An intelligent control method for active heat storage and release system of large arch shed frame

Abstract

The present invention relates to the field of intelligent control technology, and in particular to an intelligent control method for an active heat storage and release system of a large arch shed skeleton. The method obtains temperature data of the large arch shed at each sampling moment to obtain a temperature data sequence within a historical period; obtains an optimized distance metric between every two temperature data in the temperature data sequence, clusters the temperature data sequence to obtain a preset number of clusters, and determines the heat storage and release state corresponding to each cluster according to the cluster center of each cluster; obtains real-time temperature data of the large arch shed, determines a target heat storage and release state corresponding to the real-time temperature data according to the distance between the real-time temperature data and the cluster center of each cluster, and performs intelligent control on the active heat storage and release system of the large arch shed skeleton according to the target heat storage and release state, thereby improving the accuracy of heat storage and release state identification based on clustering results, so as to achieve more precise and efficient temperature control.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an intelligent control method for an active heat storage and release system of a large arch shed frame. Background Art

[0002] The active heat storage and release system of the large arch shed framework plays an important role in agricultural production. It can effectively use solar energy during the day to store heat and release it at night, thereby alleviating the impact of the temperature difference between day and night on crop growth. The traditional temperature management method for large arch sheds mainly relies on simple fixed thresholds for control. With the improvement of data acquisition technology and computing power, cluster analysis as an important data mining method is widely used to identify the system operation status or system operation mode. Therefore, the existing technology uses the K-means clustering algorithm to perform cluster analysis on the internal and external temperature difference data of the large arch shed to determine the operation mode of the active heat storage and release system of the large arch shed framework, and then regulates the temperature of the large arch shed according to the operation mode.

[0003] However, when the K-means clustering algorithm is used to perform cluster analysis on the internal and external temperature difference data of the large arch greenhouse, the cluster analysis only relies on the internal and external temperature difference data, ignoring the heat flux density characteristics and dynamic thermodynamic behavior of the active heat storage and release system of the large arch greenhouse frame. The internal and external temperature difference data cannot accurately reflect the heat exchange capacity of different large arch greenhouse materials and the thermal inertia characteristics of the system, which leads to deviations in the identification of the operating mode of the active heat storage and release system of the large arch greenhouse frame, reducing the accuracy of regulating the temperature of the large arch greenhouse according to the operating mode.

[0004] Therefore, how to improve the accuracy of identifying the operating mode of the active heat storage and release system of the large arch shed skeleton has become an urgent problem to be solved. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides an intelligent control method for an active heat storage and release system of a large arch shed skeleton, so as to solve the problem of how to improve the accuracy of identifying the operating mode of the active heat storage and release system of the large arch shed skeleton.

[0006] An embodiment of the present invention provides an intelligent control method for an active heat storage and release system of a large arch shed frame, the method comprising the following steps:

[0007] Acquire temperature data of the large arch shed at each sampling time to obtain a temperature data sequence within a historical period, wherein the temperature data includes the internal temperature and the external temperature of the large arch shed;

[0008] For any two temperature data in the temperature data sequence, respectively obtain the heat flux density of the two temperature data, obtain the adaptive heat flux density normalization coefficient between the two temperature data according to the external temperature difference and the sampling time interval between the two temperature data, and obtain the optimized distance metric of the two temperature data in the clustering process according to the internal temperature difference, the heat flux density difference and the adaptive heat flux density normalization coefficient between the two temperature data;

[0009] Obtaining an optimized distance metric between every two temperature data in the temperature data sequence, clustering the temperature data sequence according to the optimized distance metric between every two temperature data in the temperature data sequence to obtain a preset number of clusters, and determining a heat storage and release state corresponding to each cluster according to a cluster center of each cluster;

[0010] The real-time temperature data of the large arch shed is obtained, and the target heat storage and release state corresponding to the real-time temperature data is determined according to the distance between the real-time temperature data and the cluster center of each cluster, and the active heat storage and release system of the large arch shed skeleton is intelligently regulated according to the target heat storage and release state.

[0011] Preferably, the step of respectively acquiring the heat flux densities of the two temperature data comprises:

[0012] For any one of the two temperature data, the temperature difference between the internal temperature and the external temperature of the temperature data is obtained, a first ratio between the temperature difference and a preset sampling interval is calculated, and the product of the first ratio and a preset thermal conductivity coefficient of the large arch shed is used as the heat flux density of the temperature data.

[0013] Preferably, obtaining the adaptive heat flux density normalization coefficient between the two temperature data according to the external temperature difference and the sampling time interval between the two temperature data includes:

[0014] Obtaining a temperature change rate of the two temperature data according to a ratio of an absolute value of an external temperature difference between the two temperature data to a sampling time interval, calculating a difference between the temperature change rate and a preset temperature change rate threshold, and mapping the difference using a hyperbolic tangent function to obtain a corresponding first mapping value;

[0015] Acquire a second ratio of a sampling time interval between the two temperature data to a preset characteristic time constant, and negatively map the second ratio using a preset exponential function to obtain a corresponding second mapping value;

[0016] Obtain a preset thermal inertia influence coefficient, the product of the first mapping value and the second mapping value, obtain an addition value of a constant 1 and the product, and use the sum of the addition value and a preset basic heat flux density normalization coefficient as an adaptive heat flux density normalization coefficient between the two temperature data.

[0017] Preferably, obtaining the optimized distance metric of the two temperature data in the clustering process according to the internal temperature difference, the heat flux difference and the adaptive heat flux normalization coefficient between the two temperature data includes:

[0018] Obtain a first square difference of the internal temperature between the two temperature data, obtain a second square difference of the heat flux density between the two temperature data, obtain a multiplication result of the adaptive heat flux density normalization coefficient and the second square difference, perform a quadratic square root on the sum of the multiplication result and the first square difference, and obtain an optimized distance metric of the two temperature data in the clustering process.

[0019] Preferably, determining the heat storage and release state corresponding to each cluster according to the cluster center of each cluster includes:

[0020] Obtain the optimal low temperature, optimal high temperature, maximum internal and external temperature difference threshold and minimum internal and external temperature difference threshold corresponding to the large arch shed;

[0021] For any cluster, the corresponding internal and external temperature difference is obtained according to the internal temperature and external temperature corresponding to the cluster center of the cluster, and the internal temperature corresponding to the cluster center of the cluster, the optimal low temperature and the optimal high temperature are compared to obtain a first comparison result, and the internal and external temperature difference, the maximum internal and external temperature difference threshold and the minimum internal and external temperature difference threshold are compared to obtain a second comparison result, and the heat storage and release state corresponding to the cluster is determined in combination with the first comparison result and the second comparison result, wherein the heat storage and release state includes: strong heat storage state, moderate heat storage state, slight heat storage state, observation state, slight heat release state, moderate heat release state and strong heat release state.

[0022] Preferably, determining the target heat storage and release state corresponding to the real-time temperature data according to the distance between the real-time temperature data and the cluster center of each cluster includes:

[0023] For any cluster, calculate the similarity between the real-time temperature data and each temperature data in the cluster, sort all similarities from large to small, and obtain the temperature data corresponding to the first N similarities after sorting as the nearest neighbor data of the real-time temperature data;

[0024] According to the adaptive heat flux density normalization coefficient between the real-time temperature data and each of the nearest neighbor data, the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster is obtained; according to the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster, the optimized distance metric between the real-time temperature data and the cluster center of the cluster is obtained;

[0025] An optimized distance metric between the real-time temperature data and the cluster center of each cluster is obtained, and a heat storage and release state of the cluster corresponding to the minimum optimized distance metric is selected as a target heat storage and release state corresponding to the real-time temperature data.

[0026] Preferably, the calculating the similarity between the real-time temperature data and each temperature data in the cluster includes:

[0027] For any temperature data in the cluster, calculating the sampling time interval between the real-time temperature data and the temperature data, calculating the absolute value of the internal temperature difference and the absolute value of the external temperature difference between the real-time temperature data and the temperature data, and obtaining the addition result of the absolute value of the internal temperature difference and the absolute value of the external temperature difference;

[0028] A weighted sum is performed on the sampling time interval between the real-time temperature data and the temperature data and the addition result to obtain a corresponding weighted sum result, and the inverse of the weighted sum result is used as the similarity between the real-time temperature data and the temperature data.

[0029] Preferably, the step of obtaining the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster according to the adaptive heat flux density normalization coefficient between the real-time temperature data and each of the nearest neighbor data comprises:

[0030] According to the adaptive heat flux density normalization coefficient between the real-time temperature data and each of the nearest neighbor data, a mean value of the adaptive heat flux density normalization coefficient is obtained as the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster.

[0031] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0032] The present invention obtains temperature data of a large arch shed at each sampling moment to obtain a temperature data sequence within a historical period, wherein the temperature data includes the internal temperature and the external temperature of the large arch shed; for any two temperature data in the temperature data sequence, respectively obtain the heat flux density of the two temperature data, obtain an adaptive heat flux density normalization coefficient between the two temperature data according to the external temperature difference and the sampling time interval between the two temperature data, and obtain an optimized distance metric of the two temperature data in a clustering process according to the internal temperature difference, the heat flux density difference and the adaptive heat flux density normalization coefficient between the two temperature data; obtain the optimized distance metric between every two temperature data in the temperature data sequence, cluster the temperature data sequence according to the optimized distance metric between every two temperature data in the temperature data sequence, obtain a preset number of clusters, and determine the heat storage and release state corresponding to each cluster according to the cluster center of each cluster; obtain the real-time temperature data of the large arch shed, determine the target heat storage and release state corresponding to the real-time temperature data according to the distance between the real-time temperature data and the cluster center of each cluster, and intelligently regulate the active heat storage and release system of the large arch shed skeleton according to the target heat storage and release state. Among them, in the process of clustering analysis of temperature data series, by introducing heat flux density and combining it with temperature data to construct a new distance metric, the clustering analysis process not only considers the temperature difference but also the temperature change trend, which more comprehensively reflects the thermodynamic state of the system. At the same time, considering that the structural materials of large arch sheds often have a large heat capacity (the usual heat storage medium is water), which leads to a lag effect in temperature changes, an adaptive heat flux density standardization coefficient is further introduced. When constructing a new distance metric based on the heat flux density difference and the temperature data difference, the relative importance of temperature data and heat flux density is adaptively adjusted, which improves the distance metric (optimized distance metric) in the clustering analysis process to capture the overall thermodynamic state of the active heat storage and release of the large arch shed skeleton, thereby ensuring the accuracy of identifying the operating mode (heat storage and release state) of the active heat storage and release system of the large arch shed skeleton based on the clustering results, and at the same time provides a solid foundation for achieving more precise and efficient temperature control. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0034] Figure 1 It is a method flow chart of an intelligent control method of an active heat storage and release system of a large arch shed skeleton provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0035] Embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, but should not be understood as limiting the present disclosure.

[0036] It should be noted that the terms "first", "second", etc. in the specification of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0037] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0038] See also Figure 1 , is a method flow chart of an intelligent control method for an active heat storage and release system of a large arch shed skeleton provided in Embodiment 1 of the present invention, such as Figure 1 As shown, the method may include:

[0039] Step S101, obtaining the temperature data of the large arch shed at each sampling time, and obtaining a temperature data sequence in a historical period, wherein the temperature data includes the internal temperature and the external temperature of the large arch shed.

[0040] Install multiple temperature sensors at different heights and locations of the large arch shed, and set the sampling interval to 30 minutes, that is, collect temperature data of the large arch shed every 30 minutes. It is worth noting that for any sampling time, obtain the internal temperature and external temperature of the large arch shed collected by each temperature sensor at the sampling time, and calculate the average of all internal temperatures and the mean of all external temperatures , the mean and mean As the temperature data at the sampling time, record the temperature data Similarly, the temperature data at each sampling moment is obtained to obtain the temperature data at each sampling moment in the historical period to form a temperature data sequence. Preferably, the historical period is set to one week, which is not limited here and can be set according to the implementation scenario.

[0041] Step S102, for any two temperature data in the temperature data sequence, respectively obtain the heat flux density of the two temperature data, obtain the adaptive heat flux density normalization coefficient between the two temperature data according to the external temperature difference and the sampling time interval between the two temperature data, and obtain the optimized distance measurement of the two temperature data in the clustering process according to the internal temperature difference, heat flux density difference and adaptive heat flux density normalization coefficient between the two temperature data.

[0042] In the active heat storage and release system of the large arch greenhouse frame, accurately describing the thermodynamic state of the system is the key to achieving precise temperature control. Traditionally, the temperature data in the large arch greenhouse is collected and the K-means clustering algorithm is used to analyze the thermodynamic state of the active heat storage and release system of the large arch greenhouse frame. However, the traditional distance measurement in the K-means clustering algorithm only considers the temperature data and cannot fully reflect the thermodynamic characteristics of the active heat storage and release system of the large arch greenhouse frame. As a result, the clustering results are difficult to accurately reflect the actual heat storage and release state of the active heat storage and release system of the large arch greenhouse frame, making the accuracy of real-time heat storage and release control based on the clustering results insufficient, and the crops in the large arch greenhouse cannot grow within their optimal temperature range.

[0043] To solve the above problem, in an embodiment of the present invention, in the process of clustering the temperature data sequence using the K-means clustering algorithm, the distance metric between every two temperature data in the temperature data sequence is optimized so that the clustering result can more comprehensively describe the dynamic thermodynamic state of the system. Among them, for any two temperature data in the temperature data sequence, the method for optimizing the distance metric between the two temperature data is:

[0044] (1) Obtain the heat flux density of the two temperature data respectively.

[0045] Specifically, for any one of the two temperature data, the temperature difference between the internal temperature and the external temperature of the temperature data is obtained, the first ratio between the temperature difference and the preset sampling interval is calculated, and the product of the first ratio and the preset thermal conductivity coefficient of the large arch shed is used as the heat flux density of the temperature data.

[0046] In one embodiment, taking the i-th temperature data of the two temperature data as an example, the calculation expression of the heat flux density of the i-th temperature data is:

[0047]

[0048] in, represents the heat flux density of the ith temperature data, C represents the preset heat conduction coefficient of the large arch shed, represents the internal temperature of the i-th temperature data, represents the external temperature of the i-th temperature data, Indicates the preset sampling interval, which is 30 minutes.

[0049] It should be noted that the unit of C is usually W / (m²·K), and the value of C is related to the structural characteristics of the greenhouse. For example, for ordinary plastic film greenhouses: the value range of C is 3-6W / (m²·K), and for glass greenhouses: the value range of C is 5-8W / (m²·K); the heat flux density reflects the amount of heat passing through a unit area per unit time, and comprehensively describes the temperature difference and the heat conduction rate, so that the subsequent distance measurement can comprehensively consider the temperature difference and the heat flux density difference, so as to avoid the situation where the internal temperature between two temperature data is the same, but the actual external temperature and sunlight radiation intensity are different, and they are judged as the same thermodynamic state through traditional distance measurement.

[0050] Similarly, the heat flux density corresponding to each temperature data is obtained respectively.

[0051] (2) Obtain an adaptive heat flux normalization coefficient between the two temperature data according to the external temperature difference and the sampling time interval between the two temperature data.

[0052] Specifically, according to the ratio of the absolute value of the external temperature difference between the two temperature data to the sampling time interval, the temperature change rate of the two temperature data is obtained, the difference between the temperature change rate and a preset temperature change rate threshold is calculated, and the difference is mapped using a hyperbolic tangent function to obtain a corresponding first mapping value;

[0053] Acquire a second ratio of a sampling time interval between the two temperature data to a preset characteristic time constant, and negatively map the second ratio using a preset exponential function to obtain a corresponding second mapping value;

[0054] Obtain a preset thermal inertia influence coefficient, the product of the first mapping value and the second mapping value, obtain an addition value of a constant 1 and the product, and use the sum of the addition value and a preset basic heat flux density normalization coefficient as an adaptive heat flux density normalization coefficient between the two temperature data.

[0055] In one embodiment, although the introduction of heat flux density improves the thermodynamic characteristics of the active heat storage and release system of the large arch shed frame to a certain extent, the thermal inertia characteristics of the active heat storage and release system of the large arch shed frame are not fully considered. The thermal inertia makes the change of system temperature lag behind the actual environmental change. Therefore, an adaptive heat flux density normalization coefficient is introduced in the embodiment of the present invention to adjust the weight of the temperature difference and the heat flux density difference in the distance calculation. The calculation expression of the adaptive heat flux density normalization coefficient between the two temperature data is:

[0056]

[0057] in, represents the adaptive heat flux normalization coefficient between two temperature data, Represents the preset basic heat flux standardization coefficient, 1 represents a constant, Represents the preset thermal inertia influence coefficient, tanh() represents the hyperbolic tangent function, represents the parameter used to control the slope of the function, Represents the absolute value of the external temperature difference between two temperature data (the i-th temperature data and the j-th temperature data), Indicates the sampling time interval between two temperature data. represents the preset temperature change rate threshold, e represents the natural constant, Indicates the preset characteristic time constant.

[0058] Preferably, in the embodiment of the present invention, The value of is 1, and the value range is [0.5, 2], which is used to balance the weights of temperature difference and heat flux density difference in distance measurement; The value of is 0.5, and the value range is [0, 1], which is used to control the influence of thermal inertia on distance measurement; The value of is 10000, which is used to control the sensitivity of the active heat storage and release system of the large arch shed skeleton to the temperature change rate; The value of is 0.0005℃ / s, which is used to define the significant temperature change rate considered by the active heat storage and release system of the large arch shed skeleton; The value is 3600s, which is used to reflect the thermal response speed of the active heat storage and release system of the large arch shed skeleton.

[0059] By adjusting , , and Parameters, adapted to different types of large arch shed systems, for systems with large thermal inertia (such as large arch sheds using water as heat storage medium), can be increased value; for systems with faster response (such as large light-weight arch sheds), the value, by adjusting and , which can control the system's sensitivity to the rate of temperature change and can be applied in a variety of large greenhouse systems.

[0060] Used to characterize the rate of temperature change, Greater than When the external temperature is changing rapidly (such as sunrise in the morning), The value of increases, thereby increasing the weight of heat density in the subsequent distance measurement, which can timely reflect the dynamic response of the system; on the contrary, when Less than When The value of , weakens the influence of heat flux density, and relies more on temperature difference for distance measurement.

[0061] It is used to simulate the decay of thermal inertia effect over time. The influence of thermal inertia is not permanent, but gradually weakens over time. For temperature fluctuations in a short period of time, the thermal inertia effect is more significant, while for temperature fluctuations in a long period of time, the thermal inertia effect is relatively weakened. For example, after a sudden change in external temperature, the internal temperature of the large arch shed will be significantly affected for a period of time, but this effect will gradually weaken. Therefore, the thermal inertia effect is used to simulate the decay of thermal inertia effect over time. Being able to accurately capture this dynamic nature, it ensures that the impact of adjustments does not last indefinitely but rather gradually weakens over time.

[0062] It should be noted that the adaptive heat flux normalization coefficient between the two temperature data is The accuracy of describing the dynamic characteristics of the active heat storage and release system of the large arch shed skeleton has been significantly improved. It can not only reflect the instantaneous state of the system, but also accurately capture the changing trend and dynamic characteristics of the system, providing a solid foundation for achieving more precise and efficient temperature control.

[0063] (3) According to the internal temperature difference, heat flux difference and adaptive heat flux normalization coefficient between the two temperature data, the optimized distance metric of the two temperature data in the clustering process is obtained.

[0064] Specifically, obtain the first square difference of the internal temperature between the two temperature data, obtain the second square difference of the heat flux density between the two temperature data, obtain the multiplication result of the adaptive heat flux density normalization coefficient and the second square difference, take the square root of the sum of the multiplication result and the first square difference, and obtain the optimized distance metric of the two temperature data in the clustering process.

[0065] In one embodiment, the calculation expression of the optimized distance metric of two temperature data in the clustering process is:

[0066]

[0067] in, represents the optimized distance metric between the i-th temperature data and the j-th temperature data, represents the internal temperature of the i-th temperature data, represents the internal temperature of the jth temperature data, represents the adaptive heat flux normalization coefficient between the i-th temperature data and the j-th temperature data, represents the heat flux density of the ith temperature data, Represents the heat flux density of the j-th temperature data.

[0068] It should be noted that the calculation expression of the optimized distance metric takes into account both the temperature difference and the heat flux density difference, so that the distance metric in the clustering process more comprehensively reflects the thermodynamic state of the active heat storage and release system of the large arch shed skeleton. The reference of the adaptive heat flux density standardization coefficient allows the adjustment of the relative importance of the temperature difference and the heat flux density difference in the distance metric. Through the adaptive heat flux density standardization coefficient between each two temperature data, the weights of temperature and heat flux density can be balanced according to the specific application scenario. For large arch sheds with large heat capacity, the influence weight of thermal inertia is increased, while for structures with faster thermal response, the influence weight of thermal inertia is reduced accordingly, thereby identifying a more detailed thermodynamic state. For example: when the temperature changes drastically, the distance metric will be adaptively amplified to reflect that the system is in a changing state, while when the temperature change tends to be stable, the adjustment of the distance metric is relatively small.

[0069] Similarly, according to the above method of optimizing the distance metric between the i-th temperature data and the j-th temperature data, the optimized distance metric between every two temperature data in the temperature data sequence is obtained.

[0070] Step S103, obtaining an optimized distance metric between every two temperature data in the temperature data sequence, clustering the temperature data sequence according to the optimized distance metric between every two temperature data in the temperature data sequence, obtaining a preset number of clusters, and determining the heat storage and release state corresponding to each cluster according to the cluster center of each cluster.

[0071] After obtaining the optimized distance measurement between every two temperature data in the temperature data sequence, K-means clustering can be performed on the temperature data sequence according to the optimized distance measurement between every two temperature data in the temperature data sequence to obtain a preset number of clusters, wherein the number of clusters K can be obtained according to the elbow rule. The elbow rule and K-means clustering belong to the existing technology and will not be described here.

[0072] After obtaining K clusters, the heat storage and release state corresponding to each cluster is determined according to the cluster center of each cluster, which is used to provide a more reliable data basis for subsequent real-time intelligent temperature control. Among them, the heat storage and release state corresponding to each cluster is determined according to the cluster center of each cluster, including:

[0073] Obtain the optimal low temperature, optimal high temperature, maximum internal and external temperature difference threshold and minimum internal and external temperature difference threshold corresponding to the large arch shed;

[0074] For any cluster, the corresponding internal and external temperature difference is obtained according to the internal temperature and external temperature corresponding to the cluster center of the cluster, and the internal temperature corresponding to the cluster center of the cluster, the optimal low temperature and the optimal high temperature are compared to obtain a first comparison result, and the internal and external temperature difference, the maximum internal and external temperature difference threshold and the minimum internal and external temperature difference threshold are compared to obtain a second comparison result, and the heat storage and release state corresponding to the cluster is determined in combination with the first comparison result and the second comparison result, wherein the heat storage and release state includes: strong heat storage state, moderate heat storage state, slight heat storage state, observation state, slight heat release state, moderate heat release state and strong heat release state.

[0075] In one embodiment, the optimal low temperature, optimal high temperature, maximum internal and external temperature difference threshold and minimum internal and external temperature difference threshold corresponding to the large arch shed are set according to the crops in the large arch shed. For example, the suitable temperature for the flowering and fruiting period of tomatoes is 18-24 degrees Celsius, so the optimal low temperature can be set. , best high temperature , Maximum internal and external temperature difference threshold , minimum internal and external temperature difference threshold .

[0076] Take a cluster as an example, get the internal temperature corresponding to the cluster center of the cluster and external temperature , and the corresponding internal and external temperature difference is obtained ,like and , then the heat storage and release state corresponding to this cluster is a strong heat storage state; if and , then the heat storage and release state corresponding to this cluster is a moderate heat storage state; if and , then the heat storage and release state corresponding to this cluster is a slight heat storage state; if and , then the heat storage and release state corresponding to the cluster is the observation state; if and , then the heat storage and release state corresponding to this cluster is a slight heat release state; if and , then the heat storage and release state corresponding to this cluster is a moderate heat release state; if and , then the heat storage and release state corresponding to this cluster is a strong heat release state.

[0077] It should be noted that the strong heat storage state is used to characterize that the internal temperature is suitable or high, the external temperature is significantly higher than the internal temperature, and the heat flux is large; the moderate heat storage state is used to characterize that the internal temperature is suitable, the external temperature is higher than the internal temperature, and the heat flux is medium; the slight heat storage state is used to characterize that the internal temperature is suitable, the external temperature is slightly higher than the internal temperature, and the heat flux is small; the observation state is used to characterize that the internal temperature is insufficient, the external temperature is high, and the heat flux is small or medium; the slight heat release state is used to characterize that the internal temperature is suitable, the external temperature is lower than the internal temperature, the heat flux value is negative, but its absolute value is small; the moderate heat release state is used to characterize that the internal temperature is suitable, the external temperature is significantly lower than the internal temperature, the heat flux value is negative, but its absolute value is medium; the strong heat release state is used to characterize that the internal temperature is suitable or low, the external temperature is much lower than the internal temperature, the heat flux value is negative, but its absolute value is large.

[0078] At this point, the heat storage and release state corresponding to each cluster can be determined.

[0079] Step S104, obtain the real-time temperature data of the large arch shed, determine the target heat storage and release state corresponding to the real-time temperature data according to the distance between the real-time temperature data and the cluster center of each cluster, and intelligently regulate the active heat storage and release system of the large arch shed skeleton according to the target heat storage and release state.

[0080] According to the collection method of step S101, the real-time temperature data of the large arch shed is obtained , and then according to the distance between the real-time temperature data and the cluster center of each cluster, the target heat storage and release state corresponding to the real-time temperature data is determined, which is used to intelligently regulate the active heat storage and release system of the large arch greenhouse frame according to the heat storage and release state corresponding to the real-time temperature data, so as to optimize the crop growth temperature in the large arch greenhouse.

[0081] Wherein, determining the target heat storage and release state corresponding to the real-time temperature data according to the distance between the real-time temperature data and the cluster center of each cluster includes:

[0082] (1) For any cluster, calculate the similarity between the real-time temperature data and each temperature data in the cluster, sort all similarities from large to small, and obtain the temperature data corresponding to the first N similarities after sorting as the nearest neighbor data of the real-time temperature data.

[0083] The step of calculating the similarity between the real-time temperature data and each temperature data in the cluster includes:

[0084] For any temperature data in the cluster, calculating the sampling time interval between the real-time temperature data and the temperature data, calculating the absolute value of the internal temperature difference and the absolute value of the external temperature difference between the real-time temperature data and the temperature data, and obtaining the addition result of the absolute value of the internal temperature difference and the absolute value of the external temperature difference;

[0085] A weighted sum is performed on the sampling time interval between the real-time temperature data and the temperature data and the addition result to obtain a corresponding weighted sum result, and the inverse of the weighted sum result is used as the similarity between the real-time temperature data and the temperature data.

[0086] In one embodiment, taking the yth temperature data in a cluster as an example, first obtain the sampling time interval between the yth temperature data and the real-time temperature data. , Indicates the sampling time of real-time temperature data, Indicates the sampling time of the yth temperature data, and obtains , and then calculate the similarity between the y-th temperature data and the real-time temperature data:

[0087]

[0088] in, represents the similarity between the y-th temperature data and the real-time temperature data, represents the weight of the sampling time interval, represents the weight of the temperature difference, Indicates the temperature difference between the y-th temperature data and the real-time temperature data.

[0089] It should be noted that setting = , there is no restriction here, The smaller the value is, the shorter the sampling interval is, and the temperature data collected under the same state has a greater corresponding similarity; The larger the value is, the greater the difference between the two temperature data is, the less the temperature data are collected under the same state, and the smaller the corresponding similarity is.

[0090] Similarly, obtain the similarity between each temperature data in the cluster and the real-time temperature data, arrange all similarities in order from large to small, set N=5, and then take the temperature data corresponding to the first 5 similarities after arrangement as the nearest neighbor data of the real-time temperature data.

[0091] (2) According to the adaptive heat flux density normalization coefficient between the real-time temperature data and each of the nearest neighbor data, the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster is obtained; according to the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster, the optimized distance metric between the real-time temperature data and the cluster center of the cluster is obtained.

[0092] Wherein, obtaining the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster according to the adaptive heat flux density normalization coefficient between the real-time temperature data and each of the nearest neighbor data includes:

[0093] According to the adaptive heat flux density normalization coefficient between the real-time temperature data and each of the nearest neighbor data, a mean value of the adaptive heat flux density normalization coefficient is obtained as the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster.

[0094] In one embodiment, according to the above-mentioned method for obtaining the adaptive heat flux density normalization coefficient, the adaptive heat flux density normalization coefficient between the real-time temperature data and each nearest neighbor data is obtained respectively, and the average of all the adaptive heat flux density normalization coefficients is used as the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster.

[0095] After obtaining the adaptive heat flux normalization coefficient between the real-time temperature data and the cluster center of the cluster, the optimized distance metric between the real-time temperature data and the cluster center of the cluster can be obtained according to the calculation formula of the above-mentioned optimized distance metric.

[0096] Similarly, the optimized distance metric between the real-time temperature data and the cluster center of each cluster can be obtained.

[0097] (3) Obtaining an optimized distance metric between the real-time temperature data and the cluster center of each cluster, and selecting the heat storage and release state of the cluster corresponding to the minimum optimized distance metric as the target heat storage and release state corresponding to the real-time temperature data.

[0098] After determining the target heat storage and release state corresponding to the real-time temperature data, the active heat storage and release system of the large arch shed skeleton can be intelligently regulated according to the target heat storage and release state to achieve different degrees of temperature control measures. For example: If the real-time temperature data belongs to a strong heat storage state, considering that the external temperature is too high, it needs to maximize heat storage, and then regulate the active heat storage and release system of the large arch shed skeleton to the maximum flow operation state, so as to achieve rapid temperature control.

[0099] It should be noted that the focus of the present invention is on how to optimize the clustering results of the temperature data series. The method of intelligent control based on the clustering results belongs to the prior art and will not be described in detail here.

[0100] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An intelligent control method for an active heat storage and release system of a large arch shed frame, characterized in that: The method comprises: Acquire the temperature data of the large arch shed at each sampling time to obtain a temperature data sequence in a historical period, wherein the temperature data includes the internal temperature and the external temperature of the large arch shed; For any two temperature data in the temperature data sequence, respectively obtain the heat flux density of the two temperature data, obtain the adaptive heat flux density normalization coefficient between the two temperature data according to the external temperature difference and the sampling time interval between the two temperature data, and obtain the optimized distance metric of the two temperature data in the clustering process according to the internal temperature difference, the heat flux density difference and the adaptive heat flux density normalization coefficient between the two temperature data; Obtaining an optimized distance metric between every two temperature data in the temperature data sequence, clustering the temperature data sequence according to the optimized distance metric between every two temperature data in the temperature data sequence to obtain a preset number of clusters, and determining a heat storage and release state corresponding to each cluster according to a cluster center of each cluster; Acquire the real-time temperature data of the large arch shed, determine the target heat storage and release state corresponding to the real-time temperature data according to the distance between the real-time temperature data and the cluster center of each cluster, and intelligently regulate the active heat storage and release system of the large arch shed framework according to the target heat storage and release state; The step of determining a target heat storage and release state corresponding to the real-time temperature data according to a distance between the real-time temperature data and a cluster center of each cluster includes: For any cluster, calculate the similarity between the real-time temperature data and each temperature data in the cluster, sort all similarities from large to small, and obtain the temperature data corresponding to the first N similarities after sorting as the nearest neighbor data of the real-time temperature data; According to the adaptive heat flux density normalization coefficient between the real-time temperature data and each of the nearest neighbor data, the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster is obtained; according to the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster, the optimized distance metric between the real-time temperature data and the cluster center of the cluster is obtained; An optimized distance metric between the real-time temperature data and the cluster center of each cluster is obtained, and a heat storage and release state of the cluster corresponding to the minimum optimized distance metric is selected as a target heat storage and release state corresponding to the real-time temperature data.

2. The intelligent control method of the active heat storage and release system of a large arch shed frame according to claim 1 is characterized in that: The step of respectively acquiring the heat flux densities of the two temperature data comprises: For any one of the two temperature data, the temperature difference between the internal temperature and the external temperature of the temperature data is obtained, a first ratio between the temperature difference and a preset sampling interval is calculated, and the product of the first ratio and a preset thermal conductivity coefficient of the large arch shed is used as the heat flux density of the temperature data.

3. The intelligent control method of the active heat storage and release system of a large arch shed frame according to claim 1 is characterized in that: The step of obtaining an adaptive heat flux density normalization coefficient between the two temperature data according to the external temperature difference and the sampling time interval between the two temperature data comprises: Obtaining a temperature change rate of the two temperature data according to a ratio of an absolute value of an external temperature difference between the two temperature data to a sampling time interval, calculating a difference between the temperature change rate and a preset temperature change rate threshold, and mapping the difference using a hyperbolic tangent function to obtain a corresponding first mapping value; Acquire a second ratio of a sampling time interval between the two temperature data to a preset characteristic time constant, and negatively map the second ratio using a preset exponential function to obtain a corresponding second mapping value; Obtain a preset thermal inertia influence coefficient, the product of the first mapping value and the second mapping value, obtain an addition value of a constant 1 and the product, and use the sum of the addition value and a preset basic heat flux density normalization coefficient as an adaptive heat flux density normalization coefficient between the two temperature data.

4. The intelligent control method of the active heat storage and release system of a large arch shed frame according to claim 1 is characterized in that: The step of obtaining an optimized distance metric of the two temperature data in a clustering process according to an internal temperature difference, a heat flux difference and an adaptive heat flux normalization coefficient between the two temperature data includes: Obtain a first square difference of the internal temperature between the two temperature data, obtain a second square difference of the heat flux density between the two temperature data, obtain a multiplication result of the adaptive heat flux density normalization coefficient and the second square difference, perform a quadratic square root on the sum of the multiplication result and the first square difference, and obtain an optimized distance metric of the two temperature data in the clustering process.

5. The intelligent control method of the active heat storage and release system of a large arch shed frame according to claim 1 is characterized in that: The step of determining the heat storage and release state corresponding to each cluster according to the cluster center of each cluster includes: Obtain the optimal low temperature, optimal high temperature, maximum internal and external temperature difference threshold and minimum internal and external temperature difference threshold corresponding to the large arch shed; For any cluster, the corresponding internal and external temperature difference is obtained according to the internal temperature and external temperature corresponding to the cluster center of the cluster, and the internal temperature corresponding to the cluster center of the cluster, the optimal low temperature and the optimal high temperature are compared to obtain a first comparison result, and the internal and external temperature difference, the maximum internal and external temperature difference threshold and the minimum internal and external temperature difference threshold are compared to obtain a second comparison result, and the heat storage and release state corresponding to the cluster is determined in combination with the first comparison result and the second comparison result, wherein the heat storage and release state includes: strong heat storage state, moderate heat storage state, slight heat storage state, observation state, slight heat release state, moderate heat release state and strong heat release state.

6. The intelligent control method of the active heat storage and release system of a large arch shed frame according to claim 1 is characterized in that: The calculating the similarity between the real-time temperature data and each temperature data in the cluster includes: For any temperature data in the cluster, calculating the sampling time interval between the real-time temperature data and the temperature data, calculating the absolute value of the internal temperature difference and the absolute value of the external temperature difference between the real-time temperature data and the temperature data, and obtaining the addition result of the absolute value of the internal temperature difference and the absolute value of the external temperature difference; A weighted sum is performed on the sampling time interval between the real-time temperature data and the temperature data and the addition result to obtain a corresponding weighted sum result, and the inverse of the weighted sum result is used as the similarity between the real-time temperature data and the temperature data.

7. The intelligent control method of the active heat storage and release system of a large arch shed frame according to claim 1 is characterized in that: The step of obtaining the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster according to the adaptive heat flux density normalization coefficient between the real-time temperature data and each of the nearest neighbor data includes: According to the adaptive heat flux density normalization coefficient between the real-time temperature data and each of the nearest neighbor data, a mean value of the adaptive heat flux density normalization coefficient is obtained as the adaptive heat flux density normalization coefficient between the real-time temperature data and the cluster center of the cluster.

Images