A method, device and medium for monitoring moisture of a wheat store

Abstract

This application discloses a method, device, and medium for monitoring moisture in wheat warehouses. The method includes: data modeling of the warehouse used for storing wheat to obtain a warehouse model, and dividing the warehouse into several storage units within the warehouse model; determining the core data corresponding to each storage unit; analyzing the current state of the warehouse based on the warehouse model and the collected current data; and locating the current abnormal state based on the warehouse's structural data. Through data modeling and storage unit division, this method solves the problems of difficulty in detecting the causes, scope, and severity of abnormal wheat moisture levels, as well as the inaccurate problem location and untimely handling. It enables real-time early warning of abnormalities such as uneven wheat moisture distribution, excessively high wheat moisture, excessively rapid moisture changes, excessive moisture differences between adjacent points, mold, and compaction within the warehouse.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electric data processing, in particular to a wheat warehouse moisture monitoring method, device and medium. BACKGROUND

[0002] At present, in the traditional scheme, the whole industry still stays in manual sampling collection of wheat samples, and then detects the moisture of the wheat samples through instruments, and analyzes the overall situation in the warehouse through the samples.

[0003] Therefore, in the traditional scheme, the data detection is relatively rough, the representation is not strong, the analyzed data is less, the analysis strength and abnormal influencing factors are insufficient, the grasping opportunity of the abnormal situation of the wheat moisture in the warehouse is delayed, and there is no effective analysis means for the prediction of the future wheat moisture abnormality, so that the keeper needs to invest a lot of manpower and material resources to govern the abnormal situation.

[0004] In addition, there are many factors affecting the change of wheat moisture, and the influence range of each factor is different due to different actual scenes; at the same time, if the temperature of grain is heated due to pest activity or the temperature difference of each part of the warehouse is too large, the phenomenon of wheat moisture transfer from one part of the grain pile to another part may occur; it is difficult to analyze and obtain accurate analysis results only through the traditional scheme. SUMMARY

[0005] In order to solve the above problems, the present application provides a wheat warehouse moisture monitoring method, which comprises:

[0006] Data modeling is performed on the warehouse for storing wheat to obtain a warehouse model, and the warehouse is divided into a plurality of storage units in the warehouse model;

[0007] For each storage unit, the core data corresponding to the storage unit is determined, and the corresponding definition threshold for the storage unit is generated according to the core data, so that the definition threshold is used for the abnormal judgment standard of the storage unit and added to the warehouse model;

[0008] According to the warehouse model and the current data of the warehouse collected, the current state of the warehouse is analyzed by a spatial analysis method, so that the current abnormal state of the warehouse is obtained by analyzing the nearby nodes of the abnormal node in the warehouse model, and the current abnormal state includes the occurrence point, the occurrence time and the influence range;

[0009] Based on the structure data of the warehouse, the current abnormal state is positioned, and the positioning result is displayed to the user.

[0010] In one example, a warehouse for storing wheat is data modeled to obtain a warehouse model, specifically comprising:

[0011] A warehouse for storing wheat is spatially modeled to divide the warehouse into a plurality of storage units according to structure data of the warehouse in a obtained spatial model, the structure data comprising at least one of deployment structure of the moisture measuring cable, warehouse shape, warehouse volume, and grain pile volume;

[0012] For each of the storage units, corresponding moisture influencing factors in the storage unit are determined, and the moisture influencing factors in the storage unit are sorted according to scenarios to obtain a plurality of data groups, and the influence weight and influence range of each moisture influencing factor in the storage unit are determined by arranging and combining the plurality of data groups, so as to realize data modeling of the storage unit;

[0013] For the storage units that have realized data modeling, a mutual influence relationship therebetween is established, so as to realize data modeling of the warehouse to obtain a warehouse model.

[0014] In one example, the moisture influencing factors comprise at least one of a grain storage ecological region to which the warehouse belongs, current ecological region characteristics, local safe moisture, warehouse type, warehouse volume, wheat storage variety in the warehouse, current quality of the wheat, historical moisture condition, final use of the wheat, storage time of the wheat, warehouse temperature and humidity, atmospheric temperature and humidity, specific position of the storage unit in the warehouse, and moisture data of a collection point of the storage unit.

[0015] In one example, the core data comprises at least one of a warehouse where the core data is located, interval of high moisture value of different varieties to a moisture measuring point, abnormal interval of the moisture measuring point and average moisture difference value of the layer where the moisture measuring point is located, rate value of the moisture measuring point changing too fast in a period of time, ratio of a fault point to all moisture measuring points, current mold probability, current clumping probability, future mold probability, and future clumping probability.

[0016] In one example, according to the warehouse model and current data of the warehouse collected, a current state of the warehouse is analyzed by a spatial analysis method to obtain a current abnormal state of the warehouse, specifically comprising:

[0017] According to the defined threshold in the warehouse model and the current data of the warehouse collected, a current state of the warehouse is analyzed to determine an abnormal node that has occurred in the warehouse model;

[0018] analyzing, by a spatial analysis method, the nearby nodes of the abnormal node in the warehouse model to determine a neighboring water difference value between the nearby nodes and the abnormal node, the nearby nodes including at least one of upper and lower layer nodes, left and right column nodes, and left and right row nodes of the abnormal node;

[0019] determining, according to the neighboring water difference value, a point of occurrence and an influence range in a current abnormal state of the warehouse.

[0020] In one example, after determining, according to the neighboring water difference value, the point of occurrence and the influence range in the current abnormal state of the warehouse, the method further includes:

[0021] determining, by a time analysis method, a change of grain moisture corresponding to the point of occurrence over time;

[0022] determining, according to the change of grain moisture over time, a time of occurrence in the current abnormal state.

[0023] In one example, after obtaining the current abnormal state of the warehouse, the method further includes:

[0024] estimating, according to the current abnormal state and the spatial analysis method and the time analysis method, a future abnormal state of the warehouse, and displaying an estimation result to a user.

[0025] In one example, determining, according to the change of grain moisture over time, the time of occurrence in the current abnormal state specifically includes:

[0026] importing the change of grain moisture corresponding to the point of occurrence over time into the warehouse model, and performing a time model analysis to compare and analyze a current moisture value and a historical time point moisture value, to obtain an occurrence time, an already-occurred time length, and an abnormal severity level of the abnormal node, so as to obtain a pre-judgment conclusion of the abnormal node according to the occurrence time, the already-occurred time length, and the abnormal severity level, the pre-judgment conclusion including determining whether there is a mildew, condensation, or hardening abnormality.

[0027] On the other hand, the application further proposes a wheat warehouse moisture monitoring device, including:

[0028] at least one processor; and,

[0029] a memory in communication connection with the at least one processor; wherein,

[0030] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0031] modeling 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;

[0032] For each storage unit, determining core data corresponding to the storage unit, and generating a corresponding definition threshold for the storage unit according to the core data, so as to add the definition threshold to the warehouse model as an abnormality judgment standard for the storage unit;

[0033] According to the warehouse model and current data of the warehouse collected, analyzing a current state of the warehouse by a spatial analysis method, so as to obtain a current abnormal state of the warehouse by analyzing nearby nodes of an abnormal node in the warehouse model, the current abnormal state including a point of occurrence, a time of occurrence, and an influence range;

[0034] Based on structure data of the warehouse, positioning the current abnormal state, and displaying a positioning result to a user.

[0035] In another aspect, the application further provides a non-volatile computer storage medium storing computer executable instructions, the computer executable instructions being configured to:

[0036] modeling 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;

[0037] For each storage unit, determining core data corresponding to the storage unit, and generating a corresponding definition threshold for the storage unit according to the core data, so as to add the definition threshold to the warehouse model as an abnormality judgment standard for the storage unit;

[0038] According to the warehouse model and current data of the warehouse collected, analyzing a current state of the warehouse by a spatial analysis method, so as to obtain a current abnormal state of the warehouse by analyzing nearby nodes of an abnormal node in the warehouse model, the current abnormal state including a point of occurrence, a time of occurrence, and an influence range;

[0039] Based on structure data of the warehouse, positioning the current abnormal state, and displaying a positioning result to a user.

[0040] The moisture monitoring method for the wheat warehouse can bring the following beneficial effects:

[0041] By data modeling and division of storage units, the problem of difficulty in finding the cause of abnormal wheat moisture, the influence range of abnormality and the severity of abnormality, and the problem of inaccurate problem positioning and untimely processing are solved; the real-time early warning of uneven distribution of wheat moisture in the warehouse, excessive wheat moisture, excessive moisture change speed, excessive moisture difference between adjacent points, mold, and hardening and other abnormalities is realized, and analysis conclusions such as the cause of abnormality, the influence range of abnormality and the severity of abnormality are given, and accurate prediction of mold, hardening and other abnormal phenomena that will occur in the next week is made. BRIEF DESCRIPTION OF DRAWINGS

[0042] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0043] Figure 1 A flowchart of a wheat warehouse moisture monitoring method in the embodiments of the present application is shown.

[0044] Figure 2 A flowchart of a wheat warehouse moisture monitoring method in the embodiments of the present application is shown.

[0045] Figure 3 A schematic diagram of a wheat warehouse moisture monitoring device in the embodiments of the present application is shown. DETAILED DESCRIPTION

[0046] To make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application will be described in detail below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0047] The technical scheme provided by the embodiments of the present application will be described in detail below in combination with the drawings.

[0048] As shown in Figure 1 The embodiments of the present application provide a wheat warehouse moisture monitoring method, which comprises:

[0049] S101: data modeling is performed on a warehouse for storing wheat to obtain a warehouse model, and the warehouse is divided into a plurality of storage units in the warehouse model.

[0050] Specifically, when the warehouse for storing wheat is spatially modeled, in the obtained spatial model, the warehouse is divided into a plurality of storage units according to structural data of the warehouse, the structural data including at least one of a deployment structure of the water measuring cable, a warehouse shape, a warehouse volume, and a grain pile volume. For example, each region divided according to the deployment structure of the water measuring cable is taken as a storage unit. At this time, the spatial modeling of the warehouse is completed. In the spatial modeling, data of the warehouse site at different time periods can be collected first, and then point cloud data is generated according to the data. Then, a plurality of point cloud data is superimposed, and data cleaning is performed synchronously in the superimposition process to remove abnormal point clouds. Finally, spatial modeling is realized to obtain a spatial model.

[0051] For each storage unit, corresponding moisture influencing factors in the storage unit are determined, and the moisture influencing factors of the storage unit are sorted according to scenes to obtain a plurality of (for example, tens of thousands of) data groups. By arranging and combining the plurality of data groups, the influence weight and the influence range of each moisture influencing factor in the storage unit are determined to realize data modeling of the storage unit. The moisture influencing factors include at least one of a grain storage ecological region to which a warehouse belongs, current ecological region characteristics, local safe moisture, a warehouse type, a warehouse volume, a wheat storage variety in the warehouse, a current quality of the wheat, a historical moisture condition, a final use of the wheat, a storage time of the wheat, a warehouse temperature and humidity, an atmospheric temperature and humidity, a specific position of the storage unit in the warehouse, and a moisture data of a collection point of the storage unit. At this time, on the basis of the spatial modeling, data modeling of each storage unit is completed.

[0052] For the storage units for which data modeling has been realized, a mutual influence relationship therebetween is established to realize data modeling of the warehouse and obtain a warehouse model. The mutual influence relationship can be that adjacent storage units have a high influence relationship.

[0053] S102: For each storage unit, core data corresponding to the storage unit is determined, and a corresponding definition threshold is generated for the storage unit according to the core data, so that the definition threshold is used as an abnormal judgment standard for the storage unit and added to the warehouse model.

[0054] The core data can include at least one of a warehouse (the warehouse can also be referred to as a warehouse) where the core data is located, an interval of a high moisture value of a water measuring point for different varieties, an average moisture difference value and a highest moisture difference abnormal interval of the water measuring point in the layer where the water measuring point is located, a rate value of the water measuring point changing too fast within a period of time, a ratio of a fault point to all water measuring points, a current mold probability, a current clumping probability, a future mold probability, and a future clumping probability.

[0055] S103: According to the warehouse model and the current data of the warehouse collected, the current state of the warehouse is analyzed by a spatial analysis method, so as to obtain the current abnormal state of the warehouse by analyzing the nearby nodes of the abnormal node in the warehouse model, the current abnormal state including the occurrence point, the occurrence time and the influence range.

[0056] Specifically, first, according to the threshold in the warehouse model and the current data of the warehouse collected (which can be collected according to the core data to determine the current value of each core data), the current state of the warehouse is analyzed (for example, a related model is pre-trained, and then the model is used to analyze the state, the model can use a neural network model, if the warehouse model is stored in the form of a portrait, a graph convolution model can also be used, and if it is for text data, natural language processing algorithm can also be used for analysis), to determine the abnormal node in the warehouse model. The node can be a certain storage unit, or a more specific area in the storage unit, which can be represented by data stored in the database.

[0057] By the spatial analysis method, the nearby nodes of the abnormal node in the warehouse model are analyzed to determine the adjacent water difference value between the nearby nodes and the abnormal node, wherein the nearby nodes include at least one of the upper and lower nodes, the left and right column nodes, and the left and right row nodes of the abnormal node. According to the adjacent water difference value, the occurrence point and the influence range in the current abnormal state of the warehouse are determined. It should be noted that when the abnormal node is a certain area, the upper and lower layers in the nearby nodes can be the upper and lower layers when the warehouse is multi-layer, and the left and right columns and the left and right rows represent that the area is divided into a grid in the overhead view, thereby obtaining the left and right column nodes and the left and right row nodes. According to the adjacent water difference value, the greater the influence on the nearby nodes, the greater the influence range.

[0058] Further, the change of the moisture content of the grain corresponding to the occurrence point with time can also be determined by the time analysis method, and then the occurrence time in the current abnormal state is determined according to the change of the moisture content of the grain with time. At this time, the future abnormal state of the warehouse can be estimated according to the current abnormal state and the spatial analysis method and the time analysis method, and the estimation result is displayed to the user. When the time analysis method is used, some data in the early stage often needs to be considered, which has a high reference value for the current state, so the long short-term memory (LSTM) can be used to realize the time analysis method, thereby achieving better analysis effect.

[0059] Through the spatial analysis method and the time analysis method, the abnormal range and the abnormal severity of the grain condition can be more accurately estimated, and it can be predicted whether the overall or local grain is abnormal, such as mold or hardening, so as to provide effective data support for determining the optimal abnormal treatment scheme for the warehouse area.

[0060] S104: Based on the structure data of the warehouse, the current abnormal state is located, and the positioning result is displayed to the user.

[0061] Specifically, virtual reality processing technology can be integrated to realize the use of virtual reality to view the specific location of each analysis conclusion in the warehouse, and to reduce the difficulty of locating abnormal grain. For example, through the combination of virtual reality (VR) and augmented reality technology (AR), an interface device for hardware interaction between people and virtual environment is completed through an effects generator (Effects Generator), including various output devices that can produce immersion, and input devices that can measure the line of sight direction and finger movement, and the core part of the virtual reality system is realized through a visual emulator (Visual Emulator), which is the engine of VR, composed of computer software, hardware system, software supporting hardware (such as graphics acceleration card and sound card, etc.), receiving (sending) the signals generated (accepted) by the effects generator. The application system (Application) is the software part for specific problems, which can describe the specific content of simulation by using the relevant positioning results in this paper, including the dynamic logic, structure and interaction between simulation objects and users. The geometrical structural system provides information describing the physical properties (shape, color, position) of the simulation objects, which can be realized by the relevant data of the warehouse in this paper.

[0062] Through data modeling and division of storage units, the problems of difficulty in finding the causes of abnormal wheat moisture, abnormal influence range and abnormal severity, and inaccurate problem positioning and untimely problem processing are solved; real-time early warning of abnormal conditions such as uneven distribution of wheat moisture in the warehouse, high wheat moisture, rapid change of wheat moisture, excessive difference in water content between adjacent points, mold and hardening is realized, and analysis conclusions such as causes of abnormal occurrence, abnormal influence range and abnormal severity are given. At the same time, accurate prediction is made for mold and hardening and other abnormal phenomena that will occur in the next week.

[0063] In one embodiment, as Figure 2As shown, first, the moisture equipment (including sensor and other data measurement equipment) is configured, and then the moisture detection strategy (including storage strategy and the like, which will be described in detail below) is preset. In specific implementation, moisture data acquisition (i.e. the current data of the warehouse mentioned above) is performed, and then the moisture data is analyzed, the analysis is performed according to the data modeling, and the result in the time interval is displayed according to the analysis result. If the moisture is abnormal, a warning reminder and an abnormal identifier are issued, otherwise, it is normally displayed. Further, the analysis and display of a certain detection time point in the warehouse can be performed, if it is abnormal, a warning reminder and an abnormal identifier are issued, otherwise, it is normally displayed. Of course, the space and time of a single collection point can also be analyzed, and the analysis conclusion is displayed.

[0064] In one embodiment, when deploying the moisture detection line, the following implementation requirements need to be met: 1. The sensor can be placed below 30 cm from the grain surface, and the placement depth cannot be less than 30 cm; 2. 1 ℃ / m is the maximum value of the grain temperature gradient, and if it exceeds the maximum value, the moisture detection result will be inaccurate. 3. 0.1% / m is the maximum value of the grain moisture gradient, and if it exceeds the maximum value, the moisture detection result will be inaccurate. The three points meet the requirements to ensure the correctness of the moisture detection point data.

[0065] When data modeling and analysis of the moisture detection result are performed, the warehouse strategy of the data model needs to be preset first: the wheat moisture abnormality strategy, the whole wheat moisture judgment as a whole moisture over-high strategy, the data positioning judgment strategy of the fault point, and the wheat prediction strategy are preconfigured.

[0066] For moisture detection, the moisture data can be obtained by means of a cable, and the cable measurement is controlled by a control cabinet. The program and the control cabinet are connected through Socket request, and the IP and port required for connection are warehouse preset data.

[0067] The control cabinet returns the data packet after receiving and converting the specified data, and checks whether the control cabinet is normally received. After correct reception for 2 minutes, the channel number is sent again, and after correct return of data, the data is analyzed

[0068] In data modeling, each parameter information affecting the moisture is analyzed.

[0069] First, data aggregation is needed: the basic information of the warehouse affecting the moisture data is read through the warehouse interface, such as warehouse type and variety; the wheat temperature, warehouse temperature, and warehouse humidity information is read through the grain temperature detection interface; the control cabinet collected moisture data is analyzed through the interface; the current warehouse strategy preconfiguration content is read through the warehouse configuration strategy interface, and the interface reads the preconfigured safety moisture data of the current warehouse area in the city, the ecological region to which the warehouse area belongs, and the characteristics of the ecological region.

[0070] Then data modeling is performed: for the water line cable deployment method, a spatial model of each storage unit is established; by normal distribution rule, each parameter or multi-parameter affecting the moisture value is combined and analyzed, different data groups are sorted, all data groups are fused and cloud data processed, and a model component of a single storage unit is established; at the same time, through the change range of each parameter of adjacent storage units, the time change trend, and the difference of analysis results, the correlation between each storage unit is reorganized through the spatial model, and the data model of the whole warehouse is packaged.

[0071] Finally, the data is imported into the data model, and through time model analysis, the current moisture value and the moisture value at the historical time point are compared and analyzed, the specific time of abnormal occurrence, the duration of abnormal occurrence, and the severity of abnormality are analyzed. Finally, the abnormality prediction conclusion of the warehouse is given, and it is determined whether there is mold, dew, hardening and other abnormalities, so as to achieve the final purpose of early detection and early treatment of abnormality.

[0072] In one embodiment, when using a spatial analysis method, by comparing and analyzing the adjacent data above, left, right and behind the abnormal point, the specific position of the wheat abnormality and the surrounding range of the abnormality are preliminarily judged. Precise positioning of the abnormal position, combined with the time analysis method, gives the optimal treatment scheme for wheat abnormality, and unnecessary work is done.

[0073] After the data collection is completed, the Unity3d data model display is performed according to the moisture collection and analysis data; the specific position of the abnormality is accurately positioned, and in view of the actual water line cable deployment scheme in the warehouse, the actual shape of the warehouse is considered, and the Unity3d technology is integrated to realize the use of Unity3d to view the specific position of each analysis conclusion in the warehouse.

[0074] In one embodiment, the warehouse strategy configuration table mentioned above can be as shown in the following table:

[0075]

[0076]

[0077] And the above mentioned obtaining the change of grain moisture with time, the grain moisture monitoring record table can be as shown in the following table:

[0078]

[0079]

[0080]

[0081] As Figure 3As shown, the embodiment of the application also provides a moisture monitoring device for a wheat warehouse, comprising:

[0082] at least one processor; and

[0083] a memory in communication connection with the at least one processor; wherein

[0084] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0085] data modeling for a warehouse for storing wheat to obtain a warehouse model, and dividing the warehouse into a plurality of storage units in the warehouse model;

[0086] for each storage unit, determining the core data corresponding to the storage unit, and generating the corresponding definition threshold for the storage unit according to the core data, so as to add the definition threshold to the warehouse model as the abnormal judgment standard for the storage unit;

[0087] according to the warehouse model and the current data of the warehouse collected, analyzing the current state of the warehouse by a spatial analysis method, so as to obtain the current abnormal state of the warehouse by analyzing the nearby nodes of the abnormal node in the warehouse model, and the current abnormal state includes the occurrence point, the occurrence time and the influence range;

[0088] based on the structure data of the warehouse, positioning the current abnormal state, and showing the positioning result to the user.

[0089] The embodiment of the application also provides a non-volatile computer storage medium, which stores computer executable instructions, and the computer executable instructions are set to:

[0090] data modeling for a warehouse for storing wheat to obtain a warehouse model, and dividing the warehouse into a plurality of storage units in the warehouse model;

[0091] for each storage unit, determining the core data corresponding to the storage unit, and generating the corresponding definition threshold for the storage unit according to the core data, so as to add the definition threshold to the warehouse model as the abnormal judgment standard for the storage unit;

[0092] according to the warehouse model and the current data of the warehouse collected, analyzing the current state of the warehouse by a spatial analysis method, so as to obtain the current abnormal state of the warehouse by analyzing the nearby nodes of the abnormal node in the warehouse model, and the current abnormal state includes the occurrence point, the occurrence time and the influence range;

[0093] locating the current abnormal state based on the structure data of the warehouse, and displaying the locating result to a user.

[0094] Each of the embodiments in the present application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each of the embodiments mainly explains the difference from other embodiments. Especially, the device and medium embodiments are described simply because they are basically similar to the method embodiments, and the related parts can be referred to the part of the method embodiments.

[0095] The device and medium provided by the embodiments of the present application are one-to-one corresponding to the method, and therefore, the device and medium also have the similar beneficial technical effects as the method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the device and medium will not be described here.

[0096] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer-usable program code.

[0097] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device implemented in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in the flow or flows and / or block or blocks.

[0098] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in the flow or flows and / or block or blocks.

[0099] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0100] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0101] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0102] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0103] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0104] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for monitoring moisture content in wheat warehouses, characterized in that, include: Data modeling is performed on the warehouse used for storing wheat to obtain a warehouse model, and the warehouse is divided into several storage units in the warehouse model; For each storage unit, the core data corresponding to the storage unit is determined, and a corresponding threshold is generated for the storage unit based on the core data. The threshold is then used as an anomaly judgment criterion for the storage unit and added to the warehouse model. Based on the warehouse model and the current data collected from the warehouse, the current state of the warehouse is analyzed using spatial analysis methods. By analyzing the nearby nodes of the abnormal node in the warehouse model, the current abnormal state of the warehouse is obtained. The current abnormal state includes the point of occurrence, the time of occurrence, and the scope of impact. Based on the structural data of the warehouse, the current abnormal state is located, and the location result is displayed to the user; Data modeling was performed on the warehouse used for storing wheat to obtain the warehouse model, which specifically included: Spatial modeling is performed on a warehouse used for storing wheat. In the resulting spatial model, the warehouse is divided into several storage units based on the structural data of the warehouse. The structural data includes at least one of the following: the deployment structure of water measurement cables, warehouse shape, warehouse volume, and grain pile volume. For each storage unit, the moisture influencing factors in the storage unit are determined; and the moisture influencing factors in the storage unit are sorted by scenario to obtain multiple data groups. By arranging and combining the multiple data groups, the influence weight and influence range of each moisture influencing factor in the storage unit are determined to realize data modeling of the storage unit. For storage units that have already been modeled, establish the interrelationships between them to achieve data modeling of the warehouse and obtain a warehouse model; The core data includes: the warehouse location, the range of high moisture values ​​at the water testing point for different varieties, the difference between the water testing point and the average moisture value of the layer, the abnormal range of the highest moisture difference, the rate of change of the water testing point over a period of time, the ratio of the fault point to all water testing points, the current probability of mold growth, the current probability of caking, the future probability of mold growth, and the future probability of caking. Based on the warehouse model and the collected current data of the warehouse, the current state of the warehouse is analyzed using spatial analysis methods to obtain the current abnormal state of the warehouse, specifically including: Based on the defined threshold in the warehouse model and the current data of the warehouse collected, the current state of the warehouse is analyzed to identify the abnormal nodes that have occurred in the warehouse model. Using spatial analysis methods, the nearby nodes of the abnormal node in the warehouse model are analyzed to determine the adjacent water difference value between the nearby nodes and the abnormal node. The nearby nodes include at least one of the following: the upper and lower layer nodes, left and right column nodes, and left and right row nodes of the abnormal node. Based on the adjacent water difference values, determine the point of occurrence and the scope of impact in the current abnormal state of the warehouse; After determining the point of occurrence and the scope of impact of the current abnormal state of the warehouse based on the adjacent water difference values, the method further includes: The change in grain moisture content over time at the point of occurrence was determined using time analysis methods. Based on the changes in grain moisture content over time, the occurrence time of the current abnormal state is determined; After obtaining the current abnormal state of the warehouse, the method further includes: Based on the current abnormal state, as well as the spatial analysis method and the temporal analysis method, the future abnormal state of the warehouse is predicted, and the prediction results are displayed to the user. Based on the changes in grain moisture content over time, the occurrence time of the current abnormal state is determined, specifically including: The changes in grain moisture content over time at the occurrence point are imported into the warehouse model. Through time model analysis, the current moisture value is compared with the moisture value at historical time points to obtain the occurrence time, duration of occurrence, and severity of the abnormal node. Based on the occurrence time, duration of occurrence, and severity of the abnormal node, a predictive conclusion is drawn regarding the abnormal node. The predictive conclusion includes determining whether mold, condensation, or compaction abnormalities exist.

2. The method according to claim 1, characterized in that, The moisture influencing factors include at least one of the following: the grain storage ecological zone to which the storage area belongs, the current characteristics of the ecological zone, the local safe moisture level, the type of warehouse, the volume of the warehouse, the wheat variety stored in the warehouse, the current quality of the wheat, historical moisture levels, the final use of the wheat, the storage time of the wheat, the temperature and humidity of the warehouse, the ambient temperature and humidity, the specific location of the storage unit in the warehouse, and the moisture data of the storage unit collection point.

3. A moisture monitoring device for wheat warehouses, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to: perform a moisture monitoring method for a wheat warehouse as described in any one of claims 1-2.

4. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are configured to execute the moisture monitoring method for wheat warehouses as described in any one of claims 1-2.

Images