Warehouse wheat mildew early warning system and method based on multi-parameter sensor

Abstract

The present application provides a warehouse wheat mildew early warning system and method based on a multi-parameter sensor, relating to the technical field of wheat mildew early warning, which realizes real-time monitoring and early warning of warehouse wheat mildew by combining a multi-parameter sensor and a gas detection technology.The system can identify the change of carbon dioxide concentration when wheat is stored, locate the mildew risk area, and improve the identification accuracy and processing efficiency.Using the relationship model of the environment and the internal parameters, the system can predict the change of internal temperature and humidity, improving the foresight and adaptability of the mildew risk judgment.Based on the prediction of the change of carbon dioxide concentration and internal temperature and humidity, a comprehensive risk coefficient is generated.This multi-dimensional evaluation mechanism can comprehensively monitor and predict the warehouse environment, provide reliable data support for the management personnel to provide comprehensive risk prediction and coping strategies, and enhance the intelligent level and foresight of warehouse management, thereby reducing the loss caused by wheat mildew.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wheat mold warning, in particular to a warehouse wheat mold warning system and method based on a multi-parameter sensor. BACKGROUND

[0002] In warehouse management, wheat mold is a common and serious problem that affects the quality and safety of grain. Traditional mold monitoring mainly relies on manual inspection and simple environmental monitoring, which is not only time-consuming and labor-intensive, but also prone to miss early signs of mold, leading to irreversible losses. Especially in large warehouse environments, it is difficult to achieve comprehensive and timely monitoring with experience and the naked eye. With the development of technology, multi-parameter sensors have been gradually applied to warehouse management, but existing systems often fail to achieve real-time and comprehensive mold prediction and warning.

[0003] In the prior art, a wheat warehouse moisture monitoring method, device and medium are disclosed in CN115345017A, which includes: modeling the data of a warehouse for storing wheat to obtain a warehouse model, and dividing the warehouse into a plurality of storage units in the warehouse model; for each storage unit, determining the core data corresponding to the storage unit; analyzing the current state of the warehouse according to the warehouse model and the current data of the warehouse collected; and positioning the current abnormal state based on the structural data of the warehouse. Although it can provide real-time warning for uneven distribution of wheat moisture in the warehouse, excessive wheat moisture, excessive moisture change speed, excessive moisture difference between adjacent points, mold, and hardening, the warning direction only considers moisture as a factor, and the warning generated is a real-time warning based on real-time data, which lacks foresight, thus making the specific application scenario narrow and the accuracy low.

[0004] The above information disclosed in the background section is only intended to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute the prior art known to those of ordinary skill in the art. SUMMARY

[0005] The present application aims to provide a warehouse wheat mold warning system and method based on a multi-parameter sensor to solve the problems raised in the background.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0007] The warehouse wheat mold warning system based on a multi-parameter sensor comprises:

[0008] A gas detection module is used to detect the carbon dioxide concentration of wheat at different depths in the warehouse device and send the carbon dioxide concentration to the gas analysis module for analysis.

[0009] a gas analysis module for analyzing the carbon dioxide concentration of the wheat at different depths in the storage device, identifying a risk area according to the analysis result, and sending the risk area to a risk assessment decision module;

[0010] a combined sensing module including an external temperature and humidity sensor and an internal temperature and humidity sensor, for collecting environmental parameters outside the storage device and internal parameters at different depths in the storage device, and sending the environmental parameters and the internal parameters to the risk assessment decision module;

[0011] a risk assessment decision module for assessing the wheat mildew risk according to the identified risk area, the environmental parameters, the internal parameters, and a preset relationship model, and issuing a control signal to an alarm module according to the assessment result;

[0012] an alarm module including green, orange, and red alarm lights and a buzzer, for generating different types of alarms according to different control signals.

[0013] Preferably, the risk assessment decision module includes:

[0014] a first processing unit for generating a first risk coefficient corresponding to the storage device according to the risk area corresponding to the wheat at different depths in the storage device, and sending the first risk coefficient to a comprehensive processing unit;

[0015] a data analysis unit for establishing a relationship model between the environmental parameters and the internal parameters, generating corresponding predicted internal parameters based on the user-set predicted environmental parameters, and sending the predicted internal parameters to a second processing unit;

[0016] a second processing unit for generating a second risk coefficient according to the change of the predicted internal parameters, and sending the second risk coefficient to the comprehensive processing unit;

[0017] a comprehensive processing unit for weighting the first risk coefficient and the second risk coefficient, comparing a comprehensive risk coefficient with a preset risk threshold, and generating different control signals according to the comparison result and sending the control signals to the alarm module.

[0018] Preferably, the setting logic of the gas detection module and the combined sensing module is:

[0019] The gas detection module and the combined sensing module have the same collection frequency and collection frequency;

[0020] K sampling planes are arranged along the depth direction of the storage device at equal intervals, and the depth of the kth sampling plane in the storage device is denoted as l j , where subscript k represents the index of the plane, and k∈[1,K];

[0021] The plane at the depth l k of the storage device is divided into M*N grids in the horizontal and vertical directions, and a gas detection module is arranged at the center of each grid, and the combined sensing module includes an external temperature and humidity sensor and an internal temperature and humidity sensor, wherein the internal temperature and humidity sensor is arranged at the center of the grid of the sampling plane inside the storage device, and the external temperature and humidity sensor is arranged outside the storage device and arranged in the same plane as the sampling plane.

[0022] Preferably, the logic for identifying the risk area of the wheat at different depths in the storage device is as follows:

[0023] The concentration change amount of the carbon dioxide concentration of the wheat at different depths in the storage device is calculated as follows:

[0024] ΔH i,j (l k )=H i,j (l k )-ΔH i,j-1 (l k )

[0025] In the formula, ΔH i,j (l k ) represents the concentration change amount corresponding to the ith grid at the jth collection time when the depth of the storage device is l k , H i,j (l k ) represents the carbon dioxide concentration corresponding to the ith grid at the jth collection time when the depth of the storage device is l k , where j represents the index of the collection time, j∈(1,A], A represents the total number of collections, i represents the index of the grid, i∈[1,MN];

[0026] The average change amount in each grid is calculated as follows:

[0027]

[0028] In the formula, ΔH m,n,i (l k ) represents the average change amount of the ith grid, m and n represent the horizontal and vertical column numbers of the center of the ith grid, respectively, m∈[1,M], n∈[1,N];

[0029] If the average change amount of the grid satisfies:

[0030]

[0031] If the grid is considered as a risk region, wherein ξ represents a preset fluctuation coefficient.

[0032] Preferably, the generation logic of the first risk coefficient is:

[0033] The first sub-risk coefficient corresponding to the carbon dioxide concentration of the wheat at different depths of the storage device is calculated in the following manner:

[0034]

[0035] wherein represents the first sub-risk coefficient corresponding to the depth l k of the storage device, and τ represents the number of risk regions.

[0036] The first sub-risk coefficients are subjected to time series analysis to obtain the predicted values of the first sub-risk coefficients, and the predicted values of the sub-risk coefficients are subjected to weighted processing to generate the first risk coefficient corresponding to the storage device in the following manner:

[0037]

[0038] wherein represents the first risk coefficient, represents the predicted value of the first sub-risk coefficient, μ(l k represents the sub-weight coefficient corresponding to the first sub-risk coefficient of the storage device at the depth l k , μ(l k ) > 0, and μ(l1) + μ(l2) + … + μ(l K ) = 1.

[0039] Preferably, the environmental parameters include environmental temperature and environmental humidity, the internal parameters include internal temperature and internal humidity, the predicted environmental parameters include predicted environmental temperature and predicted environmental humidity, and the predicted internal parameters include predicted internal temperature and predicted internal humidity.

[0040] Preferably, the logic for establishing the relationship model between the environmental parameters and the internal parameters is:

[0041] The collected environmental parameters and internal parameters are subjected to data analysis respectively to generate fitting equations between the environmental temperature and the internal temperature at different depths of the storage device, and between the environmental humidity and the internal humidity at different depths of the storage device.

[0042] The predicted environmental temperature and the predicted environmental humidity are substituted into the fitting equations to generate the predicted internal temperature and the predicted internal humidity corresponding to different depths of the storage device.

[0043] Preferably, the logic for generating the second risk coefficient according to the change of the predicted internal parameters is:

[0044] The second sub-risk coefficient for wheat at different storage depths is calculated as follows:

[0045]

[0046] In the formula Indicates the depth of the storage device is l k The corresponding second sub-risk coefficient, T y (l k H y (l k ) represent storage device depths of l k The predicted internal temperature and predicted internal humidity are given at the location, where T0 and H0 represent the preset baseline temperature and baseline humidity, respectively, and γ1 and γ2 represent the preset adjustment coefficients, respectively.

[0047] The multiple sets of second sub-risk coefficients are then weighted to generate a second risk coefficient corresponding to the storage device. The calculation method is as follows:

[0048]

[0049] In the formula This indicates the second risk factor. This represents the second sub-risk coefficient.

[0050] Preferably, the comprehensive risk coefficient is calculated as follows:

[0051]

[0052] In the formula, ω represents the comprehensive risk coefficient, a1 and a2 represent the weighting coefficients of the first risk coefficient and the second risk coefficient, respectively, a1 and a2 are both greater than 0, and a1+a2=1;

[0053] When ω≤ω y1 At that time, the risk of wheat mold was considered low, and only the green warning light of the alarm module lit up;

[0054] When ω y1 <ω≤ω y2 At that time, the risk of wheat mold was considered to be moderate, and only the orange warning light on the alarm module lit up;

[0055] When ω y2 When the value is less than ω, the risk of wheat mold is considered high, the red alarm light on the alarm module illuminates, and the buzzer sounds.

[0056] In the formula ω y1 ω y2 ω represents the preset first risk threshold and second risk threshold, respectively. y1 ω y2are all greater than 0 and ω y1 < ω y2 .

[0057] The warehouse wheat mildew early warning method based on a multi-parameter sensor is suitable for the warehouse wheat mildew early warning system, and the specific steps include:

[0058] S1: Collecting the carbon dioxide concentration of wheat at different depths in the storage device, analyzing the carbon dioxide concentration of wheat at different depths in the storage device, identifying the risk area according to the analysis result, and generating a first risk coefficient corresponding to the storage device;

[0059] S2: Collecting the environmental parameters outside the storage device and the internal parameters at different depths in the storage device, establishing a relationship model between the environmental parameters and the internal parameters, generating predicted internal parameters by using the relationship model and the predicted environmental parameters, and generating a second risk coefficient according to the change;

[0060] S3: The first risk coefficient and the second risk coefficient are weighted to generate a comprehensive risk coefficient, which is compared with a preset risk threshold, and different types of alarms are generated according to the comparison result.

[0061] Compared with the prior art, the beneficial effects of the present application are:

[0062] The present application realizes real-time monitoring and early warning of the mildew of stored wheat by combining a multi-parameter sensor and a gas detection technology. The system can accurately identify the change of carbon dioxide concentration of wheat during storage, locate the mildew risk area, and improve the identification accuracy and processing efficiency. By using the relationship model of the environment and the internal parameters, the system can predict the change of internal temperature and humidity, improve the foresight and adaptability of the mildew risk judgment. Based on the prediction of the change of carbon dioxide concentration and internal temperature and humidity, a comprehensive risk coefficient is generated. This multi-dimensional evaluation mechanism can comprehensively monitor and predict the storage environment, provide reliable data support for management personnel to provide comprehensive risk prediction and coping strategies, and enhance the intelligent level and foresight of storage management, thereby reducing the loss caused by wheat mildew. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 The module structure diagram of the present application;

[0064] Figure 2 The overall method flowchart of the present application;

[0065] Figure 3 The change trend graph between carbon dioxide concentration and storage depth in the present application;

[0066] Figure 4 The change trend graph between temperature and storage depth in the present application;

[0067] Figure 5 Figure for the change trend between humidity and storage depth in the present application;

[0068] Figure 6 Figure for the change trend between comprehensive risk coefficient and storage depth in the present application. DETAILED DESCRIPTION

[0069] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with specific examples.

[0070] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present application should be understood as the general meaning understood by those skilled in the art to which the present application belongs. The terms "first", "second" and similar terms used in the present application do not represent any order, number or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar terms mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "up", "down", "left", "right" and the like only represent relative positional relationships, which may change accordingly when the absolute position of the described object changes.

[0071] EMBODIMENT

[0072] Referring to Figures 1-6 The present application provides a technical solution:

[0073] The warehouse wheat mildew early warning system based on a multi-parameter sensor comprises a gas detection module, a gas analysis module, a combined sensing module, a risk assessment decision module, and an alarm module, wherein the risk assessment decision module comprises a first processing unit, a data analysis unit, a second processing unit, and a comprehensive processing unit.

[0074] The gas detection module is used to detect the carbon dioxide concentration of wheat at different depths in the storage device and send the carbon dioxide concentration to the gas analysis module for analysis.

[0075] The setting logic of the gas detection module and the combined sensing module is as follows:

[0076] The gas detection module and the combined sensing module have the same acquisition frequency and acquisition frequency;

[0077] K sampling planes are arranged at equal intervals along the depth direction of the storage device, and the depth of the kth sampling plane in the storage device is denoted as l k, subscript k represents the index of the plane, and k∈[1,K];

[0078] The plane at the depth l k of the storage device is divided into M*N grids in the horizontal and vertical directions, a gas detection module is arranged at the center of each grid, the combined sensing module includes an external temperature and humidity sensor and an internal temperature and humidity sensor, wherein the internal temperature and humidity sensor is arranged at the center of the grid of the sampling plane inside the storage device, and the external temperature and humidity sensor is arranged outside the storage device and is arranged in the same plane as the sampling plane.

[0079] Specifically, the depth can also be divided according to the total depth of the storage device, for example, a storage device with a total depth of 3m, the depth from top to bottom is 0-1m for shallow layer, 1-2m for middle layer, and 2-3m for deep layer. After such division, it is more intuitive and convenient to study the typical depth (for example, the middle depth of each layer).

[0080] The gas analysis module is used to analyze the carbon dioxide concentration of the wheat at different depths in the storage device, identify the risk area according to the analysis result, and send the risk area to the first processing unit.

[0081] The logic for identifying the risk area of the wheat at different depths in the storage device is as follows:

[0082] The concentration change amount of the carbon dioxide concentration of the wheat at different depths in the storage device is calculated as follows:

[0083] ΔH i,j (l k )=H i,j (l k )-ΔH i,j-1 (l k )

[0084] The average change amount in each grid is calculated as follows:

[0085]

[0086] In the formula, ΔH i,j (l k ) represents the concentration change amount of the i-th grid corresponding to the j-th collection at the depth l k of the storage device, H i,j (l k ) represents the gas concentration of the i-th grid corresponding to the j-th collection at the depth l k of the storage device, wherein j represents the index of the collection number, j∈(1,A] and A represents the total number of collections, i represents the index of the grid, i∈[1,MN], and ΔH m,n,i (l k) represents the average change of the i-th grid, m and n represent the horizontal and vertical column numbers of the center of the i-th grid respectively, m∈[1, M], n∈[1, N]. By dividing the plane of the storage device at different depths into multiple small grids, the system can detect subtle local changes instead of simply relying on the change of the entire plane at that depth, which improves the accuracy of risk identification.

[0087] If the average change of a certain grid satisfies:

[0088]

[0089] then the grid is considered as a risk area, where ξ represents the preset fluctuation coefficient. Using the average change as the basis for judgment can balance the influence of abnormal points and reduce the misjudgment rate. Moreover, by introducing the fluctuation coefficient, the system can be flexibly adjusted according to different risk sensitivity requirements to adapt to different application scenarios.

[0090] In this step, by accurately identifying the risk area, more accurate input data can be provided for the subsequent risk assessment module, improving the early warning capability of the overall system. Moreover, after receiving the accurate concentration change and risk area information, the first processing unit can better calculate the first risk coefficient, thereby improving the accuracy of comprehensive risk assessment. Furthermore, due to the use of efficient grid calculation and change judgment algorithm, this step can support real-time data processing, making the overall system more agile in rapidly changing environments.

[0091] The first processing unit is configured to generate a first risk coefficient corresponding to the storage device according to the risk area corresponding to the different depths of wheat in the storage device, and send the first risk coefficient to the comprehensive processing unit.

[0092] The generation logic of the first risk coefficient is as follows:

[0093] The first processing unit is configured to generate a first risk coefficient corresponding to the storage device according to the risk area corresponding to the different depths of wheat in the storage device, and send the first risk coefficient to the comprehensive processing unit.

[0094]

[0095] wherein represents the first sub-risk coefficient corresponding to the depth l k of the storage device, and τ represents the number of risk areas.

[0096] It can be understood that the first sub-risk coefficient is proportional to the concentration change and the proportion of the risk area, because the release of carbon dioxide usually accompanies the mold of wheat, and when the concentration change of some areas is too large, it may be an early reflection of the impending mold. Quantifying the number of risk areas and the concentration change provides an objective standard for evaluating risk.

[0097] The first sub-risk coefficients are analyzed in time sequence to obtain the prediction value of the first sub-risk coefficient, and the prediction value of the sub-risk coefficient is weighted to generate the first risk coefficient corresponding to the storage device, and the calculation method is:

[0098]

[0099] In the formula, represents the first risk coefficient, represents the prediction value of the first sub-risk coefficient, μ(l k ) represents the sub-weight coefficient corresponding to the first sub-risk coefficient of the storage device with a depth of l k , μ(l k )>0, and μ(l1)+μ(l2)+…+μ(l K )=1. The sub-weight coefficient can be set according to the depth of the storage device, and the sub-weight coefficient increases with the increase of the depth, because the wheat at the bottom of the storage device is more prone to mold, so a larger sub-weight coefficient is needed to reflect it. The value and setting method of the sub-weight coefficient can be specifically set according to the user's experience.

[0100] By combining depth, time and space multi-dimensional factors, the prediction value of the first risk coefficient can more comprehensively reflect the risk status of the stored wheat, providing high-quality input for subsequent comprehensive evaluation, ensuring that the system can quickly respond to risk changes, improving the sensitivity and accuracy of early warning, and according to the influence of different depth risks, the weighted processing ensures the rationality and accuracy of the overall risk assessment result.

[0101] In this step, by comprehensively considering time, depth and local change, an accurate, dynamic and comprehensive risk assessment system is provided, which can identify potential risk trends in advance and provide long-term risk prediction capability.

[0102] The combination sensing module is used to collect environmental parameters outside the storage device and internal parameters at different depths inside the storage device, and sends the environmental parameters and internal parameters to the data analysis unit, the gas detection module, and the combination sensing module has the same collection frequency and collection frequency.

[0103] The data analysis unit is configured to establish a relationship model between the environmental parameters and the internal parameters, generate corresponding predicted internal parameters based on the predicted environmental parameters set by the user, and send the predicted internal parameters to the second processing unit. The environmental parameters include environmental temperature and environmental humidity. The internal parameters include internal temperature and internal humidity. The predicted environmental parameters include predicted environmental temperature and predicted environmental humidity. The predicted internal parameters include predicted internal temperature and predicted internal humidity.

[0104] The logic for establishing the relationship model between the environmental parameters and the internal parameters is as follows:

[0105] The collected environmental parameters and internal parameters are subjected to data analysis to generate fitting equations between the environmental temperature and the internal temperature at different depths of the storage device, and between the environmental humidity and the internal humidity at different depths of the storage device.

[0106] The input variables of the fitting equations are the collected environmental parameters and internal parameters, and the output variables are the internal temperature and internal humidity at different depths of the storage device. When constructing the fitting equations, statistical analysis or machine learning methods can be used for construction. Hierarchical linear regression models, multivariate linear regression models, machine learning models, and other function expressions can be used. The specific equation form can be determined according to expert experience.

[0107] The predicted environmental temperature and predicted environmental humidity are used as input variables to substitute into the fitting equations to generate the predicted internal temperature and predicted internal humidity corresponding to different depths of the storage device (i.e., the output variables of the fitting equations).

[0108] In this step, the predicted environmental temperature and predicted environmental humidity can be obtained from weather forecasts issued by weather stations. The fitting equations generated through data analysis can accurately describe the relationship between environmental parameters and internal parameters, improve the accuracy of prediction, and generate predicted internal parameters in advance to provide forward-looking support for storage management. Moreover, the prediction model can be flexibly adjusted according to different environmental conditions and storage requirements, improving the applicability and robustness of the system and enhancing the intelligent level of the system.

[0109] The second processing unit is configured to generate a second risk coefficient based on the changes in the predicted internal parameters and send the second risk coefficient to the comprehensive processing unit.

[0110] The logic for generating the second risk coefficient based on the changes in the predicted internal parameters is as follows:

[0111] The second sub-risk coefficients corresponding to the wheat at different depths of the storage device are calculated, and the calculation method is as follows:

[0112]

[0113] wherein Indicates the depth of the storage device is l k The corresponding second sub-risk coefficient, T y (l k H y (l k ) represent storage device depths of l k The predicted internal temperature and predicted internal humidity are given at the location, where T0 and H0 represent the preset baseline temperature and baseline humidity, respectively, and γ1 and γ2 represent the preset adjustment coefficients.

[0114] This system uses an exponential function to calculate the second sub-risk coefficient, effectively capturing and amplifying the impact of temperature and humidity changes on risk, thus more accurately reflecting the risk level. Furthermore, by changing the adjustment coefficient, the sensitivity of the risk assessment can be flexibly adjusted according to the requirements of different storage environments. Quantifying the risk of the predicted parameters allows the system to identify potential high-risk areas earlier, strengthening its early warning capabilities and enabling it to better adapt to different storage environments, thereby improving the robustness of the solution.

[0115] The multiple sets of second sub-risk coefficients are then weighted to generate a second risk coefficient corresponding to the storage device. The calculation method is as follows:

[0116]

[0117] In the formula This indicates the second risk factor. This represents the second sub-risk coefficient. Independent analysis of warehousing conditions at each depth identifies risk differences between depths, improving the comprehensiveness of risk assessment. Furthermore, by weighting the sub-risk coefficients at different depths, the impact of each layer can be comprehensively considered, thereby improving the accuracy of the overall risk assessment.

[0118] The integrated processing unit is used to perform weighted processing on the first risk coefficient and the second risk coefficient, generate an integrated risk coefficient, compare it with the preset risk threshold, and generate different control signals based on the comparison results and send them to the alarm module.

[0119] The alarm module includes alarm lights in three colors: green, orange, and red, and a buzzer, used to generate different types of alarms based on different control signals.

[0120] The comprehensive risk coefficient is calculated as follows:

[0121]

[0122] In the formula, ω represents the comprehensive risk coefficient, a1 and a2 respectively represent the weight coefficients of the first risk coefficient and the second risk coefficient. Both a1 and a2 are greater than 0, and a1 + a2 = 1. Since wheat mildew is mainly caused by changes in temperature and humidity, and the change in carbon dioxide concentration is also caused by changes in temperature and humidity, which is an external reflection during wheat mildew. Therefore, when constructing the comprehensive risk coefficient, the second risk coefficient is used as the main evaluation criterion, and the first risk coefficient is used as the secondary evaluation criterion. Accordingly, a1 < a2 is set. It is不难看出 from the calculation formulas of the first risk coefficient and the second risk coefficient that both are risk predictions for the mildew of wheat in the storage device at a certain future moment. The comprehensive risk coefficient is the result jointly predicted by combining multi-dimensional factors such as the carbon dioxide concentration, temperature, and humidity of wheat, which can comprehensively monitor and predict the storage environment, provide reliable data support for management personnel, and help them make more scientific decisions, thereby reducing losses and improving storage efficiency.

[0123] When ω ≤ ω y1 , it is considered that the risk of wheat mildew is low, and only the green alarm light of the alarm module lights up;

[0124] When ω y1 <ω ≤ ω y2 , it is considered that the risk of wheat mildew is medium, and only the orange alarm light of the alarm module lights up;

[0125] When ω t2 <ω, it is considered that the risk of wheat mildew is high, and the red alarm light of the alarm module lights up, and the buzzer works;

[0126] In the formula, ω y1 、ω y2 respectively represent the preset first risk threshold and second risk threshold. Both ω y1 、ω y2 are greater than 0 and ω t1 <ω y2 .

[0127] In this embodiment, a storage device with a depth of 3m is detected. The detection depth is taken as a gradient of 0.2m, and the total number of acquisitions is set to 5 times. The first risk threshold and the second risk threshold are respectively set to 0.5 and 0.7. The final detection data is shown in the following table:

[0128]

[0129] Table 1: Detection data of stored wheat

[0130] From the data in the above table and Figures 3-6It can be seen that the carbon dioxide concentration, temperature, humidity and comprehensive risk coefficient all increase with the increase of the storage depth, showing a positive correlation. This is because the ventilation of the grain pile gradually weakens from the surface to the inside, the oxygen content in the deep layer is reduced, and the microbial metabolism is strengthened due to the limited ventilation, so the microorganisms decompose organic matter under the condition of relative anaerobic conditions to increase the carbon dioxide, and the metabolic heat leads to the gradual increase of temperature and humidity; the change trend of the comprehensive risk coefficient is similar to that of the carbon dioxide concentration, humidity and temperature, so it can well reflect the overall change trend of these parameters, and the actual factors of the moldy wheat in the storage are used for the final risk evaluation.

[0131] The application also provides a warehouse wheat mildew early warning method based on a multi-parameter sensor, which is suitable for the warehouse wheat mildew early warning system.

[0132] S1: Collecting the carbon dioxide concentration of the wheat at different depths in the storage device, analyzing the carbon dioxide concentration of the wheat at different depths in the storage device, identifying the risk area according to the analysis result, and generating a first risk coefficient corresponding to the storage device;

[0133] S2: Collecting the environmental parameters outside the storage device and the internal parameters at different depths in the storage device, establishing a relationship model between the environmental parameters and the internal parameters, generating predicted internal parameters by using the relationship model and the predicted environmental parameters, and generating a second risk coefficient according to the change;

[0134] S3: The first risk coefficient and the second risk coefficient are weighted to generate a comprehensive risk coefficient, which is compared with a preset risk threshold, and different types of alarms are generated according to the comparison result.

[0135] In summary, the application realizes real-time monitoring and early warning of warehouse wheat mildew by combining multi-parameter sensors and gas detection technology. The system can identify the change of carbon dioxide concentration of wheat during storage, locate the mildew risk area, improve the identification accuracy and processing efficiency. Using the relationship model of environmental and internal parameters, the system can predict the change of internal temperature and humidity, improve the foresight and adaptability of mildew risk judgment. Based on the prediction of carbon dioxide concentration change and internal temperature and humidity change, a comprehensive risk coefficient is generated. This multi-dimensional evaluation mechanism can comprehensively monitor and predict the storage environment, provide reliable data support for management personnel to provide comprehensive risk prediction and response strategy, enhance the intelligent level and foresight of warehouse management, and reduce the loss caused by wheat mildew.

[0136] The above formulas are dimensionless values, and the formulas are obtained by software simulation of a large amount of data to obtain a formula of the latest real situation, and the preset parameters in the formula are set by the person skilled in the art according to the actual situation.

[0137] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0138] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, and can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0139] The above describes only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered by the protection scope of the present application.

Claims

1. A warehouse wheat mold early warning system based on multi-parameter sensors, characterized in that, include: A gas detection module is used to detect the carbon dioxide concentration of wheat at different depths within the storage device and send the carbon dioxide concentration data to a gas analysis module for analysis. The gas analysis module is used to analyze the carbon dioxide concentration of wheat at different depths within the storage device, identify risk areas based on the analysis results, and send the risk areas to the risk assessment and decision-making module. The combined sensing module includes an external temperature and humidity sensor and an internal temperature and humidity sensor, which are used to collect environmental parameters outside the storage device and internal parameters at different depths inside the storage device, respectively, and send the environmental parameters and internal parameters to the risk assessment and decision module. The configuration logic for the gas detection module and the combined sensing module is as follows: The gas detection module and the combined sensing module have the same acquisition frequency and acquisition frequency. K sampling planes are set at equal intervals along the depth direction of the storage device, and the depth of the k-th sampling plane in the storage device is calibrated as l. k The subscript k represents the index of the plane, and k∈[1,K]; The storage device has a depth of l k The plane at the location is divided into M*N grids in both the horizontal and vertical directions. A gas detection module is set at the center of each grid. The internal temperature and humidity sensor is set at the center of the grid on the sampling plane inside the storage device, while the external temperature and humidity sensor is set on the outside of the storage device and on the same plane as the sampling plane. The risk assessment and decision-making module is used to assess the risk of wheat mold based on the identified risk areas, environmental parameters, and internal parameters, combined with a preset relationship model, and to send control signals to the alarm module based on the assessment results. The risk assessment and decision-making module includes: The first processing unit is used to generate a first risk coefficient corresponding to the storage device based on the risk areas corresponding to wheat at different depths within the storage device, and send the first risk coefficient to the comprehensive processing unit. The data analysis unit is used to establish a relationship model between environmental parameters and internal parameters, generate corresponding predicted internal parameters based on the predicted environmental parameters set by the user, and send the predicted internal parameters to the second processing unit. The second processing unit is used to generate a second risk coefficient based on the changes in the predicted internal parameters, and send the second risk coefficient to the comprehensive processing unit. The integrated processing unit is used to perform weighted processing on the first risk coefficient and the second risk coefficient, generate an integrated risk coefficient, compare it with a preset risk threshold, and generate different control signals based on the comparison result and send them to the alarm module. The alarm module includes alarm lights in three colors: green, orange, and red, and a buzzer, which are used to generate different types of alarms based on different control signals.

2. The warehouse wheat mold early warning system based on multi-parameter sensors according to claim 1, characterized in that: The logic for identifying risk zones for wheat at different depths within the storage facility is as follows: The method for calculating the change in carbon dioxide concentration in wheat at different depths within the storage facility is as follows: ΔH i,j (l k )=H i,j (l k )-ΔH i,j-1 (l k ) In the formula ΔH i,j (l k ) indicates that the depth of the storage device is l k H represents the concentration change corresponding to the i-th grid during the j-th data collection. i,j (l k ) indicates that the depth of the storage device is l k , where j represents the index of the number of collections, j∈(1,A], A represents the total number of collections, and i represents the index of the grid, i∈[1,MN]; The average change within each grid cell is calculated as follows: In the formula ΔH m,n,i (l k ) represents the average change of the i-th grid, and m and n represent the horizontal and vertical column indices of the center of the i-th grid, respectively, m∈[1,M], n∈[1,N]; If the average change of the grid satisfies: The grid is then considered a risk zone, where ξ represents the preset volatility coefficient.

3. The warehouse wheat mold early warning system based on multi-parameter sensors according to claim 2, characterized in that: The logic for generating the first risk coefficient is as follows: The first sub-risk coefficient corresponding to the carbon dioxide concentration of wheat at different depths in the storage facility is calculated as follows: In the formula Indicates the depth of the storage device is l k The first sub-risk coefficient corresponding to the location, where τ represents the number of risk areas; Time series analysis is performed on multiple sets of first sub-risk coefficients to obtain predicted values ​​of the first sub-risk coefficients. Then, the predicted values ​​of the sub-risk coefficients are weighted to generate the first risk coefficient corresponding to the storage device. The calculation method is as follows: In the formula This indicates the first risk factor. μ(l) represents the predicted value of the first sub-risk coefficient. k ) indicates a storage device depth of l k The sub-weight coefficient corresponding to the first sub-risk coefficient, μ(l k )>0, and μ(l1)+μ(l2)+…+μ(l K ) = 1.

4. The warehouse wheat mold early warning system based on multi-parameter sensors according to claim 3, characterized in that: The environmental parameters include ambient temperature and ambient humidity; the internal parameters include internal temperature and internal humidity; the predicted environmental parameters include predicted ambient temperature and predicted ambient humidity; and the predicted internal parameters include predicted internal temperature and predicted internal humidity.

5. The warehouse wheat mold early warning system based on multi-parameter sensors according to claim 4, characterized in that: The logic for establishing a model of the relationship between environmental parameters and internal parameters is as follows: The collected environmental and internal parameters were analyzed to generate fitting equations between the ambient temperature and the internal temperature at different depths of the storage device, and between the ambient humidity and the internal humidity at different depths of the storage device. By substituting the predicted ambient temperature and humidity into the fitting equation, the predicted internal temperature and humidity corresponding to different depths of the storage device are generated.

6. The warehouse wheat mold early warning system based on multi-parameter sensors according to claim 5, characterized in that: The logic for generating the second risk coefficient based on the predicted changes in internal parameters is as follows: The second sub-risk coefficient for wheat at different storage depths is calculated as follows: In the formula Indicates the depth of the storage device is l k The corresponding second sub-risk coefficient, T y (l k H y (l k ) represent storage device depths of l k The predicted internal temperature and predicted internal humidity are given at the location, where T0 and H0 represent the preset baseline temperature and baseline humidity, respectively, and γ1 and γ2 represent the preset adjustment coefficients, respectively. The multiple sets of second sub-risk coefficients are then weighted to generate a second risk coefficient corresponding to the storage device. The calculation method is as follows: In the formula This indicates the second risk factor. This represents the second sub-risk coefficient.

7. The warehouse wheat mold early warning system based on multi-parameter sensors according to claim 6, characterized in that: The comprehensive risk coefficient is calculated as follows: In the formula, ω represents the comprehensive risk coefficient, a1 and a2 represent the weighting coefficients of the first risk coefficient and the second risk coefficient, respectively, a1 and a2 are both greater than 0, and a1+a2=1; When ω≤ω y1 At that time, the risk of wheat mold was considered low, and only the green warning light of the alarm module lit up; When ω y1 <ω≤ω y2 At that time, the risk of wheat mold was considered to be moderate, and only the orange warning light on the alarm module lit up; When ω y2 When the value is less than ω, the risk of wheat mold is considered high, the red alarm light on the alarm module illuminates, and the buzzer sounds. In the formula ω y1 ω y2 ω represents the preset first risk threshold and second risk threshold, respectively. y1 ω t2 All are greater than 0 and ω y1 <ω y2 .

8. A method for early warning of mold growth in stored wheat based on multi-parameter sensors, characterized in that: The method for early warning of mold growth in stored wheat is applicable to the wheat mold early warning system according to any one of claims 1-7, and the specific steps include: S1: Collect carbon dioxide concentrations of wheat at different depths within the storage device, analyze the carbon dioxide concentrations of wheat at different depths within the storage device, identify risk areas based on the analysis results, and generate a first risk coefficient corresponding to the storage device. S2: Collect environmental parameters outside the storage facility and internal parameters at different depths inside the storage facility, establish a relationship model between environmental parameters and internal parameters, use the relationship model and predicted environmental parameters to generate predicted internal parameters, and generate a second risk coefficient based on their changes. S3: The first risk coefficient and the second risk coefficient are weighted to generate a comprehensive risk coefficient, which is then compared with a preset risk threshold. Different types of alarms are generated based on the comparison results.

Images