Distributed forestry seedling raising spraying mechanism intelligent management and control system

Abstract

The application belongs to the field of seedling spraying control, and relates to a data analysis technology, which is used to solve the problem that the prior art cannot identify the growth stage of a nursery and adaptively adjust the spraying parameters according to the growth stage, and specifically relates to a distributed forestry seedling spraying mechanism intelligent management and control system, which comprises an intelligent management and control platform, wherein the intelligent management and control platform is communicatively connected with a growth identification module, a spraying control module, a growth evaluation module, a fault detection module and a database; the growth identification module is used for identifying and analyzing the growth state of the forestry nursery; and the spraying control module is used for automatically controlling the spraying mechanism of the forestry seedling according to irrigation parameters; the application realizes accurate irrigation of the seedling area in sections, effectively improves the water resource utilization rate, ensures the uniformity of seedling growth through dynamic matching of the growth state and the irrigation parameters, and significantly improves the system operation reliability through a real-time fault detection mechanism, thereby reducing the loss of seedlings caused by equipment abnormalities.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of seedling spraying control, and relates to data analysis technology, in particular to an intelligent management and control system for a distributed forestry seedling spraying mechanism. BACKGROUND

[0002] The intelligent management and control system for the distributed forestry seedling spraying mechanism is a modern forestry seedling management solution based on the Internet of Things, big data and artificial intelligence technology, aiming to realize precise and intelligent spraying management of distributed seedling bases.

[0003] The patent with the publication number CN109874576B discloses a full-automatic spraying control system for sprout planting houses, which can automatically control the spraying time and duration of seed soaking, germination and seedling raising, and the nozzles form a fan-shaped micro-spraying downward, realizing uniform scattering of the spraying water. However, the system cannot identify the growth stage of sprouts and adaptively adjust the spraying parameters according to the growth stage, and cannot dynamically optimize the spraying parameters according to the real-time monitoring of the growth state, resulting in that the cultivation effect of sprouts cannot be guaranteed.

[0004] In view of the above technical problems, the present application provides a solution. SUMMARY

[0005] The present application aims to provide an intelligent management and control system for a distributed forestry seedling spraying mechanism, which solves the problem that the prior art cannot identify the growth stage of a nursery and adaptively adjust the spraying parameters according to the growth stage.

[0006] The present application aims to provide an intelligent management and control system for a distributed forestry seedling spraying mechanism, which solves the problem that the prior art cannot identify the growth stage of a nursery and adaptively adjust the spraying parameters according to the growth stage.

[0007] The present application can be achieved by the following technical solutions:

[0008] The intelligent management and control system for the distributed forestry seedling spraying mechanism comprises an intelligent management and control platform, which is communicatively connected with a growth identification module, a spraying control module, a growth evaluation module, a fault detection module and a database.

[0009] The growth identification module is used to identify and analyze the growth state of the forestry nursery: the coverage area of the forestry seedling node is divided into a plurality of analysis areas, the root stem growth deviation coefficient and the leaf growth deviation coefficient of the analysis area are obtained, and whether the uniformity of the nursery growth of the analysis area meets the requirements is determined through the root stem growth deviation coefficient and the leaf growth deviation coefficient; when the requirements are met, the irrigation parameters of the analysis area are retrieved through the database.

[0010] The spraying control module is used for automatically controlling the spraying mechanism of the forestry seedling raising according to the irrigation parameters.

[0011] The growth evaluation module is used for evaluating and analyzing the growth state of the forestry seedling raising, obtaining a growth analysis coefficient of an analysis area, and determining whether the growth state of the forestry nursery of the analysis area meets the requirements through the growth analysis coefficient.

[0012] The fault detection module is used for detecting and analyzing the faults of the spraying mechanism.

[0013] Further, the obtaining process of the root stem growth deviation coefficient and the leaf growth deviation coefficient comprises: regularly taking images of the forestry nursery in the analysis area, magnifying the obtained images into pixel grid images and performing gray scale transformation and marking the images as analysis images, segmenting the root stem area and the leaf area in the analysis images through a binary method and extracting the length value of a single root stem and the area value of a single leaf, and performing variance calculation on the length values of all root stems to obtain the root stem growth deviation coefficient and performing variance calculation on the area values of all leaves to obtain the leaf growth deviation coefficient.

[0014] Further, the specific process of determining whether the growth uniformity of the nursery of the analysis area meets the requirements comprises: calling the root stem growth deviation threshold and the leaf growth deviation threshold through a database, comparing the root stem growth deviation coefficient and the leaf growth deviation coefficient of the analysis area with the root stem growth deviation threshold and the leaf growth deviation threshold respectively, and determining that the growth uniformity of the nursery of the analysis area meets the requirements if the root stem growth deviation coefficient is less than the root stem growth deviation threshold and the leaf growth deviation coefficient is less than the leaf growth deviation threshold; otherwise, determining that the growth uniformity of the nursery of the analysis area does not meet the requirements, generating a spraying optimization signal, and sending the spraying optimization signal to the mobile terminal of the manager.

[0015] Further, the calling process of the irrigation parameters comprises: summing and averaging the length values of all root stems to obtain a root stem growth performance value, summing and averaging the area values of all leaves to obtain a leaf growth performance value, and calling corresponding irrigation parameters from the database through the root stem growth performance value and the leaf growth performance value, wherein the irrigation parameters comprise a soil humidity threshold, a single irrigation duration, an irrigation water pressure, and a fertilizer solution concentration.

[0016] Further, the specific process of automatically controlling the spraying mechanism of the forestry seedling raising by the spraying control module comprises: obtaining a soil humidity value in the analysis area in real time, comparing the soil humidity value with the soil humidity threshold in the irrigation parameters corresponding to the analysis area, determining that the analysis area does not have a spraying feature if the soil humidity value is greater than the soil humidity threshold, determining that the analysis area has a spraying feature if the soil humidity value is less than or equal to the soil humidity threshold, and controlling the spraying mechanism through the single irrigation duration, the irrigation water pressure, and the fertilizer solution concentration.

[0017] Further, the growth analysis coefficient obtaining process comprises: extracting the chlorophyll content of the leaf area in the analysis image, summing up the chlorophyll content of all the leaf areas in the analysis image to obtain the growth evaluation value of the analysis area, after the planting of the forestry nursery in the analysis area is completed, establishing a rectangular coordinate system with time as the X-axis and the growth evaluation value as the Y-axis, marking the analysis points in the rectangular coordinate system with the collection time of the analysis image as the horizontal coordinate and the growth evaluation value corresponding to the analysis image as the vertical coordinate, connecting all the analysis points from left to right to obtain the analysis curve, calling the standard curve of the forestry nursery through the database and translating it into the rectangular coordinate system of the analysis curve, marking the area value of all the closed regions formed by the analysis curve and the standard curve as the growth analysis value, marking the area value of the closed region formed by the standard curve, the X-axis, the Y-axis and the intercept line segment as the growth measurement value, and marking the ratio of the growth analysis value to the growth measurement value as the growth analysis coefficient.

[0018] Further, the specific process of determining whether the growth state of the forestry nursery in the analysis area meets the requirements comprises: obtaining the growth analysis threshold value through the database, comparing the growth analysis coefficient with the growth analysis threshold value, if the growth analysis coefficient is less than the growth analysis threshold value, it is determined that the growth state of the forestry nursery in the analysis area meets the requirements, if the growth analysis coefficient is greater than or equal to the growth analysis threshold value, it is determined that the growth state of the forestry nursery in the analysis area does not meet the requirements, a parameter optimization signal is generated and sent to the mobile terminal of the management personnel.

[0019] Further, the specific process of the fault detection module for detecting and analyzing the fault of the spraying mechanism comprises: marking the spraying process of the spraying mechanism as a detection process, dividing the detection process into a plurality of detection periods, obtaining the flow fluctuation value and the water pressure fluctuation value of the detection period, obtaining the flow fluctuation threshold value and the water pressure fluctuation threshold value through the database, comparing the flow fluctuation value and the water pressure fluctuation value with the flow fluctuation threshold value and the water pressure fluctuation threshold value respectively, if the flow fluctuation value is less than the flow fluctuation threshold value and the water pressure fluctuation value is less than the water pressure fluctuation threshold value, it is determined that the nozzle does not have a fault feature, otherwise, it is determined that the nozzle has a fault feature, a fault processing signal is generated and sent to the mobile terminal of the management personnel.

[0020] Further, the obtaining process of the flow fluctuation value and the water pressure fluctuation value comprises: obtaining the spraying liquid flow and the water pressure of the nozzle in the detection period and marking them as the flow value and the pressure value respectively, marking the absolute value of the difference between the flow value of the detection period and the flow value of the previous detection period as the flow fluctuation value, and marking the difference between the maximum value and the minimum value of the pressure value in the detection period as the water pressure fluctuation value.

[0021] The present application has the following advantages:

[0022] 1、The application realizes the sub-area precise irrigation of the seedling area, effectively improves the water resource utilization rate; through the dynamic matching of the growth state and the irrigation parameter, the uniformity of the seedling growth is ensured; the real-time fault detection mechanism significantly improves the system operation reliability, reduces the seedling loss caused by equipment abnormalities;

[0023] 2、The application can accurately identify the growth difference degree of the root and stem and the leaf in the nursery area, timely trigger the spraying optimization instruction, avoid the local area irrigation excess or deficiency caused by uneven growth, and the management personnel can quickly locate the problem area and adjust the irrigation strategy according to the spraying optimization signal, so as to improve the seedling survival rate and the growth consistency;

[0024] 3、The application realizes the dynamic optimization of the irrigation parameter based on the actual growth state of the plant, through the double quantitative analysis of the root and stem and the leaf growth data, ensures that the irrigation intensity, frequency and nutrient supply are accurately matched with the current development stage of the seedling. This data-driven parameter calling mode effectively solves the problem of rigid parameter setting of the traditional system, reduces the invalid consumption of water resources and fertilizers while ensuring the irrigation effect;

[0025] 4、The application solves the problem of lack of dynamic basis for adjusting the spraying parameter in the prior art, realizes the quantitative evaluation mechanism based on the comparison of the growth curve. For example, when it is found that the growth analysis coefficient of a certain area abnormally rises in the middle period of seedling, the irrigation water pressure or the fertilizer solution ratio of the area can be adjusted in time, so as to avoid the extension of the seedling period caused by growth lag, and effectively ensure the overall growth uniformity of the nursery. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0027] Figure 1 The system block diagram of the first embodiment of the present application is shown in the figure;

[0028] Figure 2 The method flow chart of the second embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0029] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] In existing technologies, traditional forestry seedling sprinkler systems mostly adopt a fixed program control mode, which cannot dynamically adjust irrigation parameters according to the seedling growth stage. Although the patent with publication number CN109874576B achieves automated sprinkler control, it lacks the ability to identify the real-time growth status of plants, resulting in insufficient matching between the sprinkler volume and actual growth needs. In large-scale seedling production scenarios, seedlings in different areas often exhibit uneven growth due to differences in microenvironment, and existing systems cannot effectively identify these differences and make targeted adjustments, easily leading to water waste or localized insufficient irrigation.

[0031] To address these issues, researchers discovered that the dynamic correlation between growth status and irrigation demand is key to precise regulation. Analysis revealed that the uniformity of root and leaf growth serves as a core indicator for irrigation decisions. Based on this, a method was proposed to quantify growth deviations using image processing technology and establish a multi-module collaborative closed-loop management system. The system first segments the nursery area for local state analysis, then combines real-time soil data to implement differentiated irrigation, and finally evaluates the regulatory effect through growth curve comparison.

[0032] Example 1: As Figure 1 As shown, the intelligent control system for the spraying mechanism of distributed forestry seedling cultivation includes an intelligent control platform, which is connected to a growth recognition module, a spraying control module, a growth assessment module, a fault detection module, and a database.

[0033] The growth recognition module is used for recognizing and analyzing the growth state of the forestry nursery: the coverage area of the forestry seedling node is divided into a plurality of analysis areas, image shooting is performed on the forestry nursery in the analysis area at regular intervals, the image obtained by shooting is enlarged into a pixel grid image and is subjected to gray scale transformation and is marked as an analysis image, the root stem area and the leaf area in the analysis image are segmented and the length value of a single root stem and the area value of a single leaf are extracted by using a binary method, the length values of all root stems are subjected to variance calculation to obtain a root stem growth deviation coefficient, and the area values of all leaves are subjected to variance calculation to obtain a leaf growth deviation coefficient; the root stem growth deviation threshold and the leaf growth deviation threshold are called from the database, the root stem growth deviation coefficient and the leaf growth deviation coefficient of the analysis area are compared with the root stem growth deviation threshold and the leaf growth deviation threshold respectively: if the root stem growth deviation coefficient is less than the root stem growth deviation threshold and the leaf growth deviation coefficient is less than the leaf growth deviation threshold, it is determined that the uniformity of the growth of the nursery in the analysis area meets the requirements, the length values of all root stems are summed and averaged to obtain a root stem growth performance value, the area values of all leaves are summed and averaged to obtain a leaf growth performance value, the corresponding irrigation parameters are called from the database through the root stem growth performance value and the leaf growth performance value, the irrigation parameters include the soil humidity threshold, the single irrigation time length, the irrigation water pressure and the fertilizer liquid concentration; otherwise, it is determined that the uniformity of the growth of the nursery in the analysis area does not meet the requirements, a spraying optimization signal is generated and the spraying optimization signal is sent to the mobile terminal of the management personnel.

[0034] The pixel grid image refers to a grid image obtained by enlarging an original image to a size corresponding to the actual physical size of each pixel point, which can be realized by using an image interpolation algorithm, such as bilinear interpolation or bicubic interpolation, for improving the resolution of image details. The gray scale transformation refers to a processing process of converting a color image into a gray scale image, which can be realized by using a weighted average method to convert the RGB channel value into a single gray scale value, for eliminating color interference and simplifying subsequent segmentation operations. The binary method refers to a segmentation method of converting a gray scale image into a black-and-white binary image, which can be realized by using a fixed threshold method or an adaptive threshold method, such as the Otsu algorithm, for distinguishing the root stem, the leaf and the background area. The variance calculation refers to quantitative analysis of the dispersion degree of a plurality of sample data, which can be realized by using a variance formula in statistics, for measuring the growth consistency of the root stem length and the leaf area of the nursery in the area.

[0035] Specifically, the growth data of the forestry nursery in the analysis area is obtained through periodic image acquisition. After the captured image is enlarged and processed by grayscale, an analysis image is formed, and the morphological characteristics of the rhizome and leaf are extracted by using binary segmentation technology. The length value of each rhizome and the area value of the leaf are independently measured, and then the rhizome growth deviation coefficient and the leaf growth deviation coefficient are obtained by calculating the population variance. These two coefficients respectively reflect the discrete degree of the rhizome length distribution and the uniformity of the leaf area distribution in the area, and provide quantitative basis for subsequent growth uniformity judgment. For example, when the rhizome length variance of a certain analysis area is large, it indicates that there is a significant difference in the root development of the seedling in the area, and the irrigation strategy needs to be adjusted accordingly.

[0036] The rhizome growth deviation coefficient refers to the value obtained by calculating the variance of all rhizome length values, which can be specifically realized by calculating the variance of the rhizome length extracted by image segmentation technology, and is used to quantify the discrete degree of rhizome growth. The leaf growth deviation coefficient refers to the value obtained by calculating the variance of all leaf area values, which can be specifically realized by calculating the variance of the leaf area extracted by image grayscale conversion, and is used to quantify the uniformity of leaf growth. The spray optimization signal refers to the control instruction triggered when the growth uniformity is not up to standard, which can be specifically realized by sending an alarm message to a preset terminal through a mobile communication module, and is used to prompt manual intervention to adjust the irrigation strategy.

[0037] Specifically, the rhizome growth deviation threshold and the leaf growth deviation threshold corresponding to different nursery varieties are pre-stored in the database. In the judgment process, the rhizome growth deviation coefficient calculated in real time is compared with the corresponding threshold value. If both coefficients are lower than the threshold value, it is determined that the growth uniformity is up to standard. If any coefficient exceeds the threshold value, the spray optimization signal is triggered. The signal is transmitted to the terminal of the management personnel through the mobile communication network, for example, it can be set as a short message or an application program push notification, thereby realizing instant feedback of abnormal state.

[0038] The rhizome growth performance value refers to a quantitative index obtained by calculating the arithmetic mean of all rhizome length values in the analysis area, which can be specifically realized by measuring the pixel length of the rhizome area extracted by image segmentation technology and converting it into actual length units. This value is used to reflect the average growth level of the rhizome in the area. The leaf growth performance value refers to a quantitative index obtained by calculating the arithmetic mean of all leaf area values in the analysis area, which can be specifically realized by calculating the pixel area of the leaf area extracted by image processing algorithm and converting it into actual area units. This value is used to reflect the average growth state of the leaf in the area. The irrigation parameter refers to a set of preset control parameters stored in the database, which can be specifically realized by using the mapping relationship established by the correlation analysis of historical growth data and irrigation effect. Precise control is realized by matching the current growth performance value with the historical optimal parameter combination.

[0039] Specifically, when the nursery growth uniformity of the analysis area meets the requirements, the system automatically performs the irrigation parameter retrieval operation. First, the collected root length data set is subjected to arithmetic mean operation, for example, the root length of 50 seedlings in the area is added and divided by 50 to obtain a value representing the overall root development level. The same processing is performed on the leaf area data set, for example, the projected area of each leaf is converted to square centimeters and the mean value is taken. The two growth performance values are input into the database query module, which pre-stores the optimal irrigation parameter combinations corresponding to different growth stages. For example, when the root growth performance value is in the 10-15 cm interval and the leaf growth performance value is in the 20-25 cm interval, the system automatically matches the corresponding soil moisture threshold value, irrigation time, and other parameter set.

[0040] The spraying control module is used to automatically control the spraying mechanism for forestry seedling raising: the soil moisture value in the analysis area is obtained in real time, and the soil moisture value is compared with the soil moisture threshold value in the irrigation parameters corresponding to the analysis area: if the soil moisture value is greater than the soil moisture threshold value, it is determined that the analysis area does not have the spraying feature; if the soil moisture value is less than or equal to the soil moisture threshold value, it is determined that the analysis area has the spraying feature, and the spraying mechanism is controlled to spray through the single irrigation time, irrigation water pressure, and fertilizer solution concentration.

[0041] The soil moisture threshold value is a pre-set critical humidity value for determining whether to start spraying, which can be realized by real-time data collection by the soil moisture sensor and dynamic comparison with the pre-set threshold value, and the threshold value is set based on the growth requirements of different seedling varieties. The single irrigation time refers to the time length of each spraying operation, which can be realized by a timing module combined with electromagnetic valve control, for accurately regulating the irrigation water volume. The irrigation water pressure refers to the pressure value of the liquid flow in the pipeline during spraying, which can be adjusted by a pressure sensor and a variable frequency water pump linkage to ensure uniformity of spraying coverage. The fertilizer solution concentration refers to the proportion of nutrients added in the irrigation water, which can be dynamically adjusted by a proportional valve and a fertilizer solution mixing device to meet the nutritional requirements of different growth stages.

[0042] Specifically, when the soil moisture sensor detects that the real-time humidity of a certain area is lower than the pre-set threshold value, the system automatically triggers the spraying instruction, controls the spraying time, water pressure, and fertilizer solution ratio according to the irrigation parameters corresponding to the area. For example, when the humidity is detected to be insufficient, the controller starts the electromagnetic valve and synchronously adjusts the variable frequency water pump output pressure, while the fertilizer solution mixing device injects nutrients at the set ratio, until the pre-set irrigation time is reached and the system is automatically turned off. The whole process does not require manual intervention, realizing precise irrigation control.

[0043] The growth evaluation module is used for evaluating and analyzing the growth state of forestry seedling cultivation: the chlorophyll content of the leaf area in the analysis image is extracted, the chlorophyll content of all leaf areas in the analysis image is summed and averaged to obtain the growth evaluation value of the analysis area, after the planting of the analysis area in the forestry nursery is completed, a rectangular coordinate system is established with time as the X axis and the growth evaluation value as the Y axis, the collection time of the analysis image is taken as the horizontal coordinate and the growth evaluation value corresponding to the analysis image is taken as the vertical coordinate in the rectangular coordinate system, the analysis points are marked in the rectangular coordinate system, all the analysis points are connected from left to right to obtain an analysis curve, the standard curve of the forestry nursery is called from the database and translated into the rectangular coordinate system of the analysis curve, the area value of all closed regions formed by the analysis curve and the standard curve is marked as the growth analysis value, a vertical line is drawn from the rightmost endpoint of the standard curve to the X axis to obtain an intercept line segment, the area value of the closed region formed by the standard curve, the X axis, the Y axis and the intercept line segment is marked as the growth measurement value, the ratio of the growth analysis value to the growth measurement value is marked as the growth analysis coefficient, the growth analysis threshold is obtained through the database, the growth analysis coefficient is compared with the growth analysis threshold: if the growth analysis coefficient is less than the growth analysis threshold, it is determined that the growth state of the forestry nursery in the analysis area meets the requirements; if the growth analysis coefficient is greater than or equal to the growth analysis threshold, it is determined that the growth state of the forestry nursery in the analysis area does not meet the requirements, a parameter optimization signal is generated and sent to the mobile terminal of the management personnel.

[0044] The chlorophyll content refers to the concentration of photosynthesis-related pigments in the leaves, which can be realized by using spectral analysis technology to measure the reflectivity of the leaf area and converting it into a chlorophyll index, which is used to quantify the photosynthetic capacity of plants. The growth evaluation value refers to an index that reflects the overall growth state of the nursery in the region through the average value of the chlorophyll content, which can be realized by automatically calculating the chlorophyll distribution data through image processing algorithms and taking the average value, which is used to establish a dynamic growth trend model. The standard curve refers to a pre-stored benchmark curve that reflects the change of the evaluation value with time under ideal growth conditions, which can be realized by fitting a polynomial function curve through historical planting data, which is used to provide a reference system for comparing the growth state. The area value of the closed region refers to the area of the overlapping region formed by the analysis curve and the standard curve in the coordinate system, which can be realized by using integral algorithm or grid segmentation method to calculate the geometric area of the enclosed region between the curves, which is used to quantify the deviation degree of actual growth from ideal state.

[0045] Specifically, after the completion of nursery planting, the average chlorophyll content at each time point is taken as the growth evaluation value to construct a time series curve. After spatially superimposing the curve with the pre-stored standard growth curve in the database, the area of the difference region formed between the two curves is calculated, and then it is proportionally converted with the total area covered by the standard curve to finally obtain the quantitative coefficient representing the pros and cons of the growth state. For example, when the actual growth curve completely fits the standard curve, the difference area is zero, and the growth analysis coefficient reaches the optimal value; when the actual growth lags behind or leads, the difference area increases, resulting in the increase of the coefficient, triggering the parameter optimization mechanism.

[0046] The growth analysis coefficient refers to the ratio of the area value of all closed regions formed by the analysis curve and the standard curve to the growth measurement value. Specifically, the chlorophyll content of the leaf area can be extracted using image processing algorithms, and the analysis curve can be constructed by combining the time series growth evaluation value, and the area comparison calculation with the standard curve can be realized. This coefficient is used to quantify the deviation of the actual growth state from the expected standard.

[0047] The growth analysis threshold refers to the critical value for determining whether the growth state meets the standard. It can be set through historical data statistics or expert experience and stored in the database. This threshold serves as a benchmark for determining whether to adjust the irrigation parameters.

[0048] The parameter optimization signal refers to the instruction for triggering the dynamic adjustment of the irrigation parameters by the management personnel. Specifically, the signal can be pushed to the mobile terminal through the mobile communication network. This signal is used to timely feedback the growth abnormality information and promote manual intervention optimization.

[0049] Specifically, after the completion of planting in the analysis area of the forestry nursery, the chlorophyll content data of the leaves is collected regularly to establish an analysis curve of the growth evaluation value over time. The analysis curve is compared with the pre-stored standard curve in the database, and the ratio of the area of the closed region formed by the two curves to the standard curve reference area is calculated to obtain the growth analysis coefficient. When this coefficient exceeds the pre-set threshold, it indicates that the current growth rate or health state deviates from the expected target, and the system automatically generates a parameter optimization signal and pushes it to the management personnel. Thus, a closed-loop feedback mechanism based on dynamic monitoring of the growth state is realized, avoiding continuous growth deviation caused by environmental changes or equipment errors.

[0050] The fault detection module is used to perform fault detection and analysis on the sprinkler system: the sprinkler process is marked as the detection process, and the detection process is divided into several detection periods. During the detection period, the spray liquid flow rate and water pressure of the sprinkler head are acquired and marked as flow rate value and pressure value, respectively. The absolute value of the difference between the flow rate value of the detection period and the flow rate value of the previous detection period is marked as the flow rate fluctuation value. The difference between the maximum and minimum pressure values ​​during the detection period is marked as the water pressure fluctuation value. The flow rate fluctuation threshold and water pressure fluctuation threshold are obtained from the database. The flow rate fluctuation value and water pressure fluctuation value are compared with the flow rate fluctuation threshold and water pressure fluctuation threshold, respectively. If the flow rate fluctuation value is less than the flow rate fluctuation threshold and the water pressure fluctuation value is less than the water pressure fluctuation threshold, the sprinkler head is determined to have no fault characteristics; otherwise, the sprinkler head is determined to have fault characteristics, a fault processing signal is generated, and the fault processing signal is sent to the mobile terminal of the management personnel.

[0051] The detection period refers to the independent monitoring intervals that divide the spraying process according to the time dimension. Specifically, it can be implemented using a timer or a periodic sampler to achieve dynamic segmented monitoring of the spraying process.

[0052] The flow fluctuation value refers to the absolute value of the change in the flow rate of the spray liquid between adjacent detection periods. Specifically, it can be achieved by using a flow sensor to collect data in real time and using a difference calculation module to reflect the stability of the spray liquid supply.

[0053] Water pressure fluctuation value refers to the difference between the maximum and minimum water pressure of the sprinkler head within a single detection period. Specifically, it can be achieved by using a pressure sensor in conjunction with an extreme value recorder to characterize the pressure stability of the sprinkler system.

[0054] The flow fluctuation threshold and water pressure fluctuation threshold are benchmark parameters that are pre-stored in the database. They can be obtained through statistical analysis of historical operating data and are used as quantitative standards to judge the operating status of the sprinkler system.

[0055] Specifically, the spraying process is divided into multiple consecutive monitoring periods, during which the flow rate and pressure data of the sprinkler heads are collected in real time. The flow rate fluctuation value is obtained by calculating the absolute value of the difference in flow rate between adjacent periods, and the extreme pressure difference within the current period is extracted as the water pressure fluctuation value. These two parameters are compared with preset thresholds in the database. When either parameter exceeds the corresponding threshold, it is determined that the sprinkler head has fault characteristics such as blockage or pipeline leakage. After a fault handling signal is generated, it is automatically pushed to the management terminal via a wireless communication module, triggering the maintenance response mechanism.

[0056] Example 2: Figure 2 As shown, the intelligent control method for the sprinkler system in distributed forestry seedling cultivation includes the following steps:

[0057] Step one: identify and analyze the growth state of the forestry nursery: divide the coverage area of the forestry seedling node into several analysis areas, regularly obtain the root stem growth deviation coefficient and leaf growth deviation coefficient of the analysis area, and determine whether the uniformity of the nursery growth in the analysis area meets the requirements according to the root stem growth deviation coefficient and the leaf growth deviation coefficient;

[0058] Step two: automatically control the spraying mechanism of the forestry seedling: obtain the soil humidity value in the analysis area in real time, and control the spraying mechanism through the irrigation parameters when the analysis area has a spraying feature;

[0059] Step three: evaluate and analyze the growth state of the forestry seedling: obtain the growth analysis coefficient of the analysis area, and determine whether the growth state of the forestry nursery in the analysis area meets the requirements through the growth analysis coefficient;

[0060] Step four: fault detection analysis of the spraying mechanism: obtain the flow fluctuation value and water pressure fluctuation value of the detection period in the detection process, and determine whether the nozzle has a fault feature according to the flow fluctuation value and the water pressure fluctuation value.

[0061] The distributed forestry seedling spraying mechanism intelligent management and control system divides the coverage area of the forestry seedling node into several analysis areas, regularly obtains the root stem growth deviation coefficient and leaf growth deviation coefficient of the analysis area, and determines whether the uniformity of the nursery growth in the analysis area meets the requirements according to the root stem growth deviation coefficient and the leaf growth deviation coefficient. In real time, obtain the soil humidity value in the analysis area, and control the spraying mechanism through the irrigation parameters when the analysis area has a spraying feature; obtain the growth analysis coefficient of the analysis area, and determine whether the growth state of the forestry nursery in the analysis area meets the requirements through the growth analysis coefficient; obtain the flow fluctuation value and water pressure fluctuation value of the detection period in the detection process, and determine whether the nozzle has a fault feature according to the flow fluctuation value and the water pressure fluctuation value.

[0062] The above content is only an example and description of the structure of the present application. Those skilled in the art can make various modifications or supplements to the described specific embodiments or use similar ways to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined by the present claims, and should belong to the protection scope of the present application.

[0063] In the description of the specification, reference to "one embodiment", "an example", "a specific example" or the like means that a particular feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. The appearances of the phrases "in one embodiment", "an example", "a specific example" or the like in various places in the specification are not necessarily referring to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0064] The preferred embodiments of the application disclosed above are only to help explain the application. The preferred embodiments do not describe all the details of the application and limit the application to the specific embodiments. Obviously, many modifications and variations can be made in light of the contents of the specification. The specification selects and specifically describes these embodiments in order to better explain the principles and practical application of the application, so that those skilled in the art can well understand and utilize the application. The application is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent control system for a distributed forestry seedling spraying mechanism, characterized in that, It includes an intelligent management and control platform, which is communicatively connected to a growth identification module, a spray control module, a growth assessment module, a fault detection module, and a database; The growth recognition module is used to identify and analyze the growth status of forestry nurseries: the coverage area of ​​forestry seedling nodes is divided into several analysis areas, the root and stem growth deviation coefficient and leaf growth deviation coefficient of the analysis area are obtained, and the uniformity of nursery growth in the analysis area is judged by the root and stem growth deviation coefficient and leaf growth deviation coefficient; if the requirements are met, the irrigation parameters of the analysis area are retrieved from the database. The sprinkler control module is used to automatically control the sprinkler mechanism for forestry seedling cultivation according to irrigation parameters; The growth assessment module is used to assess and analyze the growth status of forestry seedlings: obtain the growth analysis coefficient of the analysis area, and determine whether the growth status of the forestry nursery in the analysis area meets the requirements through the growth analysis coefficient; The fault detection module is used to perform fault detection and analysis on the spraying mechanism; The process of obtaining the root and stem growth deviation coefficient and the leaf growth deviation coefficient includes: periodically taking pictures of forestry nurseries in the analysis area, enlarging the pictures into pixel grid images, performing grayscale transformation and marking them as analysis images, segmenting the root and stem regions and leaf regions in the analysis images using the binary method and extracting the length value of a single root and the area value of a single leaf, calculating the variance of all root and stem length values ​​to obtain the root and stem growth deviation coefficient, and calculating the variance of all leaf area values ​​to obtain the leaf growth deviation coefficient. The specific process for determining whether the nursery growth uniformity of the analysis area meets the requirements includes: retrieving the root and stem growth deviation threshold and the leaf growth deviation threshold from the database; comparing the root and stem growth deviation coefficient and the leaf growth deviation coefficient of the analysis area with the root and stem growth deviation threshold and the leaf growth deviation threshold, respectively; if the root and stem growth deviation coefficient is less than the root and stem growth deviation threshold and the leaf growth deviation coefficient is less than the leaf growth deviation threshold, then the nursery growth uniformity of the analysis area is determined to meet the requirements; otherwise, the nursery growth uniformity of the analysis area is determined to not meet the requirements, a spraying optimization signal is generated and sent to the mobile terminal of the management personnel; The process of obtaining the growth analysis coefficient includes: extracting the chlorophyll content of the leaf areas in the analysis image; summing and averaging the chlorophyll content of all leaf areas in the analysis image to obtain the growth assessment value of the analysis area; after the forestry nursery in the analysis area has completed planting, establishing a rectangular coordinate system with time as the X-axis and growth assessment value as the Y-axis; marking the analysis points in the rectangular coordinate system with the acquisition time of the analysis image as the abscissa and the corresponding growth assessment value of the analysis image as the ordinate; connecting all the analysis points from left to right to obtain the analysis curve; retrieving the standard curve of the forestry nursery from the database and translating it into the rectangular coordinate system of the analysis curve; marking the area values ​​of all closed regions formed by the analysis curve and the standard curve as growth analysis values; drawing a perpendicular line from the rightmost endpoint of the standard curve to the X-axis to obtain the interception line segment; marking the area values ​​of the closed regions formed by the standard curve, the X-axis, the Y-axis, and the interception line segment as growth measurement values; and marking the ratio of the growth analysis value to the growth measurement value as the growth analysis coefficient. The specific process for determining whether the growth status of the forestry nursery in the analysis area meets the requirements includes: obtaining the growth analysis threshold from the database, comparing the growth analysis coefficient with the growth analysis threshold; if the growth analysis coefficient is less than the growth analysis threshold, the growth status of the forestry nursery in the analysis area is determined to meet the requirements; if the growth analysis coefficient is greater than or equal to the growth analysis threshold, the growth status of the forestry nursery in the analysis area is determined to not meet the requirements, generating a parameter optimization signal and sending the parameter optimization signal to the mobile terminal of the management personnel.

2. The intelligent control system for the spray mechanism of distributed forestry seedling cultivation according to claim 1, characterized in that, The process of retrieving irrigation parameters includes: summing and averaging the length values ​​of all roots and stems to obtain the root and stem growth performance value; summing and averaging the area values ​​of all leaves to obtain the leaf growth performance value; and retrieving the corresponding irrigation parameters from the database using the root and stem growth performance value and the leaf growth performance value. The irrigation parameters include soil moisture threshold, single irrigation duration, irrigation water pressure, and fertilizer concentration.

3. The intelligent control system for the spraying mechanism of distributed forestry seedling cultivation according to claim 2, characterized in that, The specific process of the sprinkler control module automatically controlling the sprinkler mechanism for forestry seedling cultivation includes: acquiring the soil moisture value in the analysis area in real time, comparing the soil moisture value with the soil moisture threshold in the irrigation parameters corresponding to the analysis area; if the soil moisture value is greater than the soil moisture threshold, it is determined that the analysis area does not have sprinkler characteristics; if the soil moisture value is less than or equal to the soil moisture threshold, it is determined that the analysis area has sprinkler characteristics, and controlling the sprinkler mechanism by the single irrigation duration, irrigation water pressure, and fertilizer concentration.

4. The intelligent control system for the spray mechanism of distributed forestry seedling cultivation according to claim 3, characterized in that, The specific process of fault detection and analysis of the sprinkler mechanism by the fault detection module includes: marking the sprinkler process of the sprinkler mechanism as the detection process, dividing the detection process into several detection time periods, obtaining the flow fluctuation value and water pressure fluctuation value of the detection time period, obtaining the flow fluctuation threshold and water pressure fluctuation threshold through the database, and comparing the flow fluctuation value and water pressure fluctuation value with the flow fluctuation threshold and water pressure fluctuation threshold respectively: if the flow fluctuation value is less than the flow fluctuation threshold and the water pressure fluctuation value is less than the water pressure fluctuation threshold, it is determined that the sprinkler head does not have fault characteristics; otherwise, it is determined that the sprinkler head has fault characteristics, generating a fault processing signal and sending the fault processing signal to the mobile terminal of the management personnel.

5. The intelligent control system for the spray mechanism of distributed forestry seedling cultivation according to claim 4, characterized in that, The process of obtaining flow fluctuation value and water pressure fluctuation value includes: obtaining the spray liquid flow rate and water pressure of the nozzle during the detection period and marking them as flow rate value and pressure value respectively; marking the absolute value of the difference between the flow rate value of the detection period and the flow rate value of the previous detection period as the flow fluctuation value; and marking the difference between the maximum and minimum pressure values ​​during the detection period as the water pressure fluctuation value.

Images