Tilling depth detection method and system based on soil condition data

Abstract

The invention discloses a tilling depth detection method and system based on soil condition data. The system comprises a soil data acquisition module, a data transmission module, a data processing module, a tilling depth calculation module and a result display module which are in communication connection. The soil data acquisition module comprises a soil texture detection unit, a soil humidity detection unit, a soil flatness detection unit and a soil impurity detection unit; the data processing module comprises a data analysis unit and a data fusion unit; the tilling depth calculation module calculates the shoveling depth of the tilling equipment according to the soil condition data processed by the data processing module; by collecting soil condition data and utilizing a support vector machine algorithm to establish a relation model between the soil condition and the tilling depth, the shoveling depth of the tilling equipment can be accurately detected, and the accuracy and the reliability of tilling depth detection are improved; different types of soil condition data are fused, the influence of various soil conditions on the tilling depth can be comprehensively considered, and the adaptability and stability of tilling depth detection are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tillage depth detection methods, and in particular to a tillage depth detection method and system based on soil condition data. Background Art

[0002] In agricultural production, accurate detection of tillage depth (plowing depth) of tillage equipment is crucial to optimizing soil structure and increasing crop yields. Traditional tillage depth detection methods are often inaccurate and poorly adaptable, making it difficult to meet the needs of modern agricultural production. With the development of sensor technology and data analysis technology, it has become possible to detect tillage depth based on soil condition data, which can improve the accuracy and reliability of tillage depth detection. Summary of the invention

[0003] In view of the above technical problems in the related art, the present invention proposes a tillage depth detection method and system based on soil condition data, which can overcome the above shortcomings of the prior art.

[0004] To achieve the above technical objectives, the technical solution of the present invention is implemented as follows: A tillage depth detection system based on soil condition data; The tillage depth detection system based on soil condition data includes a soil data acquisition module, a data transmission module, a data processing module, a tillage depth calculation module and a result display module connected in communication; The soil data acquisition module includes a soil texture detection unit, a soil moisture detection unit, a soil flatness detection unit and a soil debris detection unit; the data transmission module is used to transmit the data collected by the soil data acquisition module to the data processing module; the data processing module includes a data analysis unit and a data fusion unit, the data analysis unit uses a support vector machine algorithm to analyze and process the collected soil condition data, and establishes a relationship model between soil conditions and tillage depth, the data fusion unit fuses different types of soil condition data to improve the accuracy of tillage depth detection; the tillage depth calculation module calculates the shoveling depth of the tillage equipment according to the soil condition data processed by the data processing module.

[0005] Furthermore, the soil texture detection unit includes a portable soil texture analyzer, and the soil texture detection unit determines the soil texture type by measuring the particle size distribution and density parameters of the soil; the soil moisture detection unit includes a soil moisture sensor, and the soil moisture sensor is used to measure the moisture content in the soil in real time; the soil flatness detection unit includes a laser scanner for detecting the flatness of the soil surface or a camera installed on the tillage equipment; the soil debris detection unit includes a camera for collecting soil images, and the soil debris detection unit uses an image recognition algorithm to detect stones and grass roots in the soil.

[0006] Furthermore, the data transmission module adopts any one of the transmission modes of serial communication wired transmission mode, Ethernet wired transmission mode, Bluetooth wireless transmission mode, Wi-Fi wireless transmission mode or ZigBee wireless transmission mode.

[0007] Furthermore, the result display module is used to display the tillage depth result calculated by the tillage depth calculation module to the user, and the result display module includes a display screen and a mobile phone APP. The tillage depth result includes a tillage depth value and a chart.

[0008] Furthermore, the soil moisture sensor is a frequency domain reflectometry sensor or a time domain reflectometry sensor.

[0009] According to another aspect of the present invention, a tillage depth detection method based on soil condition data is provided.

[0010] The tillage depth detection method based on soil condition data comprises the following steps: S1: Soil data collection: before the tillage equipment starts working, the soil data collection module is started to collect data such as soil texture, moisture, flatness and debris, and the results are transmitted to the data processing module; S2: Data transmission: the collected soil condition data is transmitted to the data processing module through the data transmission module; S3: Data analysis and fusion. After the data processing module receives the soil condition data, the data analysis unit uses a support vector machine algorithm to analyze and process the data. S4: Calculating tillage depth, the tillage depth calculation module calculates the tillage depth using a mathematical model or an empirical formula according to the soil condition data processed by the data processing module and the working parameters of the tillage equipment; S5: result display, the result display module displays the tillage depth result calculated by the tillage depth calculation module to the user in an intuitive manner; the tillage depth result is displayed as a tillage depth value on the display screen in the cab of the tillage equipment or the tillage depth information is displayed in real time through a mobile phone APP.

[0011] Furthermore, the S1 further includes the following steps: S101: before the tillage equipment starts working, the soil texture detection unit is started to analyze the soil sample to determine the soil texture type, and the result is transmitted to the data processing module; S102: before the tillage equipment starts working, the soil moisture detection unit is started to measure the moisture content in the soil in real time, and the data is transmitted to the data processing module; S103: before the tillage equipment starts working, the soil flatness detection unit is started to collect three-dimensional contour data or images of the soil surface through a laser scanner or a camera, and soil flatness information is obtained after processing, and the result is transmitted to the data processing module; S104: Before the tillage equipment starts working, the soil debris detection unit is started to collect soil images through a camera, and the debris in the soil is detected using an image recognition algorithm, and the result is transmitted to the data processing module.

[0012] Furthermore, S3 also includes the following steps: S301: preprocessing the data, including data cleaning, normalization and other operations, to improve the quality and availability of the data; S302: using a support vector machine algorithm to establish a relationship model between soil conditions and tillage depths, by collecting a large amount of soil condition data and corresponding tillage depth data for training, continuously optimizing model parameters and improving model accuracy; S303: The data fusion unit fuses different types of soil condition data, assigns different weights according to the degree of influence of different soil conditions on tillage depth, and obtains comprehensive soil condition data.

[0013] Furthermore, the mathematical model uses the following formula to calculate the tillage depth: Tillage depth = f * (soil texture weight × soil texture parameter + soil moisture weight × soil moisture parameter + soil flatness weight × soil flatness parameter + soil debris weight × soil debris parameter + tractor traction parameter + tractor speed parameter); Among them, f is a functional relationship, which is determined through experiments or data analysis; soil texture weight, soil moisture weight, soil flatness weight and soil debris weight are determined according to the influence of different soil conditions on tillage depth.

[0014] The beneficial effects of the present invention are as follows: by collecting soil condition data and using the support vector machine algorithm to establish a relationship model between soil conditions and tillage depth, the shovel depth of the tillage equipment can be accurately detected, and the accuracy and reliability of tillage depth detection can be improved. By using data fusion technology, different types of soil condition data are fused, and the influence of various soil conditions on tillage depth can be comprehensively considered, thereby improving the adaptability and stability of tillage depth detection. The result display module displays the tillage depth results to the user in an intuitive manner, which is convenient for the user to adjust the working parameters of the tillage equipment in a timely manner and improve agricultural production efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a logic block diagram of a tillage depth detection method based on soil condition data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0018] It should be understood that, in the description of the embodiments of the present invention, the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, which is only for the convenience of describing the embodiments of the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, the meaning of "several" is two or more, unless otherwise clearly and specifically defined.

[0019] In a first aspect, a tillage depth detection system based on soil condition data according to an embodiment of the present invention includes a soil data acquisition module, a data transmission module, a data processing module, a tillage depth calculation module and a result display module that are communicatively connected; the soil data acquisition module includes a soil texture detection unit, a soil moisture detection unit, a soil flatness detection unit and a soil debris detection unit.

[0020] Soil texture detection unit: A portable soil texture analyzer is used to determine the soil texture type, such as sand, loam, clay, etc., by measuring the soil's particle size distribution, density and other parameters.

[0021] Soil moisture detection unit: Use soil moisture sensor to measure the moisture content in the soil in real time. Common sensor types include frequency domain reflectometry (FDR) sensor and time domain reflectometry (TDR) sensor.

[0022] Soil flatness detection unit: The flatness of the soil surface is detected by combining a laser scanner or a camera installed on the tillage equipment with image analysis technology. The laser scanner can quickly obtain the three-dimensional contour data of the soil surface, while the image analysis technology can identify the ups and downs of the soil surface by processing the images taken by the camera.

[0023] Soil debris detection unit: uses machine vision technology to collect soil images through a camera, and uses image recognition algorithms to detect debris such as stones and grass roots in the soil.

[0024] Data transmission module: transmits the data collected by the soil data acquisition module to the data processing module. It can adopt wired transmission mode (such as serial communication, Ethernet, etc.) or wireless transmission mode (such as Bluetooth, Wi-Fi, ZigBee, etc.).

[0025] Data processing module: including data analysis unit and data fusion unit; wherein, data analysis unit: adopts support vector machine algorithm to analyze and process the collected soil condition data, and establishes the relationship model between soil condition and tillage depth.

[0026] Data fusion unit: Fusion of different types of soil condition data to improve the accuracy of tillage depth detection. For example, soil texture, moisture, flatness, and debris data can be weighted and fused, and different weights can be assigned according to the degree of influence of different soil conditions on tillage depth.

[0027] Plowing depth calculation module: Calculate the shovel depth of the tillage equipment based on the soil condition data processed by the data processing module. The tillage depth can be calculated by combining the soil condition data and the working parameters of the tillage equipment (such as the traction and speed of the tractor).

[0028] Result display module: displays the tillage depth results calculated by the tillage depth calculation module to the user in an intuitive way. It can display tillage depth values, charts and other information using display screens, mobile phone apps and other methods.

[0029] In the second aspect, according to a tillage depth detection method based on soil condition data described in an embodiment of the present invention, the purpose of this method is to provide a tillage depth detection method based on soil condition data, using a support vector machine algorithm to accurately calculate the shovel depth of the tillage equipment, provide a scientific basis for agricultural production, and improve the quality and efficiency of tillage operations. Specifically, it includes the following steps: S1: Soil data collection; Before the tillage equipment starts working, start the soil data collection module to collect data such as soil texture, moisture, flatness and debris.

[0030] The soil texture detection unit determines the soil texture type by analyzing the soil samples and transmits the results to the data processing module.

[0031] The soil moisture detection unit measures the moisture content in the soil in real time and transmits the data to the data processing module.

[0032] The soil flatness detection unit collects three-dimensional contour data or images of the soil surface through a laser scanner or camera, obtains soil flatness information after processing, and transmits the results to the data processing module.

[0033] The soil debris detection unit collects soil images through a camera, uses an image recognition algorithm to detect debris in the soil, and transmits the results to the data processing module.

[0034] S2: Data analysis and fusion; The collected soil condition data is transmitted to the data processing module through the data transmission module. If wireless transmission is used, the stability and reliability of the transmission must be ensured to avoid data loss or interference.

[0035] S3: Data transmission; After the data processing module receives the soil condition data, the data analysis unit uses the support vector machine algorithm to analyze and process the data. First, the data is preprocessed, including data cleaning, normalization and other operations to improve the quality and availability of the data.

[0036] Then, the support vector machine algorithm is used to establish the relationship model between soil conditions and tillage depth. By collecting a large amount of soil condition data and corresponding tillage depth data for training, the model parameters are continuously optimized to improve the accuracy of the model.

[0037] The data fusion unit fuses different types of soil condition data, assigns different weights according to the degree of influence of different soil conditions on tillage depth, and obtains comprehensive soil condition data.

[0038] S4: Ploughing depth calculation; The tillage depth calculation module calculates the tillage depth using a mathematical model or empirical formula based on the soil condition data processed by the data processing module and the working parameters of the tillage equipment.

[0039] For example, the tillage depth can be calculated using the following formula: Tillage depth = f* (soil texture weight × soil texture parameter + soil moisture weight × soil moisture parameter + soil flatness weight × soil flatness parameter + soil debris weight × soil debris parameter + tractor traction parameter + tractor speed parameter); Among them, f is a functional relationship, which can be determined by experiments or data analysis. The soil texture weight, soil moisture weight, soil flatness weight and soil debris weight are determined according to the influence of different soil conditions on the tillage depth.

[0040] S5: Results display; The result display module displays the tillage depth results calculated by the tillage depth calculation module to the user in an intuitive manner; the tillage depth value can be displayed on the display screen in the cab of the tillage equipment, or the tillage depth information can be viewed in real time through a mobile phone APP.

[0041] Users can adjust the working parameters of the tillage equipment according to the displayed tillage depth results to achieve the best tillage depth effect.

[0042] The specific advantages of the support vector machine algorithm selected by the present invention are as follows: 1: Small sample size and strong adaptability; In tillage depth detection, especially in some small farms or new agricultural experimental areas, the data sample size is often limited. The support vector machine algorithm performs well in small sample conditions and can make full use of limited data information for accurate analysis and modeling. For example, in a small-scale farm, there may be only dozens of sets of soil condition data and corresponding tillage depth data. The support vector machine algorithm can find the optimal hyperplane and dig out the relationship between soil conditions and tillage depth in these limited data.

[0043] 2: Powerful nonlinear processing capability; The relationship between soil conditions and tillage depth is usually complex and may be nonlinear. The support vector machine algorithm can effectively handle this nonlinear relationship by mapping the original data into a high-dimensional space using a kernel function. For example, when studying the effect of soil moisture on tillage depth, as the moisture changes, the tillage depth may not be a simple linear change, but a complex curve relationship. The kernel function of the support vector machine can adapt to this complex nonlinear change trend and accurately capture the relationship between soil conditions and tillage depth.

[0044] 3: Good generalization ability; The support vector machine algorithm aims to find a hyperplane with the largest margin, which makes it have better generalization ability when facing new data. For tillage depth detection in different farmland environments, as long as the new data has similar distribution characteristics to the training data, the support vector machine algorithm can give a more reasonable prediction result. For example, a support vector machine model established in one region can also have a good application effect in another region with similar climate and soil conditions.

[0045] 4: Parameter adjustment is relatively simple; Although the performance of the support vector machine algorithm also depends on the selection of parameters, such as the type and parameters of the kernel function, the penalty parameter, etc., the parameter adjustment of the support vector machine is relatively simple compared to other algorithms. In practical applications, it is easier for users who are not familiar with machine learning algorithms to adjust the parameters of the support vector machine. For example, when choosing a Gaussian kernel function, you only need to pay attention to a few key parameters such as the kernel width, and you can find more suitable parameter values ​​through certain experiments and experience.

[0046] The support vector machine regression implementation code is as follows: from sklearn.svm import SVR from sklearn.model_selection import train_test_split # Assume data is stored in array X and target variable is stored in array y X = np.array([...]) y = np.array([...]) # Divide into training set and test set X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2) # Create a support vector machine regressor svm_regressor = SVR() # Train the SVM regressor svm_regressor.fit(X_train, y_train) # Evaluate the SVM regressor on the test set mse = mean_squared_error(y_test, svm_regressor.predict(X_test)) In summary, with the help of the above technical solution of the present invention, by collecting soil condition data and using the support vector machine algorithm to establish a relationship model between soil conditions and tillage depth, the shoveling depth of the tillage equipment can be accurately detected, and the accuracy and reliability of tillage depth detection can be improved. By using data fusion technology to fuse different types of soil condition data, the influence of various soil conditions on tillage depth can be comprehensively considered, and the adaptability and stability of tillage depth detection can be improved. The result display module displays the tillage depth results to the user in an intuitive way, which is convenient for the user to adjust the working parameters of the tillage equipment in time and improve agricultural production efficiency and quality.

[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A tillage depth detection system based on soil condition data, characterized in that: It includes a soil data acquisition module, a data transmission module, a data processing module, a tillage depth calculation module and a result display module connected by communication; The soil data acquisition module includes a soil texture detection unit, a soil moisture detection unit, a soil flatness detection unit and a soil debris detection unit; the data transmission module is used to transmit the data collected by the soil data acquisition module to the data processing module; the data processing module includes a data analysis unit and a data fusion unit, the data analysis unit uses a support vector machine algorithm to analyze and process the collected soil condition data, and establishes a relationship model between soil conditions and tillage depth, and the data fusion unit fuses different types of soil condition data to improve the accuracy of tillage depth detection; The tillage depth calculation module calculates the shoveling depth of the tillage equipment according to the soil condition data processed by the data processing module.

2. A tillage depth detection system based on soil condition data according to claim 1, characterized in that: The soil texture detection unit includes a portable soil texture analyzer, and the soil texture detection unit determines the soil texture type by measuring the particle size distribution and density parameters of the soil; the soil moisture detection unit includes a soil moisture sensor, and the soil moisture sensor is used to measure the moisture content in the soil in real time; the soil flatness detection unit includes a laser scanner for detecting the flatness of the soil surface or a camera installed on the tillage equipment; the soil debris detection unit includes a camera for collecting soil images, and the soil debris detection unit uses an image recognition algorithm to detect stones and grass roots in the soil.

3. A tillage depth detection system based on soil condition data according to claim 1, characterized in that: The data transmission module adopts any one of the transmission modes of serial communication wired transmission mode, Ethernet wired transmission mode, Bluetooth wireless transmission mode, Wi-Fi wireless transmission mode or ZigBee wireless transmission mode.

4. The tillage depth detection system based on soil condition data according to claim 1, characterized in that: The result display module is used to display the tillage depth result calculated by the tillage depth calculation module to the user. The result display module includes a display screen and a mobile phone APP. The tillage depth result includes a tillage depth value and a chart.

5. The tillage depth detection system based on soil condition data according to claim 1, characterized in that: The soil moisture sensor is a frequency domain reflection sensor or a time domain reflection sensor.

6. The tillage depth detection method based on soil condition data according to claim 1, characterized in that: The following steps are involved: S1: Soil data collection: before the tillage equipment starts working, the soil data collection module is started to collect data such as soil texture, moisture, flatness and debris, and the results are transmitted to the data processing module; S2: Data transmission: the collected soil condition data is transmitted to the data processing module through the data transmission module; S3: Data analysis and fusion. After the data processing module receives the soil condition data, the data analysis unit uses a support vector machine algorithm to analyze and process the data. S4: Calculating tillage depth, the tillage depth calculation module calculates the tillage depth using a mathematical model or an empirical formula according to the soil condition data processed by the data processing module and the working parameters of the tillage equipment; S5: result display, the result display module displays the tillage depth result calculated by the tillage depth calculation module to the user in an intuitive manner; the tillage depth result is displayed as a tillage depth value on the display screen in the cab of the tillage equipment or the tillage depth information is displayed in real time through a mobile phone APP.

7. A tillage depth detection method based on soil condition data according to claim 6, characterized in that: The S1 also includes the following steps: S101: before the tillage equipment starts working, the soil texture detection unit is started to analyze the soil sample to determine the soil texture type, and the result is transmitted to the data processing module; S102: before the tillage equipment starts working, the soil moisture detection unit is started to measure the moisture content in the soil in real time, and the data is transmitted to the data processing module; S103: before the tillage equipment starts working, the soil flatness detection unit is started to collect three-dimensional contour data or images of the soil surface through a laser scanner or a camera, and soil flatness information is obtained after processing, and the result is transmitted to the data processing module; S104: Before the tillage equipment starts working, the soil debris detection unit is started to collect soil images through a camera, and the debris in the soil is detected using an image recognition algorithm, and the result is transmitted to the data processing module.

8. The tillage depth detection method based on soil condition data according to claim 6, characterized in that: The S3 also includes the following steps: S301: preprocessing the data, including data cleaning, normalization and other operations, to improve the quality and availability of the data; S302: using a support vector machine algorithm to establish a relationship model between soil conditions and tillage depths, by collecting a large amount of soil condition data and corresponding tillage depth data for training, continuously optimizing model parameters and improving model accuracy; S303: The data fusion unit fuses different types of soil condition data, assigns different weights according to the degree of influence of different soil conditions on tillage depth, and obtains comprehensive soil condition data.

9. The tillage depth detection method based on soil condition data according to claim 6, characterized in that: The mathematical model uses the following formula to calculate the tillage depth: Tillage depth = f *(soil texture weight × soil texture parameter + soil moisture weight × soil moisture parameter + soil flatness weight × soil flatness parameter + soil debris weight × soil debris parameter + tractor traction parameter + tractor speed parameter); Among them, f is a functional relationship, which is determined through experiments or data analysis; soil texture weight, soil moisture weight, soil flatness weight and soil debris weight are determined according to the influence of different soil conditions on tillage depth.

Images