the grain pile Department The gas concentration at the time, is the average gas concentration around the grain pile, is the maximum variation range of the ambient gas concentration around the grain pile, is the maximum height of the grain pile, is the maximum length of the grain pile, is the maximum width of the grain pile, is the time attenuation coefficient, for Directional gas concentration conduction influence coefficient, is the depth weight coefficient, , , is the coordinate of the space point.

[0124] Furthermore, cross-validation methods, such as K-fold cross-validation, are used to verify the three spatiotemporal feature models and evaluate the prediction performance of the models. Based on the verification results, the parameters of the models are adjusted and optimized to improve the prediction accuracy and generalization ability of the models. The prediction results of the models are compared and analyzed with the actual conditions to verify the accuracy and reliability of the models.

[0125] Furthermore, three spatiotemporal feature models were used to analyze the temperature, humidity and The concentration can be predicted to provide decision support for grain storage management; abnormal situations can be discovered in time and corresponding treatment measures can be taken by monitoring the temporal and spatial changes of environmental parameters. According to the prediction results of environmental parameters, the storage conditions of granaries can be optimized to improve the quality of grain storage.

[0126] S3. Obtaining spatiotemporal feature data according to the spatiotemporal feature model.

[0127] Among them, S3 includes the following steps:

[0128] S31. According to the temperature spatiotemporal characteristic model, the temperature data of multiple spatial points at multiple times in the grain pile space are obtained.

[0129] In one embodiment, 10,000 spatial points of the grain pile are evenly marked.

[0130] Furthermore, the spatial point position information and time information are used as input features and input into the trained temperature spatiotemporal feature model.

[0131] Furthermore, the temperature data of any point of the 10,000 spatial points in the grain pile space at any time is calculated and output.

[0132] S32. According to the humidity spatiotemporal characteristic model, humidity data at multiple spatial points and multiple times in the grain pile space are obtained.

[0133] In one embodiment, 10,000 spatial points of the grain pile are evenly marked.

[0134] Furthermore, the spatial point location information and time information are used as input features and input into the trained humidity spatiotemporal feature model.

[0135] Furthermore, the temperature data of any point of the 10,000 spatial points in the grain pile space at any time is calculated and output.

[0136] S33. According to the gas concentration characteristic model, the gas concentration data at multiple spatial points and multiple times in the grain pile space are obtained.

[0137] In one embodiment, 10,000 spatial points of the grain pile are evenly marked.

[0138] Furthermore, the spatial point location information and time information are used as input features and input into the trained humidity spatiotemporal feature model.

[0139] Furthermore, the gas concentration data of any point of the 10,000 spatial points in the grain pile space at any time is calculated and output.

[0140] S4. Process the spatiotemporal feature data to obtain optimized spatiotemporal feature data.

[0141] Among them, S4 includes the following steps:

[0142] S41. Use the anomaly detection model to perform anomaly detection on the spatiotemporal characteristic data of temperature, humidity and gas concentration.

[0143] In order to detect anomalies in the spatiotemporal feature data of temperature, humidity and gas concentration, the present invention designs a complex anomaly detection model that combines spatiotemporal feature extraction, deep learning and anomaly scoring mechanism. The anomaly detection model satisfies the following expression:

[0144] ,

[0145] in, is the anomaly score, indicating the dataset The degree of abnormality; is an activation function used to map the output data to the interval [0, 1], indicating the probability or degree of abnormality; A weight for each data point that can be adjusted based on the importance of the data or its temporal / spatial proximity; is a fusion function used to fuse the outputs of CNN, LSTM and FCN into a single feature vector, which can be a simple concatenation, weighted average or a more complex neural network; It is a convolutional neural network, which is used to extract Local features in Long Short-Term Memory (LSTM), used to capture time series long-term dependencies in A fully connected network for processing spatial locations , which can be mapped into a feature space; is a spatiotemporal feature dataset containing temperature, humidity and gas concentration, satisfying the following expression:

[0146] ,

[0147] in, For the The feature vector of the data point includes temperature, humidity and concentration, is the timestamp, is the three-dimensional coordinate in space, The data sequence number.

[0148] Furthermore, labeled data containing normal and abnormal samples is collected for training the model; Binary Cross-Entropy Loss or Mean Squared Error Loss can be used to calculate the loss based on the predicted value of the anomaly score and the true label (0 or 1).

[0149] Furthermore, according to the trained model, a threshold is set, and when the anomaly score exceeds the threshold, the data point is considered to be abnormal.

[0150] Furthermore, for the newly collected data, the trained model is used to calculate the anomaly score and perform anomaly detection.

[0151] S42. According to the anomaly detection, the abnormal data is eliminated to obtain the spatiotemporal feature data with missing data points.

[0152] In one embodiment, the abnormal data detected in step S41 is removed, and the data set obtained after the processing is as follows:

[0153] ,

[0154] in, This is a spatiotemporal feature dataset containing temperature, humidity and gas concentration after removing abnormal data. is the number of abnormal data.

[0155] S43. Using Newton's interpolation formula, interpolate the spatiotemporal feature data with missing data points.

[0156] Newton's interpolation formula is a polynomial interpolation method based on the concept of difference quotient, which can construct a polynomial function passing through given data points.

[0157] In one embodiment, the Newton interpolation formula is used to interpolate the spatiotemporal feature data with missing data points to fill in the missing data points. The Newton interpolation formula is as follows:

[0158] ,

[0159] in, for The order difference quotient satisfies the following expression:

[0160] ,

[0161] S44. Obtain optimized spatiotemporal feature data based on the spatiotemporal feature data after the interpolation processing.

[0162] In one embodiment, after interpolation processing in step S43, the obtained data set is as follows:

[0163] ,

[0164] in, It is a spatiotemporal characteristic dataset containing temperature, humidity and gas concentration obtained after interpolation processing.

[0165] The implementation effects of this embodiment are: first, through interpolation processing, missing data points are filled to ensure the continuity and integrity of the data; second, through data smoothing and denoising, noise and outliers are reduced, and the accuracy and reliability of the data are improved; third, feature selection and extraction highlight key spatiotemporal features, making subsequent analysis or modeling more efficient and accurate; fourth, data normalization and standardization make different features comparable, reducing deviations in the model training process; fifth, by fusing multiple spatiotemporal features, a more comprehensive feature representation is obtained, which helps to reveal hidden spatiotemporal patterns and trends.

[0166] S5. Construct a food security risk assessment model by optimizing the spatiotemporal characteristic data.

[0167] Among them, S5 includes the following steps:

[0168] S51. Determine the parameters that affect food security risks by optimizing the spatiotemporal characteristic data.

[0169] In one embodiment, the optimized temperature spatiotemporal characteristic data, humidity spatiotemporal characteristic data and Concentration spatiotemporal characteristic data to determine the parameters that affect food security risks.

[0170] Specifically, the parameters affecting food security risks include: the optimal value, maximum value, minimum value, average value and standard deviation of temperature; the optimal value, maximum value, minimum value, average value and standard deviation of humidity; Set value, maximum, minimum, mean and standard deviation of concentration.

[0171] It should be noted that for temperature parameters, the optimal value represents the temperature that is most conducive to grain storage; the maximum and minimum values ​​are used to evaluate the temperature fluctuation range; the average value reflects the overall temperature conditions; and the standard deviation reflects the stability of temperature fluctuations. For humidity parameters, the optimal value represents the most suitable storage humidity; the maximum and minimum values ​​evaluate humidity fluctuations; the average value shows the overall humidity level; and the standard deviation reveals the stability of humidity fluctuations. For concentration parameters, the set value is the ideal concentration determined according to the grain type and storage requirements; the maximum and minimum values ​​are used to monitor The concentration range; the average value reflects The standard deviation assesses the overall state of the concentration; the standard deviation assesses its fluctuation.

[0172] S52. Construct a food security risk assessment model based on the parameters.

[0173] In one embodiment, according to the requirements of food security risk assessment, feature extraction techniques such as principal component analysis (PCA) are used to select key parameters as features to construct a food security risk assessment model, which satisfies the following expression:

[0174] ,

[0175] in, is the food security risk index, , , are the optimal values ​​of temperature and humidity respectively. The set value of concentration, , , , , The temperature, humidity and The maximum and minimum concentrations, , , , , , are the mean and standard deviation of temperature, humidity and gas concentration, respectively. is the temperature, For humidity, for concentration, is a time trend function, which is used to express the impact of time changes on grain conditions. is the spatial correlation function, which is used to represent the impact of spatial location on grain conditions. , , , , , , , is the weight coefficient.

[0176] It should be noted that in the process of long-term data changes, the temperature, humidity and gas concentration data will change due to the change of time. Therefore, the present invention performs fitting analysis on these data and obtains Function, The function is as follows:

[0177] ,

[0178] in, It is time The temperature at It is time The humidity at It is time of concentration, , , , , , , , is the weight coefficient.

[0179] In addition, different results will be detected at different points in the granary at the same time, and these points will have different effects on temperature, humidity, and gas concentration due to their different positions. Therefore, the present invention introduces a spatial correlation function, which fully considers the correlation of the spatial point positions of the granary. First, an improvement is made on the basis of the Global Moran's I. The spatial correlation function considering the mutual influence between all points as follows:

[0180] ,

[0181] in, is the number of spatial point positions, , is the spatial point position and The detection value of is the spatial point position and The average value of the detection value, is the spatial point position and The detection values ​​include temperature, humidity and gas concentration.

[0182] Then, it should be noted that when calculating the food security risk index at a certain point in the grain pile at a certain moment When , the spatial correlation function needs to calculate the spatial correlation of all other points except this spatial point with it. The specific conditions are: , is the spatial point to be calculated, For all other spatial points in the grain pile, the spatial correlation function in the food security risk assessment model is as follows:

[0183] ,

[0184] S6. Based on the food security risk assessment model, the grain situation in the port granary is monitored.

[0185] Wherein, S6 further comprises the following steps:

[0186] S61. Based on the food security risk assessment model, assess the spatiotemporal grain status of the grain pile.

[0187] Specifically, S61 includes the following steps:

[0188] S611. Based on the food security risk assessment model, the grain condition of the grain pile is assessed at the same spatial point at different times.

[0189] In one embodiment, for the same spatial point in the grain pile, the temperature, humidity and Ensure that the data covers a long enough period of time to capture trends in grain conditions over time.

[0190] Furthermore, the collected data are organized in time series to ensure that the data at each time point contains the optimal value, maximum value, minimum value, average value and standard deviation of temperature, the optimal value, maximum value, minimum value, average value and standard deviation of humidity, and Set value, maximum, minimum, mean and standard deviation of concentration.

[0191] Furthermore, the sorted data are input into the food security risk assessment model to obtain the food situation assessment results at different time points.

[0192] Furthermore, according to the results of the grain condition assessment, a risk warning threshold is set. When the assessment result exceeds the warning threshold, the warning mechanism is triggered to remind the management personnel to take corresponding measures. According to the warning results and the reasons for the change in grain condition, targeted risk management measures are formulated, such as adjusting storage conditions, strengthening ventilation, fumigation, etc.

[0193] Furthermore, based on feedback and data changes in actual applications, the food security risk assessment model is continuously optimized to improve the accuracy and reliability of the assessment. The grain conditions in the grain pile are continuously monitored and the assessment results are regularly updated to ensure the safety and stability of grain storage.

[0194] S612. Based on the food security risk assessment model, the food situation of the grain pile is assessed at different spatial points at the same time.

[0195] In one embodiment, for the same time point in the grain pile, the temperature, humidity and Ensure that the data covers a large enough space to capture the changing trend of grain conditions over space.

[0196] Furthermore, the collected data are sorted according to spatial points to form a spatial distribution data set. Ensure that the data of each spatial point contains the optimal value, maximum value, minimum value, average value and standard deviation of temperature, the optimal value, maximum value, minimum value, average value and standard deviation of humidity, and Set value, maximum, minimum, mean and standard deviation of concentration.

[0197] Furthermore, the sorted data are input into the food security risk assessment model to obtain the food situation assessment results at different spatial points.

[0198] Furthermore, according to the results of the grain condition assessment, a risk warning threshold is set. When the assessment result exceeds the warning threshold, the warning mechanism is triggered to remind the management personnel to take corresponding measures. According to the warning results and the reasons for the change in grain condition, targeted risk management measures are formulated, such as adjusting storage conditions, strengthening ventilation, fumigation, etc.

[0199] Furthermore, based on feedback and data changes in actual applications, the food security risk assessment model is continuously optimized to improve the accuracy and reliability of the assessment. The grain conditions in the grain pile are continuously monitored and the assessment results are regularly updated to ensure the safety and stability of grain storage.

[0200] S62. Based on the results of the evaluation, the grain situation in the grain silo at the port is monitored.

[0201] In one embodiment, the grain situation in the port granary is monitored by utilizing the assessment results of the grain security risk assessment model.

[0202] Specifically, based on the calculation results of the food security risk assessment model, food security risks are divided into four risk levels, namely low risk, medium risk, medium-high risk and high risk.

[0203] The four risk levels correspond to seven non-continuous threshold intervals, and the six threshold intervals correspond to the following situations:

[0204] When the food security risk index In the threshold range , corresponding to medium risk level 1;

[0205] When the food security risk index In the threshold range , corresponding to the medium risk level 2;

[0206] When the food security risk index In the threshold range , corresponding to the medium risk level 3;

[0207] When the food security risk index In the threshold range , corresponding to the medium-high risk level 1;

[0208] When the food security risk index In the threshold range , corresponding to the medium-high risk level 2;

[0209] When the food security risk index In the threshold range , corresponding to the medium-high risk level 3;

[0210] When the food security risk index In the threshold range , corresponding to a high risk level.

[0211] The food security risk index that does not fall within the above risk threshold range indicates normal, and its expression is as follows:

[0212] ,

[0213] in, is the set of abnormal risk threshold intervals, is a collection of low risk threshold intervals.

[0214] It should be noted that in order to facilitate the rapid adoption of treatment measures after abnormal risks are detected, different risk levels are associated with temperature, humidity and The abnormal conditions of concentration were matched one by one.

[0215] The medium risk level 1 corresponds to abnormal temperature, normal humidity, Normal concentration;

[0216] The medium risk level 2 corresponds to normal temperature, abnormal humidity, Normal concentration;

[0217] The medium risk level 3 corresponds to normal temperature, normal humidity, Abnormal concentration;

[0218] Level 1 is medium-high risk, corresponding to abnormal temperature, abnormal humidity, Normal concentration;

[0219] Level 2 medium-high risk level corresponds to abnormal temperature, normal humidity, Abnormal concentration;

[0220] The medium-high risk level 3 corresponds to normal temperature, abnormal humidity, Abnormal concentration;

[0221] High risk level, corresponding to abnormal temperature, abnormal humidity, Abnormal concentration;

[0222] Low risk level corresponds to normal temperature, normal humidity, The concentration is normal.

[0223] When real-time monitoring shows that the food security risk level is medium risk level, medium-high risk level, and high risk level, the grain situation in the granary is judged to be "abnormal", and corresponding intelligent processing measures should be taken.

[0224] The intelligent treatment measures refer to determining the temperature, humidity, concentration, which part has a problem, and adjust the specific temperature, humidity, concentration, respectively, with the corresponding temperature, humidity, If the data is greater than the baseline value, it means that the data is too high and measures to lower the data value are needed; if the data is less than the baseline value, it means that the data is too low and measures to increase the data value are needed.

[0225] It should be noted that the benchmark value is based on the normal temperature, normal humidity, and normal The concentration range is determined by temperature, humidity and The baseline values ​​of concentration are as follows:

[0226] ,

[0227] ,

[0228] ,

[0229] in, is the reference value of temperature, is the reference value of humidity, for The baseline value of concentration, normal temperature, humidity and The concentration ranges are , , .

[0230] Therefore, based on the food security risk assessment model and basic grain data, the present invention sets a reasonable warning threshold range and benchmark value, and formulates a corresponding emergency response plan, thereby achieving continuous and accurate monitoring of the grain condition in the port granary.

[0231] See also Figure 2 , Figure 2The structure diagram of the grain condition monitoring system for a grain silo at a port in an embodiment of the present invention is shown in FIG. The system includes an input device, a processor, an output device, and a memory, wherein the input device, the processor, the output device, and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the system uses the method for monitoring grain condition in a grain silo at a port.

[0232] In this embodiment, the input device uses a variety of instruments, including but not limited to temperature monitors, humidity monitors, and gas concentration monitors; the input device is used to obtain the temperature, humidity, and Concentration data;

[0233] The processor, as the core of the system, includes a computing module and an evaluation module;

[0234] Specifically, the calculation module has various built-in mathematical algorithms, including temperature spatiotemporal characteristic model algorithm, humidity spatiotemporal characteristic model algorithm, Concentration spatiotemporal characteristic model algorithm, food security risk assessment model algorithm, exponential decay model algorithm, temperature, humidity, Concentration conduction influence coefficient algorithm, anomaly detection model algorithm, threshold interval comparison algorithm, and benchmark value comparison algorithm;

[0235] The evaluation module is connected to the calculation module, and the safety risk level of the grain and the grain pile temperature, humidity, To assess food safety risks by analyzing abnormal concentrations;

[0236] The output device includes a display screen, a warning light and a loud speaker;

[0237] Specifically, the display screen is used to display the calculation results of the calculation module and the evaluation results of the evaluation module;

[0238] The warning light does not flash when the food safety risk level is low; it flashes lights of different colors when it is medium, medium-high, or high risk, to notify management personnel to take corresponding measures to increase or decrease the temperature, humidity, measures of concentration;

[0239] Wherein, when the food safety risk level is medium risk level, the warning light flashes white, green and yellow;

[0240] When the food safety risk level is medium or high, the warning light flashes orange, purple, or blue.

[0241] The warning light flashes red when the food safety risk level is a high risk level;

[0242] The loud speaker is used to strengthen risk warnings when the food safety risk level is a high risk level.

[0243] The memory uses a high-speed solid-state hard drive, which has the characteristics of fast reading and writing speed, large capacity and high reliability. It is mainly used to store the original data obtained by the input device and the acquisition device and the result data processed by the processor, and can meet the needs of large data storage.

[0244] See also Figure 3 , Figure 3 The present invention is a flowchart of an algorithm executed by a grain storage monitoring system for a port grain warehouse in an embodiment of the present invention. Figure 3 It reflects the monitoring, data processing and early warning functions of the system.

[0245] In summary, the method for monitoring grain conditions in a grain warehouse provided by the present invention obtains the temperature, humidity and Concentration data avoids the deployment of a large number of sensors in the grain pile, greatly reducing the monitoring cost; by processing the data of the spatiotemporal feature model, high-precision data of infinite spatial points inside the grain pile is effectively obtained, realizing accurate monitoring of the grain condition in the grain warehouse at the terminal; through the food security risk assessment model, comprehensive and real-time monitoring of the grain condition in the grain warehouse at the terminal is realized, which improves the safety and management efficiency of grain storage, which is of great significance for ensuring grain quality and reducing losses, and also provides a scientific basis and technical support for grain storage management. The grain condition monitoring system for the terminal grain warehouse provided by the present invention can realize comprehensive, real-time and accurate monitoring of the grain condition in the terminal grain warehouse, which can not only improve management efficiency, but also reduce labor costs, and provide strong guarantees for the intelligent supervision of grain storage. Through high-precision sensors and Internet of Things technology, the system can monitor the temperature, humidity, It can monitor key parameters such as temperature and humidity to ensure that the grain storage environment is in the best condition, effectively prevent problems such as grain heating and mildew caused by abnormal temperature and humidity, and significantly improve the safety and stability of grain storage. It also has powerful data analysis functions, which can conduct in-depth mining and analysis of historical data, help managers understand the trends and patterns of changes in the granary environment, and provide strong support for the formulation of more scientific and reasonable storage management strategies. It also realizes remote monitoring and intelligent early warning. Once abnormal data is detected, it can immediately trigger the alarm mechanism, and notify managers in a variety of ways to deal with it in a timely manner, effectively avoiding potential safety hazards.

[0246] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for monitoring grain conditions in a wharf granary, characterized in that: The monitoring method comprises the following steps: Obtain data on the environmental characteristics of the grain silo at the wharf, the size characteristics of the grain pile, the temperature characteristics, the humidity characteristics, and the gas concentration characteristics. The data on the environmental characteristics of the grain silo include the average temperature, average humidity, average concentration, maximum temperature change, maximum humidity change and maximum The data of the concentration change amplitude, the data of the grain pile size characteristics include the data of the maximum length, maximum width and maximum height of the grain pile in the granary, the data of the temperature characteristics include the data of the fluctuation frequency, time attenuation coefficient and conduction influence coefficient of the temperature of the grain pile in the granary, the data of the humidity characteristics include the data of the fluctuation frequency, time attenuation coefficient and conduction influence coefficient of the humidity of the grain pile in the granary, the data of the gas concentration characteristics include the data of the maximum length, maximum width and maximum height of the grain pile in the granary, the data of the temperature characteristics include the data of the fluctuation frequency, time attenuation coefficient and conduction influence coefficient of the humidity of the grain pile in the granary Data on time decay coefficient of concentration and conduction influence coefficient; Based on the data, a spatiotemporal characteristic model is constructed, wherein the spatiotemporal characteristic model includes a temperature spatiotemporal characteristic model, a humidity spatiotemporal characteristic model, and a gas concentration spatiotemporal characteristic model. The temperature spatiotemporal characteristic model satisfies the following expression: ， in, is the spatial point position of the grain pile Department The temperature of the moment, is the average temperature of the environment around the grain pile, is the maximum variation of the ambient temperature around the grain pile, is the maximum height of the grain pile, for The frequency of fluctuations in direction, for The phase angle of the direction, is the maximum width of the grain pile, is the time attenuation coefficient, for Directional temperature conduction influence coefficient, for Directional conduction influence coefficient, , , is the coordinate of the spatial point, and the humidity spatiotemporal characteristic model satisfies the following expression: ， in, is the spatial point position of the grain pile Department Humidity at all times, is the average humidity of the environment around the grain pile, is the maximum change range of the ambient humidity around the grain pile, is the maximum height of the grain pile, for The frequency of fluctuations in direction, for The phase angle of the direction, is the maximum length of the grain pile, is the time attenuation coefficient, for Directional humidity conduction influence coefficient, for Directional humidity conduction influence coefficient, , , is the coordinate of the spatial point, and the gas concentration spatiotemporal characteristic model satisfies the following expression: in, is the spatial point position of the grain pile Department The gas concentration at the time, is the average gas concentration around the grain pile, is the maximum variation range of the ambient gas concentration around the grain pile, is the maximum height of the grain pile, is the maximum length of the grain pile, is the maximum width of the grain pile, is the time attenuation coefficient, for Directional gas concentration conduction influence coefficient, is the depth weight coefficient, , , is the coordinate of the space point; According to the spatiotemporal feature model, obtaining spatiotemporal feature data of a plurality of uniformly distributed spatial points at a plurality of time instants; Processing the spatiotemporal feature data to obtain optimized spatiotemporal feature data; By optimizing the spatiotemporal characteristic data, a food security risk assessment model is constructed, and the food security risk assessment model satisfies the following expression: ， in, is the food security risk assessment index, , , are the optimal values ​​of temperature and humidity and the set value of gas concentration, respectively. , are the maximum and minimum values ​​of temperature, respectively. , are the maximum and minimum values ​​of humidity, respectively. is the maximum value of gas concentration, , , , , , are the mean and standard deviation of temperature, humidity and gas concentration, respectively. is the temperature, For humidity, is the gas concentration, is the time trend function, is the spatial correlation function, , , , , , , , is the weight coefficient; According to the food security risk assessment model, the monitoring of the grain situation in the wharf grain warehouse is realized; the monitoring of the grain situation in the wharf grain warehouse according to the food security risk assessment model includes the following steps: Using the food security risk assessment model, the food security risk is divided into levels, including low risk level, medium risk level, medium-high risk level and high risk level; Determining a threshold range of a food security risk assessment index according to the level of the food security risk, wherein the threshold ranges of the food security risk assessment index corresponding to the medium risk level, the medium-high risk level, and the high risk level are not continuous; According to the threshold interval, determining whether the food security risk assessment index of a plurality of spatial points evenly distributed in the grain pile at a plurality of times falls within the threshold interval; Determining a real-time food security risk level according to whether the food security risk assessment index falls within the threshold range; Determine the temperature, humidity and Abnormal concentrations; The grain situation in the port granary is monitored through the real-time food safety risk level and the abnormal situation.

2. A method for monitoring grain conditions in a wharf granary according to claim 1, characterized in that: The processing of the spatiotemporal feature data to obtain optimized spatiotemporal feature data includes: Anomaly detection is performed on the spatiotemporal characteristic data of temperature, humidity and gas concentration using anomaly detection models; According to the anomaly detection, the abnormal data is eliminated to obtain the spatiotemporal feature data with missing data points; Using Newton's interpolation formula, interpolation processing is performed on the spatiotemporal feature data with missing data points; According to the interpolation process, optimized spatiotemporal feature data is obtained.

3. A method for monitoring grain conditions in a wharf granary according to claim 1, characterized in that: Determine the temperature, humidity and Abnormal concentration includes the following steps: Determine whether the food security situation is abnormal or normal based on the real-time food security risk level; According to the determination result of the abnormal grain condition, the temperature, humidity and Abnormal concentration.

4. A method for monitoring grain conditions in a wharf granary according to claim 1, characterized in that: The determination result of the abnormal grain condition determines the temperature, humidity, Abnormal concentrations include: Based on the determination results of abnormal grain conditions, using temperature, humidity, The optimized spatiotemporal characteristic data of concentration are respectively related to the corresponding temperature, humidity, The concentration baseline value is used for comparison; According to the comparison result, the temperature, humidity, Abnormal concentration.

5. A grain condition monitoring system for a wharf grain silo, the system using a grain condition monitoring method for a wharf grain silo according to any one of claims 1 to 4, characterized in that: The system includes an input device, a processor, an output device, and a memory, wherein the input device, the processor, the output device, and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions.

Images