Soil Crust Separation and Analysis System

Abstract

The present invention relates to the technical field of soil crust separation and analysis, and specifically relates to a soil crust separation and analysis system. The soil crust separation device acquires sample soil, acquires a side image corresponding to the sample soil; measures the thickness of the soil crust corresponding to the sample soil; separates the sample soil to obtain the sample soil crust; and acquires surface feature data corresponding to the sample soil crust; acquires crust spectral data corresponding to the sample soil crust; performs data processing on the soil crust thickness, side image, surface feature data, and crust spectral data to determine soil state data corresponding to the sample soil, and outputs corresponding treatment measures. The efficiency is improved, and the thickness of the soil crust can be accurately obtained. In addition, the system can ensure the accuracy of the soil state data. Thus, the accuracy of the treatment measures taken for the sample soil can be ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of soil crust separation and analysis, and particularly to a soil crust separation and analysis system. Background Art

[0002] Soil crust refers to a hard thin layer formed on the soil surface due to water evaporation or physical action, and its formation is closely related to the water content, particle composition, salt content, and organic matter content of the soil surface layer. Soil crusts are mainly divided into three categories: physical crusts, chemical crusts, and biological crusts. Soil crusts can significantly affect the permeability, air permeability, water retention capacity, and plant growth of the soil. Their formation can hinder water infiltration and root development, limit air circulation, and exacerbate soil erosion. Therefore, precise separation and peeling of soil samples with crusts are of great significance for agricultural soil science research. Since the thickness of soil crusts is usually in the range of sub-millimeters to millimeters and is dynamically regulated by environmental factors (such as rainfall intensity and soil texture), its slight changes can significantly affect the water conductivity, erosion resistance, and root penetration ability of the soil. Currently, in the prior art, manual separation or the use of traditional separation methods often has low efficiency and cannot accurately obtain the crust thickness. Traditional measurement methods such as the mechanical contact method of vernier calipers are prone to damage the brittle crust structure and cannot meet the requirements of modern scientific research and agricultural applications. Therefore, how to separate and analyze soil crusts has become an urgent technical problem to be solved. Summary of the Invention

[0003] In view of this, the present invention provides a soil crust separation and analysis system to solve the above technical problems.

[0004] In a first aspect, the present invention provides a soil crust separation and analysis system, including: a soil crust separation device, a crust spectral acquisition device, and an electronic device, wherein:

[0005] The soil crust separation device is used to obtain a sample soil, and during the lifting process of the sample soil, obtain a side image corresponding to the sample soil; determine the soil crust thickness corresponding to the sample soil according to the side image, and separate the sample soil to obtain a sample soil crust; and obtain surface feature data corresponding to the sample soil crust;

[0006] The crust spectral acquisition device is used to obtain crust spectral data corresponding to the sample soil crust;

[0007] The electronic device is used to perform data processing on the soil crust thickness, side image, surface feature data, and crust spectral data to determine soil state data corresponding to the sample soil; and output corresponding processing measures according to the soil state data.

[0008] The soil crust separation and analysis system provided by the embodiments of the present application, the soil crust separation device is used to obtain sample soil. During the lifting process of the sample soil, the side image corresponding to the sample soil is obtained, so that the soil crust thickness corresponding to the sample soil can be determined according to the side image, ensuring the accuracy of the measured soil crust thickness corresponding to the sample soil. Then, the sample soil is separated according to the soil crust thickness to obtain the sample soil crust corresponding to the sample soil, thus realizing the precise separation and stripping of the soil sample with crust. There is no need for manual separation or the use of traditional separation methods, improving the efficiency and accurately obtaining the soil crust thickness. It can meet the needs of modern scientific research and agricultural applications. In addition, the soil crust separation device obtains the surface feature data corresponding to the sample soil crust, so that the sample soil crust can be studied according to the surface feature data, thus contributing to the research of agricultural soil science. The crust spectral acquisition device is used to collect spectral data of the sample soil crust to obtain the crust spectral data corresponding to the sample soil crust; and transmit the crust spectral data to the electronic device, so that the electronic device can obtain the crust spectral data corresponding to the sample soil crust. The electronic device is used to process the soil crust thickness, side image, surface feature data, and crust spectral data to determine the soil state data corresponding to the sample soil, ensuring the accuracy of the determined soil state data corresponding to the sample soil, and further contributing to the research of agricultural soil science. Then, corresponding treatment measures are output according to the soil state data, so that the accuracy of the treatment measures for the sample soil can be ensured, and further the normal growth of plants can be ensured.

[0009] In an alternative embodiment, the electronic device is used to perform feature fusion on the soil crust thickness, surface feature data, crust spectral data, and side image to generate a target high-dimensional feature vector;

[0010] Perform principal component analysis on the target high-dimensional feature vector, and convert the target high-dimensional feature vector into a set of linearly independent target principal components through linear transformation;

[0011] Extract features from the target principal components to determine the soil state data corresponding to the sample soil.

[0012] The soil crust separation and analysis system provided by the embodiments of the present application performs feature fusion on the soil crust thickness, surface feature data, crust spectral data, and side image to generate a target high-dimensional feature vector, ensuring the accuracy of the generated target high-dimensional feature vector. Perform principal component analysis on the target high-dimensional feature vector, and convert the target high-dimensional feature vector into a set of linearly independent target principal components through linear transformation, ensuring the accuracy of the converted target principal components. Extract features from the target principal components to determine the soil state data corresponding to the sample soil, ensuring the accuracy of the determined soil state data corresponding to the sample soil.

[0013] In an alternative embodiment, an electronic device is configured to extract features from sample data including soil crust thickness, surface feature data, crust spectral data, and side images, and convert the extracted features into corresponding feature vectors;

[0014] Concatenate the feature vectors to generate an initial high-dimensional feature vector;

[0015] Based on a preset encoder, compress the initial high-dimensional feature vector to generate a compressed low-dimensional feature vector;

[0016] Based on a preset decoder, decode the compressed low-dimensional feature vector to generate a target high-dimensional feature vector.

[0017] The soil crust separation and analysis system provided by the embodiments of the present application extracts features from sample data including soil crust thickness, surface feature data, crust spectral data, and side images, and converts the extracted features into corresponding feature vectors, ensuring the accuracy of the feature vectors corresponding to the sample data including soil crust thickness, surface feature data, crust spectral data, and side images respectively. Then, concatenate the feature vectors to generate an initial high-dimensional feature vector, ensuring the accuracy of the generated initial high-dimensional feature vector. Then, based on a preset encoder, compress the initial high-dimensional feature vector to generate a compressed low-dimensional feature vector, ensuring that the generated compressed low-dimensional feature vector learns the features of the initial high-dimensional feature vector and reduces the dimension. Based on a preset decoder, decode the compressed low-dimensional feature vector to generate a target high-dimensional feature vector, ensuring the accuracy of the generated target high-dimensional feature vector.

[0018] In an alternative embodiment, the electronic device is further configured to obtain environmental data of the sample soil within a preset future time period; the environmental data includes at least one of temperature, precipitation, light intensity, and wind speed;

[0019] Input the environmental data, soil crust thickness, surface feature data, crust spectral data, and side images into a preset soil crust prediction model, and output future soil crust data of the sample soil within a preset future time period.

[0020] The soil crust separation and analysis system provided by the embodiment of the present application, the electronic device is further configured to obtain the environmental data of the sample soil within a preset future time period; the environmental data includes at least one of air temperature, precipitation, light intensity, and wind speed; input the environmental data, soil crust thickness, surface feature data, crust spectral data, and side image into a preset soil crust prediction model, and output the future soil crust data of the sample soil within the preset future time period, ensuring the accuracy of the future soil crust data of the sample soil corresponding to the output, so that the impact of soil crust on the soil ecosystem can be understood in advance according to the future soil crust data, and a reasonable soil management strategy can be formulated.

[0021] In an alternative embodiment, the preset soil crust prediction model includes an input gate, a memory unit, a forgetting gate, an output gate, and a generative adversarial network. The electronic device is configured to fuse the environmental data, soil crust thickness, surface feature data, crust spectral data, and side image to generate an initial fusion feature;

[0022] Input the initial fusion feature into the preset soil crust prediction model according to the time series;

[0023] The input gate extracts the target fusion feature from the current fusion feature in the initial fusion feature and adds it to the memory unit;

[0024] The memory unit fuses the target fusion feature and the historical hidden state of the previous moment to generate an updated fusion feature;

[0025] The forgetting gate determines the retained fusion feature and the discarded fusion feature from the updated fusion feature;

[0026] The output gate outputs the current hidden state based on the retained fusion feature;

[0027] Calculate the correlation between the hidden states corresponding to each moment and the future soil crust data, and determine the attention weight information corresponding to the hidden states corresponding to each moment;

[0028] According to each attention weight information, perform a weighted sum of the hidden states corresponding to each moment to obtain the target hidden state;

[0029] Input the target hidden state into the generative adversarial network to output the future soil crust data.

[0030] The soil crust separation and analysis system provided by the embodiment of the present application, the electronic device is used to fuse environmental data with soil crust thickness, surface feature data, crust spectral data, and side images to generate initial fusion features, ensuring the accuracy of the generated target fusion features. Then, the initial fusion features are input into a preset soil crust prediction model according to the time series; the input gate extracts the target fusion features from the current fusion features in the initial fusion features and adds them to the memory unit in the preset soil crust prediction model, ensuring the accuracy of the target fusion features added to the memory unit. The memory unit fuses the target fusion features with the historical hidden state at the previous moment in the memory unit to generate updated fusion features, ensuring the accuracy of the generated updated fusion features. The forgetting gate in the preset soil crust prediction model determines the retained fusion features and discarded fusion features from the updated fusion features in the memory unit, ensuring the accuracy of the determined retained fusion features and discarded fusion features. The output gate in the preset soil crust prediction model outputs the current hidden state based on the retained fusion features, ensuring the accuracy of the output current hidden state. Then, the correlation between the hidden states corresponding to each moment and the future soil crust data is calculated; according to each correlation, the attention weight information corresponding to the hidden states corresponding to each moment is determined, ensuring the accuracy of the determined attention weight information corresponding to the hidden states corresponding to each moment. Then, according to each attention weight information, the hidden states corresponding to each moment are weighted and summed to obtain the target hidden state, ensuring the accuracy of the obtained target hidden state. The target hidden state is input into the generative adversarial network in the preset soil crust prediction model to output the future soil crust data, ensuring the accuracy of the output future soil crust data, so that the impact of soil crust on the soil ecosystem can be understood in advance according to the future soil crust data, and reasonable soil management strategies can be formulated.

[0031] In an alternative embodiment, the soil crust separation device includes a core cutter assembly, a laser ranging device, and a separation assembly; the core cutter assembly is installed below the soil crust separation and analysis system, the laser ranging device is installed above the core cutter assembly, and the separation assembly is slidably installed on the connecting rod between the core cutter assembly and the laser ranging device; wherein:

[0032] The core cutter assembly is used to collect the sample soil with crust.

[0033] The laser ranging device is used to control the sample soil to lift upward in the vertical direction, and during the lifting process of the sample soil, obtain the side image; determine the soil crust thickness according to the side image; and obtain the surface feature data corresponding to the soil crust of the sample soil.

[0034] The electronic device is used to adjust the height of the separation assembly according to the soil crust thickness, control the separation assembly to separate the sample soil, and obtain the soil crust of the sample soil.

[0035] A separation component, which is used to separate the sample soil under the control of an electronic device to obtain the sample soil crust.

[0036] The soil crust separation and analysis system provided by the embodiment of the present application. The soil crust separation device includes a core cutter component, a laser ranging device, and a separation component. Among them, the core cutter component is installed below the soil crust separation and analysis system, the laser ranging device is installed above the core cutter component, and the separation component is slidably installed on the connecting rod between the core cutter component and the laser ranging device; the laser ranging device and the separation component are respectively connected to the electronic device, where: The core cutter component is used to collect the sample soil with crust. The laser ranging device is used to control the sample soil to lift upward in the vertical direction, and during the lifting process of the sample soil, obtain the side image corresponding to the sample soil; determine the soil crust thickness corresponding to the sample soil according to the side image; ensure the accuracy of the measured soil crust thickness corresponding to the sample soil. And obtain the surface feature data corresponding to the sample soil crust; thus, the sample soil crust can be studied according to the surface feature data, thereby contributing to the research of agricultural soil science. The electronic device is used to adjust the height of the separation component according to the soil crust thickness, control the separation component to separate the sample soil, and obtain the sample soil crust corresponding to the sample soil; the separation component is used to separate the sample soil under the control of the electronic device to obtain the sample soil crust. Thus, the accurate separation and peeling of the soil sample with crust are realized. There is no need for manual separation or the use of traditional separation methods, which improves the efficiency and can accurately obtain the soil crust thickness. It can meet the needs of modern scientific research and agricultural applications.

[0037] In an optional embodiment, the laser ranging device includes: a camera component, a lifting platform, a laser ranging component, and a digital display component; the laser ranging component is installed above the core cutter component, the lifting platform is installed below the core cutter component, and the digital display component is installed outside the lifting track corresponding to the lifting platform; the camera component is installed outside the lifting track corresponding to the lifting platform, and the lifting platform, the camera component, and the digital display component are all connected to the electronic device; where:

[0038] The lifting platform is used to drive the sample soil to lift upward from the core cutter component under the control of the electronic device after the core cutter component has collected the sample soil.

[0039] The electronic device is used to control the camera component to collect side images in real time when the sample soil is lifted upward.

[0040] The electronic device is also used to identify the side images, determine the contact interface between the sample soil crust and the underlying soil in the sample soil; and control the lifting platform to drive the sample soil to lift vertically upward until the contact interface is flush with the upper surface of the core cutter assembly according to the identified contact interface and then stop.

[0041] The laser ranging component is used to measure the lifting distance of the lifting platform and determine the lifting distance as the soil crust thickness corresponding to the sample soil.

[0042] The laser ranging component is also used to collect the surface feature data corresponding to the sample soil.

[0043] For the soil crust separation and analysis system provided by the embodiments of the present application, the lifting platform is used to drive the sample soil to lift upward from the core cutter assembly under the control of the electronic device after the core cutter assembly has collected the sample soil, so as to facilitate the separation of the sample soil and obtain the sample soil crust corresponding to the sample soil. The electronic device is used to control the camera component to collect side images in real time when the sample soil is lifted upward, ensuring the accuracy of the side images of the soil crust of the sample soil obtained. The electronic device is also used to identify the side images to determine the contact interface between the sample soil crust and the underlying soil in the sample soil, ensuring the accuracy of the determined contact interface between the sample soil crust and the underlying soil in the sample soil. Control the lifting platform to drive the sample soil to lift vertically upward until the contact interface is flush with the upper surface of the core cutter assembly according to the identified contact interface and then stop, so as to facilitate the measurement of the soil crust thickness and the separation of the sample soil to obtain the sample soil crust corresponding to the sample soil. The laser ranging component is used to measure the lifting distance of the lifting platform and determine the lifting distance as the soil crust thickness corresponding to the sample soil, ensuring the accuracy of the determined soil crust thickness corresponding to the sample soil. The laser ranging component is also used to collect the surface feature data corresponding to the sample soil, so that the sample soil crust can be studied based on the surface feature data, thus contributing to the research of agricultural soil science.

[0044] In an alternative embodiment, the laser ranging component includes: a laser sensor, an annular guide rail, a micro-vibration buffer component, a cross bar, a first motor, and a steel frame; where:

[0045] The diameter of the annular guide rail is the same as the size of the core cutter in the core cutter assembly and is used to carry the laser sensor.

[0046] The micro-vibration buffer component is installed on the annular guide rail and is composed of a flexible silica gel pad and a micro spring, and is used to reduce the interference of the vibration generated when the first motor drives the cross bar to slide on the laser sensor.

[0047] The first motor is used to drive the cross bar to slide so that the cross bar drives the laser sensor to slide along the steel frame.

[0048] A laser sensor, which is configured to emit a first infrared light before the lifting platform drives the sample soil to lift upward and receive a first reflected light corresponding to the first infrared light; and emit a second infrared light after the lifting platform stops and receive a second reflected light corresponding to the second infrared light;

[0049] An electronic device, which is configured to calculate the soil crust thickness based on the emission time of the first infrared light, the reception time of the first reflected light, the emission time of the second infrared light, and the reception time of the second reflected light;

[0050] The laser sensor is further configured to emit visible light to the sample soil crust and generate a reflection image corresponding to the sample soil crust based on the received visible reflection signal corresponding to the visible light;

[0051] An electronic device, which is configured to identify the reflection image to determine surface feature data corresponding to the sample soil crust, and the surface feature data includes at least one of roughness, particle distribution, and crack characteristics.

[0052] In the soil crust separation and analysis system provided by the embodiments of the present application, the diameter of the annular guide rail is the same as the size of the cutting ring in the cutting ring assembly and is used to carry the laser sensor. The micro-vibration buffer assembly is installed on the annular guide rail and is composed of a flexible silica gel pad and a micro spring, and is used to reduce the interference of the vibration generated when the first motor drives the cross bar to slide to the laser sensor. The first motor is used to drive the cross bar to slide, so that the cross bar can drive the laser sensor to slide along the steel frame. A laser sensor, which is configured to emit a first infrared light before the lifting platform drives the sample soil to lift upward and receive a first reflected light corresponding to the first infrared light; and emit a second infrared light after the lifting platform stops and receive a second reflected light corresponding to the second infrared light. An electronic device, which is configured to calculate the soil crust thickness based on the emission time of the first infrared light, the reception time of the first reflected light, the emission time of the second infrared light, and the reception time of the second reflected light, ensuring the accuracy of the obtained soil crust thickness. The laser sensor is further configured to emit visible light to the sample soil crust and generate a reflection image corresponding to the sample soil crust based on the received visible reflection signal corresponding to the visible light, ensuring the accuracy of the generated reflection image corresponding to the sample soil crust. An electronic device, which is configured to identify the reflection image to determine surface feature data corresponding to the sample soil crust, ensuring the accuracy of the determined surface feature data corresponding to the sample soil crust.

[0053] In an alternative embodiment, the electronic device is configured to identify the reflection image based on a preset generative adversarial network to determine the roughness corresponding to the sample soil crust; and / or identify the reflection image based on a crack dynamic monitoring and analysis method based on time series to determine the crack characteristics corresponding to the sample soil crust; and / or identify the reflection image based on a preset object detection algorithm to determine the particle distribution corresponding to the sample soil crust.

[0054] The soil crust separation and analysis system provided by the embodiment of the present application identifies the reflection image based on a preset generative adversarial network to determine the roughness corresponding to the sample soil crust, ensuring the accuracy of the determined roughness corresponding to the sample soil crust. The reflection image is identified by the crack dynamic monitoring and analysis method based on the time series to determine the crack characteristics corresponding to the sample soil crust, ensuring the accuracy of the determined crack characteristics corresponding to the sample soil crust. The reflection image is identified by a preset object detection algorithm to determine the particle distribution corresponding to the sample soil crust, ensuring the accuracy of the determined particle distribution corresponding to the sample soil crust.

[0055] In an alternative embodiment, the separation component includes: a sliding component, a separation slide rail, a separation knife, a second motor, a second pressure sensor, and a processor; the sliding component is installed on the connecting rod between the core cutter assembly and the laser ranging device, the sliding component drives the separation slide rail to slide on the connecting rod, the separation knife is installed on the separation slide rail, and after the sliding component drives the separation slide rail to be fixed to a specific position according to the soil crust thickness, the second motor drives the separation knife to slide on the separation slide rail to separate the sample soil to obtain the sample soil crust corresponding to the sample soil; where:

[0056] The second pressure sensor is configured to collect the resistance data during the cutting process and transmit the resistance data to the processor and the electronic device during the process of the separation knife separating the sample soil to obtain the sample soil crust corresponding to the sample soil;

[0057] The processor is configured to adjust the blade angle and cutting force of the separation knife according to the resistance data.

[0058] The soil crust separation and analysis system provided by the embodiment of the present application, the separation component includes: a sliding component, a separation slide rail, a separation knife, a second motor, a second pressure sensor, and a processor, where the sliding component is installed on the connecting rod between the core cutter assembly and the laser ranging device, the sliding component drives the separation slide rail to slide on the connecting rod, the separation knife is installed on the separation slide rail, and after the sliding component drives the separation slide rail to be fixed to a specific position according to the soil crust thickness, the second motor drives the separation knife to slide on the separation slide rail to separate the sample soil to obtain the sample soil crust corresponding to the sample soil; where: the second pressure sensor is configured to collect the resistance data during the cutting process and transmit the resistance data to the processor and the electronic device during the process of the separation knife separating the sample soil to obtain the sample soil crust corresponding to the sample soil. The processor is configured to adjust the blade angle and cutting force of the separation knife according to the resistance data, ensuring the accuracy of adjusting the blade angle and cutting force of the separation knife. Description of the Drawings

[0059] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings required for the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0060] Figure 1 is a schematic structural diagram of a first soil crust separation and analysis system according to an embodiment of the present invention;

[0061] Figure 2 is a schematic structural diagram of a second soil crust separation and analysis system according to an embodiment of the present invention;

[0062] Figure 3 is a schematic structural diagram of a third soil crust separation and analysis system according to an embodiment of the present invention;

[0063] Figure 4 is a schematic structural diagram of a fourth soil crust separation and analysis system according to an embodiment of the present invention;

[0064] Figure 5 is a schematic structural diagram of a fifth soil crust separation and analysis system according to an embodiment of the present invention;

[0065] Wherein:

[0066] The soil crust separation device is marked as 1;

[0067] The core cutter assembly is marked as 11;

[0068] The laser ranging device is marked as 12;

[0069] The camera assembly is marked as 121;

[0070] The lifting platform is marked as 122;

[0071] The laser ranging assembly is marked as 123;

[0072] The laser sensor is marked as 1231;

[0073] The annular guide rail is marked as 1232;

[0074] The micro-vibration buffer assembly is marked as 1233;

[0075] The cross bar is marked as 1234;

[0076] The first motor is marked as 1235;

[0077] The steel frame is marked as 1236;

[0078] The digital display component is marked as 124;

[0079] The separation component is marked as 13;

[0080] The sliding component is marked as 131;

[0081] The separation slide rail is marked as 132;

[0082] The separation knife is marked as 133;

[0083] The second motor is marked as 134;

[0084] The second pressure sensor is marked as 135;

[0085] The processor is marked as 136;

[0086] The crust spectral acquisition device is marked as 2;

[0087] The electronic device is marked as 3. Detailed implementation mode

[0088] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of 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.

[0089] The present invention provides a soil crust separation and analysis system, as Figure 1 shown. The soil crust separation and analysis system includes: a soil crust separation device 1, a crust spectral acquisition device 2, and an electronic device 3. Both the soil crust separation device 1 and the crust spectral acquisition device 2 are communicatively connected to the electronic device 3, where:

[0090] The soil crust separation device 1 is used to obtain sample soil, and during the lifting process of the sample soil, obtain the side image corresponding to the sample soil; determine the soil crust thickness corresponding to the sample soil according to the side image, and separate the sample soil to obtain the sample soil crust; and obtain the surface feature data corresponding to the sample soil crust;

[0091] The crust spectral acquisition device 2 is used to obtain the crust spectral data corresponding to the sample soil crust;

[0092] The electronic device 3 is used to process the soil crust thickness, side image, surface feature data, and crust spectral data to determine the soil state data corresponding to the sample soil; output corresponding processing measures according to the soil state data.

[0093] Among them, the soil state data is used to characterize the suitability of the sample soil for plant growth.

[0094] Specifically, the soil crust separation device 1 is equipped with a dedicated sampling device that can accurately collect the sample soil with crust. Then, the soil crust separation device 1 controls the sample soil to rise vertically upward, and during the upward movement of the sample soil, the side image corresponding to the sample soil is obtained. Then, the side image is transmitted to the electronic device 3, and the electronic device 3 uses an image processing algorithm to measure the soil crust thickness. Specifically, the electronic device 3 can first preprocess the side image, such as noise reduction, contrast enhancement, etc., so that the boundary between the sample soil crust and the underlying soil becomes clearer. Then the electronic device 3 can adopt an edge detection algorithm, such as the Canny algorithm, to accurately identify the boundary line between the sample soil crust and the underlying soil. By calculating the position difference of the boundary line in the image and combining the scale of the side image and the actually measured upward height of the sample soil, the soil crust thickness is accurately calculated.

[0095] Then, the soil crust separation device 1 separates the sample soil crust from the underlying soil according to the measured soil crust thickness. For the separated sample soil crust, its surface feature data, such as surface roughness, particle distribution, etc., is obtained through laser scanning or other surface measurement techniques. Specifically, the laser scanning device in the soil crust separation device 1 emits a laser beam and receives the light reflected from the surface of the soil crust. According to the time and angle information of the reflected light, a three-dimensional model of the soil crust surface is constructed, and then the surface feature data is analyzed.

[0096] The crust spectral acquisition device 2 can be a high-resolution spectrometer. The crust spectral acquisition device 2 can collect spectral data of the separated sample soil crust. The crust spectral acquisition device 2 emits light in a specific wavelength range and irradiates it on the soil crust, and then receives the light reflected from the soil crust. By analyzing the intensity and wavelength distribution of the reflected light, the spectral characteristics of the soil crust are obtained. Different chemical components will have specific absorption and reflection peaks in the spectrum. By identifying the positions and intensities of these peaks, the content and types of various chemical components in the soil crust can be inferred. Then, the collected crust spectral data is transmitted to the electronic device 3 in real time through wired or wireless transmission methods. Wired transmission can use interfaces such as USB and Ethernet to ensure the stability and high speed of data transmission; wireless transmission can use technologies such as Wi-Fi and Bluetooth to improve the flexibility of device use. After receiving the crust spectral data, the electronic device 3 integrates it with the soil crust thickness, side image, surface feature data, etc., to prepare for subsequent data processing and analysis.

[0097] The electronic device 3 utilizes its powerful data processing capabilities to comprehensively process the soil crust thickness, side images, surface feature data, and spectral data. First, the data is cleaned and preprocessed to remove noise and outliers, ensuring the accuracy and reliability of the data. Then, data fusion techniques are employed to fuse different types of data together to form a comprehensive sample soil feature dataset. For example, combining the chemical composition information in the spectral data with the surface feature data to gain a deeper understanding of the properties of the soil crust.

[0098] Then, based on the fused dataset, the electronic device 3 uses machine learning algorithms or establishes mathematical models to determine the soil state data corresponding to the sample soil. Through training with a large amount of historical data, a mapping relationship between soil features and suitable plant growth conditions is established. For example, using the support vector machine (SVM) algorithm, the soil is classified into different state data according to features such as soil crust thickness, chemical composition content, and surface roughness, and each state data corresponds to a different degree of suitable plant growth.

[0099] Finally, the electronic device 3 outputs corresponding treatment measures according to the determined soil state data. For sample soils with a higher soil grade and suitable for plant growth, it is recommended to adopt protective agricultural measures such as reasonable fertilization and water-saving irrigation to maintain the good state of the soil; for sample soils with a lower soil grade and less suitable for plant growth, targeted improvement suggestions such as adding soil amendments and deep plowing and loosening the soil are provided to improve the soil quality and increase its suitability for plant growth.

[0100] The soil crust separation and analysis system provided by the embodiments of the present application includes a soil crust separation device 1, which is used to obtain sample soil. During the lifting process of the sample soil, a side image corresponding to the sample soil is obtained, so that the soil crust thickness corresponding to the sample soil can be determined according to the side image, ensuring the accuracy of the measured soil crust thickness corresponding to the sample soil. Then, the sample soil is separated according to the soil crust thickness to obtain the sample soil crust corresponding to the sample soil, thus realizing the precise separation and stripping of the soil sample with crust. It does not require manual separation or the use of traditional separation methods, improving the efficiency and accurately obtaining the soil crust thickness. It can meet the needs of modern scientific research and agricultural applications. In addition, the soil crust separation device 1 obtains the surface feature data corresponding to the sample soil crust, so that the sample soil crust can be studied according to the surface feature data, thus contributing to the research of agricultural soil science. A crust spectrum acquisition device 2 is used to collect spectral data of the sample soil crust to obtain the crust spectral data corresponding to the sample soil crust; and the crust spectral data is transmitted to an electronic device 3, so that the electronic device 3 can obtain the crust spectral data corresponding to the sample soil crust. The electronic device 3 is used to process data such as soil crust thickness, side image, surface feature data, and crust spectral data to determine the soil state data corresponding to the sample soil, ensuring the accuracy of the determined soil state data corresponding to the sample soil, and further contributing to the research of agricultural soil science. Then, corresponding treatment measures are output according to the soil state data, so that the accuracy of the treatment measures for the sample soil can be ensured, and thus the normal growth of plants can be ensured.

[0101] In an alternative embodiment of the present application, the electronic device 3 is used to perform feature fusion on the soil crust thickness, surface feature data, crust spectral data, and side image to generate a target high-dimensional feature vector;

[0102] Perform principal component analysis on the target high-dimensional feature vector, and convert the target high-dimensional feature vector into a set of linearly independent target principal components through linear transformation;

[0103] Extract features from the target principal components to determine the soil state data corresponding to the sample soil.

[0104] In an alternative embodiment, the electronic device 3 is used to extract features from the sample data including soil crust thickness, surface feature data, crust spectral data, and side image, and convert the extracted features into corresponding feature vectors;

[0105] Stitch the feature vectors together to generate an initial high-dimensional feature vector;

[0106] Based on a preset encoder, perform compression processing on the initial high-dimensional feature vector to generate a compressed low-dimensional feature vector;

[0107] Based on a preset decoder, the compressed low-dimensional feature vector is decoded to generate a target high-dimensional feature vector.

[0108] Specifically, the electronic device 3 can extract features from the sample data including soil crust thickness, surface feature data, crust spectral data, and side images respectively, and convert the extracted features into corresponding feature vectors.

[0109] For the soil crust thickness, the electronic device 3 can use the soil crust thickness as a direct feature and convert it into a one-dimensional feature vector. For example, if the soil crust thickness is d, the corresponding feature vector can be expressed as [d]. For the surface feature data, the surface feature data may include information such as roughness, particle distribution, and crack features. For roughness, the electronic device 3 can obtain a value through a specific roughness calculation method; the particle distribution can be obtained as a set of values by statistically analyzing the proportion of particles of different particle sizes; the crack features can be quantified by the length, width, and number of cracks. These quantified values are combined into a feature vector. For example, if the roughness is r, the statistical values of particle distribution are [p1, p2,..., p n , and the quantified values of crack features are [c1, c2, c3], then the feature vector corresponding to the surface feature data is [r, p1, p2,..., p n , c1, c2, c3]. For the crust spectral data, the crust spectral data records information such as the reflectivity of the soil crust at different wavelengths. The reflectivity values corresponding to each wavelength are combined into a feature vector. For example, if the reflectivities at m wavelengths are [s1, s2,..., s m , then the feature vector corresponding to the crust spectral data is [s1, s2,..., s m . For the side images, image processing algorithms can be used to extract features, such as edge features and texture features. The image is converted into a feature vector of a fixed length through methods such as convolutional neural network (CNN). Suppose the obtained feature vector after processing is [i1, i2,..., i k .

[0110] Then, the electronic device 3 splices the feature vectors to generate an initial high-dimensional feature vector.

[0111] The preset encoder is usually a neural network model, which is used to compress the initial high-dimensional feature vector, remove redundant information therein, extract more representative features, and generate a compressed low-dimensional feature vector. The preset encoder processes the input initial high-dimensional feature vector through a series of linear transformations and non-linear activation functions. For example, the preset encoder may contain multiple fully connected layers, and each fully connected layer performs weighted summation on the input feature vector and performs non-linear transformation through an activation function (such as ReLU), and finally maps the high-dimensional feature vector to a low-dimensional space to obtain a compressed low-dimensional feature vector.

[0112] The preset decoder is also a neural network model, and its function is to restore the compressed low-dimensional feature vector to a high-dimensional feature vector. The structure of the preset decoder is similar to that of the preset encoder, but the processing process is opposite. The preset decoder receives the compressed low-dimensional feature vector and maps it back to the high-dimensional space through a series of linear transformations and non-linear activation functions to generate a target high-dimensional feature vector. In this process, the preset decoder tries to retain as much important information in the original feature vector as possible while removing the noise that may be introduced during the compression process.

[0113] Then, the electronic device 3 first normalizes the target high-dimensional feature vector so that the mean of each feature is 0 and the standard deviation is 1. This can eliminate the influence of the dimension of different features and ensure that each feature has the same importance in the principal component analysis. Let the target high-dimensional feature vector be X = [x1, x2,..., x l , and the normalized feature vector is X std .

[0114] Next, the electronic device 3 calculates the covariance matrix C of the normalized target high-dimensional feature vector. The covariance matrix C reflects the correlation between each feature. For the target high-dimensional feature vector X std of n samples, the element C ij of the covariance matrix C is the covariance between the i-th feature and the j-th feature, and the calculation formula is , where x ki is the i-th eigenvalue of the k-th sample, and is the mean of the i-th feature.

[0115] Perform eigenvalue decomposition on the covariance matrix C to obtain eigenvalues and the corresponding eigenvectors . The eigenvalue represents the variance size of each principal component, and the larger the variance, the more information the principal component contains. Sort the eigenvalues from large to small, and the corresponding eigenvectors are also arranged in the same order.

[0116] Select the first p principal components (p < l) according to the magnitudes of the eigenvalue such that the proportion of the sum of the variances of these p principal components to the total variance reaches a certain threshold (such as 80% or 90%). These principal components are linear combinations of the original feature vectors and are linearly independent of each other. Project the standardized target high-dimensional feature vector onto these p principal components to obtain the target principal components.

[0117] Finally, the electronic device 3 inputs the target principal components into the input layer of a preset multi-layer perceptron model. After the non-linear transformation of multiple hidden layers of the preset multi-layer perceptron model, the prediction result of the soil state data is finally obtained at the output layer. The MLP can learn the complex non-linear relationships between the features and has good performance in dealing with complex soil grade classification problems.

[0118] The soil crust separation and analysis system provided by the embodiment of the present application extracts features from the sample data including soil crust thickness, surface feature data, crust spectral data, and side images, and converts the extracted features into corresponding feature vectors, ensuring the accuracy of the converted sample data including the feature vectors corresponding to the soil crust thickness, surface feature data, crust spectral data, and side images respectively. Then, the feature vectors are concatenated to generate an initial high-dimensional feature vector, ensuring the accuracy of the generated initial high-dimensional feature vector. Then, based on a preset encoder, the initial high-dimensional feature vector is compressed to generate a compressed low-dimensional feature vector, ensuring that the generated compressed low-dimensional feature vector not only learns the features of the initial high-dimensional feature vector but also reduces the dimension. Based on a preset decoder, the compressed low-dimensional feature vector is decoded to generate a target high-dimensional feature vector, ensuring the accuracy of the generated target high-dimensional feature vector.

[0119] Then, perform principal component analysis on the target high-dimensional feature vector, and convert the target high-dimensional feature vector into a set of linearly independent target principal components through linear transformation, ensuring the accuracy of the converted target principal components. Extract features from the target principal components to determine the soil state data corresponding to the sample soil, ensuring the accuracy of the determined soil state data corresponding to the sample soil.

[0120] In an alternative embodiment of the present application, the electronic device 3 is further configured to obtain environmental data of the sample soil within a preset future time period; the environmental data includes at least one of temperature, precipitation, light intensity, and wind speed;

[0121] Input the environmental data, the soil crust thickness, the surface feature data, the crust spectral data, and the side images into a preset soil crust prediction model, and output the future soil crust data of the sample soil within the preset future time period.

[0122] In an alternative embodiment, the preset soil crust prediction model includes an input gate, a memory unit, a forget gate, an output gate, and a generative adversarial network. The electronic device 3 is configured to fuse environmental data with soil crust thickness, surface feature data, crust spectral data, and side images to generate initial fusion features;

[0123] Input the initial fusion features into the preset soil crust prediction model according to the time series;

[0124] The input gate extracts target fusion features from the current fusion features in the initial fusion features and adds them to the memory unit;

[0125] The memory unit fuses the target fusion features with the historical hidden state of the previous moment to generate updated fusion features;

[0126] The forget gate determines the retained fusion features and the discarded fusion features from the updated fusion features in the memory unit;

[0127] The output gate outputs the current hidden state based on the retained fusion features;

[0128] Calculate the correlation between the hidden states corresponding to each moment and the future soil crust data; and determine the attention weight information corresponding to the hidden states corresponding to each moment;

[0129] According to the attention weight information, perform a weighted sum of the hidden states corresponding to each moment to obtain the target hidden state;

[0130] Input the target hidden state into the generative adversarial network in the preset soil crust prediction model to output the future soil crust data.

[0131] Specifically, the electronic device 3 obtains the environmental data of the sample soil within a preset future time period. These environmental data include at least one of temperature, precipitation, light intensity, and wind speed. There are various ways to obtain these data. For example, they can be obtained from the official database of the meteorological department, professional meteorological monitoring stations, or environmental sensors installed near the sample soil. These environmental data are crucial for predicting the changes in soil crust because the formation, development, and changes of soil crust are closely related to external environmental conditions. For example, the temperature affects the evaporation rate of water in the soil, precipitation directly changes the soil humidity, light intensity affects the soil temperature and microbial activities, and wind speed affects the erosion and particle movement on the soil surface.

[0132] Then, the electronic device 3 fuses the acquired environmental data with the sample data (soil crust thickness, surface feature data, crust spectral data, and side images) to generate initial fusion features. During the fusion process, different types of data may require different preprocessing. For example, environmental data is usually numerical data and may need to be normalized to unify its value range to between [0, 1] or [-1, 1] to eliminate the influence of the dimension between different data; for data such as side images, image processing algorithms may be used to extract features, and then the extracted features are fused with other data. The fusion method can adopt a simple splicing method, connecting the feature vectors of different data in sequence, or a more complex feature fusion algorithm, such as a neural network-based fusion method, by training a fusion network to learn the internal relationship between different data, so as to generate more representative initial fusion features.

[0133] Next, the electronic device 3 inputs the initial fusion features into a preset soil crust prediction model. The input gate in the preset soil crust prediction model extracts target fusion features from the current fusion features in the initial fusion features and adds them to the memory unit in the model. The input gate is like a filter, and it decides which information can enter the memory unit through a sigmoid activation function. The output value of the sigmoid function is between 0 and 1. The closer the value is to 1, the more likely the information is to be selected to enter the memory unit, and the closer it is to 0, the more likely the information is to be discarded. In this way, the input gate can screen out the information useful for predicting soil crust changes and pass it to the memory unit for further processing.

[0134] The memory unit in the preset soil crust prediction model fuses the target fusion features with the historical hidden state at the previous moment in the memory unit to generate updated fusion features. The role of the memory unit is to store and transmit historical information, and it can remember the impact of past inputs on the current state. When updating the fusion features, the tanh activation function is usually used to transform the target fusion features, and then a weighted sum is performed with the historical hidden state at the previous moment. In this way, the current new information can be combined with the past historical information, enabling the model to comprehensively consider the information at different time points for prediction.

[0135] The forgetting gate in the preset soil crust prediction model determines the retained fusion features and the discarded fusion features from the updated fusion features in the memory unit. The forgetting gate also uses the sigmoid activation function, which decides which information in the memory unit needs to be retained and which information can be forgotten. As time goes by, some old information may no longer be helpful for the current prediction. The forgetting gate can delete this information from the memory unit to avoid information overload, while retaining the key information useful for prediction.

[0136] The output gate in the preset soil crust prediction model outputs the current hidden state based on the retained fused features. The output gate also uses the sigmoid activation function to determine which information can be output from the memory unit as the current hidden state. The current hidden state contains the model's understanding and representation of the soil crust state at the current moment, which will serve as the basis for the next calculation.

[0137] Finally, the electronic device 3 calculates the correlation between the hidden states corresponding to each moment and the future soil crust data. Various statistical methods can be used for the calculation of the correlation, such as the Pearson correlation coefficient, cosine similarity, etc. By calculating the correlation, the influence degree of the hidden state at each moment on the future soil crust data can be understood.

[0138] Based on the calculated correlation, the electronic device 3 determines the attention weight information corresponding to the hidden states at each moment. The attention weight information reflects the importance degree of the hidden state at each moment when predicting the future soil crust data. Usually, the softmax function is used to convert the correlation value into a probability distribution as the attention weight. The larger the weight, the greater the contribution of the hidden state at that moment to the prediction result.

[0139] The electronic device 3 performs a weighted sum of the hidden states corresponding to each moment according to the respective attention weight information to obtain the target hidden state. Through the weighted sum, the model can focus more on the hidden states at those moments that are more important for predicting the future soil crust data, thereby improving the prediction accuracy.

[0140] The target hidden state is input into the generative adversarial network (GAN) in the preset soil crust prediction model to output the future soil crust data. The generative adversarial network consists of a generator and a discriminator. The generator attempts to generate future soil crust data similar to the real soil crust data based on the target hidden state, and the discriminator is responsible for judging whether the generated data is real. Through the adversarial training between the generator and the discriminator, the generator can continuously learn how to generate more realistic future soil crust data and finally output the prediction result that meets the requirements, that is, the future soil crust data.

[0141] The soil crust separation and analysis system provided by the embodiment of the present application, the electronic device 3 is further configured to obtain the environmental data of the sample soil within a preset duration in the future; the environmental data includes at least one of air temperature, precipitation, light intensity, and wind speed; fuse the environmental data with the soil crust thickness, surface feature data, crust spectral data, and side image to generate an initial fusion feature, ensuring the accuracy of the generated target fusion feature. Then, input the initial fusion feature into a preset soil crust prediction model according to the time series; the input gate in the preset soil crust prediction model extracts the target fusion feature from the current fusion feature in the initial fusion feature and adds it to the memory unit in the preset soil crust prediction model, ensuring the accuracy of the target fusion feature added to the memory unit. The memory unit fuses the target fusion feature with the historical hidden state at the previous moment in the memory unit to generate an updated fusion feature, ensuring the accuracy of the generated updated fusion feature. The forgetting gate in the preset soil crust prediction model determines the retained fusion feature and the discarded fusion feature from the updated fusion feature in the memory unit, ensuring the accuracy of the determined retained fusion feature and discarded fusion feature. The output gate in the preset soil crust prediction model outputs the current hidden state based on the retained fusion feature, ensuring the accuracy of the output current hidden state. Then, calculate the correlation between the hidden state corresponding to each moment and the future soil crust data; according to each correlation, determine the attention weight information corresponding to the hidden state corresponding to each moment, ensuring the accuracy of the determined attention weight information corresponding to the hidden state corresponding to each moment. Then, perform weighted summation on the hidden states corresponding to each moment according to each attention weight information to obtain the target hidden state, ensuring the accuracy of the obtained target hidden state. Input the target hidden state into the generative adversarial network in the preset soil crust prediction model to output the future soil crust data, ensuring the accuracy of the output future soil crust data, so that the impact of soil crust on the soil ecosystem can be understood in advance according to the future soil crust data, and a reasonable soil management strategy can be formulated.

[0142] In an alternative embodiment of the present application, as Figure 2 shown, the soil crust separation device 1 includes a core cutter assembly 11, a laser ranging device 12, and a separation assembly 13; the core cutter assembly 11 is installed below the soil crust separation and analysis system, the laser ranging device 12 is installed above the core cutter assembly 11, and the separation assembly 13 is slidably installed on the connecting rod between the core cutter assembly 11 and the laser ranging device 12; wherein:

[0143] The core cutter assembly 11 is used to collect the sample soil with crust; wherein, the inside of the core cutter assembly 11 is treated with a special hydrophilic polymer coating.

[0144] A laser distance measuring device 12 is used to control the sample soil to lift upward in the vertical direction, and during the lifting process of the sample soil, obtain side images; determine the soil crust thickness according to the side images; and obtain the surface feature data corresponding to the sample soil crust.

[0145] An electronic device 3 is used to adjust the height of the separation component 13 according to the soil crust thickness, control the separation component 13 to separate the sample soil, and obtain the sample soil crust.

[0146] The separation component 13 is used to separate the sample soil under the control of the electronic device 3 to obtain the sample soil crust.

[0147] In an optional implementation manner, as Figure 3 shown, the laser distance measuring device 12 includes: a camera component 121, a lifting platform 122, a laser distance measuring component 123, and a digital display component 124. Among them, the laser distance measuring component 123 is installed above the core cutter component 11, the lifting platform 122 is installed below the core cutter component 11, and the digital display component 124 is installed outside the lifting track corresponding to the lifting platform 122; the camera component 121 is installed outside the lifting track corresponding to the lifting platform 122, and the lifting platform 122, the camera component 121, and the digital display component 124 are all connected to the electronic device 3; where:

[0148] The lifting platform 122 is used to drive the sample soil to lift upward from the core cutter component 11 under the control of the electronic device 3 after the core cutter component 11 has collected the sample soil.

[0149] The electronic device 3 is used to control the camera component 121 to collect side images in real time when the sample soil is lifted upward.

[0150] The electronic device 3 is further used to identify each side image, determine the contact interface between the sample soil crust and the lower layer soil in the sample soil; control the lifting platform 122 to drive the sample soil to lift upward in the vertical direction until the contact interface is flush with the upper surface of the core cutter component 11 and stop according to the identified contact interface.

[0151] The laser distance measuring component 123 is used to measure the lifting distance of the lifting platform 122 under the control of the electronic device 3, and determine the lifting distance as the soil crust thickness corresponding to the sample soil.

[0152] The laser distance measuring component 123 is further used to collect the surface feature data corresponding to the sample soil under the control of the electronic device 3.

[0153] In an optional implementation manner, as Figure 4As shown in the figure, the laser ranging component 123 includes: a laser sensor 1231, an annular guide rail 1232, a micro-vibration buffer component 1233, a cross bar 1234, a first motor 1235, and a steel frame 1236; where:

[0154] The diameter of the annular guide rail 1232 is the same as the size of the ring knife in the ring knife component 11 and is used to carry the laser sensor 1231.

[0155] The micro-vibration buffer component 1233 is installed on the annular guide rail 1232 and is composed of a flexible silica gel pad and a micro spring, and is used to reduce the interference of the vibration generated when the first motor 1235 drives the cross bar 1234 to slide on the laser sensor 1231.

[0156] The first motor 1235 is used to drive the cross bar 1234 to slide so that the cross bar 1234 drives the laser sensor 1231 to slide along the steel frame 1236.

[0157] The laser sensor 1231 is used to emit a first infrared light and receive a first reflected light corresponding to the first infrared light before the lifting platform 122 drives the sample soil to be lifted upward; after the lifting platform 122 stops, it emits a second infrared light and receives a second reflected light corresponding to the second infrared light.

[0158] The electronic device 3 is used to calculate the soil crust thickness based on the emission time of the first infrared light, the reception time of the first reflected light, the emission time of the second infrared light, and the reception time of the second reflected light.

[0159] The laser sensor 1231 is further used to emit visible light to the sample soil crust and generate a reflection image corresponding to the sample soil crust based on the received visible reflection signal corresponding to the visible light.

[0160] The electronic device 3 is used to identify the reflection image and determine the surface feature data corresponding to the sample soil crust, and the surface feature data includes at least one of roughness, particle distribution, and crack characteristics.

[0161] In an alternative embodiment, the electronic device 3 is used to identify the reflection image based on a preset generative adversarial network to determine the roughness corresponding to the sample soil crust; and / or, identify the reflection image based on a time-series crack dynamic monitoring and analysis method to determine the crack characteristics corresponding to the sample soil crust; and / or, identify the reflection image based on a preset object detection algorithm to determine the particle distribution corresponding to the sample soil crust.

[0162] In an alternative embodiment, as Figure 5As shown in the figure, the separation component 13 includes a sliding component 131, a separation slide rail 132, a separation knife 133, a second motor 134, a second pressure sensor 135, and a processor 136. Among them, the sliding component 131 is installed on the connecting rod between the ring knife component 11 and the laser ranging device 12. The sliding component 131 drives the separation slide rail 132 to slide on the connecting rod. The separation knife 133 is installed on the separation slide rail 132. After the sliding component 131 drives the separation slide rail 132 to be fixed at a specific position according to the soil crust thickness, the second motor 134 drives the separation knife 133 to slide on the separation slide rail 132 to separate the sample soil and obtain the sample soil crust corresponding to the sample soil. Among them:

[0163] The second pressure sensor 135 is used to collect the resistance data during the cutting process and transmit the resistance data to the processor 136 and the electronic device 3 during the process of the separation knife 133 separating the sample soil to obtain the sample soil crust corresponding to the sample soil.

[0164] The processor 136 is used to adjust the blade angle and cutting force of the separation knife 133 according to the resistance data.

[0165] Specifically, after the ring knife component 11 completes the sample collection, the lifting platform 122 starts to work. The electronic device 3 sends an instruction to the lifting platform 122 to drive the motor to drive the lifting platform 122 to rise, thereby driving the sample soil to be lifted upward from the ring knife component 11. During the lifting process, the electronic device 3 controls the imaging component 121 to continuously capture side images at a certain frame rate. The imaging component 121 converts the image of the side of the sample soil crust into a digital image signal through the principle of optical imaging and transmits it to the electronic device 3 in real time. The electronic device 3 uses an image processing algorithm to analyze the side image, identify the contact interface between the soil crust and the underlying soil in the sample soil, and when the contact interface is flush with the upper surface of the ring knife component 11, controls the lifting platform 122 to stop lifting.

[0166] The specific recognition process can be as follows: The electronic device 3 first denoises the collected side image of the sample soil crust to eliminate the noise introduced by factors such as environmental interference and equipment sensor errors. The Gaussian filtering algorithm is used to construct a Gaussian kernel function to perform weighted averaging on each pixel and its neighborhood in the side image of the sample soil crust. For example, for a 3×3 Gaussian kernel, the weight of the central pixel is the highest, and the weights of the surrounding pixels gradually decrease to smooth the image, remove salt-and-pepper noise and Gaussian noise, etc., to make the image clearer and provide a good basis for subsequent processing.

[0167] Then, the electronic device 3 converts the color side image into a grayscale side image to simplify the computational complexity. The weighted average method can be used. According to the sensitivity differences of the human eye to the three primary colors of red, green, and blue, different weights, such as 0.299, 0.587, and 0.114, are assigned respectively to convert the color pixels into grayscale values. To highlight the boundary between the soil crust and the underlying soil, the histogram equalization algorithm is used to redistribute the grayscale values of the image, making the grayscale distribution more uniform, enhancing the contrast, and making the contact interface more easily recognizable in the image.

[0168] Next, the electronic device 3 can use the Canny edge detection algorithm to extract the edge information in the grayscale side image. This algorithm first calculates the gradient magnitude and direction of the grayscale side image, refines the edges through non-maximum suppression, and then uses double-threshold detection to determine the true edges. For example, by setting a high threshold and a low threshold, the pixels with a gradient magnitude higher than the high threshold are determined as strong edges, those lower than the low threshold are discarded, and for the pixels between the two, if they are connected to the strong edges, they are retained, otherwise they are discarded, so as to accurately outline the potential boundary between the soil crust and the underlying soil.

[0169] To further enhance the edge features, the electronic device 3 can perform morphological operations. Specifically, the electronic device 3 uses the dilation operation to expand the edges through a structuring element (such as a rectangle, a circle) to connect the broken edges; then performs the erosion operation to remove the isolated noise points and small burrs, making the edges more continuous and accurate. For example, by selecting a 3×3 rectangular structuring element for dilation and erosion operations, the edge features can be effectively optimized.

[0170] Finally, based on the image after edge detection and morphological operations, and combined with the grayscale difference between the soil crust and the underlying soil, the electronic device 3 adopts a threshold segmentation algorithm. For example, the Otsu algorithm can automatically calculate an optimal threshold to divide the image into the foreground (soil crust) and the background (underlying soil), thereby determining the contact interface. If the grayscale value of the soil crust is higher than that of the underlying soil, the pixels greater than the threshold are classified as the soil crust, and those less than the threshold are the underlying soil, and the boundary between the two is the contact interface.

[0171] Then, the laser ranging component 123 measures the soil crust thickness by utilizing the propagation characteristics of light. Before the lifting platform 122 drives the sample soil to rise upward, the laser sensor 1231 in the laser ranging component 123 emits the first infrared light. After the infrared light encounters the upper surface of the sample soil crust and is reflected back, the laser sensor 1231 receives the first reflected light. The electronic device 3 calculates the first distance between the laser sensor 1231 and the upper surface of the sample soil crust before the sample soil is lifted according to the propagation speed of light and the emission time of the first infrared light and the reception time of the first reflected light through a formula. Similarly, after the lifting platform 122 stops, the laser sensor 1231 emits the second infrared light and receives the second reflected light, and calculates the second distance between the laser sensor 1231 and the upper surface of the sample soil crust after the sample soil is lifted. Finally, the electronic device 3 subtracts the second distance from the first distance to obtain the soil crust thickness corresponding to the sample soil.

[0172] In addition, the laser sensor 1231 can also emit visible light to the sample soil crust. After the visible light is reflected on the surface of the soil crust, the laser sensor 1231 receives the visible reflection signal corresponding to the visible light, thereby generating a reflection image corresponding to the sample soil crust. For this reflection image, the electronic device 3 analyzes it using different algorithms.

[0173] Specifically, to improve the accuracy of subsequent analysis, the electronic device 3 can preprocess the reflection image. The noise in the image is removed using a filtering algorithm. Median filtering can effectively eliminate salt-and-pepper noise, while Gaussian filtering is suitable for removing Gaussian noise, making the reflection image clearer. The contrast of the image is enhanced through gray-scale transformation, making the texture features more obvious. For example, using the histogram equalization method, the gray-scale values of the image are redistributed, stretching the gray-scale range and highlighting the details on the surface of the soil crust. In addition, an image dehazing algorithm is adopted to remove the image blur caused by environmental factors and restore the real texture information, making the cracks more obvious in the image.

[0174] Then, the electronic device 3 inputs the reflection image corresponding to the sample soil crust whose roughness is to be determined into the trained preset generative adversarial network. Here, the reflection image needs to have the same preprocessing method as the training data to ensure the consistency of the data format and feature scale. The generator in the preset generative adversarial network generates a simulated soil crust image according to the features of the input reflection image. This soil crust image is generated based on the roughness feature pattern learned by the generator during the training process, and it attempts to imitate the roughness performance of the real image.

[0175] The discriminator evaluates the input real reflection image and the simulated soil crust image generated by the generator, and outputs the probability values that the two images are real images. By comparing these two probability values and the performance of the generator and discriminator during the training process, the roughness of the sample soil crust can be inferred. For example, if the probability value obtained by the image generated by the generator in the discriminator is close to the probability value of the real image, it indicates that the generator can better simulate the roughness characteristics of the current sample. Combining the relationship between the roughness learned by the generator during the training process and the generated image, the roughness corresponding to the sample soil crust can be determined. In addition, some quantitative indicators, such as mean squared error (MSE), peak signal-to-noise ratio (PSNR), etc., can be used to measure the difference between the generated image and the real image, and further accurately determine the roughness of the soil crust.

[0176] Among them, the training process of the preset generative adversarial network includes: collecting a large number of soil crust reflection images with different roughnesses as training data. These images need to be preprocessed, such as normalization processing, to unify the pixel values of the images to a specific range, such as [0, 1] or [-1, 1], to improve the training effect and stability. During the training process, the generator and the discriminator conduct an adversarial game. The generator tries to generate more realistic images to deceive the discriminator, while the discriminator tries to improve its discrimination ability and accurately identify the generated images. Specifically, the generator generates an image based on random noise, and the discriminator judges the real image and the generated image. The loss function of the discriminator is based on its judgment results of the real image and the generated image, and it hopes to output 1 for the real image and 0 for the generated image. The loss function of the generator is based on the discriminator's judgment result of the generated image, and it hopes that the discriminator misjudges the generated image as a real image, that is, outputs a probability value close to 1. Through the backpropagation algorithm, the parameters of the generator and the discriminator are updated respectively to continuously improve their capabilities. During the training process, some optimization strategies can also be adopted, such as adjusting the learning rate, using regularization methods, etc., to prevent the model from overfitting and improve the generalization ability of the model. Based on the preset generative adversarial network (GAN), through the adversarial training of the generator and the discriminator, the model learns the characteristic patterns of the surface roughness of the soil crust, so as to determine the roughness corresponding to the sample soil crust.

[0177] In addition, the electronic device 3 calculates the gradient magnitude and direction of the reflection image, and adopts non-maximum suppression and double-threshold detection steps, which can accurately detect the edges of the cracks. During the detection process, it is necessary to reasonably adjust the parameters of the algorithm, such as high and low thresholds, according to the characteristics of the image and actual requirements, to ensure that the detected crack edges are complete and accurate.

[0178] For the detected cracks, the electronic device 3 can calculate characteristic parameters such as crack length, width, area, and quantity. For the crack length, it can be obtained by counting and calculating the pixel points on the crack edge; the crack width can be measured in the direction perpendicular to the crack; the crack area is calculated by accumulating the pixel points in the crack region; and the crack quantity is obtained by marking and counting the detected cracks. Through these quantified characteristic parameters, the state of the soil crust cracks can be comprehensively described.

[0179] In addition, the electronic device 3 can also input the reflection image into a trained object detection model. The convolutional layer and pooling layer in the object detection model extract the image features of the reflection image, and then perform object detection according to different algorithms. Taking YOLO as an example, the prediction results of each grid are calculated to obtain a series of bounding boxes and class probabilities. The overlapping bounding boxes with a high degree of overlap are removed through the non-maximum suppression (NMS) algorithm, and the most accurate detection results are retained.

[0180] According to the detected particle bounding boxes, the distribution density of the particles is calculated. The object detection model can divide the image into multiple sub-regions, count the number of particles in each sub-region, and obtain the spatial distribution density map of the particles. For the particle size distribution, the equivalent diameter or area of each particle is calculated through the size of the bounding box, and a histogram of the particle sizes is drawn to analyze the proportion of particles of different sizes. In addition, the electronic device 3 can also introduce spatial autocorrelation analysis to study the spatial correlation of the particle distribution and determine whether the particles are randomly distributed, aggregated, or uniformly distributed.

[0181] Finally, the electronic device 3 can calculate the specific position that the separation component 13 needs to move to according to the soil crust thickness measured by the laser ranging device 12. Then, it controls the sliding component 131 to drive the separation slide rail 132 to slide on the connecting rod to this specific position to complete the positioning preparation work before separation.

[0182] Then, the second motor 134 drives the blade of the separation knife 133 to slide on the separation slide rail 132 to cut and separate the sample soil. During the cutting process, the second pressure sensor 135 can collect the resistance data in real time. Based on the piezoelectric effect or the strain gauge principle, the second pressure sensor 135 converts the cutting resistance into an electrical signal and transmits this data to the processor 136 and the electronic device 3.

[0183] Based on the received resistance data, the processor 136 calculates the required blade angle and cutting force adjustment value for the separating knife 133 in the current cutting state through an algorithm. Then, it controls the actuator of the separating knife 133 to adjust the blade angle and cutting force to ensure the smooth progress of the separation process. If the resistance is too large, it may be caused by an inappropriate blade angle or excessive cutting force, resulting in damage to the soil crust. At this time, the processor 136 will reduce the cutting force and adjust the blade angle; if the resistance is too small, it may be due to insufficient cutting force leading to incomplete separation, and the processor 136 will increase the cutting force. The electronic device 3 can also monitor and adjust the entire separation process based on the pressure data to ensure the separation quality.

[0184] In an alternative embodiment, the sliding component 131 of the separation component 13 can be equipped with a high-precision linear magnetic encoder. The linear magnetic encoder can accurately measure the position of the sliding module in real time, and its accuracy is higher than that of traditional optoelectronic encoders, reaching ±0.01 mm. This enables the cutting device to more accurately position when automatically adjusting the cutting height according to the crust thickness, ensuring the accuracy of the cutting position and further improving the accuracy of soil crust separation.

[0185] The soil crust separation and analysis system provided by the embodiments of the present application. The soil crust separation device 1 includes a core cutter assembly 11, a laser ranging device 12, and a separation assembly 13. Among them, the core cutter assembly 11 is installed below the soil crust separation and analysis system, the laser ranging device 12 is installed above the core cutter assembly 11, and the separation assembly 13 is slidably installed on the connecting rod between the core cutter assembly 11 and the laser ranging device 12; the laser ranging device 12 and the separation assembly 13 are respectively connected to the electronic device 3, where: The core cutter assembly 11 is used to collect the sample soil with crust; among them, the inside of the core cutter assembly 11 is treated with a special hydrophilic polymer coating. The lifting platform 122 is used to drive the sample soil to lift upward from the core cutter assembly 11 under the control of the electronic device 3 after the core cutter assembly 11 collects the sample soil, so as to facilitate the separation of the sample soil and obtain the sample soil crust corresponding to the sample soil. The electronic device 3 is used to control the imaging component 121 to collect side images in real time when the sample soil is lifted upward, ensuring the accuracy of the obtained side images of the soil crust. The electronic device 3 is also used to identify each side image to determine the contact interface between the sample soil crust and the underlying soil in the sample soil, ensuring the accuracy of the determined contact interface between the sample soil crust and the underlying soil in the sample soil. According to the identified contact interface, control the lifting platform 122 to drive the sample soil to lift vertically upward until the contact interface is flush with the upper surface of the core cutter assembly 11 and stop, so as to facilitate measuring the soil crust thickness and separating the sample soil to obtain the sample soil crust corresponding to the sample soil. The laser ranging component 123 is used to measure the lifting distance of the lifting platform 122 under the control of the electronic device 3 and determine the lifting distance as the soil crust thickness corresponding to the sample soil, ensuring the accuracy of the determined soil crust thickness corresponding to the sample soil. The laser ranging component 123 is also used to collect the surface feature data corresponding to the sample soil under the control of the electronic device 3, so that the sample soil crust can be studied based on the surface feature data, thus contributing to the research of agricultural soil science.

[0186] The electronic device 3 is used to store the soil crust thickness and surface feature data, and adjust the height of the separation assembly 13 according to the soil crust thickness, and control the separation assembly 13 to separate the sample soil to obtain the sample soil crust corresponding to the sample soil.

[0187] The diameter of the annular guide rail 1232 is the same as the size of the annular cutter in the annular cutter assembly 11 and is used to carry the laser sensor 1231. The micro-vibration buffer assembly 1233, which is installed on the annular guide rail 1232 and consists of a flexible silica gel pad and a micro spring, is used to reduce the interference of the vibration generated when the first motor 1235 drives the cross bar 1234 to slide to the laser sensor 1231. The first motor 1235 is used to drive the cross bar 1234 to slide, so that the cross bar 1234 can drive the laser sensor 1231 to slide along the steel frame 1236. The diameter of the annular guide rail 1232 is the same as the size of the annular cutter in the annular cutter assembly 11 and is used to carry the laser sensor 1231. The micro-vibration buffer assembly 1233, which is installed on the annular guide rail 1232 and consists of a flexible silica gel pad and a micro spring, is used to reduce the interference of the vibration generated when the first motor 1235 drives the cross bar 1234 to slide to the laser sensor 1231. The first motor 1235 is used to drive the cross bar 1234 to slide, so that the cross bar 1234 can drive the laser sensor 1231 to slide along the steel frame 1236. The laser sensor 1231 is used to emit the first infrared light and receive the first reflected light corresponding to the first infrared light before the lifting platform 122 drives the sample soil to lift upward; after the lifting platform 122 stops, it emits the second infrared light and receives the second reflected light corresponding to the second infrared light. The electronic device 3 is used to determine the first distance between the laser sensor 1231 and the upper surface of the sample soil crust before the sample soil is lifted based on the emission time of the first infrared light and the reception time of the first reflected light, ensuring the accuracy of the determined first distance. Based on the emission time of the second infrared light and the reception time of the second reflected light, determine the second distance between the laser sensor 1231 and the upper surface of the sample soil crust after the sample soil is lifted, ensuring the accuracy of the determined second distance. Subtract the second distance from the first distance to calculate the soil crust thickness corresponding to the sample soil, ensuring the accuracy of the obtained soil crust thickness. The laser sensor 1231 is also used to emit visible light to the sample soil crust and generate a reflection image corresponding to the sample soil crust based on the received visible reflection signal, ensuring the accuracy of the generated reflection image corresponding to the sample soil crust. The electronic device 3 is used to identify the reflection image based on a preset generative adversarial network to determine the roughness corresponding to the sample soil crust, ensuring the accuracy of the determined roughness corresponding to the sample soil crust. Identify the reflection image based on the crack dynamic monitoring and analysis method based on time series to determine the crack characteristics corresponding to the sample soil crust, ensuring the accuracy of the determined crack characteristics corresponding to the sample soil crust. Identify the reflection image based on a preset object detection algorithm to determine the particle distribution corresponding to the sample soil crust, ensuring the accuracy of the determined particle distribution corresponding to the sample soil crust.

[0188] The separation component 13 includes: a sliding component 131, a separation slide rail 132, a separation knife 133, a second motor 134, a second pressure sensor 135, and a processor 136. Among them, the sliding component 131 is installed on the connecting rod between the ring knife component 11 and the laser ranging device 12. The sliding component 131 drives the separation slide rail 132 to slide on the connecting rod. The separation knife 133 is installed on the separation slide rail 132. After the sliding component 131 drives the separation slide rail 132 to be fixed at a specific position according to the soil crust thickness, the second motor 134 drives the separation knife 133 to slide on the separation slide rail 132 to separate the sample soil and obtain the sample soil crust corresponding to the sample soil. Among them: The second pressure sensor 135 is used to collect the resistance data during the cutting process and transmit the resistance data to the processor 136 and the electronic device 3 when the separation knife 133 separates the sample soil to obtain the sample soil crust corresponding to the sample soil. The processor 136 is used to adjust the blade angle and cutting force of the separation knife 133 according to the resistance data, ensuring the accuracy of adjusting the blade angle and cutting force of the separation knife 133.

[0189] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A soil crust separation and analysis system, characterized in that, Including: A core cutter assembly, a camera assembly, a lifting platform, a laser ranging assembly, a separation assembly, a digital display assembly, a crust spectral acquisition device, and an electronic device; wherein: The core cutter assembly is used to collect the sample soil with crust. The lifting platform is used to drive the sample soil to lift upward from the core cutter assembly under the control of the electronic device after the core cutter assembly has collected the sample soil. The electronic device is used to control the camera assembly to collect side images in real time when the sample soil is lifted upward. The electronic device is also used to adopt the Gaussian filtering algorithm, construct a Gaussian kernel function, perform weighted averaging on each pixel and its neighborhood in each crust side view to obtain a denoised color image; according to the sensitivity differences of the human eye to the three primary colors of red, green, and blue, different weights are assigned to the three primary colors of red, green, and blue respectively, and the denoised color image is converted into a grayscale image according to the weight information; extract the edges in the grayscale image based on the edge detection algorithm; use the dilation operation to expand the edges through the structuring element to connect the broken edges; then perform the erosion operation to remove isolated noise points and small burrs to obtain the image after morphological operation; adopt the threshold segmentation algorithm to divide the image after morphological operation into the sample soil crust and the underlying soil, and determine the contact interface between the sample soil crust and the underlying soil; control the lifting platform to drive the sample soil to lift vertically upward until the contact interface is flush with the upper surface of the core cutter assembly and stop according to the identified contact interface. The laser ranging assembly is used to measure the lifting distance of the lifting platform and determine the thickness of the soil crust corresponding to the sample soil as the lifting distance. The laser ranging assembly is also used to collect the surface feature data corresponding to the sample soil crust. The electronic device is used to adjust the height of the separation assembly according to the soil crust thickness, control the separation assembly to separate the sample soil, and obtain the sample soil crust. The crust spectral acquisition device is used to obtain the crust spectral data corresponding to the sample soil crust. The electronic device is used to perform data processing on the soil crust thickness, side images, surface feature data, and crust spectral data to determine the soil state data corresponding to the sample soil; output corresponding processing measures according to the soil state data.

2. The soil crust separation and analysis system according to claim 1, characterized in that, The said electronic device is used for Performing feature fusion on the soil crust thickness, the surface feature data, the crust spectral data, and the side images to generate a target high-dimensional feature vector; Performing principal component analysis on the target high-dimensional feature vector, and converting the target high-dimensional feature vector into a set of linearly independent target principal components through linear transformation; Performing feature extraction on the target principal components to determine the soil state data corresponding to the sample soil.

3. The soil crust separation and analysis system according to claim 2, wherein The said electronic device is used for Performing feature extraction on the soil crust thickness, surface feature data, crust spectral data, and side images, and converting the extracted features into corresponding feature vectors; Concatenating each of the said feature vectors to generate an initial high-dimensional feature vector; Based on a preset encoder, performing compression processing on the initial high-dimensional feature vector to generate a compressed low-dimensional feature vector; Based on a preset decoder, performing decoding processing on the compressed low-dimensional feature vector to generate the target high-dimensional feature vector.

4. The soil crust separation and analysis system according to claim 1, wherein The electronic device is further configured to obtain environmental data of the sample soil within a preset future time period; the environmental data includes at least one of air temperature, precipitation, light intensity, and wind speed; Input the environmental data, the soil crust thickness, the surface feature data, the crust spectral data, and the side image into a preset soil crust prediction model, and output the future soil crust data of the sample soil corresponding to the preset future time period.

5. The soil crust separation and analysis system according to claim 4, wherein The preset soil crust prediction model includes an input gate, a memory unit, a forgetting gate, an output gate, and a generative adversarial network. The electronic device is configured to fuse the environmental data, the soil crust thickness, the surface feature data, the crust spectral data, and the side image to generate an initial fusion feature; Input the initial fusion feature into the preset soil crust prediction model according to a time series; The input gate extracts a target fusion feature from the current fusion feature in the initial fusion feature and adds it to the memory unit; The memory unit fuses the target fusion feature and the historical hidden state at the previous moment to generate an updated fusion feature; The forgetting gate determines a retained fusion feature and a discarded fusion feature from the updated fusion feature; The output gate outputs the current hidden state based on the retained fusion feature; Calculate the correlation between the hidden states corresponding to each moment and the future soil crust data, and determine the attention weight information corresponding to the hidden states corresponding to each moment; According to each attention weight information, perform a weighted sum of the hidden states corresponding to each moment to obtain a target hidden state; Input the target hidden state into the generative adversarial network and output the future soil crust data.

6. The soil crust separation and analysis system according to claim 1, wherein, The core cutter assembly is installed below the soil crust separation and analysis system, the laser ranging assembly is installed above the core cutter assembly, the lifting platform is installed below the core cutter assembly, and the camera assembly is installed outside the lifting track corresponding to the lifting platform; the digital display assembly is installed outside the lifting track corresponding to the lifting platform; the separation assembly is slidably installed on the connecting rod between the core cutter assembly and the laser ranging device.

7. The soil crust separation and analysis system according to claim 1 or 6, characterized in that, The laser ranging assembly includes: a laser sensor, an annular guide rail, a micro-vibration buffer assembly, a cross bar, a first motor, and a steel frame; wherein: The diameter of the annular guide rail is the same as the size of the core cutter in the core cutter assembly and is used to carry the laser sensor; The micro-vibration buffer assembly is installed on the annular guide rail and is composed of a flexible silica gel pad and a micro spring; The first motor is used to drive the cross bar to slide, so that the cross bar drives the laser sensor to slide along the steel frame; The laser sensor is configured to emit a first infrared light and receive a first reflected light corresponding to the first infrared light before the lifting platform drives the sample soil to lift upward; after the lifting platform stops, emit a second infrared light and receive a second reflected light corresponding to the second infrared light; The electronic device is configured to calculate the soil crust thickness based on the emission time of the first infrared light, the reception time of the first reflected light, the emission time of the second infrared light, and the reception time of the second reflected light. The laser sensor is further configured to emit visible light to the sample soil crust and generate a reflection image corresponding to the sample soil crust based on the received visible reflection signal corresponding to the visible light. The electronic device is configured to identify the reflection image to determine the surface feature data corresponding to the sample soil crust, where the surface feature data includes at least one of roughness, particle distribution, and crack characteristics.

8. The soil crust separation and analysis system according to claim 7, characterized in that The electronic device is configured to identify the reflection image based on a preset generative adversarial network to determine the roughness corresponding to the sample soil crust. and / or identify the reflection image based on a time series-based crack dynamic monitoring and analysis method to determine the crack characteristics corresponding to the sample soil crust. and / or identify the reflection image based on a preset object detection algorithm to determine the particle distribution corresponding to the sample soil crust.

9. The soil crust separation and analysis system according to claim 1, characterized in that The separation component includes: a sliding component, a separation slide rail, a separation knife, a second motor, a second pressure sensor, and a processor; the sliding component is installed on a connecting rod between the core cutter assembly and the laser ranging device, the sliding component drives the separation slide rail to slide on the connecting rod, the separation knife is installed on the separation slide rail, and after the sliding component drives the separation slide rail to be fixed to a specific position according to the soil crust thickness, the second motor drives the separation knife to slide on the separation slide rail to separate the sample soil to obtain the sample soil crust corresponding to the sample soil; where: The second pressure sensor is configured to collect resistance data during the cutting process when the separation knife separates the sample soil to obtain the sample soil crust corresponding to the sample soil, and transmit the resistance data to the processor and the electronic device. The processor is configured to adjust the blade angle and cutting force of the separation knife according to the resistance data.

Images