Novel irrigation, fertilization and plant growth monitoring all-in-one machine

Abstract

The invention relates to the field of fertigation, in particular to a novel fertigation and plant growth monitoring all-in-one machine which evaluates the change period of monitoring data according to initial monitoring data of a plant growth monitoring data acquisition module. Obtaining a first offset degree according to the difference between the plant growth monitoring time sequence data window and the change period evaluation result of the monitoring data; according to the first offset degree, performing optimization evaluation on the trend difference between the plant growth monitoring time sequence data windows, and obtaining an optimized distance measurement result; completing a clustering process according to the optimized distance measurement result; evaluating the abnormal degree of the plant growth monitoring time sequence data window according to cluster distribution in the clustering result; numerical optimization of the plant growth monitoring data is carried out according to an abnormal degree evaluation result of the plant growth monitoring time sequence data window, and an accurate result of the plant growth monitoring data is obtained, so that the precision of irrigation and fertilization demand evaluation of the all-in-one machine is improved.

Description

Technical Field

[0001] The invention relates to the technical field of irrigation and fertilization, and in particular to a novel all-in-one machine for irrigation, fertilization and plant growth monitoring. Background Art

[0002] With the development of modern agriculture, intelligent irrigation, fertilization and plant growth monitoring technology plays an important role in increasing crop yields, optimizing resource utilization and reducing environmental load. The integrated irrigation, fertilization and plant growth monitoring equipment manages nutrient solution supply and environmental data in real time through the central control module, making agricultural production more efficient and accurate. However, in environments with high humidity, such as greenhouses, humid climate conditions or high salinity environments, the sensor surface is easily disturbed by mineral deposition, resulting in data acquisition distortion or signal loss, thereby affecting the system's accurate judgment and regulation of the plant growth environment. This monitoring problem caused by environmental influences seriously restricts the stability and practicality of the all-in-one machine, especially during long-term use, minerals in the soil (such as salt) may be deposited on the sensor surface, which will lead to inaccurate monitoring data during the collection of plant growth monitoring data. Therefore, how to ensure the accuracy of sensor monitoring data in the plant growth monitoring all-in-one machine has become an urgent problem to be solved in the development of intelligent agricultural equipment. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a novel all-in-one irrigation and fertilization and plant growth monitoring machine to solve the problem of how to ensure the accuracy of sensor monitoring data in the all-in-one plant growth monitoring machine.

[0004] In an embodiment of the present invention, a novel integrated fertigation and plant growth monitoring machine is provided, comprising a device frame, wherein the device frame comprises a plant growth monitoring data acquisition module, a plant growth monitoring data storage module, a central control module, a plant planting module, a nutrient solution mixing module and a fertigation module, wherein the central control module stores the data collected by the plant growth monitoring data acquisition module in the plant growth monitoring data storage module, wherein the central control module controls the fertigation module according to the plant growth monitoring data in the plant growth monitoring data storage module, and wherein the central control module controls the fertigation module according to the plant growth monitoring data in the plant growth monitoring data storage module, and wherein the central control module controls the fertigation module according to the plant growth monitoring data in the plant growth monitoring data storage module, and wherein the steps of:

[0005] Step 1. The central control module obtains the plant growth monitoring data in the plant growth data storage module;

[0006] Step 2. The central control module performs optimization analysis based on the acquired plant growth monitoring data, obtains abnormal detection results of the plant growth monitoring data, and optimizes the plant growth monitoring values;

[0007] Step 3. The central control module evaluates the irrigation and fertilization demand based on the numerically optimized plant growth monitoring data;

[0008] Step 4. The central control module controls the fertigation module according to the fertigation demand assessment result;

[0009] The numerical optimization process described in step 2 is as follows: dividing the plant growth monitoring time series data window according to the plant growth monitoring data to obtain the plant growth monitoring time series data window; evaluating the change period of the monitoring data according to the initial monitoring data of the plant growth monitoring data acquisition module to obtain the evaluation result of the change period of the monitoring data; obtaining the first offset degree according to the difference between the plant growth monitoring time series data window and the evaluation result of the change period of the monitoring data; optimizing and evaluating the trend difference between the plant growth monitoring time series data windows according to the first offset degree to obtain the optimized distance measurement result; completing the clustering process according to the optimized distance measurement result to obtain the clustering result of the plant growth monitoring time series data window; evaluating the abnormality degree of the plant growth monitoring time series data window according to the cluster distribution in the clustering result; and numerically optimizing the plant growth monitoring data according to the abnormality degree evaluation result of the plant growth monitoring time series data window to obtain the optimization result of the plant growth monitoring data.

[0010] Preferably, the plant growth monitoring data acquisition module includes a soil moisture sensor, a soil EC sensor, a nutrient solution pH value sensor, a nutrient solution level sensor and a photosynthetic sensor, and the soil moisture sensor, soil EC sensor, nutrient solution pH value sensor, nutrient solution level sensor and photosynthetic sensor are respectively connected to the central control module through a data transmission line.

[0011] Preferably, dividing the plant growth monitoring time series data window according to the plant growth monitoring data to obtain the plant growth monitoring time series data window includes:

[0012] The monitoring time series data of each sensor in the plant growth monitoring data acquisition module is obtained, and the multi-dimensional plant growth monitoring time series data of the plant growth monitoring data acquisition module in the novel irrigation and fertilization and plant monitoring all-in-one machine is obtained by integrating the monitoring time series data of each sensor, wherein each dimension corresponds to a sensor; the multi-dimensional plant growth monitoring time series data is divided into time series data windows according to the set time series data window length, and the plant growth monitoring time series data window is obtained.

[0013] Preferably, performing a change period evaluation of the monitoring data according to the initial monitoring data of the plant growth monitoring data acquisition module to obtain a change period evaluation result of the monitoring data includes:

[0014] The multidimensional plant growth monitoring time series data of the plant growth monitoring data acquisition module is obtained, and the plant growth monitoring time series data of each dimension is subjected to STL decomposition to obtain the periodic item component corresponding to each dimension, and the periodic component mean sequence of the first five periods of the periodic component corresponding to any dimension is used as the change period evaluation result of the monitoring data.

[0015] Preferably, the step of obtaining the first offset degree according to the difference between the plant growth monitoring time series data window and the monitoring data change cycle evaluation result includes:

[0016] Obtain the change cycle evaluation result of any dimension of the monitoring data and any plant growth monitoring time series data window in the dimension, and determine the time series data window corresponding to the plant growth monitoring time series data window in the change cycle evaluation result of the monitoring data in the dimension according to the timestamp distance between the plant growth monitoring time series data window and the previous irrigation and fertilization time point; obtain the plant growth monitoring time series data window and the time series data window corresponding to the window in the change cycle evaluation result of the monitoring time series data, perform linear fitting on the two time series data windows respectively by the least squares method, obtain the linear fitting slopes corresponding to the two time series data windows respectively, and use the linear fitting slopes corresponding to the two time series data windows as the first trend feature of the window, subtract the first trend features of the two time series data windows and calculate the absolute value as the first trend feature difference; substitute the opposite number of the first trend feature difference into an exponential function with the natural constant e as the base, and obtain the first exponential function result accordingly, and use the subtraction result between the constant 1 and the first exponential function result as the first offset degree of the plant growth monitoring time series data window.

[0017] Preferably, optimizing and evaluating the trend difference between the plant growth monitoring time series data windows according to the first offset degree to obtain an optimized distance measurement result includes:

[0018] Obtain any two plant growth monitoring time series data windows, and use the first offset degree mean of the two plant growth monitoring time series data windows as the trend item difference weight; use the first trend feature difference between the two plant growth monitoring time series data windows as the trend item difference; subtract the constant 1 from the trend item difference weight as the DTW distance item weight; use the structure of multiplying the DTW distance item weight and the DTW distance between the two plant growth monitoring time series data windows as the first distance metric, and use the calculation result of multiplying the trend item difference weight and the trend item difference as the second distance metric; use the calculation result of adding the first distance metric and the second distance metric as the optimized distance metric result between the two plant growth monitoring time series data windows.

[0019] Preferably, completing the clustering process according to the optimized distance measurement result to obtain the clustering result of the plant growth monitoring time series data window includes:

[0020] Obtain all plant growth monitoring time series data windows in any dimension, and perform The clustering process obtains the clustering result of the plant growth monitoring time series data window.

[0021] Preferably, the abnormality evaluation of the plant growth monitoring time series data window according to the cluster distribution in the clustering result includes:

[0022] The clustering result of the plant growth monitoring time series data window is obtained, and the clusters in the clustering result are sorted from most to least according to the number of plant growth monitoring time series data windows in the cluster as the cluster sorting result of the clustering result; the number of plant growth monitoring time series data windows in the clusters from front to back is accumulated, and the clusters whose number of plant growth monitoring time series data windows accounts for 80% of the total number of plant growth monitoring time series data windows are taken as regular clusters, and the remaining clusters are taken as irregular clusters; the optimized distance measurement result between the plant growth monitoring time series data window in the regular cluster and the plant growth monitoring time series data window corresponding to the cluster center point of the cluster to which it belongs is taken as the abnormality degree assessment distance, and the optimized distance between the plant growth monitoring time series data window in the irregular cluster and the plant growth monitoring time series data window corresponding to the cluster center point of the regular cluster closest to the optimized distance measurement is taken as the abnormality degree assessment distance; the result of normalizing the abnormality degree assessment distance of the plant growth monitoring time series data window is taken as the abnormality degree of the plant growth monitoring time series data window.

[0023] Preferably, the numerical optimization of the plant growth monitoring data is performed according to the abnormality evaluation result of the plant growth monitoring time series data window to obtain the optimization result of the plant growth monitoring data, including:

[0024] Obtain the plant growth monitoring time series data window, the monitoring time series data window in the change cycle evaluation result corresponding to the plant growth monitoring time series data window and the abnormality degree corresponding to the plant growth monitoring time series data window, subtract the center point of the monitoring time series data window in the change cycle evaluation result corresponding to the plant growth monitoring time series data window from the center point of the plant growth monitoring time series data window as a first numerical difference, multiply the abnormality degree corresponding to the plant growth monitoring time series data window by the first numerical difference as a first optimized value, and add the first optimized value to the numerical value corresponding to the center point of the plant growth monitoring time series data window as an optimization result of the plant growth monitoring data corresponding to the center point of the plant growth monitoring time series data window.

[0025] Preferably, the central control module performs irrigation and fertilization demand assessment based on the numerically optimized plant growth monitoring data, including:

[0026] Obtain optimized plant growth monitoring data, obtain a characteristic vector of the plant's current growth environment based on the optimized plant growth monitoring data, compare the characteristic vector of the current growth environment with the growth requirement standard of the plant species to calculate the deviation, and obtain an irrigation and fertilization demand assessment based on the deviation between the characteristic vector of the current growth environment and the growth requirement standard of the plant species.

[0027] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0028] The present invention obtains plant growth monitoring data in a plant growth data storage module through a central control module; the central control module performs optimization analysis based on the obtained plant growth monitoring data, obtains abnormal detection results of the plant growth monitoring data and performs plant growth monitoring numerical optimization; the central control module evaluates the irrigation and fertilization demand based on the plant growth monitoring data after the numerical optimization; the central control module controls the irrigation and fertilization module based on the irrigation and fertilization demand evaluation result; wherein the numerical optimization process includes: dividing the plant growth monitoring time series data window according to the plant growth monitoring data, and obtaining the plant growth monitoring time series data window; evaluating the change period of the monitoring data according to the initial monitoring data of the plant growth monitoring data acquisition module, and obtaining The variation cycle evaluation result of the monitoring data; obtaining a first offset degree according to the difference between the plant growth monitoring time series data window and the variation cycle evaluation result of the monitoring data; optimizing and evaluating the trend difference between the plant growth monitoring time series data windows according to the first offset degree, and obtaining an optimized distance measurement result; completing a clustering process according to the optimized distance measurement result, and obtaining a clustering result of the plant growth monitoring time series data window; evaluating the abnormality degree of the plant growth monitoring time series data window according to the cluster distribution in the clustering result; and numerically optimizing the plant growth monitoring data according to the abnormality degree evaluation result of the plant growth monitoring time series data window, and obtaining an optimized result of the plant growth monitoring data. Among them, the distance is measured by optimizing the distance between the plant growth monitoring time series data windows to obtain several clusters, and the abnormality degree of each plant growth monitoring time series data window is determined by the distribution information of the clusters. Then, the plant growth monitoring time series data is numerically optimized according to the abnormality degree. When evaluating the plant irrigation and fertilization needs of the plant growth monitoring data, the irrigation and fertilization evaluation results are optimized to obtain more rigorous irrigation and fertilization evaluation results, thereby avoiding the erroneous evaluation of the irrigation and fertilization needs caused by numerical anomalies, and improving the control accuracy of the irrigation and fertilization and plant growth monitoring all-in-one machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0030] Figure 1 A flow chart of a novel all-in-one irrigation and fertilization and plant growth monitoring machine provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0032] 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 toothpaste can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an unexpected 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.

[0033] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0034] The specific scenario targeted by the present invention is to optimize the monitoring values ​​of plant growth monitoring data of an all-in-one irrigation, fertilization and plant growth monitoring machine.

[0035] See also Figure 1 , is a method flow chart of a novel integrated irrigation and fertilization and plant growth monitoring machine provided in the first embodiment of the present invention, such as Figure 1 As shown, a novel integrated machine for fertigation and plant growth monitoring may include:

[0036] Step S101: the central control module obtains the plant growth monitoring data in the plant growth data storage module.

[0037] Step S102: the central control module performs optimization analysis based on the acquired plant growth monitoring data, obtains abnormality detection results of the plant growth monitoring data, and performs plant growth monitoring value optimization.

[0038] Step S201 , dividing plant growth monitoring time series data windows according to the plant growth monitoring data to obtain plant growth monitoring time series data windows.

[0039] The monitoring time series data of each sensor in the plant growth monitoring data acquisition module is obtained, and the multi-dimensional plant growth monitoring time series data of the plant growth monitoring data acquisition module in the novel irrigation and fertilization and plant monitoring all-in-one machine is obtained by integrating the monitoring time series data of each sensor, wherein each dimension corresponds to a sensor; the multi-dimensional plant growth monitoring time series data is divided into time series data windows according to the set time series data window length, and the plant growth monitoring time series data window is obtained.

[0040] It should be noted that the embodiment of the present invention sets the time series data window length The plant growth monitoring time series data window is divided, and the time series data window corresponding to each sensor monitoring data point is obtained. Furthermore, the first 10 data points and the last 10 data points in the sensor monitoring time series data are not divided into time series data windows and subsequently analyzed.

[0041] Step S202: perform a change cycle evaluation on the monitoring data based on the initial monitoring data of the plant growth monitoring data acquisition module to obtain a change cycle evaluation result of the monitoring data; obtain a first offset degree based on the difference between the plant growth monitoring time series data window and the change cycle evaluation result of the monitoring data; optimize and evaluate the trend difference between the plant growth monitoring time series data windows based on the first offset degree to obtain an optimized distance measurement result.

[0042] After obtaining all the plant growth monitoring time series data windows of any dimension in the plant growth monitoring data, the change cycle of the monitoring data can be evaluated through the initial plant growth monitoring data. Considering that after the all-in-one machine is put into use, the initial monitoring data can be considered as the monitoring data when the sensor is in a brand new state. The initial monitoring data of the sensor can be used as the ideal change cycle of the monitoring data, so that the subsequent monitoring data can be judged according to the ideal change cycle, so as to obtain the degree of deviation between the sensor monitoring data and the ideal change cycle. The multi-dimensional plant growth monitoring time series data of the plant growth monitoring data acquisition module is obtained, and the plant growth monitoring time series data of each dimension is subjected to STL decomposition to obtain the periodic term component corresponding to each dimension, and the periodic component mean sequence of the first five periods of the periodic component corresponding to any dimension is used as the change cycle evaluation result of the monitoring data.

[0043] In one embodiment, assuming that The first dimension of plant growth monitoring time series data The first of the initial cycles The monitoring data is , then the calculation expression of the evaluation result of the change period of the monitoring data is:

[0044]

[0045] in, Indicates the evaluation results of the change cycle of monitoring data, represents the cycle number in the first 5 cycles, Indicates The first dimension of plant growth monitoring time series data The first of the initial cycles Monitoring data.

[0046] It should be noted that STL decomposition belongs to the prior art and will not be described in detail here.

[0047] After obtaining the evaluation result of the change period of the monitoring data, the first deviation degree can be evaluated according to the difference between the plant growth monitoring time series data window and the evaluation result of the change period of the monitoring data. Obtain the change cycle evaluation result of any dimension of the soil monitoring data and any plant growth monitoring time series data window in the dimension, determine the time series data window corresponding to the plant growth monitoring time series data window in the change cycle evaluation result of the soil monitoring data in the dimension according to the timestamp distance between the plant growth monitoring time series data window and the previous irrigation and fertilization time point; obtain the plant growth monitoring time series data window and the time series data window corresponding to the window in the change cycle evaluation result of the soil monitoring time series data, perform linear fitting on the two time series data windows respectively by the least squares method, obtain the linear fitting slopes corresponding to the two time series data windows respectively, and use the linear fitting slopes corresponding to the two time series data windows as the first trend feature of the window, subtract the first trend features of the two time series data windows and calculate the absolute value as the first trend feature difference; substitute the opposite number of the first trend feature difference into an exponential function with the natural constant e as the base, obtain the first exponential function result, and use the subtraction result between the constant 1 and the first exponential function result as the first offset degree of the plant growth monitoring time series data window.

[0048] In one embodiment, assuming that The first dimension The least squares linear fitting slope corresponding to the center point of the plant growth monitoring time series data window is , No. The first dimension The least squares linear fitting slope of the monitoring data change cycle evaluation sequence time series data window corresponding to the plant growth monitoring time series data window is , then the calculation expression of the first offset degree of the plant growth monitoring time series data window is:

[0049]

[0050] in, Indicates In the dimension The first offset degree of the plant growth monitoring time series data window, 1 represents a constant, Represents a natural constant , Indicates The first dimension The least squares linear fitting slope corresponding to the center point of the plant growth monitoring time series data window, Indicates The first dimension The least squares linear fitting slope of the monitoring data change cycle evaluation sequence time series data window corresponding to the plant growth monitoring time series data window, || represents the absolute value sign.

[0051] It should be noted that the first offset degree of the plant growth monitoring time series data window is evaluated based on the difference between the plant growth monitoring time series data window and the corresponding ideal periodic change data in the monitoring data periodic evaluation result sequence. The greater the difference in the corresponding fitting slope between the plant growth monitoring time series data window and the corresponding ideal periodic change data, the greater the deviation of the change trend presented by the plant growth monitoring time series data window. The larger the value of , the greater the first offset degree of the plant growth monitoring time series data window.

[0052] After obtaining the first offset degree of the plant growth monitoring time series data window, the trend difference between the plant growth monitoring time series data windows can be optimized and evaluated according to the first offset degree to obtain the optimized distance measurement result. Get any two plant growth monitoring time series data windows, take the first offset degree average of the two plant growth monitoring time series data windows as the trend item difference weight; take the first trend feature difference between the two plant growth monitoring time series data windows as the trend item difference; subtract the constant 1 from the trend item difference weight as Distance item weight; The distance term weight and the distance between the two plant growth monitoring time series data windows The distance multiplication structure is used as the first distance metric, and the calculation result of multiplying the trend item difference weight and the trend item difference is used as the second distance metric; the calculation result of adding the first distance metric and the second distance metric is used as the optimized distance metric result between the two plant growth monitoring time series data windows.

[0053] In one embodiment, assuming that The first monitoring dimension The plant growth monitoring time series data window is , No. The first monitoring dimension The plant growth monitoring time series data window is , then the calculation expression of the optimized distance metric between the two time series data windows is:

[0054]

[0055] in, Indicates The optimized distance measurement result between two plant growth monitoring time series data windows in dimensions, represents a constant, Indicates In the dimension The first offset degree of the plant growth monitoring time series data window, Indicates In the dimension The first offset degree of the plant growth monitoring time series data window, express and Between distance, represents the absolute value of the difference in the slope of the least square linear fit between two plant growth monitoring time series data windows, and || represents the absolute value sign.

[0056] It should be noted that when performing distance measurement between two plant growth monitoring time series data windows, the purpose is to perform a clustering process through distance measurement, so as to cluster and divide the plant growth monitoring time series data windows, and then perform anomaly analysis of the plant growth monitoring data through the cluster distribution information formed by the plant growth monitoring time series data windows in the clustering results, so as to identify and eliminate abnormal data, and then perform numerical optimization to ensure that the central control module of the all-in-one machine can perform irrigation and fertilization control during the plant growth process through accurate plant growth monitoring data. In the plant growth monitoring module, when the sensor has surface scaling and other conditions that may cause inaccurate sensor monitoring data, it will appear as an abnormal change trend in the time series data window. Therefore, in the distance measurement of the clustering process, the distance between the traditional time series data windows is used. The distance is measured based on the trend difference between the distance and the plant growth monitoring time series data window in the current scene, and on this basis, the average first offset degree of the two plant growth monitoring time series data windows is used as the weight of the trend difference item, thereby ensuring that the trend difference item is introduced more accurately in the process of distance measurement.

[0057] Step S203, completing the clustering process according to the optimized distance measurement result, obtaining the clustering result of the plant growth monitoring time series data window; and evaluating the abnormality degree of the plant growth monitoring time series data window according to the cluster distribution in the clustering result.

[0058] After obtaining the optimized distance measurement result, the clustering process can be completed according to the optimized distance measurement result to obtain the clustering result of the plant growth monitoring time series data window. The clustering process obtains the clustering result of the plant growth monitoring time series data window.

[0059] In one embodiment, setting Clustering process Value is , divide the plant growth monitoring time series data window of any dimension into Clusters, The value can be adjusted according to the actual scenario and is not required. When evaluating the abnormal distribution of clusters in the clustering results, A higher value can more accurately identify potential anomalous data.

[0060] After the clustering result is obtained, the abnormality degree of the plant growth monitoring time series data window is evaluated according to the cluster distribution in the clustering result.

[0061] The clustering result of the plant growth monitoring time series data window is obtained, and the clusters in the clustering result are sorted from most to least according to the number of plant growth monitoring time series data windows in the cluster as the cluster sorting result of the clustering result, and the number of plant growth monitoring time series data windows in the clusters from front to back is accumulated, and the clusters whose number of plant growth monitoring time series data windows accounts for 80% of the total number of plant growth monitoring time series data windows are taken as regular clusters, and the remaining clusters are taken as irregular clusters. The optimized distance measurement result between the plant growth monitoring time series data window in the regular cluster and the plant growth monitoring time series data window corresponding to the cluster center point of the cluster to which it belongs is taken as the abnormality degree evaluation distance, and the optimized distance between the plant growth monitoring time series data window in the irregular cluster and the plant growth monitoring time series data window corresponding to the cluster center point of the regular cluster closest to the optimized distance measurement is taken as the abnormality degree evaluation distance; the abnormality degree evaluation distance of the plant growth monitoring time series data window is normalized as the abnormality degree of the plant growth monitoring time series data window.

[0062] Step S204, performing numerical optimization of the plant growth monitoring data according to the abnormality evaluation result of the plant growth monitoring time series data window, and obtaining the optimization result of the plant growth monitoring data.

[0063] Obtain the plant growth monitoring time series data window, the monitoring time series data window in the change cycle evaluation result corresponding to the plant growth monitoring time series data window and the abnormality degree corresponding to the plant growth monitoring time series data window, subtract the center point of the monitoring time series data window in the change cycle evaluation result corresponding to the plant growth monitoring time series data window from the center point of the plant growth monitoring time series data window as a first numerical difference, multiply the abnormality degree corresponding to the plant growth monitoring time series data window by the first numerical difference as a first optimized value, and add the first optimized value to the numerical value corresponding to the center point of the plant growth monitoring time series data window as an optimization result of the plant growth monitoring data corresponding to the center point of the plant growth monitoring time series data window.

[0064] In one embodiment, assuming that In the dimension The abnormal degree of plant growth monitoring time series data is , then the calculation expression of the optimization result of plant growth monitoring data is:

[0065]

[0066] in, represents the optimization result of plant growth monitoring data, Indicates In the dimension The original value of the plant growth monitoring time series data, Indicates In the dimension The abnormality of plant growth monitoring time series data, Indicates The first dimension The monitoring data change cycle evaluation sequence time series data corresponding to the plant growth monitoring time series data.

[0067] It should be noted that the numerical optimization of the plant growth monitoring data is to use the abnormality degree of the plant growth monitoring data as an adjustment weight to reduce the numerical difference between the plant growth monitoring data and the corresponding data points in the change cycle evaluation sequence, thereby making the numerical difference between the plant growth monitoring time series data and the corresponding data points in the change cycle evaluation sequence smaller, thereby reducing the numerical abnormality of the plant growth monitoring data, and the abnormality degree The higher the value, the higher the degree of numerical optimization is required, and the amount of optimization of the original value The higher.

[0068] Step S103: the central control module evaluates the irrigation and fertilization demand according to the numerically optimized plant growth monitoring data.

[0069] After obtaining the optimization result of the plant growth monitoring data, the irrigation and fertilization demand assessment can be performed in the central control module according to the numerically optimized plant growth monitoring data. The optimized plant growth monitoring data is obtained, and the characteristic vector of the current growth environment of the plant is obtained according to the optimized plant growth monitoring data. The characteristic vector of the current growth environment is compared with the growth requirement standard of the plant species to calculate the deviation, and the irrigation and fertilization demand assessment result is obtained according to the deviation between the characteristic vector of the current growth environment and the growth requirement standard of the plant species.

[0070] Step S104: the central control module controls the fertigation module according to the fertigation demand assessment result.

[0071] After the central control module obtains the fertigation demand assessment result, the central control module sends control information to the fertigation module to control the fertigation module to complete the fertigation of the plant planting module.

[0072] In summary, the embodiment of the present invention obtains the plant growth monitoring data in the plant growth data storage module through the central control module; the central control module performs optimization analysis based on the obtained plant growth monitoring data, obtains the abnormal detection result of the plant growth monitoring data and performs plant growth monitoring numerical optimization; the central control module evaluates the irrigation and fertilization demand based on the plant growth monitoring data after the numerical optimization; the central control module controls the irrigation and fertilization module based on the irrigation and fertilization demand evaluation result; wherein the numerical optimization process includes: dividing the plant growth monitoring time series data window according to the plant growth monitoring data, and obtaining the plant growth monitoring time series data window; evaluating the change period of the monitoring data according to the initial monitoring data of the plant growth monitoring data acquisition module; The invention relates to a method for optimizing the plant growth monitoring time series data window and obtaining a change period evaluation result of the monitoring data; obtaining a first offset degree according to the difference between the plant growth monitoring time series data window and the change period evaluation result of the monitoring data; optimizing and evaluating the trend difference between the plant growth monitoring time series data windows according to the first offset degree, and obtaining an optimized distance measurement result; completing a clustering process according to the optimized distance measurement result, and obtaining a clustering result of the plant growth monitoring time series data window; evaluating the abnormality degree of the plant growth monitoring time series data window according to the cluster distribution in the clustering result; and performing numerical optimization of the plant growth monitoring data according to the abnormality degree evaluation result of the plant growth monitoring time series data window, and obtaining an optimization result of the plant growth monitoring data. Among them, the distance is measured by optimizing the distance between the plant growth monitoring time series data windows to obtain several clusters, and the abnormality degree of each plant growth monitoring time series data window is determined by the distribution information of the clusters. Then, the plant growth monitoring time series data is numerically optimized according to the abnormality degree. When evaluating the plant irrigation and fertilization needs of the plant growth monitoring data, the irrigation and fertilization evaluation results are optimized to obtain more rigorous irrigation and fertilization evaluation results, thereby avoiding the erroneous evaluation of the irrigation and fertilization needs caused by numerical anomalies, and improving the control accuracy of the irrigation and fertilization and plant growth monitoring all-in-one machine.

[0073] 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. A novel integrated fertigation and plant growth monitoring machine, comprising a device frame, wherein the device frame is provided with a plant growth monitoring data acquisition module, a plant growth monitoring data storage module, a central control module, a plant planting module, a nutrient solution mixing module and a fertigation module, wherein the central control module stores the data collected by the plant growth monitoring data acquisition module in the plant growth monitoring data storage module, and the central control module controls the fertigation module according to the plant growth monitoring data in the plant growth monitoring data storage module, and wherein: The central control module controls the irrigation and fertilization module according to the plant growth monitoring data stored in the plant growth monitoring data storage module, including the following steps: Step 1. The central control module obtains the plant growth monitoring data in the plant growth data storage module; Step 2. The central control module performs optimization analysis based on the acquired plant growth monitoring data, obtains abnormal detection results of the plant growth monitoring data, and optimizes the plant growth monitoring values; Step 3. The central control module evaluates the irrigation and fertilization demand based on the numerically optimized plant growth monitoring data; Step 4. The central control module controls the fertigation module according to the fertigation demand assessment result; The numerical optimization process described in step 2 is as follows: dividing the plant growth monitoring time series data window according to the plant growth monitoring data to obtain the plant growth monitoring time series data window; evaluating the change period of the monitoring data according to the initial monitoring data of the plant growth monitoring data acquisition module to obtain the evaluation result of the change period of the monitoring data; obtaining the first offset degree according to the difference between the plant growth monitoring time series data window and the evaluation result of the change period of the monitoring data; optimizing and evaluating the trend difference between the plant growth monitoring time series data windows according to the first offset degree to obtain the optimized distance measurement result; completing the clustering process according to the optimized distance measurement result to obtain the clustering result of the plant growth monitoring time series data window; evaluating the abnormality degree of the plant growth monitoring time series data window according to the cluster distribution in the clustering result; and numerically optimizing the plant growth monitoring data according to the abnormality degree evaluation result of the plant growth monitoring time series data window to obtain the optimization result of the plant growth monitoring data.

2. The novel integrated irrigation and fertilization and plant growth monitoring machine according to claim 1 is characterized in that: The plant growth monitoring data acquisition module includes a soil moisture sensor, a soil EC sensor, a nutrient solution pH value sensor, a nutrient solution level sensor and a photosynthesis sensor. The soil moisture sensor, the soil EC sensor, the nutrient solution pH value sensor, the nutrient solution level sensor and the photosynthesis sensor are respectively connected to the central control module through a data transmission line.

3. The novel integrated irrigation and fertilization and plant growth monitoring machine according to claim 1 is characterized in that: The step of dividing the plant growth monitoring time series data window according to the plant growth monitoring data to obtain the plant growth monitoring time series data window includes: The monitoring time series data of each sensor in the plant growth monitoring data acquisition module is obtained, and the multi-dimensional plant growth monitoring time series data of the plant growth monitoring data acquisition module in the novel irrigation and fertilization and plant monitoring all-in-one machine is obtained by integrating the monitoring time series data of each sensor, wherein each dimension corresponds to a sensor; the multi-dimensional plant growth monitoring time series data is divided into time series data windows according to the set time series data window length, and the plant growth monitoring time series data window is obtained.

4. The novel integrated irrigation and fertilization and plant growth monitoring machine according to claim 1 is characterized in that: The step of evaluating the change period of the monitoring data according to the initial monitoring data of the plant growth monitoring data acquisition module and obtaining the evaluation result of the change period of the monitoring data includes: The multidimensional plant growth monitoring time series data of the plant growth monitoring data acquisition module is obtained, and the plant growth monitoring time series data of each dimension is subjected to STL decomposition to obtain the periodic item component corresponding to each dimension, and the mean sequence of the first five periods of the periodic component corresponding to any dimension in all dimensions is used as the change period evaluation result of the monitoring data.

5. The novel integrated irrigation and fertilization and plant growth monitoring machine according to claim 1 is characterized in that: The obtaining of the first offset degree according to the difference between the plant growth monitoring time series data window and the monitoring data change cycle evaluation result includes: Obtain the change cycle evaluation result of any dimension of the monitoring data and any plant growth monitoring time series data window in the dimension, and determine the time series data window corresponding to the plant growth monitoring time series data window in the change cycle evaluation result of the monitoring data in the dimension according to the timestamp distance between the plant growth monitoring time series data window and the previous irrigation and fertilization time point; obtain the plant growth monitoring time series data window and the time series data window corresponding to the window in the change cycle evaluation result of the monitoring time series data, perform linear fitting on the two time series data windows respectively by the least squares method, obtain the linear fitting slopes corresponding to the two time series data windows respectively, and use the linear fitting slopes corresponding to the two time series data windows as the first trend feature of the window, subtract the first trend features of the two time series data windows and calculate the absolute value as the first trend feature difference; substitute the opposite number of the first trend feature difference into an exponential function with the natural constant e as the base, and obtain the first exponential function result accordingly, and use the subtraction result between the constant 1 and the first exponential function result as the first offset degree of the plant growth monitoring time series data window.

6. The novel integrated irrigation and fertilization and plant growth monitoring machine according to claim 1, characterized in that: The optimizing and evaluating the trend difference between the plant growth monitoring time series data windows according to the first offset degree to obtain an optimized distance measurement result includes: Obtain any two plant growth monitoring time series data windows, and use the first offset degree mean of the two plant growth monitoring time series data windows as the trend item difference weight; use the first trend feature difference between the two plant growth monitoring time series data windows as the trend item difference; subtract the constant 1 from the trend item difference weight as the DTW distance item weight; use the structure of multiplying the DTW distance item weight and the DTW distance between the two plant growth monitoring time series data windows as the first distance metric, and use the calculation result of multiplying the trend item difference weight and the trend item difference as the second distance metric; use the calculation result of adding the first distance metric and the second distance metric as the optimized distance metric result between the two plant growth monitoring time series data windows.

7. The novel integrated irrigation and fertilization and plant growth monitoring machine according to claim 1, characterized in that: The step of completing the clustering process according to the optimized distance measurement result to obtain the clustering result of the plant growth monitoring time series data window includes: All plant growth monitoring time series data windows of any dimension are obtained, and a K-means clustering process is performed according to the optimized distance measurement results between the plant growth monitoring time series data windows to obtain the clustering results of the plant growth monitoring time series data windows.

8. The novel integrated irrigation and fertilization and plant growth monitoring machine according to claim 1, characterized in that: The abnormality evaluation of the plant growth monitoring time series data window according to the cluster distribution in the clustering result includes: The clustering result of the plant growth monitoring time series data window is obtained, and the clusters in the clustering result are sorted from most to least according to the number of plant growth monitoring time series data windows in the cluster as the cluster sorting result of the clustering result; the number of plant growth monitoring time series data windows in the clusters from front to back is accumulated, and the clusters whose number of plant growth monitoring time series data windows accounts for 80% of the total number of plant growth monitoring time series data windows are taken as regular clusters, and the remaining clusters are taken as irregular clusters; the optimized distance measurement result between the plant growth monitoring time series data window in the regular cluster and the plant growth monitoring time series data window corresponding to the cluster center point of the cluster to which it belongs is taken as the abnormality degree assessment distance, and the optimized distance between the plant growth monitoring time series data window in the irregular cluster and the plant growth monitoring time series data window corresponding to the cluster center point of the regular cluster closest to the optimized distance measurement is taken as the abnormality degree assessment distance; the result of normalizing the abnormality degree assessment distance of the plant growth monitoring time series data window is taken as the abnormality degree of the plant growth monitoring time series data window.

9. The novel integrated irrigation and fertilization and plant growth monitoring machine according to claim 1, characterized in that: The step of performing numerical optimization of the plant growth monitoring data according to the abnormality evaluation result of the plant growth monitoring time series data window to obtain the optimization result of the plant growth monitoring data includes: Obtain the plant growth monitoring time series data window, the monitoring time series data window in the change cycle evaluation result corresponding to the plant growth monitoring time series data window and the abnormality degree corresponding to the plant growth monitoring time series data window, subtract the center point of the monitoring time series data window in the change cycle evaluation result corresponding to the plant growth monitoring time series data window from the center point of the plant growth monitoring time series data window as a first numerical difference, multiply the abnormality degree corresponding to the plant growth monitoring time series data window by the first numerical difference as a first optimized value, and add the first optimized value to the numerical value corresponding to the center point of the plant growth monitoring time series data window as an optimization result of the plant growth monitoring data corresponding to the center point of the plant growth monitoring time series data window.

10. The novel integrated irrigation and fertilization and plant growth monitoring machine according to claim 1, characterized in that: The central control module evaluates the demand for irrigation and fertilization based on the numerically optimized plant growth monitoring data, including: Obtain optimized plant growth monitoring data, obtain a characteristic vector of the plant's current growth environment based on the optimized plant growth monitoring data, compare the characteristic vector of the current growth environment with the growth requirement standard of the plant species to calculate the deviation, and obtain an irrigation and fertilization demand assessment based on the deviation between the characteristic vector of the current growth environment and the growth requirement standard of the plant species.

Images