Spectral rapid determination system and method for nutritional ingredients of castanea henryi

Abstract

The present invention discloses a castanea henryi nutritional ingredient spectrum rapid determination system and a method thereof, and belongs to the technical field of ingredient determination, the castanea henryi nutritional ingredient spectrum rapid determination system comprises a sample information acquisition module used for acquiring water content data of castanea henryi sample spectrum determination in different time periods, the time period distinguishing mode comprises acquisition of the storage period of castanea henryi and statistics of the continuous day number of the storage period, dividing the obtained water content data based on the number of continuous days, and obtaining data features in the water content data; according to the method, water content data of the castanea henryi samples in different storage periods are obtained, a database is constructed according to the water content data, the water content data are divided in the database, and characteristic data in the water content data are collected, so that the water content change trend of the castanea henryi samples is analyzed; according to the method, a plurality of water contents can be calculated on the castanea henryi sample according to the spectral reflectance of different measuring points, so that the water content difference between the measuring points is analyzed, and the judgment on the change trend of the water content of the castanea henryi is more accurate.

Description

Technical Field

[0001] The invention relates to the technical field of component determination, in particular to a system and method for rapid spectrum determination of Castanea henryi nutrient components. Background Art

[0002] With the improvement of living standards and changes in consumption concepts, people are paying more and more attention to the quality of fruits and their effects on consumer health. Among them, the nutrients contained in fruits are one of the important concerns of people when purchasing. As a nut food rich in nutrients, chestnuts are deeply loved by consumers because they are rich in nutrients such as healthy fats, proteins, vitamins and minerals. Among them, the moisture content of chestnuts is an important parameter for evaluating their quality. If the moisture content is too high, the activity of microorganisms such as pathogens will be enhanced during storage, increasing the possibility of rotting and deterioration; if the moisture content is too low, it will affect its taste, resulting in chestnuts that are not full and light in quality, thus affecting economic benefits. The traditional technology for determining the moisture content of chestnuts is mostly carried out by drying and weight loss, which is destructive to chestnuts and takes a long time to measure. In recent years, studies have shown that near-infrared spectroscopy can determine the moisture content of nuts. Spectroscopy is a technology that analyzes the properties of substances by measuring the absorption, reflection or transmission of substances under different wavelengths of light.

[0003] In spectroscopy, the principle is to analyze the chemical composition and properties of a substance by measuring its absorption, reflection or transmission in the near-infrared band (700-2500nm). When light is irradiated onto the surface of a sample, molecules of different components will respond differently to the light, forming a spectrum curve. By analyzing the spectrum curve, the moisture content of the sample can be inferred.

[0004] However, in the prior art, near-infrared spectroscopy technology is mostly used to measure the moisture content of chestnuts by selecting a measurement point on the surface of the chestnut and then emitting near-infrared light of a specific band toward the selected measurement point to observe the changes in the spectral curve of the light in this band, thereby inferring the moisture content of the chestnuts.

[0005] However, in the measurement process, the measurement steps include from DNA samples to final data acquisition, among which each link of sample detection, library construction and sequencing will affect the data quality and quantity, and the data quality will directly affect the results of subsequent information analysis, especially in the step of database construction after sample detection. It is difficult to predict the trend of changes in the moisture content of chestnuts based on the data feature analysis in the constructed database, which affects the analysis results of subsequent information and causes large differences in the moisture content of chestnuts cultivated in the same period, thereby affecting people's eating experience. Summary of the invention

[0006] The present invention has been proposed in view of the above-mentioned problems existing in the technical field of conventional component measurement.

[0007] Therefore, one of the objects of the present invention is to provide a system and method for rapid spectral determination of nutritional components of henryi, which obtains moisture content data of henryi samples at different storage periods, constructs a database based on the moisture content data, divides the moisture content data in the database, and collects characteristic data therein to analyze the moisture content change trend of the henryi samples. At the same time, when collecting moisture content data, multiple moisture contents can be calculated on the henryi samples according to the spectral reflectance of different measurement points to analyze the moisture content difference between the measurement points, so that the judgment of the moisture content change trend of the henryi is more accurate, and then auxiliary guidance is provided for planting operations to ensure people's eating experience.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0009] In one aspect, the present invention provides a system for rapid spectrum determination of nutritional components of Castanea henryi, comprising:

[0010] A sample information acquisition module is used to obtain the moisture content data of the chromatographic measurement of the castanea henryi sample in different time periods, wherein the time period distinction method includes obtaining the storage period of the castanea henryi, counting the duration of the storage period, dividing the obtained moisture content data based on the duration, and obtaining the data features therein;

[0011] A data fusion management unit is used to construct a database according to the data features, wherein in the database, the data features are divided into θ1, θ2, ..., θ n , n represents the nth data feature, in response to the division of the acquired moisture content data based on the continuous days; the data fusion management unit includes a calculation module, an analysis module and a determination module;

[0012] The calculation module is used to calculate the data difference of the moisture content data in each data feature based on the divided data features;

[0013] The analysis module is used to arrange the data size of the calculation results based on the calculation results of the calculation module, and analyze the change trend of the water content data;

[0014] The determination module is used to determine the change trend; wherein, according to the given level content of the moisture content data, when the change trend develops toward a level lower than the given level content, the system determines that the moisture content of the obtained Castanea henryi sample is a low moisture content, otherwise, no determination is made;

[0015] A data collection module, the data collection module responds to the determination result of the determination module, and is used to collect the moisture content data when it is determined that the moisture content of the obtained Castanea henryi sample is the low moisture content, and the collection method includes collecting at least 5 moisture content data every day during the storage period;

[0016] A data processing unit, which responds to the moisture content data collected by the data collection module, and is used to count the total number of the collected data and process it, wherein the processing method includes intercepting the middle three data from all the data to the first data after the moisture content is lower than the level content, marking the data as reference data; and marking the data in this process as later data; the data processing unit includes an early data acquisition module, a processing module and an early warning module;

[0017] The early data acquisition module is used to acquire the first data to the three data in the middle from all the data, and mark the data in this process as early data;

[0018] The processing module is used to analyze and process the change rules of the early data and the late data based on the early data and the late data, and generate a prediction model;

[0019] The early warning model is used to issue an early warning based on the analysis and processing results; when the data in the early data changes toward the middle three data, the system determines that the probability that the moisture content of the corresponding chestnut sample is lower than the level content is 50%; when the middle three data in the late data changes toward the reference data, the system determines that the probability that the moisture content of the corresponding chestnut sample is lower than the level content is 100%, and issues an early warning.

[0020] As a preferred embodiment of the present invention, the spectral data corresponding to the data is obtained based on the previous data, the spectral data includes spectral reflectance, and the acquisition method includes: collecting reflection time in the corresponding Castanea henryi sample, intercepting the near-infrared light irradiation depth of the corresponding Castanea henryi sample based on the reflection time, and recording and storing the depth data, and obtaining the change of the reflected spectral curve at the same time; marking the depth data as first depth data; and obtaining a measurement point corresponding to the first depth data, and marking the measurement point as a first measurement point;

[0021] A second measuring point and a third measuring point are selected on the corresponding Castanea henryi sample, depth data between different measuring points and changes in the spectral curve corresponding to the depth data are collected, and the moisture content is calculated according to the following formula:

[0022] Among them, u k represents the change of the uth spectral curve at the kth interval measured between the measurement points;

[0023] In the formula, r i represents the r-th depth data collected at the i-th time in the third measuring point, x represents the water content corresponding to the depth data, and p represents the water content difference between the measuring points.

[0024] As a preferred embodiment of the present invention, the number of Castanea henryi samples corresponding to the previous data is obtained based on the moisture content, and a data set is generated by changing the three spectral curves obtained in different Castanea henryi samples, and the spectral reflectance characteristics in each of the data sets are analyzed, and at least 10 characteristic values ​​are selected, and the weight of the characteristic value in the spectral reflectance of all data sets is calculated, and the weight is calculated according to the following formula:

[0025] Where j represents the average spectral reflectance in all data sets;

[0026] Where n is a eigenvector representing the minimum spectral reflectance obtained in each data set, i represents the difference between the minimum spectral reflectance and the maximum spectral reflectance in the corresponding data set, and m is o represents the difference between the mth maximum spectral reflectances obtained at the oth time in all data sets, and f represents the changing trend of the difference.

[0027] As a preferred scheme of the present invention, wherein: based on the changing trend, the time of acquiring all chestnut samples is classified into early acquisition time, mid-term acquisition time and late acquisition time, and the minimum spectral reflectance is preset according to the early acquisition time and the late acquisition time, and the total number of chestnut samples at the early acquisition time and the late acquisition time is counted, and among the total number, when the number of times the spectral reflectance is lower than the preset spectral reflectance is less than one-third, the system determines that the moisture content of the chestnut sample is stable, otherwise, no determination is made and an early warning is issued.

[0028] As a preferred embodiment of the present invention, the spectral reflectance of the first measuring point and the second measuring point are collected based on the chestnut sample obtained at the previous acquisition time, the change characteristics of the spectral reflectance of the two are analyzed, and the 20 to 30 spectral reflectances with the largest number of occurrences are intercepted from the change characteristics. When the difference between the spectral reflectance and the preset spectral reflectance is ≤10%, the system determines that the moisture content of the corresponding chestnut sample is stable. In this case, no relevant measurement is performed on the third measuring point; otherwise, no determination is made and an early warning is issued.

[0029] As a preferred solution of the present invention, the average reflectance is calculated among the spectral reflectances with the largest number of occurrences, and the average reflectance is marked as a coefficient of variation. The spectral reflectance change value of the second measuring point is calculated based on the coefficient of variation with the first measuring point as the target, and is calculated based on the following formula:

[0030] Among them, θ represents the change value of spectral reflectance;

[0031] In the formula, λ represents the preset standard deviation, σ represents the mean, and if the spectral reflectance change value shows a decreasing trend with respect to the spectral reflectance of the first measuring point, the system determines that the moisture content belonging to the second measuring point is in a decreasing state, otherwise, no determination is made.

[0032] As a preferred embodiment of the present invention, when the system determines that the moisture content of the second measuring point is in a reduced state, the spectral reflectance corresponding to the reduced state is collected, and at least 3 to 10 characteristic reflectances that first appear in the spectral reflectance are collected, and the characteristic reflectances are marked as judgment data. If the characteristic reflectance collected from the chestnut sample in a future period is the same as the judgment data, the system determines that the moisture content of the subsequent second measuring point will be in a reduced state, otherwise, no determination will be made.

[0033] As a preferred solution of the present invention, the judgment data is divided into several evaluation indicators, and the data is normalized, the weight of each evaluation indicator in the total spectral reflectance is calculated, and the degree of reduction in the moisture content of the chestnut samples in the future period is determined based on the calculated weight.

[0034] In another aspect, the present invention provides a method for a system for rapid spectrum determination of nutritional components of Castanea henryi, comprising the following steps:

[0035] Acquire moisture content data of the chromatographic measurement of the castanea henryi sample in different time periods, wherein the time period differentiation method includes acquiring the storage period of the castanea henryi, counting the duration of the storage period, dividing the acquired moisture content data based on the duration, and acquiring data features therein;

[0036] A database is constructed according to the data features, wherein in the database, the data features are divided into θ1, θ2, ..., θ n , n represents the nth data feature, in response to the division of the acquired moisture content data based on the number of continuous days;

[0037] Calculate the data difference of the moisture content data in each data feature, arrange the data according to the data size of the calculation results, and analyze the change trend of the moisture content data;

[0038] Determining the change trend; wherein, a level content is given to the moisture content data, and when the change trend develops toward a level content lower than the given level content, the system determines that the moisture content of the obtained Castanea henryi sample is a low moisture content, otherwise, no determination is made;

[0039] When it is determined that the moisture content of the obtained Castanea henryi sample is the low moisture content, the moisture content data is collected, and the collection method includes collecting at least 5 moisture content data every day during the storage period;

[0040] Counting the total number of collected data and processing them, wherein the processing method includes intercepting the middle three data from all the data to the first data after the data is lower than the level content, marking the data as reference data; and marking the data in this process as later data;

[0041] Obtain the first data to the three data in the middle from all the data, and mark the data in this process as early data;

[0042] The changing rules of the previous data and the later data are analyzed and processed, and a prediction model is generated.

[0043] The present invention obtains moisture content data of different storage periods through chestnut samples, builds a database according to the moisture content data, divides the moisture content data in the database, collects characteristic data therein, so as to analyze the moisture content change trend of the chestnut samples; at the same time, when collecting the moisture content data, multiple moisture contents can be calculated on the chestnut samples according to the spectral reflectance of different measuring points, so as to analyze the moisture content difference between the measuring points, and then obtain the stability of the moisture content of the chestnut samples, so as to make the judgment of the moisture content change trend of the chestnut more accurate, and then provide auxiliary guidance for the planting operation, so as to ensure people's eating experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative labor. Among them:

[0045] Figure 1 This is a schematic diagram of the modular structure of a system for rapid spectrum determination of nutrients of Castanea henryi according to an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of a method flow of an embodiment of the present invention;

[0047] Figure 3 It is a schematic diagram of the process structure of an embodiment of the present invention;

[0048] Numbers in the figure: 110 - sample information acquisition module; 120 - data fusion management unit; 1201 - calculation module; 1202 - analysis module; 1203 - determination module; 130 - data acquisition module; 140 - data processing unit; 1401 - preliminary data acquisition module; 1402 - processing module; 1403 - early warning module. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0050] During the measurement process, every link from sample testing, library construction and sequencing will affect the data quality and quantity, and the data quality will directly affect the results of subsequent information analysis. Especially in the step of database construction after sample testing, it is difficult to predict the trend of changes in the moisture content of chestnuts based on the data feature analysis in the constructed database, which will affect the analysis results of subsequent information and cause large differences in the moisture content of chestnuts cultivated in the same period, thus affecting people's eating experience.

[0051] Based on this, the present invention proposes a system and method for rapid spectral determination of nutritional components of chestnut, which obtains moisture content data of chestnut samples in different storage periods, builds a database based on the moisture content data, divides the moisture content data in the database, and collects characteristic data therein to analyze the moisture content change trend of the chestnut samples, thereby providing auxiliary guidance for planting operations to ensure people's eating experience.

[0052] The present invention is further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0053] Reference Figures 1 to 3 , is an embodiment of the present invention, which provides a system for rapid spectrum determination of nutritional components of Castanea henryi, comprising:

[0054] The sample information acquisition module 110 is used to obtain the moisture content data of the spectral measurement of the castanea henryi sample in different time periods. The time period classification method includes obtaining the storage period of the castanea henryi, counting the duration of the storage period, dividing the obtained moisture content data based on the duration, and obtaining the data features therein;

[0055] The data fusion management unit 120 is used to construct a database according to the data features, wherein in the database, the data features are divided into θ1, θ2, ..., θ n, n represents the nth data feature, in response to the division of the acquired moisture content data based on the number of continuous days; the data fusion management unit 120 includes a calculation module 1201, an analysis module 1202 and a determination module 1203;

[0056] The calculation module 1201 is used to calculate the data difference of the moisture content data in each data feature based on the divided data features;

[0057] The analysis module 1202 is used to arrange the data size of the calculation results based on the calculation results of the calculation module 1201, and analyze the change trend of the water content data;

[0058] The determination module 1203 is used to determine the change trend; wherein, for the moisture content data, a level content is given, and when the change trend develops toward a level lower than the given level content, the system determines that the moisture content of the obtained Castanea henryi sample is a low moisture content, otherwise, no determination is made;

[0059] The data collection module 130 responds to the determination result of the determination module 1203, and is used to collect moisture content data when it is determined that the moisture content of the obtained Castanea henryi sample is low moisture content, and the collection method includes collecting at least 5 moisture content data every day during the storage period;

[0060] The data processing unit 140 responds to the moisture content data collected by the data collection module 130, and is used to count the total number of the collected data and process it. The processing method includes intercepting the middle 3 data from all the data to the first data after the moisture content is lower than the horizontal content, marking the data as reference data; and marking the data in this process as later data; the data processing unit 140 includes an early data acquisition module 1401, a processing module 1402 and an early warning module 1403;

[0061] The early data acquisition module 1401 is used to acquire the first data to the three data in the middle from all the data, and mark the data in this process as early data;

[0062] It should be noted that in this embodiment, spectral data corresponding to the data is obtained based on the previous data, and the spectral data includes spectral reflectance, and the acquisition method includes: collecting reflection time in the corresponding chestnut sample, intercepting the near-infrared light irradiation depth of the corresponding chestnut sample based on the reflection time, and recording and storing the depth data, and obtaining the change of the reflected spectral curve at the same time; marking the depth data as first depth data; and obtaining a measurement point corresponding to the first depth data, and marking the measurement point as a first measurement point;

[0063] The second and third measuring points were selected on the corresponding Castanea henryi sample, the depth data between the different measuring points and the change of the spectral curve corresponding to the depth data were collected, and the moisture content was calculated according to the following formula:

[0064] Among them, u k represents the change of the uth spectral curve at the kth interval measured between the measurement points;

[0065] In the formula, r i represents the r-th depth data collected at the i-th time in the third measuring point, x represents the water content corresponding to the depth data, and p represents the water content difference between the measuring points;

[0066] On the basis of the above, this embodiment obtains the number of chestnut samples corresponding to the previous data based on the moisture content, generates a data set by changing the three spectral curves obtained in different chestnut samples, analyzes the spectral reflectance characteristics in each data set, selects at least 10 eigenvalues, calculates the weight of the eigenvalue in the spectral reflectance of all data sets, and calculates it according to the following formula:

[0067] Where j represents the average spectral reflectance in all data sets;

[0068] Where n is the eigenvector, which represents the minimum spectral reflectance obtained in each data set, i represents the difference between the minimum spectral reflectance and the maximum spectral reflectance in the corresponding data set, and m is o represents the difference between the mth maximum spectral reflectance obtained at the oth time in all data sets, and f represents the changing trend of the difference;

[0069] In the present embodiment, based on the change trend, the time of obtaining all chestnut samples is classified into early acquisition time, mid-term acquisition time and late acquisition time, and the minimum spectral reflectance is preset according to the early acquisition time and the late acquisition time, and the total number of chestnut samples at the early acquisition time and the late acquisition time is counted. Among the total number, when the number of times the spectral reflectance is lower than the preset spectral reflectance is less than one-third, the system determines that the moisture content of the chestnut sample is stable, otherwise, it does not determine and issues an early warning;

[0070] On the basis of the above, this embodiment collects the spectral reflectance of the first measurement point and the second measurement point based on the chestnut sample acquired at the previous acquisition time, analyzes the change characteristics of the spectral reflectance of the two, and intercepts the 20 to 30 spectral reflectances with the most occurrences in the change characteristics. When the difference between the spectral reflectance and the preset spectral reflectance is ≤10%, the system determines that the moisture content of the corresponding chestnut sample is stable. In this case, no relevant measurement is performed on the third measurement point; otherwise, no determination is made and an early warning is issued;

[0071] It should be emphasized in this embodiment that the average reflectance is calculated from the spectral reflectances that appear the most times, and the average reflectance is marked as the coefficient of variation. The spectral reflectance change value of the second measurement point is calculated based on the coefficient of variation with the first measurement point as the target, and is calculated according to the following formula:

[0072] Among them, θ represents the change value of spectral reflectance;

[0073] In the formula, λ represents the preset standard deviation, σ represents the mean value, and if the spectral reflectance change value shows a decreasing trend with respect to the spectral reflectance of the first measurement point, the system determines that the moisture content belonging to the second measurement point is in a decreasing state, otherwise, no determination is made;

[0074] Further, when the system determines that the moisture content of the second measurement point is in a reduced state, the spectral reflectance corresponding to the reduced state is collected, and at least 3 to 10 characteristic reflectances that appear first are collected in the spectral reflectance, and the characteristic reflectance is marked as judgment data. If the characteristic reflectance collected from the castanea henryi sample in the future period is the same as the judgment data, the system determines that the moisture content of the subsequent second measurement point will be in a reduced state, otherwise, no determination is made;

[0075] The judgment data is divided into several evaluation indicators, and the data is normalized to calculate the weight of each evaluation indicator in the total spectral reflectance, and the reduction degree of the moisture content of the Castanea henryi samples in the future period is determined according to the calculated weight;

[0076] The processing module 1402 is used to analyze and process the change rules of the previous data and the later data based on the previous data and the later data, and generate a prediction model;

[0077] The early warning model 1403 is used to issue an early warning based on the analysis and processing results; when the data in the current period data changes toward the middle three data, the system determines that the probability that the moisture content of the corresponding chestnut sample is lower than the horizontal content is 50%; when the middle three data in the later period data changes toward the reference data, the system determines that the probability that the moisture content of the corresponding chestnut sample is lower than the horizontal content is 100%, and issues an early warning.

[0078] Based on the above, the present application obtains moisture content data of chestnut samples at different storage periods, constructs a database based on the moisture content data, divides the moisture content data in the database, and collects characteristic data therein to analyze the moisture content change trend of the chestnut samples, and then provides auxiliary guidance for planting operations to ensure people's eating experience.

[0079] In combination with the above-mentioned Castanea henryi nutrient component spectrum rapid determination system, this embodiment also proposes a working method applied to the system, as follows:

[0080] S10: obtaining moisture content data of the castanea henryi sample measured by spectroscopy in different time periods, wherein the time period classification method includes obtaining the storage period of the castanea henryi, counting the duration of the storage period, dividing the obtained moisture content data based on the duration, and obtaining data features therein;

[0081] S20: construct a database based on the data features, wherein the data features are divided into θ1, θ2, ..., θ n , n represents the nth data feature, in response to the division of the acquired moisture content data based on the number of continuous days;

[0082] S30: Calculate the data difference of the moisture content data in each data feature, arrange the data according to the size of the calculation results, and analyze the change trend of the moisture content data;

[0083] S40: determining the change trend; wherein, according to the given level content of the moisture content data, when the change trend develops toward a level lower than the given level content, the system determines that the moisture content of the obtained Castanea henryi sample is a low moisture content, otherwise, no determination is made;

[0084] S50: when it is determined that the moisture content of the obtained Castanea henryi sample is low, collecting moisture content data, the collecting method includes collecting at least 5 moisture content data every day during the storage period;

[0085] S60: Counting the total number of collected data and processing them, wherein the processing method includes intercepting the first data after the middle three data are lower than the horizontal content from all the data, marking the data as reference data; and marking the data in this process as later data;

[0086] S70: Obtain the first data to the three data in the middle from all the data, and mark the data in this process as early data;

[0087] S80: Analyze and process the changing patterns of the previous data and the later data, and generate a prediction model.

[0088] In summary, the present invention obtains moisture content data of different storage periods through chestnut samples, constructs a database according to the moisture content data, divides the moisture content data in the database, and collects characteristic data therein to analyze the moisture content change trend of the chestnut samples. At the same time, when collecting the moisture content data, multiple moisture contents can be calculated on the chestnut samples according to the spectral reflectance of different measurement points to analyze the moisture content difference between the measurement points, and then obtain the stability of the moisture content of the chestnut samples, so that the judgment of the moisture content change trend of the chestnut is more accurate, and then the planting operation is assisted and guided to ensure people's eating experience.

[0089] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A system for rapid spectrum determination of nutritional components of Castanea henryi, characterized in that: include: A sample information acquisition module is used to obtain the moisture content data of the chromatographic measurement of the castanea henryi sample in different time periods, wherein the time period distinction method includes obtaining the storage period of the castanea henryi, counting the duration of the storage period, dividing the obtained moisture content data based on the duration, and obtaining the data features therein; A data fusion management unit is used to construct a database according to the data features, wherein in the database, the data features are divided into θ1, θ2, ..., θ n , n represents the nth data feature, in response to the division of the acquired moisture content data based on the continuous days; the data fusion management unit includes a calculation module, an analysis module and a determination module; The calculation module is used to calculate the data difference of the moisture content data in each data feature based on the divided data features; The analysis module is used to arrange the data size of the calculation results based on the calculation results of the calculation module, and analyze the change trend of the water content data; The determination module is used to determine the change trend; wherein, according to the given level content of the moisture content data, when the change trend develops toward a level lower than the given level content, the system determines that the moisture content of the obtained Castanea henryi sample is a low moisture content, otherwise, no determination is made; A data collection module, the data collection module responds to the determination result of the determination module, and is used to collect the moisture content data when it is determined that the moisture content of the obtained Castanea henryi sample is the low moisture content, and the collection method includes collecting at least 5 moisture content data every day during the storage period; A data processing unit, which responds to the moisture content data collected by the data collection module, and is used to count the total number of the collected data and process it, wherein the processing method includes intercepting the middle three data from all the data to the first data after the moisture content is lower than the level content, marking the data as reference data; and marking the data in this process as later data; the data processing unit includes an early data acquisition module, a processing module and an early warning module; The early data acquisition module is used to acquire the first data to the three data in the middle from all the data, and mark the data in this process as early data; The processing module is used to analyze and process the change rules of the early data and the late data based on the early data and the late data, and generate a prediction model; The early warning model is used to issue an early warning based on the analysis and processing results; when the data in the early data changes toward the middle three data, the system determines that the probability that the moisture content of the corresponding chestnut sample is lower than the level content is 50%; when the middle three data in the late data changes toward the reference data, the system determines that the probability that the moisture content of the corresponding chestnut sample is lower than the level content is 100%, and issues an early warning.

2. A Castanea henryi nutrient component spectrum rapid determination system as claimed in claim 1, characterized in that: Based on the previous data, spectral data corresponding to the data is obtained, wherein the spectral data includes spectral reflectance, and the obtaining method includes: collecting reflection time in the corresponding Castanea henryi sample, intercepting the near-infrared light irradiation depth of the corresponding Castanea henryi sample based on the reflection time, and recording and storing the depth data, and obtaining the change of the reflected spectral curve at the same time; marking the depth data as first depth data; and obtaining a measurement point corresponding to the first depth data, and marking the measurement point as a first measurement point; A second measuring point and a third measuring point are selected on the corresponding Castanea henryi sample, depth data between different measuring points and changes in the spectral curve corresponding to the depth data are collected, and the moisture content is calculated according to the following formula: Among them, u k represents the change of the uth spectral curve at the kth interval measured between the measurement points; In the formula, r i represents the r-th depth data collected at the i-th time in the third measuring point, x represents the water content corresponding to the depth data, and p represents the water content difference between the measuring points.

3. A Castanea henryi nutrient component spectrum rapid determination system as claimed in claim 2, characterized in that: Based on the moisture content, the number of Castanea henryi samples corresponding to the previous data is obtained, and a data set is generated by changing the three spectral curves obtained from different Castanea henryi samples. The spectral reflectance characteristics in each of the data sets are analyzed, and at least 10 eigenvalues ​​are selected. The weight of the eigenvalues ​​in the spectral reflectance of all the data sets is calculated, and the weight is calculated according to the following formula: Where j represents the average spectral reflectance in all data sets; Where n is a eigenvector representing the minimum spectral reflectance obtained in each data set, i represents the difference between the minimum spectral reflectance and the maximum spectral reflectance in the corresponding data set, and m is o represents the difference between the mth maximum spectral reflectances obtained at the oth time in all data sets, and f represents the changing trend of the difference.

4. A Castanea henryi nutrient component spectrum rapid determination system as claimed in claim 3, characterized in that: Based on the changing trend, the acquisition time of all chestnut samples is classified into early acquisition time, mid-term acquisition time and late acquisition time, and the minimum spectral reflectance is preset according to the early acquisition time and the late acquisition time. The total number of chestnut samples in the early acquisition time and the late acquisition time is counted. Among the total number, when the number of times the spectral reflectance is lower than the preset spectral reflectance is less than one-third, the system determines that the moisture content of the chestnut sample is stable. Otherwise, no determination is made and an early warning is issued.

5. A Castanea henryi nutrient component spectrum rapid determination system as claimed in claim 4, characterized in that: Based on the spectral reflectance of the first measurement point and the second measurement point collected from the chestnut sample acquired at the previous acquisition time, the change characteristics of the spectral reflectance of the two are analyzed, and 20 to 30 spectral reflectances with the largest number of occurrences are intercepted from the change characteristics. When the difference between the spectral reflectance and the preset spectral reflectance is ≤10%, the system determines that the moisture content of the corresponding chestnut sample is stable, and in this case, the third measurement point is not measured; Otherwise, no judgment will be made and an early warning will be issued.

6. A Castanea henryi nutrient component spectrum rapid determination system as claimed in claim 5, characterized in that: At The average reflectance is calculated from the spectral reflectances with the largest number of occurrences, and the average reflectance is marked as the coefficient of variation. The spectral reflectance change value of the second measurement point is calculated based on the coefficient of variation with the first measurement point as the target, and is calculated based on the following formula: Among them, θ represents the change value of spectral reflectance; In the formula, λ represents the preset standard deviation, σ represents the mean, and if the spectral reflectance change value shows a decreasing trend with respect to the spectral reflectance of the first measuring point, the system determines that the moisture content belonging to the second measuring point is in a decreasing state, otherwise, no determination is made.

7. A Castanea henryi nutrient component spectrum rapid determination system as claimed in claim 6, characterized in that: When the system determines that the moisture content belonging to the second measuring point is in a reduced state, the spectral reflectance corresponding to the reduced state is collected, and at least 3 to 10 characteristic reflectances that appear first are collected in the spectral reflectance, and the characteristic reflectance is marked as judgment data. If the characteristic reflectance collected from the chestnut sample in a future period is the same as the judgment data, the system determines that the moisture content of the subsequent second measuring point will be in a reduced state, otherwise, no determination is made.

8. A Castanea henryi nutrient component spectrum rapid determination system as claimed in claim 7, characterized in that: The judgment data is divided into several evaluation indicators, and the data is normalized, the weight of each evaluation indicator in the total spectral reflectance is calculated, and the reduction degree of the moisture content of the castanea henryi samples in the future period is determined according to the calculated weight.

9. A method for the rapid spectrum determination system of Castanea henryi nutrient components as claimed in claim 1, characterized in that: The following steps are involved: Acquire moisture content data of the chromatographic measurement of the castanea henryi sample in different time periods, wherein the time period differentiation method includes acquiring the storage period of the castanea henryi, counting the duration of the storage period, dividing the acquired moisture content data based on the duration, and acquiring data features therein; A database is constructed according to the data features, wherein in the database, the data features are divided into θ1, θ2, ..., θ n , n represents the nth data feature, in response to the division of the acquired moisture content data based on the number of continuous days; Calculate the data difference of the moisture content data in each data feature, arrange the data according to the data size of the calculation results, and analyze the change trend of the moisture content data; Determining the change trend; wherein, a level content is given to the moisture content data, and when the change trend develops toward a level content lower than the given level content, the system determines that the moisture content of the obtained Castanea henryi sample is a low moisture content, otherwise, no determination is made; When it is determined that the moisture content of the obtained Castanea henryi sample is the low moisture content, the moisture content data is collected, and the collection method includes collecting at least 5 moisture content data every day during the storage period; Counting the total number of collected data and processing them, wherein the processing method includes intercepting the middle three data from all the data to the first data after the content is lower than the level, marking the data as reference data; and marking the data in this process as later data; Obtain the first data to the three data in the middle from all the data, and mark the data in this process as early data; The changing rules of the previous data and the later data are analyzed and processed, and a prediction model is generated.

Images