Automatic green plant pruning and branch and leaf recycling system for landscape engineering

Abstract

The invention belongs to the technical field of green plant pruning, and discloses an automatic green plant pruning and branch and leaf recycling system for landscape engineering. Comprising the following modules: a data acquisition module used for acquiring parameter data of green plants in landscape engineering in real time; and the health assessment module is used for assessing the health score of the green plant according to the collected parameter data and marking the to-be-pruned area according to the health score. According to the invention, the health assessment module is arranged, a laser radar, a multispectral camera, an infrared thermal imager and a temperature and humidity sensor are integrated, branch and leaf density, leaf surface moisture content, temperature and environment data are synchronously acquired, a green plant health score of a corresponding to-be-pruned area is output, and green plants in landscape engineering are classified and marked according to the health score. Classification marks are a low-health area, a middle-health area and a high-health area, and evaluation comprehensiveness is improved through multi-modal data fusion.

Description

Technical Field

[0001] The present invention relates to the technical field of green plant pruning, and more specifically, to an automatic green plant pruning and branch and leaf recycling system for landscape engineering. Background Art

[0002] In landscape engineering, the regular pruning and maintenance of green plants are key links to ensure aesthetics and ecological health. Existing automated pruning equipment can obtain information such as the shape and density of branches and leaves through sensors, such as visual cameras, and judge the pruning requirements based on this information, such as whether the green plants need to be pruned and how much length to be pruned.

[0003] However, existing automated pruning equipment mostly relies on a single sensor to judge pruning requirements, and can only obtain information on the shape or density of branches and leaves, unable to comprehensively evaluate the physiological state of plants, such as moisture content and diseases. Only visually identifying the density of branches and leaves ignores the abnormal leaf surface temperature caused by drought or pests, resulting in inaccurate pruning strategies. And existing path planning mostly optimizes the path length or coverage based on fixed rules, unable to dynamically adapt to the plant health state, not considering the health priority of plants, resulting in high-density or diseased areas not being processed preferentially. Moreover, when planning the pruning path, it is unable to predict and adopt a reasonable and energy-saving path, resulting in increased energy consumption of the pruning robotic arm. Summary of the Invention

[0004] In order to solve the problems in the background art that existing automated pruning equipment cannot comprehensively evaluate the physiological state of plants, cannot dynamically adapt to the plant health state, and cannot predict and adopt a reasonable and energy-saving path, the present invention proposes an automatic green plant pruning and branch and leaf recycling system for landscape engineering.

[0005] To achieve the above object, the present invention provides the following technical solutions: An automatic green plant pruning and branch and leaf recycling system for landscape engineering, including the following modules: A data acquisition module for real-time acquisition of parameter data of green plants in landscape engineering; A health assessment module for evaluating the health score of green plants according to the acquired parameter data and marking the areas to be pruned according to the health score; A path planning module for generating the shortest pruning path in landscape engineering according to the health score of green plants; A path optimization module for obtaining historical energy consumption data and constructing an energy consumption prediction model, and using the energy consumption prediction model to optimize the shortest pruning path to obtain an optimized pruning path; An execution module for pruning branches and leaves along the optimized pruning path through a multi-degree-of-freedom pruning robotic arm, collecting the cut branches and leaves, and performing recycling and resource treatment.

[0006] Further, the parameter data includes the branch and leaf density D per unit area密度 , the spectral reflectance R of the leaf surface 红外 , the leaf surface temperature T 叶面 , the ambient temperature T 环境 and the leaf water content H 含水 , by integrating lidar to scan the green plant area, generating three-dimensional point cloud data, and calculating and obtaining the branch and leaf density D 密度 , obtaining the spectral reflectance R of the leaf surface through a multispectral camera 红外 , and inversely obtaining the leaf water content H 含水 , obtaining the thermal image of the green plant through an infrared thermal imager, selecting the leaf surface area in the thermal image, and obtaining the leaf surface temperature T 叶面 , obtaining the ambient temperature T of the environment through a temperature and humidity sensor 环境 .

[0007] Furthermore, the process of obtaining the branch and leaf density D 密度 includes: Dividing the three-dimensional point cloud data into grid cells with a unit volume of V, and counting the number of points N in each grid;

[0008] The process of obtaining the leaf water content H 含水 includes: The spectral reflectance R of the leaf surface 红外 includes R near-infrared and R short-wave infrared, and the leaf water content is negatively correlated with the reflectance;

[0009] where a and b are calibration coefficients, which are determined by calibrating leaf samples in the laboratory.

[0010] Furthermore, obtaining the corresponding health score P according to the parameter data:

[0011] where: D 标准 is the preset standard density value of branches and leaves, which needs to be set according to the plant type; H 阈值 is the drought warning threshold; ω1, ω2 and ω3 are weight coefficients.

[0012] Furthermore, set X and Y, compare the health score P with the set X and Y to obtain the area to be pruned, and the area to be pruned includes the low-health area and the medium-health area; When P < X, it is marked as the low-health area and needs to be pruned first; When X ≤ P ≤ Y, it is marked as the medium-health area and needs to be selectively pruned; When P > Y, it is marked as a high-health area and does not require pruning for the time being.

[0013] Further, the process of generating the shortest pruning path for the low-health area and obtaining the shortest distance for the medium-health area in the path planning module includes: Set a starting point and an ending point within the landscape project. The pruning robotic arm is set at the starting point. Based on the comparison results of the health score P with X and Y, connect the centers of all low-health areas in sequence from the starting point to generate the shortest pruning path, and obtain the shortest moving distance of all medium-health areas from the shortest pruning path.

[0014] Further, the process of obtaining historical energy consumption data and constructing an energy consumption prediction model in the path optimization module includes: The factors affecting the pruning energy consumption of the pruning robotic arm include: moving distance, foliage density of the area to be pruned, branch diameter, branch moisture content, and aging wear score of the pruning robotic arm; Obtain the branch diameter of the area to be pruned through lidar point cloud analysis and deep learning fitting, obtain the branch moisture content of the area to be pruned through multispectral imaging and near-infrared spectroscopy analysis, and obtain the aging wear score of the pruning robotic arm through multi-sensor fusion and digital twin model; Monitor the joint motor current I of the pruning robotic arm through a current sensor. Through current analysis, aging will cause an increase in friction and an increase in current;

[0015] I 实测 refers to the actual value measured by the current sensor, and I 基准 refers to the reference value of the current under normal conditions, is I 实测 and I 基准 is the difference between them; Collect the vibration spectrum f of the pruning robotic arm through a vibration sensor, and identify abnormal frequencies through vibration analysis, such as the frequency band of bearing damage; Obtain the aging wear score S of the pruning robotic arm;

[0016] f 异常 refers to the frequency band with abnormal vibration spectrum, and are weight coefficients; Obtain the historical energy consumption data of the pruning robotic arm in a single area to be pruned. The historical energy consumption data includes the moving distance corresponding to the pruning robotic arm working on a single area to be pruned, the foliage density of the single area to be pruned, the branch diameter of the single area to be pruned, the branch moisture content of the single area to be pruned, the aging wear score of the pruning robotic arm, and the corresponding historical pruning energy consumption; An energy consumption prediction set is generated based on the moving distance corresponding to different areas to be pruned by the pruning robotic arm, the foliage density of the corresponding area to be pruned, the branch diameter of the corresponding area to be pruned, the moisture content of the branches in the corresponding area to be pruned, the aging wear score of the pruning robotic arm, and the corresponding historical pruning energy consumption, and it is divided into a training set and a test set; A convolutional neural network is constructed. The moving distance corresponding to different areas to be pruned by the pruning robotic arm in the training set, the foliage density of the corresponding area to be pruned, the branch diameter of the corresponding area to be pruned, the moisture content of the branches in the corresponding area to be pruned, and the aging wear score of the pruning robotic arm are used as the input data of the convolutional neural network, and the historical pruning energy consumption in the training set is used as the output data of the convolutional neural network; The convolutional neural network is trained to obtain an initial convolutional neural network, and the test set is used to verify the model of the initial convolutional neural network. The initial convolutional neural network with a test error threshold less than or equal to the preset value is output as the energy consumption prediction model.

[0017] Further, the process of using the energy consumption prediction model to optimize the shortest pruning path in the path optimization module to obtain an optimized pruning path includes: The shortest moving distance of each medium-healthy area from the shortest pruning path, the foliage density of the medium-healthy area, the branch diameter of the medium-healthy area, the moisture content of the branches in the medium-healthy area, and the aging wear score of the pruning robotic arm are input into the energy consumption prediction model to obtain the actual additional pruning energy consumption required for the pruning robotic arm to introduce each medium-healthy area on the basis of the shortest pruning path; The moving distance of the pruning robotic arm from the current low-healthy area to the next adjacent low-healthy area, the foliage density of the next low-healthy area, the branch diameter of the next low-healthy area, the moisture content of the branches in the next low-healthy area, and the aging wear score of the pruning robotic arm are input into the energy consumption prediction model to obtain the actual shortest pruning energy consumption required for the pruning robotic arm on its local shortest pruning path; The actual shortest pruning energy consumption refers to the energy consumption of the pruning robotic arm working along the local shortest pruning path between two adjacent low-healthy areas, and the actual additional pruning energy consumption refers to the energy consumption after adding another medium-healthy area between two adjacent low-healthy areas; The energy consumption ratio is obtained by dividing the actual additional pruning energy consumption by the actual shortest pruning energy consumption. The energy consumption ratio is compared with the set energy consumption threshold. If the energy consumption ratio is less than the set energy consumption threshold, the corresponding medium-healthy area is included in the shortest pruning path. The actual additional pruning energy consumption and the actual shortest pruning energy consumption of all medium-healthy areas are predicted, and the corresponding energy consumption ratios are obtained respectively. All medium-healthy areas with an energy consumption ratio less than the energy consumption threshold are included in the shortest pruning path to generate the final optimized pruning path of the pruning robotic arm.

[0018] Further, the process of pruning branches and leaves by the multi-degree-of-freedom pruning robotic arm and collecting and recycling the pruned branches and leaves includes: Prune the branches and leaves of the nodes by the robotic arm according to the optimized final pruning path, collect the pruned branches and leaves through the negative pressure adsorption system, and perform resource treatment using a crushing and compressing device. The blade gap of the crushing and compressing device can be adjusted to control the particle size of the crushed branches and leaves, and then compress and store the crushed branches and leaves.

[0019] Technical effects and advantages of a green plant automatic pruning and branch and leaf recycling system for landscape engineering of the present invention: (1) By setting up a health assessment module, integrating a lidar, a multispectral camera, an infrared thermal imager, and a temperature and humidity sensor to synchronously collect the branch and leaf density, leaf surface moisture content, temperature, and environmental data, output the green plant health score of the corresponding area to be pruned, and classify and mark the green plants in the landscape project according to the health score. The classification marks are respectively the low-health area, the medium-health area, and the high-health area, and the comprehensiveness of the assessment is improved through multi-modal data fusion.

[0020] (2) By setting up a path planning module and a path optimization module, classify and grade the area to be pruned according to the health score to obtain the low-health area, the medium-health area, and the high-health area. Connect all the low-health areas and generate the initial shortest pruning path. By constructing an energy consumption prediction model, predict the actual excess pruning energy consumption and the actual shortest pruning energy consumption of all medium-health areas, and respectively obtain the corresponding energy consumption ratios. Incorporate all medium-health areas with energy consumption ratios less than the energy consumption threshold into the shortest pruning path to generate the final optimized pruning path of the pruning robotic arm. Description of the Drawings

[0021] Figure 1 It is a schematic structural diagram of the system of the present invention. Detailed Embodiments

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0023] Refer to Figure 1 , a green plant automatic pruning and branch and leaf recycling system for landscape engineering, including the following modules: A data acquisition module for real-time acquisition of parameter data of green plants in the landscape project; A health assessment module, which is used to evaluate the health score of green plants according to the collected parameter data and mark the area to be pruned according to the health score; A path planning module, which is used to generate the shortest pruning path within the landscape project according to the health score of green plants; A path optimization module, which is used to obtain historical energy consumption data and build an energy consumption prediction model, and use the energy consumption prediction model to optimize the shortest pruning path to obtain an optimized pruning path; An execution module, which is used to prune branches and leaves along the optimized pruning path through a multi-degree-of-freedom pruning robotic arm carried, collect the pruned branches and leaves, and perform recycling and resource treatment.

[0024] It should be further noted that in the specific implementation process, the parameter data includes the foliage density D per unit area 密度 , the spectral reflectance R of the leaf surface 红外 , the leaf surface temperature T 叶面 , the ambient temperature T 环境 and the leaf surface moisture content H 含水 ; By integrating lidar to scan the green plant area, three-dimensional point cloud data is generated. Each point contains coordinate (x, y, z) information, and the foliage density D is calculated and obtained 密度 , and the point cloud density is positively correlated with the foliage density D 密度 ; The spectral reflectance R of the leaf surface is obtained through a multispectral camera 红外 , and the leaf surface moisture content H is retrieved 含水 ; Use a blackbody radiation source to calibrate the infrared camera to eliminate ambient radiation interference. Obtain the thermal imaging image of the green plant through an infrared thermal imager, frame the leaf surface area in the thermal image, and obtain the leaf surface temperature T 叶面 ; The ambient temperature T of the environment is obtained through a temperature and humidity sensor 环境 , and the temperature and humidity sensor is installed at the top of the device and away from the heat source of the robotic arm to avoid local temperature interference.

[0025] It should be further noted that in the specific implementation process, the process of obtaining the foliage density D 密度 includes: Divide the three-dimensional point cloud data into grid cells with a unit volume of V (such as 1 m³), and count the number of points N in each grid cell;

[0026] The process of obtaining the leaf surface moisture content H 含水 includes: The spectral reflectance R of the leaf surface 红外 includes and , the leaf surface water content is negatively correlated with the reflectance;

[0027] Among them, a and b are calibration coefficients, which are determined by calibrating leaf samples in the laboratory; Taking shrubs as an example, rose leaves are calibrated in the laboratory, a is 0.85, and b is 12.3; Taking trees as an example, camphor tree leaves are calibrated in the laboratory, a is 1.02, and b is 8.7.

[0028] It should be further noted that in the specific implementation process, the corresponding health score P is obtained according to various parameter data:

[0029] Among them: D 标准 is the preset standard density value of branches and leaves, which needs to be set according to the plant type. Taking shrubs as an example: ; H 阈值 is the drought warning threshold, and the preset value is 30%. Most landscape plants wilt when the water content < 30%, and emergency irrigation or pruning is required; ω1, ω2, and ω3 are weight coefficients, and their initial values are 0.4, 0.3, and 0.3 respectively. Historical operation data (branch and leaf density, water content, temperature difference) and the health score evaluated manually are collected, and ω1, ω2, and ω3 are obtained through training with a large amount of data.

[0030] It should be further noted that in the specific implementation process, X and Y are set, and the health score P is compared with the set X and Y to obtain the area to be pruned. The area to be pruned includes the low-health area and the medium-health area: X is set to 0.6, and Y is set to 0.8; When P < 0.6, it is marked as the low-health area and needs to be pruned first; When 0.6 ≤ P ≤ 0.8, it is marked as the medium-health area and needs to be selectively pruned; When P > 0.8, it is marked as the high-health area and does not need to be pruned for the time being; Taking shrubs as an example, if the branch and leaf density D of the shrub 密度 > D 标准 , the leaf surface water content H 含水 reaches 40%, and there are pests on the leaf surface, resulting in the leaf surface temperature T 叶面 > the environmental temperature T 环境 , and finally the obtained P < 0.6, and it needs to be pruned first.

[0031] It should be further noted that in the specific implementation process, the process of generating the shortest pruning path for the low-health area and obtaining the shortest distance for the medium-health area in the path planning module includes: Set a starting point and an ending point within the landscape project. The pruning robotic arm is set at the starting point. Based on the comparison results of the health score P with X and Y, connect the centers of all low-health areas in sequence from the starting point. The connection method follows the principle of proximity, starting from the starting point and connecting to the center of the nearest low-health area until the ending point to generate the shortest pruning path; Taking a single medium-health area C as an example, obtain the two low-health areas that are closest to the center of the medium-health area C and are adjacent before and after on the shortest pruning path, denoted as A and B. Take the shortest path length of moving the pruning robotic arm from A to C and then to B as the shortest moving distance for adding C to the shortest pruning path. Use the same method to obtain the shortest moving distance between each medium-health area and the shortest pruning path respectively.

[0032] It should be further noted that in the specific implementation process, the process of obtaining historical energy consumption data and constructing an energy consumption prediction model in the path optimization module includes: The factors affecting the pruning energy consumption of the pruning robotic arm include: moving distance, foliage density of the area to be pruned, branch diameter, branch water content, and aging wear score of the pruning robotic arm; Obtain the branch diameter of the area to be pruned through lidar point cloud analysis and deep learning fitting, obtain the branch water content of the area to be pruned through multispectral imaging and near-infrared spectroscopy analysis, and obtain the aging wear score of the pruning robotic arm through multi-sensor fusion and digital twin model; Monitor the joint motor current I of the pruning robotic arm through a current sensor. Through current analysis, aging will cause an increase in friction and an increase in current;

[0033] I 实测 refers to the actual value measured by the current sensor. I 基准 refers to the reference value of the current under normal conditions. is I 实测 and I 基准 the difference between them; Collect the vibration spectrum f of the pruning robotic arm through a vibration sensor, and identify abnormal frequencies through vibration analysis, such as the frequency band of bearing damage; Obtain the aging wear score S of the pruning robotic arm;

[0034] f 异常 refers to the frequency band with abnormal vibration spectrum. and is the weight coefficient, and its initial values are 0.4 and 0.6 respectively. Historical data (f 异常 , ) and the aging and wear scores evaluated manually are collected, and ω4 and ω5 are obtained after training with a large amount of data; Obtain the historical energy consumption data of the pruning robot arm in a single area to be pruned. The historical energy consumption data includes the moving distance corresponding to the pruning robot arm working on a single area to be pruned, the foliage density of the single area to be pruned, the branch diameter of the single area to be pruned, the water content of the branches in the single area to be pruned, the aging and wear score of the pruning robot arm, and the corresponding historical pruning energy consumption; Generate an energy consumption prediction set according to the moving distance corresponding to the pruning robot arm working on different areas to be pruned, the foliage density of the corresponding area to be pruned, the branch diameter of the corresponding area to be pruned, the water content of the branches in the corresponding area to be pruned, the aging and wear score of the pruning robot arm, and the corresponding historical pruning energy consumption, and divide it into a training set and a test set; Construct a convolutional neural network. The moving distance corresponding to the pruning robot arm working on different areas to be pruned, the foliage density of the corresponding area to be pruned, the branch diameter of the corresponding area to be pruned, the water content of the branches in the corresponding area to be pruned, and the aging and wear score of the pruning robot arm in the training set are used as the input data of the convolutional neural network, and the historical pruning energy consumption in the training set is used as the output data of the convolutional neural network; Train the convolutional neural network to obtain an initial convolutional neural network, use the test set to verify the model of the initial convolutional neural network, and output the initial convolutional neural network with a test error threshold less than or equal to the preset value as the energy consumption prediction model.

[0035] It should be further noted that in the specific implementation process, the process of using the energy consumption prediction model to optimize the shortest pruning path in the path optimization module to obtain the optimized pruning path includes: Input the shortest moving distance of each medium-health area from the shortest pruning path, the foliage density of the medium-health area, the branch diameter of the medium-health area, the water content of the branches in the medium-health area, and the aging and wear score of the pruning robot arm into the energy consumption prediction model to obtain the actual additional pruning energy consumption required for the pruning robot arm to introduce each medium-health area on the basis of the shortest pruning path; Input the moving distance of the pruning robot arm from the current low-health area to the next adjacent low-health area, the foliage density of the next low-health area, the branch diameter of the next low-health area, the water content of the branches in the next low-health area, and the aging and wear score of the pruning robot arm into the energy consumption prediction model to obtain the actual shortest pruning energy consumption required for the pruning robot arm on its local shortest pruning path; The actual shortest pruning energy consumption refers to the energy consumption when the pruning robotic arm works along the local shortest pruning path between two adjacent low-health areas. The actual redundant pruning energy consumption refers to the energy consumption when another medium-health area is added between two adjacent low-health areas and the work is carried out; Divide the actual redundant pruning energy consumption by the actual shortest pruning energy consumption to obtain the energy consumption ratio. Compare the energy consumption ratio with the set energy consumption threshold. If the energy consumption ratio is less than the set energy consumption threshold, incorporate the corresponding medium-health area into the shortest pruning path. Predict the actual redundant pruning energy consumption and the actual shortest pruning energy consumption for all medium-health areas, and respectively obtain the corresponding energy consumption ratios. Incorporate all medium-health areas with energy consumption ratios less than the energy consumption threshold into the shortest pruning path to generate the final optimized pruning path of the pruning robotic arm; In the embodiment of the present invention, by obtaining the energy consumption ratios of the actual redundant pruning energy consumption and the actual shortest pruning energy consumption for all medium-health areas, it is predicted whether to incorporate the corresponding medium-health areas into the shortest pruning path. Among them, the shortest pruning energy consumption is fixed, and mainly the actual redundant pruning energy consumption is predicted. The actual redundant pruning energy consumption is related to the moving distance of the pruning robotic arm, the branch diameter of the medium-health area, the branch moisture content, and the aging wear score of the pruning robotic arm; The length of the moving distance of the pruning robotic arm directly affects the magnitude of the actual redundant pruning energy consumption. The longer the moving distance, the greater the actual redundant pruning energy consumption and the greater the energy consumption ratio. The moving distance of the pruning robotic arm is positively correlated with the energy consumption ratio; The thickness of the branch diameter in the medium-health area indirectly affects the magnitude of the actual redundant pruning energy consumption. The thicker the branch diameter, the greater the actual redundant pruning energy consumption and the greater the energy consumption ratio. The branch diameter is positively correlated with the energy consumption ratio; The amount of branch moisture content in the medium-health area indirectly affects the magnitude of the actual redundant pruning energy consumption. The more the branch moisture content, the greater the actual redundant pruning energy consumption and the greater the energy consumption ratio. The branch moisture content is positively correlated with the energy consumption ratio; The size of the aging wear score of the pruning robotic arm indirectly affects the magnitude of the actual redundant pruning energy consumption. The larger the aging wear score, the greater the actual redundant pruning energy consumption and the greater the energy consumption ratio. The aging wear score is positively correlated with the energy consumption ratio; If the branch diameter in a certain medium-health area is relatively thick, the branch moisture content is relatively high, the moving distance to this medium-health area is relatively long, and the aging wear score of the pruning robotic arm is relatively large, then the required actual redundant pruning energy consumption is relatively large, the energy consumption ratio is relatively large, and it is greater than the energy consumption threshold. It is not recommended to incorporate this medium-health area into the shortest pruning path; Suppose the actual excessive pruning energy consumption of a certain medium-healthy area is 990 joules, the energy consumption threshold is 1.25, and the actual shortest pruning energy consumption is 720 joules. Then the energy consumption ratio is the actual excessive pruning energy consumption of 990 joules divided by the actual shortest pruning energy consumption of 720 joules, and its value is 1.375. Since the energy consumption ratio of 1.375 is greater than the energy consumption threshold of 1.25, it is not recommended to include this medium-healthy area in the shortest pruning path.

[0036] It should be further noted that in the specific implementation process, the process of pruning branches and leaves by the multi-degree-of-freedom pruning robotic arm and collecting and recycling the pruned branches and leaves includes: Pruning the branches and leaves of the nodes by the robotic arm according to the optimized path, collecting the pruned branches and leaves through the negative pressure adsorption system, adjusting the attitude position and suction force of the negative pressure adsorption system to collect all the fallen branches and leaves, and performing resource treatment by using a crushing and compression device. The blade gap of the crushing and compression device can be adjusted to control the particle size of the pruned branches and leaves after crushing, and then the crushed branches and leaves are compressed and stored. The blade gap adjusts the particle size to adapt to different resource requirements.

[0037] As mentioned above, this is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art in the technical field disclosed in the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

[0038] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An automatic green plant pruning and branch and leaf recycling system for landscape engineering, characterized in that, It includes the following modules: A data acquisition module, which is used to collect the parameter data of green plants in the landscape project in real time; A health assessment module, which is used to evaluate the health score of green plants according to the collected parameter data, and mark the areas to be pruned according to the health score; A path planning module, which is used to generate the shortest pruning path in the landscape project according to the health score of green plants; A path optimization module, which is used to obtain historical energy consumption data and construct an energy consumption prediction model, and use the energy consumption prediction model to optimize the shortest pruning path to obtain an optimized pruning path; An execution module, which is used to prune the branches and leaves along the optimized pruning path through the multi-degree-of-freedom pruning robotic arm carried, collect the cut branches and leaves, and perform recycling and resource treatment.

2. The automatic green plant pruning and branch and leaf recycling system for landscape engineering according to claim 1, wherein The parameter data includes the foliage density D per unit area 密度 , the spectral reflectance R of the leaf surface 红外 , the leaf surface temperature T 叶面 , the ambient temperature T 环境 , and the leaf surface moisture content H 含水 . By integrating lidar to scan the green plant area, three-dimensional point cloud data is generated, and the foliage density D is calculated and obtained 密度 . The spectral reflectance R of the leaf surface is obtained by a multispectral camera 红外 , and the leaf surface moisture content H is retrieved 含水 . The thermal imaging image of the green plants is obtained by an infrared thermal imager. The leaf surface area is selected in the thermal imaging map to obtain the leaf surface temperature T 叶面 . The ambient temperature T of the environment is obtained by a temperature and humidity sensor 环境 .

3. The automatic green plant pruning and foliage recycling system for landscape engineering according to claim 2, characterized in that, Obtaining the foliage density D 密度 The process includes: Divide the 3D point cloud data into grid cells with a unit volume of V, and count the number of points N in each grid cell; Obtaining the leaf surface moisture content H 含水 The process includes: Leaf surface spectral reflectance R 红外 including and , the leaf surface moisture content is negatively correlated with the reflectance; Wherein, a and b are calibration coefficients, which are determined by calibrating blade samples in the laboratory.

4. The automatic trimming and foliage recycling system for green plants used in landscape engineering according to claim 3, characterized in that, Obtain the corresponding health score P according to each parameter data: Wherein: D 标准 is a preset standard density value of branches and leaves, which needs to be set according to the plant type; H 阈值 is the drought warning threshold; ω1, ω2, and ω3 are weight coefficients.

5. The automatic green plant pruning and foliage recycling system for landscape engineering according to claim 4, wherein Set X and Y, compare the health score P with the set X and Y to obtain the areas to be pruned, and the areas to be pruned include low-health areas and medium-health areas; When P < X, it is marked as a low-health area and needs to be pruned first; When X ≤ P ≤ Y, it is marked as a medium-health area and needs to be selectively pruned; When P > Y, it is marked as a high-health area and does not need to be pruned temporarily.

6. The automatic green plant pruning and branch and leaf recycling system for landscape engineering according to claim 5, wherein The process of generating the shortest pruning path for the low-health area and obtaining the shortest distance for the medium-health area in the path planning module includes: Set a starting point and an ending point in the landscape project. The pruning robotic arm is set at the starting point. Based on the comparison results of the health score P with X and Y, connect the centers of all low-health areas in sequence from the starting point to generate the shortest pruning path, and obtain the shortest moving distance of all medium-health areas from the shortest pruning path.

7. The automatic trimming and foliage recycling system for green plants used in landscape engineering according to claim 6, characterized in that, The process of obtaining historical energy consumption data and constructing an energy consumption prediction model in the path optimization module includes: The factors affecting the pruning energy consumption of the pruning robotic arm include: moving distance, foliage density of the area to be pruned, branch diameter, branch moisture content, and aging wear score of the pruning robotic arm; Obtain the branch diameter of the area to be pruned through lidar point cloud analysis and deep learning fitting, obtain the branch moisture content of the area to be pruned through multispectral imaging and near-infrared spectroscopy analysis, and obtain the aging wear score of the pruning robotic arm through multi-sensor fusion and digital twin model; Monitor the joint motor current I of the pruning robotic arm through a current sensor. Through current analysis, aging will cause increased friction and rising current; I 实测 refers to the value actually measured by the current sensor, I 基准 refers to the reference value of the current under normal conditions, is I 实测 the difference between I 基准 and I Collect the vibration spectrum f of the pruning robotic arm through a vibration sensor, and identify abnormal frequencies through vibration analysis, such as the bearing damage frequency band; Obtain the aging wear score S of the pruning robotic arm; f 异常 refers to the frequency band with abnormal vibration spectrum, and are weighting coefficients; Obtain the historical energy consumption data of the pruning robotic arm in a single area to be pruned. The historical energy consumption data includes the corresponding moving distance when the pruning robotic arm works on a single area to be pruned, the foliage density of the single area to be pruned, the branch diameter of the single area to be pruned, the branch moisture content of the single area to be pruned, the aging wear score of the pruning robotic arm, and the corresponding historical pruning energy consumption; An energy consumption prediction set is generated based on the moving distance corresponding to different areas to be pruned by the pruning robotic arm, the foliage density of the corresponding areas to be pruned, the trunk diameter of the corresponding areas to be pruned, the moisture content of the trunks in the corresponding areas to be pruned, the aging wear score of the pruning robotic arm, and the corresponding historical pruning energy consumption, and it is divided into a training set and a test set; A convolutional neural network is constructed. The moving distance corresponding to different areas to be pruned by the pruning robotic arm, the foliage density of the corresponding areas to be pruned, the trunk diameter of the corresponding areas to be pruned, the moisture content of the trunks in the corresponding areas to be pruned, and the aging wear score of the pruning robotic arm in the training set are used as the input data of the convolutional neural network, and the historical pruning energy consumption in the training set is used as the output data of the convolutional neural network; The convolutional neural network is trained to obtain an initial convolutional neural network, and the test set is used to verify the model of the initial convolutional neural network. The initial convolutional neural network with an output less than or equal to the preset test error threshold is output as the energy consumption prediction model.

8. The automatic trimming and foliage recycling system for green plants used in landscape engineering according to claim 7, characterized in that, The process of optimizing the shortest pruning path by using the energy consumption prediction model in the path optimization module includes: The shortest moving distance of each medium-healthy area from the shortest pruning path, the foliage density of the medium-healthy area, the trunk diameter of the medium-healthy area, the moisture content of the trunks in the medium-healthy area, and the aging wear score of the pruning robotic arm are input into the energy consumption prediction model to obtain the actual additional pruning energy consumption required for the pruning robotic arm to introduce each medium-healthy area on the basis of the shortest pruning path; The moving distance of the pruning robotic arm from the current low-healthy area to the next adjacent low-healthy area, the foliage density of the next low-healthy area, the trunk diameter of the next low-healthy area, the moisture content of the trunks in the next low-healthy area, and the aging wear score of the pruning robotic arm are input into the energy consumption prediction model to obtain the actual shortest pruning energy consumption required for the pruning robotic arm on its local shortest pruning path; The actual shortest pruning energy consumption refers to the energy consumption of the pruning robotic arm working along the local shortest pruning path between two adjacent low-healthy areas, and the actual additional pruning energy consumption refers to the energy consumption after adding another medium-healthy area between two adjacent low-healthy areas; The energy consumption ratio is obtained by dividing the actual additional pruning energy consumption by the actual shortest pruning energy consumption. The energy consumption ratio is compared with the set energy consumption threshold. If the energy consumption ratio is less than the set energy consumption threshold, the corresponding medium-healthy area is included in the shortest pruning path. The actual additional pruning energy consumption and the actual shortest pruning energy consumption of all medium-healthy areas are predicted, and the corresponding energy consumption ratios are obtained respectively. All medium-healthy areas with energy consumption ratios less than the energy consumption threshold are included in the shortest pruning path to generate the final optimized pruning path of the pruning robotic arm.

9. The automatic green plant pruning and branch and leaf recycling system for landscape engineering according to claim 8, wherein The process of pruning the foliage by the multi-degree-of-freedom pruning robotic arm carried, collecting the pruned foliage, and recycling and resource-processing it includes: Prune the branches and leaves of the nodes by the robotic arm according to the optimized final pruning path, collect the pruned branches and leaves through the negative pressure adsorption system, and perform resource treatment using the crushing and compressing device. The blade gap of the crushing and compressing device can be adjusted to control the particle size of the crushed branches and leaves, and then compress and store the crushed branches and leaves.

Images