Intelligent targeted low-temperature regulation and control system and method based on dynamic heat insulation blocking principle

Abstract

The invention discloses an intelligent targeted low-temperature regulation and control system and method based on a dynamic heat insulation blocking principle, and particularly relates to the technical field of intelligent temperature control, and the method comprises the steps: dividing a regulation and control region into M control sub-regions according to a division rule, and arranging a group of temperature control combination devices and I groups of temperature and humidity monitoring devices in each control sub-region; the temperature control combined device comprises a ground temperature control pipeline and a top temperature control device; in the T time period, obtaining grain monitoring data of the I group of temperature and humidity monitoring devices in the mth control sub-region; according to the invention, the control sub-regions are divided, and the temperature control combination device and the plurality of temperature and humidity monitoring devices are arranged in each control sub-region, so that the temperature and humidity of each region can be monitored in real time, and the grain temperature can be accurately regulated and controlled. According to the temperature control mode based on region division, the high-temperature region and the potential problem region of the grains in the control region can be recognized more quickly and more accurately, so that the abnormal region is preferentially regulated and controlled, and resource waste of overall temperature control is avoided.

Description

Technical Field

[0001] The present invention relates to the field of intelligent temperature control technology, and more specifically, to an intelligent targeted low-temperature control system and method based on the dynamic thermal insulation blocking principle. Background Art

[0002] During the storage of grains, fluctuations in temperature and humidity can lead to pests, mildew, and loss of nutrients. Especially under low-temperature storage conditions, how to evenly cool and control the temperature becomes a technical difficulty. Traditional cooling methods mainly include natural ventilation and mechanical cooling. However, the effect of natural ventilation is limited by external climatic conditions, making it difficult to achieve precise temperature control; mechanical cooling is usually an overall cooling mode, which has high energy consumption and is difficult to dynamically adjust according to local temperature changes of grains.

[0003] In the existing methods, for example, the Chinese patent application with publication number CN106383534A discloses a control system for a vacuum low-temperature grain drying tower, including a microcomputer, a control interface, a remote controller, a temperature regulator, a temperature sensor, a humidity detector, a fault detector, a display, a timer, a circuit breaker, a vacuum environment monitor, a data storage device, a data retriever, an alarm and a hazard flashing light, wherein the microcomputer is connected to the control interface by induction, the microcomputer is connected to the remote controller by induction, the microcomputer controls the temperature regulator, the microcomputer controls the temperature sensor, the microcomputer controls the humidity detector, the fault detector, the display, the timer, the circuit breaker, the vacuum environment monitor, the data storage device, the data retriever, the alarm and the hazard flashing light. The invention can better control the temperature of the drying tower, which is beneficial to grain drying, and at the same time facilitates the more accurate operation of the drying tower, and can remotely control the operation of the system. Although the above method can realize grain temperature control and achieve the effect of grain cooling, research and application of the above method and the prior art have found that the above method and the prior art have at least the following partial defects:

[0004] 1. The above method is used for environmental control of the entire area, without detailed division of grain areas, which may lead to poor temperature control effects in local areas and lack of zoning monitoring and precise temperature control capabilities for different granary sub-areas;

[0005] 2. It can only perform temperature control operations based on simple sensor data and lacks a closed-loop feedback mechanism and adaptive adjustment capabilities.

[0006] To this end, the present invention provides an intelligent targeted low-temperature control system and method based on the dynamic thermal insulation blocking principle. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent targeted low-temperature control system and method based on the dynamic thermal insulation blocking principle to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above purpose, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides an intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle, comprising:

[0010] Step 1: Divide the control area into M control sub-areas according to the division rule, and set a group of temperature control combination devices and I group of temperature and humidity monitoring devices in each control sub-area; the temperature control combination device includes a ground temperature control pipe and a top temperature control device; M and I are integers greater than zero;

[0011] Step 2: within a time period of T, obtaining grain monitoring data of a group I of temperature and humidity monitoring devices in the mth control sub-area; the grain monitoring data includes a regional temperature coefficient and a regional humidity coefficient;

[0012] Step 3: Input the grain monitoring data in the time period T into the pre-built monitoring and analysis model to obtain the temperature and humidity evaluation coefficient in the time period T+a; a is an integer greater than zero;

[0013] Step 4: Input the temperature and humidity evaluation coefficients in the time period T+a into the pre-built temperature control strategy prediction model to obtain the temperature control strategy, and automatically control the temperature control combination device based on the temperature control strategy;

[0014] Step 5: Obtain a first control coefficient of the first temperature-controlled closing device and a second control coefficient of the second temperature-controlled closing device, and determine whether to close the corresponding temperature-controlled closing device based on the first control coefficient or the second control coefficient.

[0015] Furthermore, the division rule is to divide the control area into equal parts according to the area or the grain height. Each of the ground temperature control pipes consists of an inlet pipe and a return pipe, and each return pipe is equipped with a first temperature control closing device; each ground temperature control pipe surrounds the corresponding control sub-area and is used to control the grain temperature at the bottom of each control sub-area. Each of the top temperature control devices is a variable frequency air cooling system that adjusts the temperature and speed of the wind to reduce the top and air temperature of the control area by air cooling; and a second temperature control closing device is provided in the return air duct of the top temperature control device;

[0016] Each set of temperature and humidity monitoring devices includes H temperature sensors and humidity sensors, which are evenly arranged from bottom to top with equal spacing.

[0017] Furthermore, the method for obtaining grain monitoring data of a group I of temperature and humidity monitoring devices in the mth control sub-area includes:

[0018] Acquire regional temperature data, wherein the regional temperature data includes a maximum temperature, a minimum temperature, an average temperature, and a temperature change rate;

[0019] The regional temperature data is calculated by formulating the regional temperature coefficient, and the calculation formula is:

[0020] ;

[0021] ;

[0022] ;

[0023] ;

[0024] ;

[0025] In the formula, represents the regional temperature coefficient of the mth control sub-region, Indicates the maximum temperature, Indicates the minimum temperature. represents the temperature value of the first temperature and humidity monitoring device, represents the average temperature, represents the rate of temperature change, and Indicates that within the T time period and Temperature data at two monitoring moments; Indicates the monitoring time interval, >0, , and is the preset weight factor.

[0026] Furthermore, the method for obtaining grain monitoring data of a group I of temperature and humidity monitoring devices in the mth control sub-area also includes:

[0027] Acquire regional humidity data, wherein the regional humidity data includes a maximum humidity value, a minimum humidity value, an average humidity value, and a humidity change rate;

[0028] The regional humidity data is calculated by formulating the regional humidity coefficient, and the calculation formula is:

[0029] ;

[0030] ;

[0031] ;

[0032] ;

[0033] ;

[0034] In the formula, represents the regional humidity coefficient of the mth control sub-region, Indicates the maximum humidity value, Indicates the minimum humidity value. Represents the humidity value of the first temperature and humidity monitoring device, Represents the average humidity value, represents the humidity change rate, and Indicates that within the T time period and Humidity data at two monitoring moments; Indicates the monitoring time interval, >0, , and is the preset weight factor.

[0035] Furthermore, the generation logic of the monitoring and analysis model is as follows:

[0036] Acquiring historical grain monitoring data, the historical grain monitoring data including a plurality of groups of regional temperature coefficients and regional humidity coefficients within a time span and corresponding temperature and humidity assessment coefficients;

[0037] The historical grain monitoring data is divided into an evaluation training set and an evaluation test set; a regression network model is constructed, the regional temperature coefficient and the regional humidity coefficient in the evaluation training set are used as the input of the regression network model, and the temperature and humidity evaluation coefficient in the evaluation training set is used as the output of the regression network model, the regression network model is trained to obtain an initial regression network, and the training goal is to minimize the sum of the first prediction accuracies. The initial regression network is evaluated using the evaluation test set, and the initial regression network when the sum of the first prediction accuracies reaches convergence is used as a pre-constructed monitoring and analysis model; the regression network model is a decision tree regression network model, a support vector machine regression network model, a linear regression network model or a random forest regression network model.

[0038] Furthermore, the logic for obtaining the temperature and humidity evaluation coefficients in the historical grain monitoring data is as follows:

[0039] The regional temperature coefficient and regional humidity coefficient in the historical grain monitoring data are extracted, and the regional temperature coefficient and regional humidity coefficient are fused and calculated to obtain the temperature and humidity assessment coefficient; the calculation formula is:

[0040] ;

[0041] In the formula, represents the temperature and humidity evaluation coefficient of the mth control sub-area, is the correction constant, .

[0042] Furthermore, the training method of the temperature control strategy prediction model includes:

[0043] Pre-collecting the temperature and humidity evaluation coefficients of group A, where A is an integer greater than 1, and setting corresponding temperature control strategies according to the temperature and humidity evaluation coefficients of group A, wherein the temperature control strategies include opening the ground temperature control pipe control, the top temperature control device control, or the ground temperature control pipe and the top temperature control device combined control, and setting different digital labels for different temperature control strategies; marking the digital labels of the temperature control strategies as prediction labels, and converting the temperature and humidity evaluation coefficients and the corresponding prediction labels into a corresponding set of feature vectors;

[0044] Each group of feature vectors is used as the input of the temperature control strategy prediction model. The temperature control strategy prediction model takes a group of prediction labels corresponding to each group of temperature and humidity evaluation coefficients as output, and takes the actual prediction labels corresponding to each group of temperature and humidity evaluation coefficients as prediction targets, where the actual prediction labels are pre-set prediction labels corresponding to the temperature and humidity evaluation coefficients; minimizing the sum of prediction errors between the prediction labels corresponding to all temperature and humidity evaluation coefficients and the actual prediction labels is used as the training target; the temperature control strategy prediction model is specifically a deep neural network model.

[0045] Furthermore, the method for obtaining the first control coefficient of the first temperature control closing device includes:

[0046] Within a preset time period, obtaining an average temperature value of the first temperature control closing device within a preset time span, and marking the average temperature value as a first control coefficient;

[0047] The method for obtaining the second control coefficient of the second temperature control closing device includes:

[0048] In a preset time period, an average temperature value of the second temperature control closing device in a preset time span is obtained, and the average temperature value is marked as a second control coefficient.

[0049] Further, the method for determining whether to close the corresponding temperature control closing device based on the first control coefficient includes:

[0050] Presetting a first control coefficient threshold, and comparing the first control coefficient with the first control coefficient threshold;

[0051] If the first control coefficient is less than or equal to the first control coefficient threshold, a closing instruction is generated;

[0052] If the first control coefficient is greater than the first control coefficient threshold, no closing instruction is generated.

[0053] In a second aspect, the present invention provides an intelligent targeted low temperature control system based on the dynamic thermal insulation blocking principle, which is used to implement the above-mentioned intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle, including:

[0054] A region division unit is used to divide the control region into M control sub-regions according to the division rule, and each control sub-region is provided with a group of temperature control combination devices and I group of temperature and humidity monitoring devices; the temperature control combination device includes a ground temperature control pipe and a top temperature control device; M and I are integers greater than zero;

[0055] A monitoring unit, used to obtain grain monitoring data of a group I of temperature and humidity monitoring devices in an m-th control sub-area within a T time period; the grain monitoring data includes a regional temperature coefficient and a regional humidity coefficient;

[0056] The analysis and prediction unit is used to input the grain monitoring data in the time period T into the pre-built monitoring and analysis model to obtain the temperature and humidity evaluation coefficient in the time period T+a; a is an integer greater than zero;

[0057] The temperature control unit is used to input the temperature and humidity evaluation coefficients in the time period T+a into the pre-built temperature control strategy prediction model to obtain the temperature control strategy, and automatically control the temperature control combination device based on the temperature control strategy;

[0058] The closing control unit is used to obtain a first control coefficient of a first temperature-controlled closing device and a second control coefficient of a second temperature-controlled closing device, and determine whether to close the corresponding temperature-controlled closing device based on the first control coefficient or the second control coefficient.

[0059] Technical effects and advantages of the present invention:

[0060] 1. The present invention divides the control area into M control sub-areas, and sets a temperature control combination device and multiple groups of temperature and humidity monitoring devices in each control sub-area, so as to realize real-time monitoring of temperature and humidity in each area and precise grain temperature control. This temperature control method based on regional division can more quickly and accurately identify high-temperature areas and potential problem areas in the control area, so as to give priority to regulating abnormal areas and avoid waste of overall temperature control resources; introduce a temperature control strategy prediction model, dynamically adjust the working state of the temperature control equipment according to historical grain monitoring data and prediction data, and have higher adaptive capabilities.

[0061] 2. The present invention uses a monitoring and analysis model and a temperature control strategy prediction model to predict future temperature and humidity change trends. This advance prediction mechanism allows the system to start the temperature control equipment before an abnormality occurs, reducing the risk of grain deterioration caused by heating or excessive humidity in the control area. At the same time, the prediction model can also optimize the allocation of temperature control resources, reduce unnecessary temperature control operations, and thus reduce energy consumption and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a flow chart of the intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle of Example 1;

[0063] Figure 2 This is a flow chart of a method for determining whether to close a corresponding temperature control closing device in Example 1;

[0064] Figure 3 This is a schematic diagram of the structure of the intelligent targeted low-temperature control system based on the dynamic thermal insulation blocking principle of Example 2. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0067] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0068] Example 1

[0069] See also Figure 1 As shown, this embodiment discloses an intelligent targeted low temperature control method based on the principle of dynamic thermal insulation blocking, the method is applied to a cloud server, the cloud server is remotely connected to a management terminal, and the method includes:

[0070] Step 1: Divide the control area into M control sub-areas according to the division rules, and set a group of temperature control combination devices and I group of temperature and humidity monitoring devices in each control sub-area; the temperature control combination device includes a ground temperature control pipe and a top temperature control device;

[0071] It should be noted that: the control area is the area where grain monitoring is required. The division rule is to divide the control area into equal parts by area or grain height. This embodiment takes the equal division of area as an example. Each of the ground temperature control pipes is composed of an inlet pipe and a return pipe, and each return pipe is equipped with a first temperature control closing device; each ground temperature control pipe surrounds the corresponding control sub-area, and is used to control the grain temperature at the bottom of each control sub-area. Each top temperature control device is a variable frequency air cooling system, which adjusts the temperature and speed of the wind, and reduces the top and air temperature of the control area by air cooling; and a second temperature control closing device is provided in the return air duct of the top temperature control device.

[0072] Each set of temperature and humidity monitoring devices includes H temperature sensors and humidity sensors, which are evenly arranged from bottom to top with equal spacing, and are used to monitor the temperature distribution and humidity changes of grains in the ground area in real time.

[0073] It should be noted that M, I and H are all integers greater than zero.

[0074] Step 2: within a time period of T, obtaining grain monitoring data of a group I of temperature and humidity monitoring devices in the mth control sub-area; the grain monitoring data includes a regional temperature coefficient and a regional humidity coefficient; m=1, 2, ..., M;

[0075] The unit of the T time period is minutes or hours, which is specifically set by those skilled in the art and is not further limited here.

[0076] In a preferred embodiment, the method for obtaining grain monitoring data of a group I of temperature and humidity monitoring devices in the mth control sub-area includes:

[0077] Acquire regional temperature data, wherein the regional temperature data includes a maximum temperature, a minimum temperature, an average temperature, and a temperature change rate;

[0078] The regional temperature data is calculated by formulating the regional temperature coefficient, and the calculation formula is:

[0079] ;

[0080] ;

[0081] ;

[0082] ;

[0083] ;

[0084] In the formula, represents the regional temperature coefficient of the mth control sub-region, Indicates the maximum temperature, Indicates the minimum temperature. represents the temperature value of the first temperature and humidity monitoring device, represents the average temperature, represents the rate of temperature change, Indicates that within the T time period and Temperature data at two monitoring moments; Indicates the monitoring time interval, >0, , and The weight factors are preset and are set by those skilled in the art based on experience.

[0085] In a preferred embodiment, the method for obtaining grain monitoring data of a group I of temperature and humidity monitoring devices in the mth control sub-area further includes:

[0086] Acquire regional humidity data, wherein the regional humidity data includes a maximum humidity value, a minimum humidity value, an average humidity value, and a humidity change rate;

[0087] The regional humidity data is calculated by formulating the regional humidity coefficient, and the calculation formula is:

[0088] ;

[0089] ;

[0090] ;

[0091] ;

[0092] ;

[0093] In the formula, represents the regional humidity coefficient of the mth control sub-region, Indicates the maximum humidity value, Indicates the minimum humidity value. Represents the humidity value of the first temperature and humidity monitoring device, Represents the average humidity value, represents the humidity change rate, and Indicates that within the T time period and Humidity data at two monitoring moments; Indicates the monitoring time interval, >0, , and The weight factors are preset and are set by those skilled in the art based on experience.

[0094] Step 3: Input the grain monitoring data in the time period T into the pre-built monitoring and analysis model to obtain the temperature and humidity evaluation coefficient in the time period T+a; a is an integer greater than zero;

[0095] It should be noted that the specific value of a is determined according to the time span preset by a person skilled in the art. For example, assuming that the time T is 9:10 and the time span is set to 10 minutes, the value range of a is 10, that is, the grain monitoring data between 9:10 and 9:20 is obtained;

[0096] Specifically, the generation logic of the monitoring and analysis model is as follows:

[0097] Acquiring historical grain monitoring data, the historical grain monitoring data including a plurality of groups of regional temperature coefficients and regional humidity coefficients within a time span and corresponding temperature and humidity assessment coefficients;

[0098] It should be noted that the specific duration of each group of time spans is determined according to the time spans preset by those skilled in the art;

[0099] The logic for obtaining the temperature and humidity evaluation coefficients in the historical grain monitoring data is as follows:

[0100] The regional temperature coefficient and regional humidity coefficient in the historical grain monitoring data are extracted, and the regional temperature coefficient and regional humidity coefficient are fused and calculated to obtain the temperature and humidity assessment coefficient; the calculation formula is:

[0101] ;

[0102] In the formula, represents the temperature and humidity evaluation coefficient of the mth control sub-area, is the correction constant, .

[0103] The historical grain monitoring data is divided into an evaluation training set and an evaluation test set; a regression network model is constructed, the regional temperature coefficient and the regional humidity coefficient in the evaluation training set are used as the input of the regression network model, and the temperature and humidity evaluation coefficient in the evaluation training set is used as the output of the regression network model. The regression network model is trained to obtain an initial regression network, and the training goal is to minimize the sum of the first prediction accuracies. The initial regression network is evaluated using the evaluation test set, and the initial regression network when the sum of the first prediction accuracies reaches convergence is used as a pre-constructed monitoring and analysis model; wherein the calculation formula for the first prediction accuracy is: , where is the number of each group of regional temperature coefficient and regional humidity coefficient, is the first prediction accuracy, For the The predicted values ​​of the temperature and humidity assessment coefficients corresponding to the group regional temperature coefficients and regional humidity coefficients, For the The actual values ​​of the temperature and humidity evaluation coefficients corresponding to the group area temperature coefficient and the area humidity coefficient;

[0104] It should be noted that the regression network model is a decision tree regression network model, a support vector machine regression network model, a linear regression network model or a random forest regression network model.

[0105] Step 4: Input the temperature and humidity evaluation coefficients in the time period T+a into the pre-built temperature control strategy prediction model to obtain the temperature control strategy, and automatically control the temperature control combination device based on the temperature control strategy;

[0106] In implementation, the training method of the temperature control strategy prediction model includes:

[0107] The temperature and humidity evaluation coefficients of group A are collected in advance, where A is an integer greater than 1. Corresponding temperature control strategies are set according to the temperature and humidity evaluation coefficients of group A. The temperature control strategies include opening the ground temperature control pipe control, the top temperature control device control, or the ground temperature control pipe and the top temperature control device combined control. Different digital labels are set for different temperature control strategies. For example, the digital label for opening the ground temperature control pipe control is set to 1, the digital label for opening the top temperature control device control is set to 2, and the digital label for the combined control of the ground temperature control pipe and the top temperature control device is set to 3; the temperature control strategies corresponding to the temperature and humidity evaluation coefficients are collected by technical personnel in this field during the continuous testing of historical temperature and humidity evaluation coefficients, and technical personnel in this field judge in turn based on actual experience that under the conditions of different temperature and humidity evaluation coefficients of group A, the different temperature and humidity evaluation coefficients of group A are set to corresponding temperature control strategies in turn.

[0108] The digital labels of the temperature control strategies are marked as prediction labels, and the temperature and humidity evaluation coefficients and the corresponding prediction labels are converted into a corresponding set of feature vectors;

[0109] Each set of feature vectors is used as the input of the temperature control strategy prediction model. The temperature control strategy prediction model uses a set of prediction labels corresponding to each set of temperature and humidity evaluation coefficients as output, and uses the actual prediction labels corresponding to each set of temperature and humidity evaluation coefficients as the prediction target. The actual prediction label is the pre-set prediction label corresponding to the temperature and humidity evaluation coefficient; the training goal is to minimize the sum of the prediction errors between the prediction labels corresponding to all temperature and humidity evaluation coefficients and the actual prediction labels; wherein the calculation formula for the prediction error is: ,in, is the prediction error, is the group number of the characteristic vector corresponding to the temperature and humidity evaluation coefficient, For the The predicted label corresponding to the group temperature and humidity assessment coefficient, For the The actual prediction labels corresponding to the group temperature and humidity assessment coefficients are obtained; and the temperature control strategy prediction model is trained until the sum of the prediction errors reaches convergence and the training is stopped, wherein the temperature control strategy prediction model is specifically a deep neural network model.

[0110] Step 5: Obtain a first control coefficient of the first temperature control closing device and a second control coefficient of the second temperature control closing device, and determine whether to close the corresponding temperature control closing device based on the first control coefficient or the second control coefficient;

[0111] In implementation, the method for obtaining the first control coefficient of the first temperature control closing device includes:

[0112] In a preset time period, an average temperature value of the first temperature-controlled closing device in a preset time span is obtained, and the average temperature value is marked as a first control coefficient.

[0113] In implementation, the method for obtaining the second control coefficient of the second temperature control closing device includes:

[0114] In a preset time period, an average temperature value of the second temperature control closing device in a preset time span is obtained, and the average temperature value is marked as a second control coefficient.

[0115] See also Figure 2 As shown, in implementation, the method for determining whether to close the corresponding temperature control closing device based on the first control coefficient includes:

[0116] Presetting a first control coefficient threshold, and comparing the first control coefficient with the first control coefficient threshold;

[0117] If the first control coefficient is less than or equal to the first control coefficient threshold, a closing instruction is generated, indicating that the ground temperature control pipe in the mth control sub-area has reached the preset first control coefficient threshold, and the ground temperature control pipe needs to be closed by controlling the first temperature control closing device.

[0118] If the first control coefficient is greater than the first control coefficient threshold, no shutdown instruction is generated, indicating that the ground temperature control pipe in the mth control sub-area has not yet reached the preset first control coefficient threshold, and it is necessary to continue to monitor the temperature in the ground temperature control pipe in the mth control sub-area.

[0119] The method for judging whether to close the corresponding temperature-controlled closing device based on the second control coefficient is the same as the method for judging whether to close the corresponding temperature-controlled closing device based on the first control coefficient, and will not be repeated here. The difference is that the method for judging whether to close the corresponding temperature-controlled closing device based on the second control coefficient presets the second control coefficient threshold, and the first control coefficient threshold and the second control coefficient threshold are both obtained by technical personnel in this field based on experience. By way of example, the first control coefficient threshold or the second control coefficient threshold is any value between 15°C and 20°C.

[0120] This embodiment divides the control area into M control sub-areas, and sets a temperature control combination device and multiple groups of temperature and humidity monitoring devices in each control sub-area, so as to achieve real-time monitoring of temperature and humidity in each area and precise grain temperature control. This temperature control method based on regional division can more quickly and accurately identify high-temperature areas and potential problem areas in the control area, so as to give priority to regulating abnormal areas and avoid waste of overall temperature control resources; introduce a temperature control strategy prediction model to dynamically adjust the working state of the temperature control equipment according to historical monitoring data and prediction data, and have higher adaptive capabilities.

[0121] This embodiment uses the monitoring and analysis model and the temperature control strategy prediction model to predict future temperature and humidity change trends. This advance prediction mechanism allows the system to start the temperature control equipment before an abnormality occurs, reducing the risk of grain deterioration caused by overheating or excessive humidity in the control area. At the same time, the prediction model can also optimize the allocation of temperature control resources and reduce unnecessary temperature control operations, thereby reducing energy consumption and maintenance costs.

[0122] Example 2

[0123] See also Figure 3 As shown, this embodiment provides an intelligent targeted low-temperature control system based on the principle of dynamic thermal insulation and blocking, and the system includes: a region division unit, a monitoring unit, an analysis and prediction unit, a temperature control unit and a shutdown control unit; each unit is connected by wired and / or wireless means to realize data transmission between modules;

[0124] A region division unit is used to divide the control region into M control sub-regions according to the division rule, and each control sub-region is provided with a group of temperature control combination devices and I group of temperature and humidity monitoring devices; the temperature control combination device includes a ground temperature control pipe and a top temperature control device; M and I are integers greater than zero;

[0125] A monitoring unit, used to obtain grain monitoring data of a group I of temperature and humidity monitoring devices in an m-th control sub-area within a T time period; the grain monitoring data includes a regional temperature coefficient and a regional humidity coefficient;

[0126] The analysis and prediction unit is used to input the grain monitoring data in the time period T into the pre-built monitoring and analysis model to obtain the temperature and humidity evaluation coefficient in the time period T+a; a is an integer greater than zero;

[0127] The temperature control unit is used to input the temperature and humidity evaluation coefficients in the time period T+a into the pre-built temperature control strategy prediction model to obtain the temperature control strategy, and automatically control the temperature control combination device based on the temperature control strategy;

[0128] The closing control unit is used to obtain a first control coefficient of a first temperature-controlled closing device and a second control coefficient of a second temperature-controlled closing device, and determine whether to close the corresponding temperature-controlled closing device based on the first control coefficient or the second control coefficient.

[0129] The formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weight factors in the formula and the preset thresholds in the analysis process are set by technicians in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the weight factor depends on the amount of sample data and the corresponding processing coefficient initially set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0130] Example 3

[0131] This embodiment provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by the one or more processors, the intelligent targeted low-temperature control method based on the dynamic thermal insulation blocking principle as described above may be executed.

[0132] The system according to the embodiment of the present application can also be implemented with the help of the architecture of the following electronic device. The electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, an input / output, a hard disk, etc. A storage device in an electronic device, such as a ROM or a hard disk, can store the intelligent targeted low-temperature control method based on the dynamic thermal insulation blocking principle provided in the present application. Furthermore, the electronic device may also include a user interface. Of course, the above architecture is only exemplary. When implementing different devices, one or more components in the above electronic device may be omitted according to actual needs.

[0133] Example 4

[0134] This embodiment provides a computer-readable storage medium storing instructions. When the instructions are executed on a computer, the computer executes the intelligent targeted low-temperature control method based on the dynamic thermal insulation blocking principle of Example 1.

[0135] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0136] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent targeted low temperature control method based on the principle of dynamic thermal insulation and blocking, characterized in that: include: Step 1: Divide the control area into M control sub-areas according to the division rule, and set a group of temperature control combination devices and I group of temperature and humidity monitoring devices in each control sub-area; the temperature control combination device includes a ground temperature control pipe and a top temperature control device; M and I are integers greater than zero; Step 2: within a time period of T, obtaining grain monitoring data of a group I of temperature and humidity monitoring devices in the mth control sub-area; the grain monitoring data includes a regional temperature coefficient and a regional humidity coefficient; Step 3: Input the grain monitoring data in the time period T into the pre-built monitoring and analysis model to obtain the temperature and humidity evaluation coefficient in the time period T+a; a is an integer greater than zero; Step 4: Input the temperature and humidity evaluation coefficients in the time period T+a into the pre-built temperature control strategy prediction model to obtain the temperature control strategy, and automatically control the temperature control combination device based on the temperature control strategy; Step 5: Obtain a first control coefficient of the first temperature-controlled closing device and a second control coefficient of the second temperature-controlled closing device, and determine whether to close the corresponding temperature-controlled closing device based on the first control coefficient or the second control coefficient.

2. The intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle according to claim 1 is characterized in that: The division rule is to divide the control area into equal parts according to the area or the grain height. Each of the ground temperature control pipes consists of an inlet pipe and a return pipe, and each return pipe is equipped with a first temperature control closing device; each ground temperature control pipe surrounds the corresponding control sub-area and is used to control the grain temperature at the bottom of each control sub-area. Each of the top temperature control devices is a variable frequency air cooling system that adjusts the temperature and speed of the wind to reduce the top and air temperature of the control area by air cooling; and a second temperature control closing device is provided in the return air duct of the top temperature control device; Each set of temperature and humidity monitoring devices includes H temperature sensors and humidity sensors, which are evenly arranged from bottom to top with equal spacing.

3. The intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle according to claim 2 is characterized in that: The method for obtaining grain monitoring data of a group I of temperature and humidity monitoring devices in the mth control sub-area includes: Acquire regional temperature data, wherein the regional temperature data includes a maximum temperature, a minimum temperature, an average temperature, and a temperature change rate; The regional temperature data is calculated by formulating the regional temperature coefficient, and the calculation formula is: ； ； ； ； ； In the formula, represents the regional temperature coefficient of the mth control sub-region, Indicates the maximum temperature, Indicates the minimum temperature. represents the temperature value of the first temperature and humidity monitoring device, represents the average temperature, represents the rate of temperature change, and Indicates that within the T time period and Temperature data at two monitoring moments; Indicates the monitoring time interval, >0, , and is the preset weight factor.

4. The intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle according to claim 3 is characterized in that: The method for obtaining grain monitoring data of a group I of temperature and humidity monitoring devices in the mth control sub-area also includes: Acquire regional humidity data, wherein the regional humidity data includes a maximum humidity value, a minimum humidity value, an average humidity value, and a humidity change rate; The regional humidity data is calculated by formulating the regional humidity coefficient, and the calculation formula is: ； ； ； ； ； In the formula, represents the regional humidity coefficient of the mth control sub-region, Indicates the maximum humidity value, Indicates the minimum humidity value. Represents the humidity value of the first temperature and humidity monitoring device, Represents the average humidity value, represents the humidity change rate, and Indicates that within the T time period and Humidity data at two monitoring moments; Indicates the monitoring time interval, >0, , and is the preset weight factor.

5. The intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle according to claim 4 is characterized in that: The generation logic of the monitoring and analysis model is as follows: Acquiring historical grain monitoring data, the historical grain monitoring data including a plurality of groups of regional temperature coefficients and regional humidity coefficients within a time span and corresponding temperature and humidity assessment coefficients; The historical grain monitoring data is divided into an evaluation training set and an evaluation test set; a regression network model is constructed, the regional temperature coefficient and the regional humidity coefficient in the evaluation training set are used as the input of the regression network model, and the temperature and humidity evaluation coefficient in the evaluation training set is used as the output of the regression network model, the regression network model is trained to obtain an initial regression network, and the training goal is to minimize the sum of the first prediction accuracies. The initial regression network is evaluated using the evaluation test set, and the initial regression network when the sum of the first prediction accuracies reaches convergence is used as a pre-constructed monitoring and analysis model; the regression network model is a decision tree regression network model, a support vector machine regression network model, a linear regression network model or a random forest regression network model.

6. The intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle according to claim 5 is characterized in that: in, The logic for obtaining the temperature and humidity evaluation coefficients in the historical grain monitoring data is as follows: The regional temperature coefficient and regional humidity coefficient in the historical grain monitoring data are extracted, and the regional temperature coefficient and regional humidity coefficient are fused and calculated to obtain the temperature and humidity assessment coefficient; the calculation formula is: ； In the formula, represents the temperature and humidity evaluation coefficient of the mth control sub-area, is the correction constant, .

7. The intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle according to claim 6 is characterized in that: The training method of the temperature control strategy prediction model includes: Pre-collecting the temperature and humidity evaluation coefficients of group A, where A is an integer greater than 1, and setting corresponding temperature control strategies according to the temperature and humidity evaluation coefficients of group A, wherein the temperature control strategies include opening the ground temperature control pipe control, the top temperature control device control, or the ground temperature control pipe and the top temperature control device combined control, and setting different digital labels for different temperature control strategies; marking the digital labels of the temperature control strategies as prediction labels, and converting the temperature and humidity evaluation coefficients and the corresponding prediction labels into a corresponding set of feature vectors; Each group of feature vectors is used as the input of the temperature control strategy prediction model. The temperature control strategy prediction model takes a group of prediction labels corresponding to each group of temperature and humidity evaluation coefficients as output, and takes the actual prediction labels corresponding to each group of temperature and humidity evaluation coefficients as prediction targets, where the actual prediction labels are pre-set prediction labels corresponding to the temperature and humidity evaluation coefficients; minimizing the sum of prediction errors between the prediction labels corresponding to all temperature and humidity evaluation coefficients and the actual prediction labels is used as the training target; the temperature control strategy prediction model is specifically a deep neural network model.

8. The intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle according to claim 7 is characterized in that: The method for obtaining the first control coefficient of the first temperature control closing device includes: Within a preset time period, obtaining an average temperature value of the first temperature control closing device within a preset time span, and marking the average temperature value as a first control coefficient; The method for obtaining the second control coefficient of the second temperature control closing device includes: In a preset time period, an average temperature value of the second temperature control closing device in a preset time span is obtained, and the average temperature value is marked as a second control coefficient.

9. The intelligent targeted low temperature control method based on the dynamic thermal insulation blocking principle according to claim 8 is characterized in that: The method for judging whether to close the corresponding temperature control closing device based on the first control coefficient includes: Presetting a first control coefficient threshold, and comparing the first control coefficient with the first control coefficient threshold; If the first control coefficient is less than or equal to the first control coefficient threshold, a closing instruction is generated; If the first control coefficient is greater than the first control coefficient threshold, no closing instruction is generated.

10. An intelligent targeted low temperature control system based on the principle of dynamic thermal insulation and blocking, used to implement the intelligent targeted low temperature control method based on the principle of dynamic thermal insulation and blocking as described in any one of claims 1 to 9, characterized in that: include: A region division unit is used to divide the control region into M control sub-regions according to the division rule, and each control sub-region is provided with a group of temperature control combination devices and I group of temperature and humidity monitoring devices; the temperature control combination device includes a ground temperature control pipe and a top temperature control device; M and I are integers greater than zero; A monitoring unit, used to obtain grain monitoring data of a group I of temperature and humidity monitoring devices in an m-th control sub-area within a T time period; the grain monitoring data includes a regional temperature coefficient and a regional humidity coefficient; The analysis and prediction unit is used to input the grain monitoring data in the time period T into the pre-built monitoring and analysis model to obtain the temperature and humidity evaluation coefficient in the time period T+a; a is an integer greater than zero; The temperature control unit is used to input the temperature and humidity evaluation coefficients in the time period T+a into the pre-built temperature control strategy prediction model to obtain the temperature control strategy, and automatically control the temperature control combination device based on the temperature control strategy; The closing control unit is used to obtain a first control coefficient of a first temperature-controlled closing device and a second control coefficient of a second temperature-controlled closing device, and determine whether to close the corresponding temperature-controlled closing device based on the first control coefficient or the second control coefficient.

Images