Volatile substance dynamic acquisition and analysis system and method for early detection of tomato root rot

Abstract

The invention relates to the technical field of agricultural disease control, in particular to a system and a method for dynamically collecting and analyzing volatile substances for early detection of tomato root rot. The method comprises the following steps: setting acquisition parameters, acquiring gas information of a plurality of targets according to the acquisition parameters, preprocessing to obtain preprocessed information, performing gas chromatography on the preprocessed information, creating a gas characteristic model in combination with a gas chromatography result, and inputting the acquired real-time gas information into the gas characteristic model. The root rot score of the real-time gas information output by the gas characteristic model is obtained, the collection period of the real-time gas information is judged according to the root rot score of the real-time gas information, and early warning is given out according to the collection period. And setting a relatively high weight for the gas type with high concentration, thereby calculating the root rot index of the gas information, and determining the root rot period of the gas information according to the root rot index.

Description

Technical Field

[0001] The invention relates to the technical field of agricultural disease prevention and control, and in particular to a volatile substance dynamic collection and analysis system and method for early detection of tomato root rot. Background Art

[0002] Root rot is a fungal disease that causes root rot, and the ability to absorb water and nutrients gradually weakens, eventually leading to the death of the entire plant, which is mainly manifested by yellowing and wilting of the leaves. In the early stages of the disease, only individual lateral roots and fibrous roots are affected, and the disease gradually spreads to the taproot. After the taproot is affected, the ability to absorb water and nutrients gradually weakens. The aboveground part is in short supply of nutrients, and the new leaves turn yellow first. When the disease is serious, the wilting condition cannot be restored at night, and the leaves of the entire plant turn yellow and wither. Root rot can cause plants to produce volatile gases.

[0003] A Chinese patent with publication number CN114287424B discloses the use of volatile substances in the prevention and treatment of tomato crown rot and root rot, and discloses that acetoin and 2-heptanol have significant inhibitory effects on the pathogens of tomato crown rot and root rot, and can be used as effective ingredients for the prevention and treatment of tomato crown rot and root rot. However, the prior art does not mention how to detect the condition of tomato root rot, which makes it difficult to detect tomato root rot in time and easily delays the best time for treatment. Summary of the invention

[0004] The purpose of the present invention is to address the problems existing in the background technology and to propose a dynamic collection and analysis system and method for volatile substances for early detection of tomato root rot.

[0005] The technical solution of the present invention:

[0006] On the one hand, the present application provides a method for dynamic collection and analysis of volatile substances for early detection of tomato root rot, comprising:

[0007] Setting acquisition parameters, respectively acquiring gas information of multiple targets according to the acquisition parameters, and preprocessing the gas information to remove invalid gas information and obtain preprocessed information;

[0008] Performing gas chromatography analysis on the preprocessed information and creating a gas characteristic model based on the gas chromatography analysis results;

[0009] Collecting real-time gas information, inputting the collected real-time gas information into a gas characteristic model, and obtaining a root rot score of the real-time gas information output by the gas characteristic model;

[0010] The root decay score of the real-time gas information is used to determine the collection period of the real-time gas information, and an early warning is issued based on the collection period.

[0011] Preferably, setting acquisition parameters, respectively acquiring gas information of multiple targets according to the acquisition parameters, and preprocessing the gas information to remove invalid gas information and obtain preprocessed information, including:

[0012] Create a gas data table;

[0013] Set corresponding acquisition parameters for each acquisition target; the acquisition parameters include acquisition cycle and acquisition frequency;

[0014] According to the collection parameters, the gas data and gas samples of each collection target in different collection cycles are collected, and all the collected gas data are put into the gas data table.

[0015] Preferably, setting acquisition parameters, respectively acquiring gas information of multiple targets according to the acquisition parameters, and preprocessing the gas information to remove invalid gas information and obtain preprocessed information, further comprising:

[0016] Select a collection target;

[0017] Select a collection period of the collection target and all gas data in the collection period from the gas data table;

[0018] Setting a frequency threshold, and passing all gas data in the acquisition period through the frequency threshold in sequence, so as to filter the gas data and obtain a filtered signal;

[0019] Calculate the standard deviation of the filtered signal and set the signal range based on the standard deviation;

[0020] Determine whether the filtered signal is within the signal range;

[0021] If the filtered signal is not within the signal range, the filtered signal is deleted;

[0022] If the filtered signal is within the signal range, the filtered signal is recorded as a preprocessed signal and put into the gas data table;

[0023] Return to select a collection cycle of the collection target and all gas data under the collection cycle from the gas data table until all collection cycles of the collection target are selected;

[0024] Return to select a collection target until all collection targets are selected, and obtain multiple pre-processed signals of each collection target.

[0025] Preferably, performing gas chromatography analysis on the preprocessing information and creating a gas characteristic model in combination with the gas chromatography analysis result includes:

[0026] Select a preprocessing signal from the gas data table;

[0027] Acquire a gas sample corresponding to the preprocessing signal;

[0028] performing gas chromatography on the gas sample to divide the gas sample into a plurality of sub-samples;

[0029] Perform ion mobility spectrometry analysis on each sub-sample to obtain the analysis results of the gas sample;

[0030] Return to select a preprocessing signal from the gas data table until all preprocessing signals in the gas data table are selected, and obtain the analysis result of the gas sample corresponding to each preprocessing signal.

[0031] Preferably, performing gas chromatography analysis on the preprocessing information and creating a gas characteristic model in combination with the gas chromatography analysis result further comprises:

[0032] Create gas characteristic models;

[0033] For each acquisition target, a plurality of preprocessing signals of each acquisition cycle of each acquisition target and an analysis result of a gas sample corresponding to each preprocessing signal are obtained respectively, and a coupling relationship of acquisition cycle-preprocessing signal-gas sample-analysis result of the gas sample is created for each preprocessing signal respectively, and the coupling relationship of acquisition cycle-preprocessing signal-gas sample-analysis result of the gas sample is recorded as a training sample, thereby obtaining a plurality of training samples;

[0034] Divide all training samples into training sets and test sets according to random proportions;

[0035] Inputting the training set into the gas characteristic model to train the gas characteristic model, thereby obtaining a trained gas characteristic model;

[0036] Input the test set into the trained gas characteristic model to verify whether the trained gas characteristic model is trained;

[0037] For each acquisition cycle, set the gas weight corresponding to its reference gas;

[0038] The root rot index of each collection cycle is calculated by the formula based on the gas weight corresponding to the reference gas;

[0039] Formula 1;

[0040] Among them, is the root rot score of the real-time gas information, is the gas score of the i-th reference gas, is the weight parameter of the i-th reference gas, and is the total number of reference gases.

[0041] Preferably, inputting the training set into the gas characteristic model to train the gas characteristic model to obtain the trained gas characteristic model includes:

[0042] Randomly select a collection period from the training set;

[0043] The gas types included in the analysis results of the gas samples of the collection period are sorted according to the gas concentrations;

[0044] Select the gas type with the gas concentration in the first M; record the first M gas types as the reference gas of the acquisition period;

[0045] Return to randomly select a collection cycle from the training set until all the collection cycles in the training set are selected and completed, and obtain the reference gas for each collection cycle.

[0046] Preferably, collecting real-time gas information, inputting the collected real-time gas information into a gas characteristic model, and obtaining a root rot score of the real-time gas information output by the gas characteristic model include:

[0047] Collect real-time gas information;

[0048] Performing gas chromatography analysis on the real-time gas information to obtain analysis results of the real-time gas information;

[0049] Inputting real-time gas information and gas chromatography analysis results into the trained gas characteristic model, and obtaining prediction results output by the trained gas characteristic model;

[0050] The similarity between the prediction result and the reference gas is calculated, and the collection period corresponding to the reference gas with the highest similarity is selected.

[0051] Preferably, the real-time gas information and the gas chromatography analysis results are input into the trained gas characteristic model, and the prediction results output by the trained gas characteristic model are obtained, including:

[0052] Acquire the gas type that is the same as the reference gas of the corresponding collection period of the real-time gas information;

[0053] The root rot score of the real-time gas information is calculated by formula 2;

[0054] Formula 2;

[0055] Among them, is the root rot score of the real-time gas information, is the a-th gas type, is the weight parameter corresponding to the a-th gas type, and is the total number of gas types in the real-time gas information that are the same as the reference gas of the corresponding collection period.

[0056] Preferably, judging the collection period of the real-time gas information by the root rot score of the real-time gas information, and issuing an early warning according to the collection period, includes:

[0057] Set root rot deviation threshold;

[0058] Calculate the difference between the root rot score of the real-time gas information and the root rot index of the alternative period;

[0059] Determine whether the difference between the root rot score of the real-time gas information and the root rot index of the candidate period is less than or equal to the root rot deviation threshold;

[0060] If the difference between the root rot score of the real-time gas information and the root rot index of the alternative period is less than or equal to the root rot deviation threshold, it is determined that the collection period of the real-time gas and the alternative period are in the same root rot period.

[0061] On the other hand, the present application also provides a dynamic collection and analysis system of volatile substances for early detection of tomato root rot, comprising:

[0062] A collection component, through which gas data is collected;

[0063] A processing component, the processing component includes a processing unit and a gas data unit, the processing unit controls the gas data unit to analyze the gas data, and inputs the analysis result to the processing unit, and the processing unit executes the dynamic collection and analysis method of volatile substances for early detection of tomato root rot described in any one of the above.

[0064] Compared with the prior art, the above technical solution of the present invention has the following beneficial technical effects:

[0065] By setting the acquisition parameters, the gas information of multiple targets is collected respectively according to the acquisition parameters, and the gas information is preprocessed to obtain preprocessed information. Thereafter, the preprocessed information is subjected to gas chromatography analysis, and a gas characteristic model is created in combination with the gas chromatography analysis results. The collected real-time gas information is then input into the gas characteristic model to obtain the root rot score of the real-time gas information output by the gas characteristic model. The acquisition cycle of the real-time gas information is determined by the root rot score of the real-time gas information, and an early warning is issued according to the acquisition cycle. The present application calculates the root rot index of the gas information by sorting the gas types contained in the gas information according to their concentrations and setting a higher weight for gas types with high concentrations, thereby determining the root rot cycle of the gas information according to the root rot index. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is a schematic flow chart of a method for dynamically collecting and analyzing volatile substances for early detection of tomato root rot proposed by the present invention;

[0067] Figure 2 This is a structural schematic diagram of a volatile substance dynamic collection and analysis system for early detection of tomato root rot proposed by the present invention.

[0068] Reference numerals

[0069] 100, acquisition component; 200, processing component; 201, processing unit; 202, gas processing data unit. DETAILED DESCRIPTION

[0070] Embodiment 1, as Figure 1 As shown, the present invention proposes a method for dynamic collection and analysis of volatile substances for early detection of tomato root rot, comprising:

[0071] S100, setting acquisition parameters, respectively acquiring gas information of multiple targets according to the acquisition parameters, and preprocessing the gas information to remove invalid gas information and obtain preprocessed information;

[0072] S200, performing gas chromatography analysis on the preprocessing information, and creating a gas characteristic model based on the gas chromatography analysis result;

[0073] S300, collecting real-time gas information, inputting the collected real-time gas information into a gas characteristic model, and obtaining a root rot score of the real-time gas information output by the gas characteristic model;

[0074] S400, judging the collection period of the real-time gas information according to the root decay score of the real-time gas information, and issuing an early warning according to the collection period.

[0075] In the present invention, by setting acquisition parameters, gas information of multiple targets is collected respectively according to the acquisition parameters, and the gas information is preprocessed to obtain preprocessed information, and then the preprocessed information is subjected to gas chromatography analysis, and a gas characteristic model is created in combination with the gas chromatography analysis results, and then the collected real-time gas information is input into the gas characteristic model to obtain the root rot score of the real-time gas information output by the gas characteristic model, and the acquisition period of the real-time gas information is judged by the root rot score of the real-time gas information, and an early warning is issued according to the acquisition period. The present application calculates the root rot index of the gas information by sorting the gas types contained in the gas information according to the concentration and setting a higher weight for the gas type with a large concentration, so as to determine the root rot period of the gas information according to the root rot index.

[0076] In an optional embodiment, the S100 includes:

[0077] S110, creating a gas data table;

[0078] S120, setting corresponding acquisition parameters for each acquisition target; the acquisition parameters include acquisition period and acquisition frequency;

[0079] S130, collecting gas data and gas samples of each collection target in different collection cycles according to the collection parameters, and putting all the collected gas data into a gas data table.

[0080] It should be noted that different collection cycles correspond to different root rot cycles, and the total cycle composed of all collection cycles should include the entire cycle of root rot, so that the subsequent gas characteristic model can make predictions for different root rot cycles;

[0081] For example, there are collection cycles A, B and C. Collection cycle A corresponds to the early stage of root rot, collection cycle B corresponds to the middle stage of root rot, and collection cycle C corresponds to the late stage of root rot.

[0082] In an optional embodiment, the S100 further includes:

[0083] S140, selecting a collection target;

[0084] S141, selecting a collection period of the collection target and all gas data in the collection period from the gas data table;

[0085] S142, setting a frequency threshold, and passing all gas data in the collection period through the frequency threshold in sequence to filter the gas data to obtain a filtered signal;

[0086] Specifically, bandpass filtering is a signal processing technique used to allow only signals within a specific frequency range from a set of frequencies to pass through, while attenuating signals of other frequencies to an extremely low level. The bandpass filter combines the characteristics of the high-pass filter and the low-pass filter, and achieves the frequency selection function by combining these two filters;

[0087] S143, calculating the standard deviation of the filtered signal, and setting the signal range based on the standard deviation;

[0088] Optionally, the maximum value of the signal range may be three times the standard deviation, that is, the signal range is created by a three times standard deviation method;

[0089] S144, determining whether the filtered signal is within the signal range;

[0090] S145, if the filtered signal is not within the signal range, deleting the filtered signal;

[0091] Specifically, when deleting the filtered signal, the gas sample corresponding to the filtered signal is deleted at the same time;

[0092] S146, if the filtered signal is within the signal range, the filtered signal is recorded as a preprocessed signal and put into the gas data table;

[0093] S147, returning to select a collection cycle of the collection target and all gas data under the collection cycle from the gas data table, until all collection cycles of the collection target are selected;

[0094] S148, returning to select a collection target, until all collection targets are selected, and obtaining multiple pre-processed signals of each collection target.

[0095] It should be noted that by setting the signal range of the signal, outliers in the filtered signal can be eliminated to avoid affecting the subsequent training of the gas characteristic model. At the same time, the number of samples can be reduced, thereby improving the training efficiency.

[0096] In an optional embodiment, the S200 includes:

[0097] S210, selecting a preprocessing signal from the gas data table;

[0098] S220, obtaining a gas sample corresponding to the preprocessing signal;

[0099] S230, performing gas chromatography analysis on the gas sample to divide the gas sample into a plurality of sub-samples;

[0100] S240, performing ion mobility spectrometry analysis on each sub-sample to obtain an analysis result of the gas sample;

[0101] S250, returning to select a preprocessing signal from the gas data table until all preprocessing signals in the gas data table are selected, and obtaining the analysis result of the gas sample corresponding to each preprocessing signal.

[0102] It should be noted that the present application detects the type of gas contained in the gas sample by performing gas chromatography-ion mobility spectrometry detection technology on the gas sample. Since different collection periods contain different gas types, the collection period corresponding to the gas sample can be determined according to the type of gas type, thereby further determining the root rot period corresponding to the gas sample.

[0103] The reason why gas chromatography-ion mobility spectrometry detection technology is used is that this technology combines the high separation efficiency of gas chromatography and the high sensitivity of ion mobility spectrometry, and can accurately and real-time determine volatile and semi-volatile organic compounds. Through the gas chromatography part, the various components in the mixture are gradually separated in the chromatographic column according to their chemical properties, and then these separated compounds enter the ion mobility spectrometry part. The ions move in the migration tube according to their respective mobility in the electric field, thereby achieving secondary separation and detection.

[0104] In an optional embodiment, the S200 further includes:

[0105] S260, creating a gas characteristic model;

[0106] S261, for each acquisition target, respectively obtain multiple preprocessing signals of each acquisition cycle of each acquisition target and the analysis result of the gas sample corresponding to each preprocessing signal, and respectively create a coupling relationship of acquisition cycle-preprocessing signal-gas sample-analysis result of the gas sample for each preprocessing signal, and record the coupling relationship of acquisition cycle-preprocessing signal-gas sample-analysis result of the gas sample as a training sample, thereby obtaining multiple training samples;

[0107] Specifically, since each collection cycle has its unique corresponding root rot cycle, after determining the collection cycle, its corresponding root rot cycle can also be determined;

[0108] S262, dividing all training samples into a training set and a test set according to a random ratio;

[0109] Specifically, the proportion of the training set should be higher than that of the test set;

[0110] S263, inputting the training set into the gas characteristic model to train the gas characteristic model, thereby obtaining a trained gas characteristic model;

[0111] S264, inputting the test set into the trained gas characteristic model to verify whether the trained gas characteristic model is trained;

[0112] S265, for each acquisition cycle, respectively setting the gas weight corresponding to the reference gas;

[0113] S266, calculating the root rot index of each collection period by using a formula in combination with the gas weight corresponding to the reference gas;

[0114] Formula 1;

[0115] Among them, is the root rot score of the real-time gas information, is the gas score of the i-th reference gas, is the weight parameter of the i-th reference gas, and is the total number of reference gases;

[0116] Specifically, in order to ensure that the credibility of the root rot index is the same for all root rot disease cycles, before calculating the root rot index by formula 1, it is necessary to set the corresponding gas scores for all gas types;

[0117] When executing step S264, the gas samples and preprocessing signals in the test set are input into the trained gas characteristic model, and the reference gas of the collection period corresponding to each gas sample output by the trained gas characteristic model is obtained. The reference gas of the collection period corresponding to each gas sample output by the gas characteristic model is compared with the analysis results of the gas samples in the training set. If the results are consistent, it proves that the gas characteristic model has been trained.

[0118] It should be noted that by creating and training a gas characteristic model so that the gas characteristic model has the ability to output the collection period corresponding to the gas information based on the input gas data and gas samples, the real-time gas information and the corresponding gas samples can be input into the gas characteristic model to obtain the collection period corresponding to the real-time gas information, thereby further determining the root rot period corresponding to the real-time gas information.

[0119] In an optional embodiment, the S263 includes:

[0120] K100, randomly selects a collection period from the training set;

[0121] K101, sorting the gas types contained in the analysis results of the gas samples of the collection period according to the size of the gas concentration;

[0122] K102, select the gas type with the gas concentration in the first M; record the first M gas types as the reference gas of the acquisition period;

[0123] K103, returning to step K102, until all the acquisition cycles in the training set are selected and completed, and the reference gas of each acquisition cycle is obtained;

[0124] It should be noted that different collection cycles correspond to different root rot cycles, and the types and concentrations of gases contained in different root rot cycles are different. The greater the concentration, the greater the proportion of the gas type in the corresponding root rot cycle. Therefore, a greater weight is given to the gas type with a large concentration, thereby reflecting the importance of this gas type in the corresponding root rot cycle.

[0125] After assigning the corresponding weight to the reference gas, the root rot index of the collection period is calculated by combining the gas weight corresponding to the reference gas, and the root rot index is used as the judgment standard for identifying the period in which the gas is located.

[0126] For example, the reference gases of collection period A are gas 1, gas 2, gas 3, gas 4 and gas 5, the reference gases of collection period B are gas 2, gas 4, gas 5, gas 6 and gas 9, and the reference gases of collection period C are gas 1, gas 3, gas 6, gas 13 and gas 15. The root rot index of collection period A, collection period B and collection period C are calculated by formula 1 based on the gas scores of gas 1 to gas 6 and the weight corresponding to each gas type.

[0127] In an optional embodiment, the S300 includes:

[0128] S310, collecting real-time gas information;

[0129] S320, performing gas chromatography analysis on the real-time gas information to obtain analysis results of the real-time gas information;

[0130] S330, inputting the real-time gas information and the gas chromatography analysis results into the trained gas characteristic model, and obtaining the prediction results output by the trained gas characteristic model;

[0131] S340, calculating the similarity between the prediction result and the reference gas, and screening out the collection period corresponding to the reference gas with the highest similarity; recording the collection period corresponding to the reference gas with the highest similarity as the candidate period.

[0132] It should be noted that since irrelevant gas types are not included in the gas characteristic model, even if the real-time gas information contains gas types that are irrelevant to the root rot cycle, these irrelevant gas types will not affect the root rot score calculated by the real-time gas information, so that the present application can avoid the interference of irrelevant gas types to improve the accuracy of root rot cycle judgment.

[0133] After the real-time gas information is input into the gas characteristic model, if the reference gases of the real-time gas information output by the gas characteristic model are gas 1, gas 2, gas 4, gas 5 and gas 9, since the reference gas of the real-time gas information has the highest similarity with the reference gas of collection period B, it can be preliminarily determined that the candidate period of the real-time gas information is collection period B.

[0134] In an optional embodiment, the S300 further includes:

[0135] S350, screening the gas types included in the real-time gas information for the gas type that is the same as the reference gas in the candidate period;

[0136] S360, calculating the root rot score of the real-time gas information by formula 2;

[0137] Formula 2;

[0138] Among them, is the root rot score of the real-time gas information, is the gas score of the a-th gas type in the real-time gas information, is the weight parameter corresponding to the a-th gas type, and is the total number of gas types in the real-time gas information that are the same as the reference gas of the corresponding collection period;

[0139] Specifically, the weight parameter corresponding to each gas type is uniquely determined within the collection period. Therefore, after the alternative period of the real-time gas information is preliminarily confirmed through step S340, the weight parameter corresponding to the gas type of the alternative period can be substituted into the real-time gas information and calculated by formula 2.

[0140] It should be noted that, since the alternative period of real-time gas information has been preliminarily determined to be collection period B through the aforementioned embodiment, the weight parameter corresponding to the gas type of collection period B is substituted into Formula 2, and the root rot score of the real-time gas information is calculated by Formula 2.

[0141] The root rot score is a value used to calculate the similarity between the root rot index of the collection period of the real-time gas information and the alternative period. The closer the root rot score of the real-time gas information is to the root rot index of the collection period, the closer the collection period of the real-time gas information is to the alternative period.

[0142] In an optional embodiment, the S400 includes:

[0143] S410, setting a root rot deviation threshold;

[0144] S420, calculating the difference between the root rot score of the real-time gas information and the root rot index of the alternative period;

[0145] S430, determining whether the difference between the root rot score of the real-time gas information and the root rot index of the candidate period is less than or equal to the root rot deviation threshold;

[0146] S440, if the difference between the root rot score of the real-time gas information and the root rot index of the candidate period is less than or equal to the root rot deviation threshold, it is determined that the collection period of the real-time gas and the candidate period are in the same root rot period;

[0147] Specifically, "the collection period of the real-time gas and the alternative period are in the same root rot period" does not mean the same period in terms of collection time, but the uniformity of the tomato root rot period, that is, if the difference between the root rot score of the real-time gas information and the root rot index of the alternative period is less than or equal to the root rot deviation threshold, and the alternative period is in the middle of the root rot period, then similarly, it can be considered that the corresponding collection period of the real-time gas information is also in the root rot period;

[0148] Optionally, if the difference between the root rot score of the real-time gas information and the root rot index of the alternative period is greater than the root rot deviation threshold, it is determined that the collection period of the real-time gas is not in the same period as the alternative period, and the process returns to step S310.

[0149] Optionally, since there may be multiple candidate cycles, in this case, the weights corresponding to the gas types included in each candidate cycle need to be respectively substituted into Formula 2, and the root rot scores of the real-time gas information are calculated multiple times using Formula 2 under different weights, and the candidate cycle with the smallest difference with the root rot score of the gas information is selected as the corresponding cycle;

[0150] For example, the existing candidate cycles are collection cycle A and collection cycle D, and the weight parameters corresponding to the gas types included in collection cycle A and collection cycle D are shown in Table-1 Gas Type Weight Table;

[0151] Table-1 Gas type weight table

[0152] Gas type weights for the acquisition cycle

[0153] Collection cycle A gas 1 0.5

[0154] Gas 2 1.0

[0155] Gas 3 0.3

[0156] …

[0157] Collection cycle D gas 1 1.2

[0158] Gas 2 0.6

[0159] Gas 3 0.5

[0160] …

[0161] ………

[0162] Then, after respectively substituting the weights corresponding to the gas types included in the collection period A and the weights corresponding to the gas types included in the collection period D into formula 2, the root rot scores of the real-time gas information when the alternative period is the collection period A and the root rot scores of the real-time gas information when the alternative period is the collection period D can be calculated in combination with the gas types included in the real-time gas information. The root rot scores of the real-time gas information when the alternative period is the collection period A are recorded as root rot scores A, and the root rot scores of the real-time gas information when the alternative period is the collection period D are recorded as root rot scores D;

[0163] Then, the difference a between the root rot score A and the root rot index of the collection period A, and the difference d between the root rot score D and the root rot index of the collection period D are calculated respectively. If both the difference a and the difference d meet the root rot deviation threshold, the collection period with the smaller difference is selected as the corresponding period. If one of the difference a and the difference d does not meet the root rot deviation threshold, the collection period that meets the root rot deviation threshold is selected as the corresponding period. If both the difference a and the difference d do not meet the root rot deviation threshold, return to step S310.

[0164] It should be noted that after calculating the root rot score of the real-time gas information, the similarity between the collection period of the real-time gas information and the alternative period is observed by judging the difference between the root rot score of the real-time gas information and the root rot index of the alternative period. The smaller the difference, the higher the similarity.

[0165] The present application sets up double detection. First, the gas type contained in the real-time gas information is checked for similarity with the gas type contained in all collection cycles to preliminarily screen out alternative cycles that may be closer to the collection cycle in which the real-time gas information is located. Then, the closest collection cycle is determined by calculating the difference between the root rot score of the real-time gas information and the root rot index of the alternative cycle. The collection cycle in which the real-time gas information is located is placed in the same period as the alternative cycle. Through double detection, the accuracy and reliability of detection of the cycle in which tomato root rot is located is improved.

[0166] The present application also provides a dynamic collection and analysis system for volatile substances for early detection of tomato root rot, including a collection component 100 and a processing component 200.

[0167] The gas data is collected by the collection component 100, and the processing component 200 includes a processing unit 201 and a gas data unit 202. The processing unit 201 controls the gas data unit 202 to analyze the gas data, and inputs the analysis result to the processing unit 201. The processing unit 201 executes the dynamic collection and analysis method of volatile substances for early detection of tomato root rot described in Example 1;

[0168] Specifically, the collection target in this application should include the entire cycle of tomato root rot to ensure that the collected gas information can cover the complete cycle of tomato root rot.

[0169] It should be noted that gas information of multiple collection targets is collected respectively by multiple collection components 100, and the collected gas information is input into the processing component 200, and the gas information is processed by the gas data unit 202 of the processing component 200 to calculate the root rot index of the collection target, and finally the processing unit 201 determines whether it is necessary to issue an early warning according to the root rot index.

[0170] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto, and various changes can be made within the knowledge scope of technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A method for dynamic collection and analysis of volatile substances for early detection of tomato root rot, characterized in that: include: Setting acquisition parameters, respectively acquiring gas information of multiple targets according to the acquisition parameters, and preprocessing the gas information to remove invalid gas information and obtain preprocessed information; Performing gas chromatography analysis on the preprocessed information and creating a gas characteristic model based on the gas chromatography analysis results; Collecting real-time gas information, inputting the collected real-time gas information into a gas characteristic model, and obtaining a root rot score of the real-time gas information output by the gas characteristic model; The root decay score of the real-time gas information is used to determine the collection period of the real-time gas information, and an early warning is issued based on the collection period.

2. The method for dynamic collection and analysis of volatile substances for early detection of tomato root rot according to claim 1, characterized in that: Set acquisition parameters, collect gas information of multiple targets respectively according to the acquisition parameters, and pre-process the gas information to remove invalid gas information and obtain pre-processed information, including: Create a gas data table; Set corresponding acquisition parameters for each acquisition target; the acquisition parameters include acquisition cycle and acquisition frequency; According to the collection parameters, the gas data and gas samples of each collection target in different collection cycles are collected, and all the collected gas data are put into the gas data table.

3. The method for dynamic collection and analysis of volatile substances for early detection of tomato root rot according to claim 2, characterized in that: Setting acquisition parameters, respectively acquiring gas information of multiple targets according to the acquisition parameters, and preprocessing the gas information to remove invalid gas information and obtain preprocessed information, further comprising: Select a collection target; Select a collection period of the collection target and all gas data in the collection period from the gas data table; Setting a frequency threshold, and passing all gas data in the acquisition period through the frequency threshold in sequence, so as to filter the gas data and obtain a filtered signal; Calculate the standard deviation of the filtered signal and set the signal range based on the standard deviation; Determine whether the filtered signal is within the signal range; If the filtered signal is not within the signal range, the filtered signal is deleted; If the filtered signal is within the signal range, the filtered signal is recorded as a preprocessed signal and put into the gas data table; Return to select a collection cycle of the collection target and all gas data under the collection cycle from the gas data table until all collection cycles of the collection target are selected; Return to select a collection target until all collection targets are selected, and obtain multiple pre-processed signals of each collection target.

4. The method for dynamic collection and analysis of volatile substances for early detection of tomato root rot according to claim 3, characterized in that: Perform gas chromatography analysis on the preprocessing information and create a gas characteristic model based on the gas chromatography analysis results, including: Select a preprocessing signal from the gas data table; Acquire a gas sample corresponding to the preprocessing signal; performing gas chromatography on the gas sample to divide the gas sample into a plurality of sub-samples; Perform ion mobility spectrometry analysis on each sub-sample to obtain the analysis results of the gas sample; Return to select a preprocessing signal from the gas data table until all preprocessing signals in the gas data table are selected, and obtain the analysis result of the gas sample corresponding to each preprocessing signal.

5. The method for dynamic collection and analysis of volatile substances for early detection of tomato root rot according to claim 4, characterized in that: Perform gas chromatography analysis on the preprocessing information and create a gas characteristic model based on the gas chromatography analysis results, including: Create gas characteristic models; For each acquisition target, a plurality of preprocessing signals of each acquisition cycle of each acquisition target and an analysis result of a gas sample corresponding to each preprocessing signal are obtained respectively, and a coupling relationship of acquisition cycle-preprocessing signal-gas sample-analysis result of the gas sample is created for each preprocessing signal respectively, and the coupling relationship of acquisition cycle-preprocessing signal-gas sample-analysis result of the gas sample is recorded as a training sample, thereby obtaining a plurality of training samples; Divide all training samples into training sets and test sets according to random proportions; Inputting the training set into the gas characteristic model to train the gas characteristic model, thereby obtaining a trained gas characteristic model; Input the test set into the trained gas characteristic model to verify whether the trained gas characteristic model is trained; For each acquisition cycle, set the gas weight corresponding to its reference gas; The root rot index of each collection cycle is calculated by the formula based on the gas weight corresponding to the reference gas; Formula 1; Among them, is the root rot score of the real-time gas information, is the gas score of the i-th reference gas, is the weight parameter of the i-th reference gas, and is the total number of reference gases.

6. The method for dynamic collection and analysis of volatile substances for early detection of tomato root rot according to claim 5, characterized in that: The training set is input into the gas characteristic model to train the gas characteristic model, and the trained gas characteristic model is obtained, including: Randomly select a collection period from the training set; The gas types included in the analysis results of the gas samples of the collection period are sorted according to the gas concentrations; Select the gas type with the gas concentration in the first M; record the first M gas types as the reference gas of the acquisition period; Return to randomly select a collection cycle from the training set until all the collection cycles in the training set are selected and completed, and obtain the reference gas for each collection cycle.

7. The method for dynamic collection and analysis of volatile substances for early detection of tomato root rot according to claim 6, characterized in that: Collect real-time gas information, input the collected real-time gas information into the gas characteristic model, and obtain the root rot score of the real-time gas information output by the gas characteristic model, including: Collect real-time gas information; Performing gas chromatography analysis on the real-time gas information to obtain analysis results of the real-time gas information; Inputting real-time gas information and gas chromatography analysis results into the trained gas characteristic model, and obtaining prediction results output by the trained gas characteristic model; The similarity between the prediction result and the reference gas is calculated, and the collection period corresponding to the reference gas with the highest similarity is selected.

8. The method for dynamic collection and analysis of volatile substances for early detection of tomato root rot according to claim 7, characterized in that: Input the real-time gas information and gas chromatography analysis results into the trained gas characteristic model, and obtain the prediction results output by the trained gas characteristic model, including: Acquire the gas type that is the same as the reference gas of the corresponding collection period of the real-time gas information; The root rot score of the real-time gas information is calculated by formula 2; Formula 2; Among them, is the root rot score of the real-time gas information, is the a-th gas type, is the weight parameter corresponding to the a-th gas type, and is the total number of gas types in the real-time gas information that are the same as the reference gas of the corresponding collection period.

9. The method for dynamic collection and analysis of volatile substances for early detection of tomato root rot according to claim 8, characterized in that: The root decay score of real-time gas information is used to determine the collection period of real-time gas information, and an early warning is issued according to the collection period, including: Set root rot deviation threshold; Calculate the difference between the root rot score of the real-time gas information and the root rot index of the alternative period; Determine whether the difference between the root rot score of the real-time gas information and the root rot index of the candidate period is less than or equal to the root rot deviation threshold; If the difference between the root rot score of the real-time gas information and the root rot index of the alternative period is less than or equal to the root rot deviation threshold, it is determined that the collection period of the real-time gas and the alternative period are in the same root rot period.

10. A dynamic collection and analysis system of volatile substances for early detection of tomato root rot, characterized in that: include: A collection component, through which gas data is collected; A processing component, wherein the processing component includes a processing unit and a gas data unit, wherein the processing unit controls the gas data unit to analyze the gas data, and inputs the analysis result to the processing unit, and the processing unit executes the dynamic collection and analysis method of volatile substances for early detection of tomato root rot as described in any one of claims 1 to 9.

Images