Tree disease and pest detection method and device based on electronic nose and hollow structure identification

Abstract

The application provides a tree disease and pest detection method and device based on an electronic nose and hollow structure identification, and relates to the technical field of disease and pest detection, and comprises the following steps: a hollow structure with an embedded electronic nose is attached to a branch detection part, a spatial position is positioned, candidate marker gas is collected, a type and a concentration value are extracted, a concentration variation coefficient and a complexity are calculated to adjust a filter time point quantity, and a filtered concentration value is obtained through sliding average filtering; the marker gas is screened in combination with a disease and pest related gas database, a detection-axis distance is calculated, a priority coefficient of each part is obtained in combination with a filtered concentration average value of the marker gas; the priority coefficients are arranged in descending order and the first m positions are screened, a critical distance is set based on a highest priority part as a reference point, detection-reference distances of the remaining parts from the reference point are measured and compared, and the number of infection points is judged. The application dynamically adjusts a filter window, reduces data noise, combines spatial positioning and priority division, and avoids the disadvantages that multiple high concentration points are misjudged as multiple infection points.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of pest detection, and particularly relates to a tree pest detection method and device based on an electronic nose and hollow structure recognition. BACKGROUND

[0002] With the development of technology, the electronic nose and hollow structure recognition technology bring new ideas for tree pest detection. The electronic nose can quickly detect the changes in volatile organic compounds released by plants. When plants are attacked by pests, the metabolism changes and specific VOCs are released. For example, after citrus is infected with Huanglongbing, specific volatile substances that attract psyllopsis are produced. When tea trees are attacked by Ectropis oblique, a large amount of high-concentration volatile organic compounds are released. By analyzing these VOCs, the health status of trees can be determined. However, the electronic nose sensor has limitations in sensitivity, selectivity and stability, is easily affected by environmental factors such as temperature, humidity and light, and different research methods and data analysis methods lack unified standards, which affects the detection accuracy and result comparability. The hollow structure has the characteristics of directional enrichment of target gas through specific cavity design, can accurately capture the volatile gas released by the detection part of the tree to be detected, reduces the interference of irrelevant gas in the surrounding environment, significantly increases the concentration of the target gas in the detection area, and enhances the recognition ability of the electronic nose to low-concentration characteristic gas.

[0003] In the prior art, the disclosure number CN119380079A provides a tea tree pest degree prediction method based on electronic nose technology, which comprises the following steps: pretreating a plurality of tea trees so that the tea trees have different types of pests; using an electronic nose to detect the volatile gas of all tea trees within a certain time after being attacked by pests, and obtaining the response curve of the electronic nose of the tea trees with different pest types under different pest degrees; processing the response curve of the electronic nose, and extracting tea tree pest characteristic data; constructing and training a tea tree pest classifier based on the tea tree pest characteristic data and the corresponding pest types; for each type of pest, constructing and training a pest degree prediction network based on the tea tree pest characteristic data and the corresponding pest degree; collecting the volatile gas of the tea tree to be detected by the electronic nose and processing it to obtain the test pest characteristic data, inputting the test pest characteristic data into the tea tree pest classifier to obtain a classification result, and inputting the test pest characteristic data into the corresponding pest degree prediction network based on the classification result to obtain a pest degree prediction result. The method can quickly identify the pest type and predict the pest degree.

[0004] However, there are still the following shortcomings. As can be seen from the above statements, in the gas data processing link, the prior art only performs conventional processing on the electronic nose response curve, does not dynamically adjust the filter window size through the "concentration variation coefficient and complexity", and such a processing manner is difficult to eliminate false signals caused by instantaneous environmental interference (such as airflow fluctuation around tea trees), so that noise is easily mixed into the extracted feature data, and the contaminated feature data directly affects the accuracy of subsequent data processing.

[0005] Secondly, the prior art does not perform spatial positioning and priority division on the detection part, directly leading to the inability to distinguish the disease and pest risk differences of different parts of the same plant, the inability to judge the spread state of the disease and pests in combination with the spatial position relationship, and especially the misjudgment of multiple high-concentration points as multiple infection points caused by the spread of the same infection point to different parts. SUMMARY

[0006] The purpose of the present application is to provide a tree disease and pest detection method and device based on an electronic nose and hollow structure recognition to solve the problems raised in the above background technology.

[0007] To achieve the above purpose, the present application provides the following technical solutions:

[0008] A tree disease and pest detection method based on an electronic nose and hollow structure recognition, and the specific steps include:

[0009] S1. The hollow structure with the built-in electronic nose is attached to the detection part of the branch, the spatial positions of different detection parts are positioned, and the candidate marker gas of the detection part in the detection time period is collected, the types and concentration values of the candidate marker gas at each time point are extracted, the concentration variation coefficient and complexity are calculated, the number of filter time points is adjusted accordingly, the sliding average filtering is performed, and the filtered concentration values of the candidate marker gas at different time points at each detection part are obtained;

[0010] S2. The filtered concentration values are analyzed according to the pre-set disease and pest associated gas database to screen out the marker gas, the vertical distance between the detection part and the trunk central axis is obtained as the detection-axis distance based on the spatial positions of different detection parts, and the priority coefficient of each detection part is obtained by combining the filtered concentration average values of the marker gas at each detection part in the detection time period, which is used to represent the disease and pest risk degree;

[0011] S3. The priority coefficients of all detection parts are arranged in descending order, the detection parts with the top m priority coefficients are screened out, the detection part with the highest priority is taken as the reference point, the critical distance is set with the reference point as the center, the straight line distance between the other m-1 detection parts and the reference point is measured as the detection-reference distance, the detection-reference distance is compared with the critical distance one by one, and the number of infection points of the disease and pests is judged according to the comparison result.

[0012] Furthermore, the concentration of the candidate marker gas during the detection period is normalized, and then the mean of the normalized candidate marker gas concentration is calculated. The concentration variation coefficient and the complexity of the candidate marker gas are calculated according to the following formula:

[0013] ;

[0014] ;

[0015] ;

[0016] in, is the complexity of the candidate marker gas, is the number of candidate marker gases, For the The concentration variation coefficient of the candidate marker gas, For the The standard deviation of the concentration of the candidate marker gas in the detection time period, For the The mean of the concentrations of the candidate marker gases, is the mean value of the concentration variation coefficient of all candidate marker gases, is the index of the candidate marker gas, ;

[0017] Adjust the filter window size according to the complexity of the candidate marker gas:

[0018] ;

[0019] in, is the number of filtering time points, is the reference value of the number of filtering time points, is the first level threshold of complexity, is the second level threshold of complexity.

[0020] Furthermore, the specific steps for obtaining the filtered concentration value are as follows:

[0021] For each candidate marker gas at each detection location, within its corresponding detection time period, for each time point, its concentration value is calculated relative to the nearest concentration value at that time point. The average of the concentration values ​​at the time points is used as the filtered concentration value at that time point.

[0022] Furthermore, the marker gases are screened out based on the preset pest-related gas database. The specific steps are as follows:

[0023] From the candidate marker gases, retain the gases that match the types of pest gases in the database;

[0024] Calculate the filtered mean concentration of these gases during the detection period. If the mean falls within the gas concentration range corresponding to the pests and diseases in the database, the gas is listed as a candidate gas.

[0025] For a gas to be selected, if its filtered concentration value exceeds the preset threshold at more than three consecutive time points during the detection period, it will be included in the pre-selected marker gas set;

[0026] From the preselected marker gas set, the gas with the highest average concentration after filtering is selected as the final marker gas.

[0027] Furthermore, based on the spatial positions of different detection parts, the vertical distances between them and the central axis of the trunk are obtained. The specific steps are as follows:

[0028] Set up a cross section every 50 cm along the trunk upward direction, and measure the coordinates of the center of the cross section at different heights of the trunk;

[0029] Connect the centers of the cross sections at each height to form a virtual straight line, which is the central axis of the trunk;

[0030] Based on the spatial positions of different detection parts, determine the coordinates of each detection part in space;

[0031] According to the distance formula from the midpoint of spatial geometry to the straight line, the vertical distance from the coordinates of each detection part to the central axis of the trunk is calculated.

[0032] Furthermore, based on the filtered mean concentration of the marker gas at each detection location during the detection period and the detection-axis distance, the priority coefficient of the pest risk at different detection locations is obtained, according to the following formula:

[0033] ;

[0034] in, For the Priority coefficient of pest and disease risk of each detection part, For the The average concentration of the marker gas at each detection location after filtering during the detection period, For the The detection-axis distance of each detection part, is the index of the detection part, , is the number of test sites;

[0035] Where, is the weight coefficient of the filtered mean concentration of the marker gas at the detection site, is the weight coefficient of the inspection-axis distance, On the basis of ;

[0036] The priority coefficients of all detection sites are arranged in descending order, and the detection sites ranked in the top m positions are screened out, and the specific steps are as follows:

[0037] Set the sorting rule:

[0038] Rule one: sort according to the priority coefficient from large to small;

[0039] Rule two: if there are multiple detection sites with the same priority coefficient, sort according to the average concentration of the marker gas after filtering, and the one with the higher average concentration is ranked in the front;

[0040] According to rule one, all detection sites are arranged in descending order according to the priority coefficient, and the preliminary sorting result is obtained;

[0041] Check the preliminary sorting result, if there are detection sites with the same priority coefficient, extract the average concentration of the marker gas after filtering from these detection sites, and sort according to rule two, adjust the order, and select the detection sites ranked in the top m positions.

[0042] Further, compare the detection-base distance with the critical distance one by one, and according to the comparison result, judge the number of infection points of the plant diseases and insect pests, and the specific steps are as follows:

[0043] Compare the detection-base distance with the set critical distance one by one, count the number of detection sites with detection-base distance greater than critical distance, and mark it as ;

[0044] If , that is, all detection-base distances are less than or equal to the critical distance, it is determined that the infection point of the plant diseases and insect pests on the tree is one;

[0045] If , that is, there is at least one detection-base distance greater than the critical distance, it is determined that the infection point of the plant diseases and insect pests on the tree is multiple.

[0046] To achieve the above purpose, the present application also provides the following technical scheme:

[0047] A tree plant disease and insect pest detection system based on an electronic nose and hollow structure recognition, the system is used for executing any one of the above-mentioned tree plant disease and insect pest detection methods based on an electronic nose and hollow structure recognition, comprising:

[0048] The data acquisition module is used for adhering the hollow structure with the electronic nose to the detection part of the branch, positioning the spatial positions of different detection parts, and collecting candidate marker gases of the detection part in a detection time period, extracting the types and concentration values of the candidate marker gases at each time point, calculating the concentration variation coefficient and complexity, adjusting the number of filtering time points according to the concentration variation coefficient and complexity, and obtaining the filtered concentration values of the candidate marker gases at different time points at each detection part through sliding average filtering.

[0049] The data processing module is used for analyzing the filtered concentration values according to a preset pest and disease related gas database, screening out marker gases, obtaining the vertical distance from the detection part to the trunk axis as the detection-axis distance based on the spatial positions of different detection parts, and obtaining the priority coefficient of each detection part based on the filtered concentration average values of the marker gases at each detection part in the detection time period, which is used for representing the risk degree of pests and diseases.

[0050] The judgment module is used for arranging the priority coefficients of all detection parts in descending order, screening out the detection parts with the top m priority coefficients, taking the detection part with the highest priority as a reference point, setting a critical distance with the reference point as the center, measuring the straight line distances between the other m-1 detection parts and the reference point, comparing the distances with the critical distance one by one, and judging the number of infection points of pests and diseases according to the comparison results.

[0051] Compared with the prior art, the present application has the following beneficial effects:

[0052] The present application dynamically adjusts the size of the filtering window by calculating the concentration variation coefficient and complexity of the candidate marker gases, and then obtains the filtered concentration values through sliding average filtering. This process can flexibly adapt the filtering strength according to the fluctuation characteristics of the gas concentration, effectively filters the false signals caused by instantaneous environmental interference, reduces the noise in the feature data, and provides a more reliable data basis for subsequent marker gas screening and priority coefficient calculation.

[0053] A complete spatial positioning and priority division system is constructed through multiple steps. The detection-axis distance is calculated based on the spatial positions of different detection parts, and the priority coefficient of each detection part is obtained based on the filtered concentration average values of the marker gases, so as to realize the quantitative ordering of the risk degree, screen out the detection parts with the top m priority coefficients, take the detection part with the highest priority as a reference point, set a critical distance with the reference point as the center, measure the detection-axis distances between the other m-1 detection parts and the reference point, compare the distances with the critical distance one by one, and judge the number of infection points of pests and diseases. This process fully combines the spatial position relationship and the risk priority, makes the judgment of the number of infection points more scientific and accurate, avoids the disadvantage that multiple high-concentration points are misjudged as multiple infection points only according to the gas concentration, and accurately distinguishes the independent infection points and the diffusion area. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 The whole method flowchart of the present application is shown in the figure;

[0055] Figure 2 The module composition block diagram of the present application is shown in the figure;

[0056] Figure 3 The fitting diagram of the number of candidate marker gas species and complexity of the present application is shown in the figure;

[0057] Figure 4 The fitting diagram of the mean of concentration variation coefficient and complexity of the present application is shown in the figure;

[0058] Figure 5 The fitting diagram of the mean of filtered concentration and priority coefficient of the present application is shown in the figure;

[0059] Figure 6 The fitting diagram of the distance of detection-axis and priority coefficient of the present application is shown in the figure. DETAILED DESCRIPTION

[0060] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with specific examples.

[0061] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present application should be understood as the common meanings understood by those skilled in the art to which the present application belongs. The terms "first", "second" and similar terms used in the present application do not represent any order, number or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar terms mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "up", "down", "left", "right" and the like only represent relative positional relationships, and when the absolute positions of the described objects change, the relative positional relationships may also change accordingly.

[0062] Example 1:

[0063] Please refer to Figures 1-6 The present application provides a technical solution:

[0064] A tree disease and pest detection method based on electronic nose and hollow structure recognition, the specific steps comprising:

[0065] S1. The hollow structure with the electronic nose is attached to the detection site of the branch, the spatial positions of different detection sites are positioned, and the candidate marker gas of the detection site in the detection time period is collected. The type and concentration value of the candidate marker gas at each time point are extracted, the concentration variation coefficient and complexity are calculated, the number of filtering time points is adjusted accordingly, and the filtered concentration value of the candidate marker gas at different time points at each detection site is obtained after sliding average filtering;

[0066] On the basis of the above embodiment, the hollow structure with the electronic nose is attached to the detection site of the branch, and the spatial positions of different detection sites are positioned. The specific steps are as follows:

[0067] 1) Taking the intersection point of the ground and the main stem as the coordinate origin, a three-dimensional rectangular coordinate system is established, wherein the X-axis points to the side of the tree trunk along the horizontal direction, the Y-axis points upward along the vertical direction of the ground, and the Z-axis points along the horizontal direction perpendicular to the X-axis;

[0068] 2) A small GPS module is installed outside the hollow structure;

[0069] 3) The hollow structure with the electronic nose is closely attached to the detection site of the branch, and the position of the hollow structure is adjusted to make it fully contact with the surface of the branch, so as to avoid positioning deviation caused by looseness;

[0070] 4) The three-dimensional coordinate data of the hollow structure is collected in real time by the positioning module , and the average value is calculated as the spatial coordinates of the detection site after continuous collection for multiple times;

[0071] On the basis of the above embodiment, the candidate marker gas of the detection site in the detection time period is collected, and the type and concentration value of the candidate marker gas at each time point are extracted. The specific steps are as follows:

[0072] 1) According to the type of tree and common types of pests and diseases, the detection time period (such as 24 hours continuously) and the sampling interval (sampling once every 1 hour) are preset, and the detection range and sensitivity of the electronic nose are calibrated;

[0073] 2) After the hollow structure is attached to the detection site and the positioning is completed, the gas collection function of the electronic nose is started, and the gas released by the detection site is adsorbed in real time by the gas sensor array built in the structure;

[0074] 3) Each time the electronic nose system automatically records the current sampling time to form a time stamp, ensuring that the gas data and the sampling time correspond one by one;

[0075] 4) After sampling, the electronic nose analyzes the gas sample using its built-in data analysis module. Based on the sensor array's response characteristics and the sensor's response to the changes in resistance and conductivity, it identifies and outputs candidate marker gases, such as ethanol, ethylene, and indole.

[0076] 5) For each candidate marker gas identified, the sensor's response strength, including voltage signal value and current change, is compared and converted with a preset concentration calibration curve to calculate the concentration value of the gas at the current time point. The concentration calibration curve is obtained by calibrating with a standard gas of known concentration;

[0077] 6) The candidate marker gas types, corresponding concentration values ​​and timestamps extracted at each time point are synchronously stored in the system database to form a raw gas data record table;

[0078] 7) Repeat steps 2-6 throughout the entire detection period according to the preset sampling interval to ensure that complete gas data is collected at each time point until the detection period ends.

[0079] Based on the above embodiment, the concentration of the candidate marker gas during the detection period is normalized, and then the mean of the normalized candidate marker gas concentration is calculated, and the concentration variation coefficient is calculated according to the following formula:

[0080] ;

[0081] ;

[0082] in, is the number of candidate marker gases, For the The concentration variation coefficient of the candidate marker gas, For the The standard deviation of the concentration of the candidate marker gas in the detection time period, For the The mean of the concentrations of the candidate marker gases, is the mean value of the concentration variation coefficient of all candidate marker gases, is the index of the candidate marker gas, ;

[0083] Table 1. Changes in the complexity of candidate marker gases with the number of species and the mean value of the concentration coefficient of variation

[0084]

[0085] According to Table 1, as the number of candidate marker gas species increases from 1 to 15, the average of the concentration variation coefficient increases from 0.2 to 3.0, the complexity increases from 0.6 to 9.0, and the change range of the three is always in a fixed proportion, which conforms to the linear law, and the complexity of the candidate marker gas is positively correlated with the number of species and the average of the concentration variation coefficient.

[0086] According to Figures 3-4 It can be seen that the complexity of the candidate marker gas is positively correlated with the two parameters in a linear manner:

[0087] The fitting line of the complexity of the candidate marker gas and the number of species is a straight line, and the complexity increases linearly with the increase of the number of candidate marker gas species, and the more the number of species, the higher the complexity of the gas composition;

[0088] The fitting line of the complexity of the candidate marker gas and the average of the concentration variation coefficient is a straight line, and the complexity increases linearly with the increase of the average of the concentration variation coefficient, and the higher the concentration variation coefficient, the higher the complexity of the composition.

[0089] On the basis of the above embodiment, the complexity of the candidate marker gas is calculated, and the formula is as follows:

[0090] ;

[0091] Among them, is the complexity of the candidate marker gas, and the complexity is used to evaluate the complexity of the gas composition in combination with the number of species and the average of the concentration variation coefficient of the candidate marker gas, and the greater the complexity, the higher the complexity of the gas composition;

[0092] On the basis of the above, it should be noted that:

[0093] The number of species is the number of candidate marker gases related to tree diseases and pests, and when increases, it directly reflects the aggravation of metabolic disorder of trees caused by diseases and pests, the diversity of gas composition is improved, the complexity increases, therefore, and are positively correlated.

[0094] The average of the concentration variation coefficient is an index for measuring the fluctuation degree of the candidate marker gas at multiple collection times, and when increases, it reflects the rhythm disorder of gas release of trees caused by diseases and pests, and the concentration fluctuation is intensified, and the complexity increases, therefore, and are positively correlated.

[0095] The mean of the number of species and the mean of the coefficient of variation of concentration describe gas composition characteristics from two different dimensions. Both are positively correlated with "gas composition complexity," but they are independent parameters, reflecting the complexity of gas composition from the perspectives of gas composition diversity and concentration volatility, respectively. The two cannot replace each other. Therefore, they can be integrated into a comprehensive indicator that can be quantified and compared through linear combination.

[0096] In summary, the above function form is set to express the functional relationship between complexity and the number of candidate marker gas types and the mean value of the concentration variation coefficient.

[0097] Adjust the filter window size according to the complexity of the candidate marker gas:

[0098] ;

[0099] in, is the number of filtering time points, is the reference value of the number of filtering time points, is the first level threshold of complexity, is the second level threshold of complexity.

[0100] On the basis of the above, it should be noted that:

[0101] By analyzing the complexity of a large number of labeled samples (gas composition data with known health, mild abnormality, and severe abnormality) Analyze and find the natural dividing point:

[0102] Three types of samples were collected (healthy sample set , mildly abnormal sample set ), severely abnormal sample set ), calculate the complexity of each sample separately ;

[0103] statistics 、 、 The distribution range of medium complexity shows obvious "clustering characteristics":

[0104] The complexity is concentrated in the lower range; The complexity is concentrated in the medium range; The complexity is concentrated in the higher range;

[0105] Pick Maximum value and The midpoint between the minimum and the normal value, ensuring healthy and mildly abnormal Values ​​are clearly separated; Similarly, take the maximum value and the minimum value, avoiding the overlap of light and heavy anomalies values.

[0106] On the basis of the above, it needs to be explained that:

[0107] When the complexity is low (i.e. ): There are few gas species in the signal, the concentration fluctuation is gentle, and the noise interference is weak. At this time, a large filter window is not needed, and the reference value can be used to suppress a small amount of noise while accurately preserving the details of the original signal;

[0108] When the complexity is medium (i.e. ): New marker gases appear in the signal, the concentration fluctuation amplitude increases, and the degree of mixing of noise and effective features rises. At this time, a larger window is needed to enhance the noise suppression capability while avoiding excessive smoothing that causes light anomaly features to be hidden;

[0109] When the complexity is high (i.e. ): There are many gas species in the signal, the concentration fluctuation is severe, and the noise and effective features are highly mixed. At this time, a larger window must be used to strongly smooth the noise, ensuring that the extracted core features are stable and reliable, and avoiding that the noise is misjudged as a pest signal.

[0110] The window size increases with the complexity (i.e. ), which conforms to the rule that "the higher the complexity, the more chaotic the signal, the stronger the filtering needed".

[0111] On the basis of the above embodiment, the specific steps of obtaining the filtered concentration value are as follows:

[0112] For each candidate marker gas of each detection part, in its corresponding detection time period, for the concentration value at each time point, the mean value of the concentration values at the nearest time points to the time point is calculated as the filtered concentration value at the time point.

[0113] S2. According to the preset pest and disease associated gas database, analyze the filtered concentration value to screen out the marker gas, obtain the vertical distance between it and the main trunk axis as the detection-axis distance based on the spatial position of different detection parts, and combine the filtered concentration mean value of the marker gas at each detection part in the detection time period to obtain the priority coefficient of each detection part, which is used to represent the degree of pest and disease risk. Before calculating the priority coefficient of each detection part, the detection-axis distance and the filtered concentration mean value are normalized.

[0114] On the basis of the above embodiments, the marker gas is screened according to the preset pest and disease associated gas database, and the specific steps are as follows:

[0115] From the candidate marker gas, the gas matched with the pest and disease gas type in the database is retained;

[0116] The average value of the filtered concentration of these gases in the detection period is calculated, and if the average value falls within the gas concentration range of the corresponding pest and disease in the database, it is listed as a candidate gas;

[0117] For the candidate gas, if the filtered concentration value at more than 3 consecutive time points in the detection period exceeds the preset threshold, it is included in the preselected marker gas set;

[0118] From the preselected marker gas set, the gas with the highest average value of the filtered concentration is selected as the final marker gas.

[0119] On the basis of the above embodiments, based on the spatial position of different detection sites, the perpendicular distance from the trunk central axis is obtained, and the specific steps are as follows:

[0120] Every 50 cm along the upward direction of the trunk, a cross section is set, and the cross section center coordinates of the trunk at different heights are measured;

[0121] Connecting the cross section centers at different heights forms a virtual straight line, which is the trunk central axis;

[0122] Based on the spatial position of different detection sites, the coordinates of each detection site in space are determined , The X-axis coordinate value, Y-axis coordinate value and Z-axis coordinate value of the detection site are respectively determined;

[0123] According to the distance formula from the midpoint of the space geometry to the straight line, the perpendicular distance from the coordinates of each detection site to the trunk central axis is calculated.

[0124] Table 2. Priority coefficient changes with filtered concentration average value, detection-axis distance

[0125]

[0126] According to table 2, as the filtered concentration average value increases from 0.5 to 6.5, the priority coefficient increases from 0.38 to 5.08, and when the detection-axis distance is relatively stable, the priority coefficient increases correspondingly with each increase in the concentration average value, which reflects the positive contribution of the concentration average value to the priority. Therefore, the priority coefficient and the filtered concentration average value are positively correlated.

[0127] As the distance between the detector and the axis decreases from 5.0 to 0.8, the priority coefficient increases. Especially at smaller distances, a small change in distance leads to a more significant increase in the priority coefficient, reflecting that closer distances have a more significant impact on priority. Therefore, the priority coefficient is negatively correlated with the distance between the detector and the axis.

[0128] according to Figures 5-6 It can be seen that the fitting line of the mean concentration after filtering and the priority coefficient is a straight line, which is linearly positively correlated. That is, the larger the mean concentration after filtering, the higher the priority coefficient. The change trends of the two are uniform and synchronized. The mean concentration has a stable positive driving effect on the priority.

[0129] The fitting line of the inspection-axis distance and the priority coefficient is a curve, which shows a nonlinear negative correlation. The smaller the inspection-axis distance, the higher the priority coefficient. When the distance is small, a small change in the distance will cause a more obvious change in the priority coefficient, reflecting the reverse effect of distance on priority and its nonlinear characteristics.

[0130] On the basis of the above embodiment, the priority coefficients of pest and disease risks at different detection locations are obtained according to the filtered average concentration of the marker gas at each detection location during the detection period and the detection-axis distance, and the formula is as follows:

[0131] ;

[0132] in, For the The priority coefficient of the pest and disease risk of each detection part is used to combine the two index parameters of the filtered concentration mean and the detection-axis distance to comprehensively evaluate the pest and disease risk of the detection part. The larger the priority coefficient, the higher the risk of the detection part being damaged by pests and diseases.

[0133] For the The average concentration of the marker gas at each detection location after filtering during the detection period, For the The detection-axis distance of each detection part, is the index of the detection part, , is the number of test sites;

[0134] On the basis of the above, it should be noted that:

[0135] When pests and diseases move in tree branches, they will continuously release specific marker gases. The more active the activity and the higher the population density, the greater the amount of gas released, and the gas concentration around the detection site will also increase accordingly. Therefore, the average concentration of the marker gas after filtering It can directly reflect the activity level of pests and diseases. The greater, the more intense the pest activity in the part, the higher the risk level. Thus, it can be judged that is positively correlated with the priority coefficient.

[0136] The central axis of the tree trunk is the core channel for nutrient and water transport. The closer the branch is to the central axis, the more closely related it is to the trunk in terms of physiology. If the part is affected by pests and diseases, not only will it be easy to quickly invade the trunk and affect the overall metabolism, but it will also accelerate the spread of the disease due to its proximity to the core channel. Conversely, the farther the part is from the central axis, the greater the threat to the overall tree. Therefore, the central-axis distance is negatively correlated with the priority coefficient.

[0137] The function uses addition to stack the two items, which can achieve comprehensive evaluation of two independent indicators:

[0138] When and change at the same time (increase at the same time decrease), the positive contribution of the two items will be stacked, making more significantly reflect the trend of risk increase; When the change direction of the two is opposite (increases but

[0139] increases), the additive form can balance the influence of the two through the adjustment of the weight coefficient, avoiding the one-sidedness of a single indicator on risk assessment. This linear stacking form is simple and intuitive, and can flexibly reflect the relative importance of the two parameters in risk assessment, meeting the actual needs of "comprehensive multiple indicators to judge risk".

[0140] Based on the above, the function relationship between the priority coefficient and the filtered concentration average and the central-axis distance is expressed as follows.

[0141] In the formula, is the weight coefficient of the filtered concentration average of the detection part marker gas,

[0142] is the weight coefficient of the central-axis distance. The filtered concentration average of the marker gas is a core indicator that directly reflects the intensity of pest activity. The presence and activity of pests and diseases will directly lead to an increase in the concentration of marker gases, and the concentration is strongly correlated with the population density and degree of harm of pests and diseases, which is the "direct evidence" of risk judgment, and the central-axis distance

[0143] ​​​​​More embodied is the "potential impact range" of risk, the closer to the trunk of the site risk spread harm more, but this effect needs to be based on "there are pest activities", if a part of the extremely low, almost no sign of gas release, even very small, the actual risk is low. Therefore, as direct evidence of risk should be given more weight, so, on the basis of , let ;

[0144] As an embodiment, the value range of 0.5-1.0, the value range of 0-0.5, the specific value is set by the technical personnel according to the actual situation, not limited here.

[0145] S3. The priority coefficients of all detection sites are arranged in descending order, and the detection sites ranked in the top m are selected. The highest priority detection site is taken as a reference point, a critical distance is set around the reference point, the straight-line distance between the other m-1 detection sites and the reference point is measured as the detection-reference distance, and the detection-reference distance is compared with the critical distance one by one. According to the comparison result, the number of infection points of pests is judged.

[0146] On the basis of the above embodiment, the priority coefficients of all detection sites are arranged in descending order, and the detection sites ranked in the top m are selected. The specific steps are as follows:

[0147] Set the sorting rule:

[0148] Rule one: sort according to the priority coefficient from large to small;

[0149] Rule two: if there are multiple detection sites with the same priority coefficient, sort according to the average concentration of the filtered marker gas from high to low, and the one with higher average concentration is ranked in front;

[0150] According to rule one, all detection sites are arranged in descending order of priority coefficient to get the preliminary sorting result;

[0151] Check the preliminary sorting result. If there are detection sites with the same priority coefficient, extract the average concentration of the filtered marker gas from these detection sites, and sort them according to rule two for the second time to adjust the order, and select the top m detection sites.

[0152] On the basis of the above embodiment, the highest priority detection site is taken as a reference point, a critical distance is set around the reference point, the straight-line distance between the other m-1 detection sites and the reference point is measured as the detection-reference distance, and the specific steps are as follows:

[0153] From the screened first m detection sites, the first ranked detection site, i.e. the highest priority detection site, is selected as a reference point, and its spatial coordinates in a three-dimensional rectangular coordinate system are called , The X-axis coordinate value, Y-axis coordinate value and Z-axis coordinate value of the reference point are respectively called ,

[0154] In combination with the biological characteristics (adult activity range, larval diffusion radius) of the target pest, the growth characteristics (branch diameter, branch density) of the tree trunk, and the historical detection data, the specific value of the critical distance is set, for example, for a small activity range of the trunk borer pest, the critical distance can be set to 5-10 cm; for the disease that is easy to spread through airflow, the critical distance can be appropriately expanded to 15-20 cm;

[0155] From the screened first m detection sites, the spatial coordinates of the remaining m-1 detection sites except the reference point are extracted, and are respectively called , and are one-to-one associated with the corresponding detection site identifiers, The X-axis coordinate value, Y-axis coordinate value and Z-axis coordinate value of the first detection site are respectively called

[0156] According to the distance formula between two points in a three-dimensional space, the straight-line distance between each detection site and the reference point is calculated as the detection-reference distance, and the detection-reference distance , wherein, is the straight-line distance between the first detection site and the reference point, .

[0157] On the basis of the above embodiment, the detection-reference distance is compared with the critical distance one by one, and according to the comparison result, the number of infection points of the pest is judged, and the specific steps are as follows:

[0158] The detection-reference distance of the m-1 detection sites is compared with the set critical distance one by one, the number of detection sites with detection-reference distance > critical distance is counted, and is called ;

[0159] If , i.e. all detection-reference distances are ≤ critical distance, it is determined that the infection point of the pest on the tree is 1;

[0160] If , i.e. there is at least one detection-reference distance > critical distance, it is determined that the infection point of the pest on the tree is multiple.

[0161] Please refer to Figure 2 , the present application also provides a technical solution:

[0162] A tree disease and pest detection system based on an electronic nose and hollow structure recognition, the system is used to execute any of the above-mentioned tree disease and pest detection methods based on an electronic nose and hollow structure recognition, comprising:

[0163] A data acquisition module is used to attach the hollow structure with the built-in electronic nose to the detection part of the branch, position the spatial position of different detection parts, and collect the candidate marker gas of the detection part in the detection time period, extract the type and concentration value of the candidate marker gas at each time point, calculate the concentration variation coefficient and complexity, and adjust the number of filtering time points accordingly, and obtain the filtered concentration value of the candidate marker gas at each detection part at different time points through sliding average filtering;

[0164] A data processing module is used to analyze the filtered concentration value according to the preset disease and pest associated gas database to screen out the marker gas, obtain the perpendicular distance from the detection axis as the detection axis distance based on the spatial position of different detection parts, and obtain the priority coefficient of each detection part based on the filtered concentration average value of the marker gas at each detection part in the detection time period, which is used to represent the disease and pest risk degree.

[0165] A judgment module is used to arrange the priority coefficients of all detection parts in descending order, screen out the detection parts with the top m priority coefficients, take the detection part with the highest priority as the reference point, set a critical distance with the reference point as the center, measure the straight line distance between the other m-1 detection parts and the reference point, and compare them one by one with the critical distance, and according to the comparison result, judge the number of infection points of the disease and pest.

[0166] The above formulas are all de-dimensioned to calculate their numerical values. The formula is obtained by software simulation of a large amount of data to obtain a formula closest to the actual situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0167] The above embodiments can be realized all or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized in the form of a computer program product in whole or in part. Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0168] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, and may be located in one place, or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiment of the present application according to actual needs.

[0169] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A tree disease and pest detection method based on an electronic nose and hollow structure identification, characterized in that, The specific steps include: S1. Attach the hollow structure containing the electronic nose to the detection area of ​​the branch, locate the spatial position of different detection areas, and collect candidate marker gases at the detection areas during the detection period. Extract the type and concentration of the candidate marker gases at each time point, calculate the concentration coefficient of variation and complexity, adjust the number of filtering time points accordingly, and perform sliding average filtering to obtain the filtered concentration values ​​of the candidate marker gases at each detection area at different time points. S2. Analyze the filtered concentration values ​​based on a preset pest-associated gas database to identify marker gases. Based on the spatial location of different detection locations, the vertical distance between each location and the central axis of the trunk is calculated as the detection-axis distance. Combined with the average filtered concentration of the marker gas at each detection location over the detection period, the priority coefficient for each detection location is calculated to represent the degree of pest risk. S3. Arrange the priority coefficients of all test sites in descending order, select the top m test sites with the highest priority coefficients, use the highest priority test site as the reference point, set a critical distance with the reference point as the center, measure the straight-line distance between the other m-1 test sites and the reference point as the test-to-reference distance, and compare each test-to-reference distance with the critical distance. Based on the comparison results, determine the number of infected sites of the pest or disease; Normalize the concentration of the candidate marker gas during the detection period, then calculate the mean of the normalized candidate marker gas concentration, and calculate the concentration variation coefficient and the complexity of the candidate marker gas according to the following formula: wherein, a complexity of the candidate marker gas, a number of species of the candidate marker gas, a concentration of the candidate marker gas, a coefficient of variation of the concentration of the candidate marker gas, a standard deviation of the concentration of the candidate marker gas, a standard deviation of the concentration of the candidate marker gas over the detection time period, a mean of the concentration of the candidate marker gas, a mean of the coefficient of variation of the concentration of all candidate marker gases, a mean of the coefficient of variation of the concentration of all candidate marker gases, an index of the candidate marker gas, ; Adjust the filter window size according to the complexity of the candidate marker gas: wherein is a number of filter time points, is a reference value for the number of filter time points, is a first hierarchical threshold value for the complexity, is a second hierarchical threshold value for the complexity. 2.The tree disease and pest detection method based on the electronic nose and hollow structure recognition of claim 1, wherein, The specific steps to obtain the filtered concentration value are as follows: For each candidate marker gas of each detection part, in its corresponding detection time period, for the concentration value at each time point, the average of the concentration values at the time points closest to the time point is calculated as the filtered concentration value at the time point. For each candidate marker gas of each detection part, in its corresponding detection time period, for the concentration value at each time point, the average of the concentration values at the time points closest to the time point is calculated as the filtered concentration value at the time point. 3.The tree disease and pest detection method based on the electronic nose and hollow structure recognition of claim 2, characterized in that, The marker gases are screened out based on the preset pest-related gas database. The specific steps are as follows: From the candidate marker gases, retain the gases that match the types of pest gases in the database; Calculate the filtered mean concentration of these gases during the detection period. If the mean falls within the gas concentration range corresponding to the pests and diseases in the database, the gas is listed as a candidate gas. For a gas to be selected, if its filtered concentration value exceeds the preset threshold at more than three consecutive time points during the detection period, it will be included in the pre-selected marker gas set; From the preselected marker gas set, the gas with the highest average concentration after filtering is selected as the final marker gas. 4.The tree disease and pest detection method based on the electronic nose and hollow structure recognition of claim 1, wherein, Based on the spatial position of different detection parts, the vertical distance between them and the central axis of the trunk is obtained. The specific steps are as follows: Set up a cross section every 50 cm along the trunk upward direction, and measure the coordinates of the center of the cross section at different heights of the trunk; Connect the centers of the cross sections at each height to form a virtual straight line, which is the central axis of the trunk; Based on the spatial positions of different detection parts, determine the coordinates of each detection part in space; According to the distance formula from the midpoint of spatial geometry to the straight line, the vertical distance from the coordinates of each detection part to the central axis of the trunk is calculated. 5.The tree disease and pest detection method based on electronic nose and hollow structure recognition of claim 4, characterized in that, According to the filtered mean concentration of the marker gas at each detection location during the detection period and the detection-axis distance, the priority coefficient of the pest risk at different detection locations is obtained according to the following formula: wherein, is a priority coefficient of the jth detection site for detecting a pest risk, is a filtered concentration average of the kth detection site of the marker gas in the detection time period, is a detection axis distance of the jth detection site, is an index of the detection site, , is a number of detection sites;​​​ In the formula, is the weight coefficient of the average value of the filtered concentration of the site marker gas, is the weight coefficient of the distance between the detection axes, and is the weight coefficient of the distance between the detection axes, and ; The priority coefficients of all detection positions are arranged in descending order, and the detection positions with the top m priority coefficients are screened out, and the specific steps are as follows: Set the sorting rules: Rule one: sort according to the priority coefficient from large to small; Rule two: if there are multiple detection positions with the same priority coefficient, sort according to the average concentration of the marker gas after filtering, and the one with the higher average concentration is placed in front; According to rule one, all detection positions are arranged in descending order according to the priority coefficient, and the preliminary sorting result is obtained; Check the preliminary sorting result, if there are detection positions with the same priority coefficient, extract the average concentration of the marker gas after filtering from these detection positions, and sort them according to rule two, adjust the order, and select the top m detection positions. 6.The tree disease and pest detection method based on the electronic nose and hollow structure recognition of claim 5, wherein, Compare the detection-base distance with the critical distance one by one, and judge the number of infection points of pests and diseases according to the comparison result, and the specific steps are as follows: The detection base distance is compared with the set critical distance one by one, and the number of detection sites with detection base distance > critical distance is counted, denoted as ; If If all the distances are less than or equal to the critical distance, the infection point on the tree is determined to be one. If If there is at least one detection-base distance greater than the critical distance, it is determined that the infection point on the tree is multiple.

7. A tree disease and pest detection system based on electronic nose and hollow structure recognition, the system is used to perform the tree disease and pest detection method based on electronic nose and hollow structure recognition in any one of claims 1-6, characterized in that, It includes: Data acquisition module, used to paste the hollow structure with electronic nose on the detection position of branch, locate the spatial position of different detection positions, and collect the candidate marker gas of detection position in the detection period, extract the type and concentration value of candidate marker gas at each time point, calculate the concentration variation coefficient and complexity, adjust the number of filtering time points accordingly, and get the filtered concentration value of candidate marker gas at different time points at each detection position after moving average filtering; Data processing module, used to analyze the filtered concentration value according to the preset pest and disease associated gas database to screen out the marker gas, based on the spatial position of different detection positions, get the vertical distance between the detection position and the trunk axis as the detection-axis distance, and combine the filtered concentration average of the marker gas at each detection position in the detection period, get the priority coefficient of each detection position, which is used to represent the risk degree of pests and diseases; Judgment module, used to arrange the priority coefficients of all detection positions in descending order, and screen out the detection positions with the top m priority coefficients, take the detection position with the highest priority as the reference point, set the critical distance with the reference point as the center, measure the straight line distance between the other m-1 detection positions and the reference point, compare them with the critical distance one by one, and judge the number of infection points of pests and diseases according to the comparison result.

Images