An automatic leveling system for peanut harvesters in hilly and mountainous areas

Abstract

The present invention relates to the technical field of peanut harvesters, and more specifically to an automatic leveling system for peanut harvesters in hilly and mountainous areas. The system comprises a data acquisition module, a data preprocessing module, an adaptive slope prediction and adjustment module, a dynamic control and adjustment module, and a power drive module, wherein: the data acquisition module collects the working status data of the peanut harvester in real time; the data preprocessing module preprocesses the collected working status data; the adaptive slope prediction and adjustment module dynamically adjusts the angle of the working platform of the peanut harvester; the dynamic control and adjustment module performs real-time adjustment and dynamic correction and outputs control instructions; and the power drive module drives an electric hydraulic unit or a mechanical arm to perform automatic adjustment. The present invention ensures the stability and accuracy of the peanut harvester in various complex terrains, reduces the risk of operation interruption due to terrain changes, and effectively improves the efficiency of the harvesting operation.

Description

Technical Field

[0001] The invention relates to the technical field of peanut harvesters, in particular to an automatic leveling system for peanut harvesters in hilly and mountainous areas. Background Art

[0002] With the continuous improvement of the level of agricultural mechanization, peanut harvesters, as an important agricultural machinery and equipment, have been widely used in modern agriculture. However, the operating environment under complex terrain conditions such as hilly and mountainous areas has put forward higher requirements on the stability and adaptability of peanut harvesters. Due to the uneven terrain and frequent changes in slope, traditional peanut harvesters are easily affected by the terrain during operation, resulting in tilting and instability of the operating platform, thereby affecting the operating efficiency and crop harvest quality. Therefore, how to achieve adaptive leveling and efficient operation of peanut harvesters under complex terrain conditions has become an important issue that needs to be urgently solved in the field of agricultural machinery.

[0003] In the existing technology, although some peanut harvesters are equipped with basic leveling functions, they usually rely on a single sensor to obtain terrain data, which is easily affected by measurement errors and environmental noise, resulting in inaccurate data and unable to meet the leveling needs under complex terrain conditions. In addition, traditional leveling systems mostly use control algorithms with fixed rules and lack the ability to predict dynamic changes in terrain, which makes it difficult for the operating platform to adjust quickly under sudden slope changes or high load conditions, resulting in platform instability or operation interruption problems. Especially in hilly and mountainous environments, the existing system has shown obvious deficiencies in coping with terrain complexity and operating load fluctuations, and cannot meet the actual needs of efficient and stable operations.

[0004] In response to the above problems, the present invention provides an automatic leveling system for a peanut harvester in hilly and mountainous areas, which ensures the stability and adaptability of the working platform under complex terrain and high load conditions, thereby improving the efficiency and quality of peanut harvesting operations. Summary of the Invention

[0005] The invention provides an automatic leveling system for a peanut harvester in hilly and mountainous areas.

[0006] An automatic leveling system for a peanut harvester in hilly and mountainous areas includes a data acquisition module, a data preprocessing module, an adaptive slope prediction and adjustment module, a dynamic control and adjustment module, and a power drive module, wherein;

[0007] The data acquisition module collects the working status data of the peanut harvester in real time, including the longitudinal and lateral tilt angles of the peanut harvester and the slope data of the working ground;

[0008] The data preprocessing module preprocesses the collected working status data, including denoising, smoothing and filtering;

[0009] The adaptive slope prediction and adjustment module predicts the slope change trend of the working area based on the pre-processed working status data, and dynamically adjusts the working platform angle of the peanut harvester according to the prediction result;

[0010] The dynamic control and adjustment module performs real-time adjustment and dynamic correction based on the adjusted working platform angle of the peanut harvester in combination with real-time working status data and workload, and outputs control instructions;

[0011] The power drive module drives the electric hydraulic unit or the mechanical arm to perform automatic adjustment according to the output control instructions.

[0012] Optionally, the data acquisition module includes:

[0013] Tilt angle acquisition: Use acceleration sensors and gyroscopes to collect longitudinal and lateral tilt angle data of the peanut harvester in real time;

[0014] Ground slope collection: Use lidar to scan the working ground and obtain ground slope data in real time.

[0015] Optionally, the data preprocessing module includes:

[0016] Denoising: Use the mean denoising method (moving average method) to denoise the collected working status data;

[0017] Smoothing: Use the exponentially weighted moving average method to smooth the denoised working status data;

[0018] Filtering: The Kalman filter algorithm is used to filter the smoothed working status data.

[0019] Optionally, the adaptive slope prediction and adjustment module includes:

[0020] Slope feature extraction: Perform multi-dimensional analysis on the pre-processed working status data to extract the slope characteristics of the current terrain, including the slope fluctuation range, change frequency, and steep slope distribution;

[0021] Slope trend prediction: Based on the extracted slope features, predict the changing trend of terrain slope;

[0022] Working platform adjustment: Based on the results of slope trend prediction and combined with the operating speed of the peanut harvester, the working platform angle of the peanut harvester is adjusted.

[0023] Optionally, the slope feature extraction includes:

[0024] Slope fluctuation range calculation: Use the maximum and minimum values ​​of the terrain slope data to calculate the slope fluctuation range R;

[0025] Slope change frequency calculation: Count the number of slope value changes per unit time to reflect the frequency characteristics of slope changes, and use fast Fourier transform to extract the frequency components of slope data. ;

[0026] Steep slope distribution detection: The slope value exceeds the predetermined threshold T (steep slope standard is The number of occurrences and distribution locations of steep slopes are counted to form a set S of steep slope points.

[0027] Optionally, the slope trend prediction includes:

[0028] Feature input: The extracted slope features are used as input variables and combined with historical slope data to form multiple input variables;

[0029] Slope prediction: Use multivariate regression model to model multiple input variables and predict the slope value at the next moment ;

[0030] Output slope change rate: based on the predicted slope value at the next moment , calculate the slope change rate , used to describe the magnitude of trend changes.

[0031] Optionally, the working platform adjustment includes:

[0032] Calculate target adjustment angle: Based on predicted future slope values and the current slope value , combined with the peanut harvester's operating speed v, calculate the target adjustment angle of the working platform ;

[0033] Smooth Target Angle: Uses Exponentially Weighted Moving Average (EWMA) to smooth the target adjustment angle.

[0034] Optionally, the dynamic control and adjustment module includes:

[0035] Real-time adjustment: Generate real-time adjustment signals based on the smoothed adjustment angle and the current working platform angle;

[0036] Dynamic correction: Combine real-time working status data and workload to dynamically correct the real-time adjustment signal and optimize the control effect.

[0037] Optionally, the real-time adjustment includes:

[0038] Error calculation: calculate the current platform angle Adjustment angle after smoothing The error between

[0039] Real-time adjustment: Based on the angle error, a proportional-integral-derivative (PID) control algorithm is used to generate a real-time adjustment signal .

[0040] Optionally, the dynamic correction includes:

[0041] Workload monitoring: Monitor the workload in real time and when the workload exceeds the load threshold When , it is necessary to correct the real-time adjustment signal;

[0042] Correction signal generation: Dynamically adjust the real-time regulation signal according to the monitored load changes , generating the corrected regulation signal .

[0043] Beneficial effects of the present invention:

[0044] The present invention realizes efficient functional division and collaborative work through modular design. The data acquisition module can obtain the longitudinal and lateral tilt angles of the peanut harvester and the slope information of the working ground in real time and accurately, and overcomes the error problem of a single sensor through the integration of multiple sensors. The data preprocessing module combines advanced algorithms such as mean denoising, exponentially weighted moving average method and smoothing filtering to effectively remove environmental noise and sensor errors, and retain key trends and change characteristics, providing high-quality data support for slope prediction and dynamic adjustment, thereby improving the system's response speed, stability and adaptability to complex terrain.

[0045] The present invention, through the adaptive slope prediction and adjustment module based on multi-dimensional analysis of slope characteristics, combined with multivariate regression model and trend prediction algorithm, realizes accurate prediction of slope changes in complex terrain, and dynamically adjusts the working platform angle to adapt to different terrains. By perceiving the dynamic changes of the terrain in advance and adjusting the platform angle in combination with the operating speed, the stability and accuracy of the peanut harvester in various complex terrains are ensured, the risk of operation interruption caused by terrain changes is reduced, and the efficiency of the harvesting operation is effectively improved, providing an intelligent solution for operations in complex environments such as hilly and mountainous areas.

[0046] The present invention combines real-time adjustment and dynamic correction functions through a dynamic control adjustment module, generates a real-time adjustment signal through the smoothed adjustment angle, ensures that the platform can quickly respond to changes, and dynamically generates a correction signal based on the operating load, effectively compensating for the impact of load changes on the stability of the working platform, avoiding the occurrence of tilting or instability. The setting of the load threshold is based on the statistical analysis of historical data, and the correction conditions are scientifically set in combination with the average value and standard deviation to ensure the adaptability and accuracy of the system under high-load operating conditions. Through optimized signal generation and dynamic adjustment, the system significantly improves the stability and efficiency of the operating platform, while reducing energy consumption and mechanical load, providing a guarantee for the long-term reliable operation of the peanut harvester under complex conditions such as hilly and mountainous areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 Schematic diagram of system function modules according to an embodiment of the present invention;

[0049] Figure 2 Schematic diagram of an adaptive slope prediction and adjustment module according to an embodiment of the present invention;

[0050] Figure 3 This is the structural diagram of the peanut harvester. DETAILED DESCRIPTION

[0051] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It is also noted that, to provide a more detailed description, the following embodiments are best and preferred embodiments, and those skilled in the art may employ alternative methods for implementing certain known technologies. Furthermore, the accompanying drawings are intended only to provide a more detailed description of the embodiments and are not intended to limit the present invention.

[0052] It should be noted that references in the specification to "one embodiment," "an embodiment," "exemplary embodiments," "some embodiments," etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not necessarily every embodiment will include such specific features, structures, or characteristics. Furthermore, when specific features, structures, or characteristics are described in conjunction with an embodiment, it is within the knowledge of persons skilled in the relevant art to implement such features, structures, or characteristics in conjunction with other embodiments (whether or not explicitly described).

[0053] In general, terms can be understood, at least in part, from their use in context. For example, depending at least in part on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending at least in part on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0054] like Figure 1-Figure 3 As shown, an automatic leveling system for peanut harvesters in hilly and mountainous areas includes a data acquisition module, a data preprocessing module, an adaptive slope prediction and adjustment module, a dynamic control and adjustment module, and a power drive module, wherein;

[0055] The data acquisition module collects the working status data of the peanut harvester in real time, including the longitudinal and lateral tilt angles of the peanut harvester and the slope data of the working ground;

[0056] The data preprocessing module preprocesses the collected working status data, including denoising, smoothing and filtering;

[0057] The adaptive slope prediction and adjustment module predicts the slope change trend of the working area based on the pre-processed working status data, and dynamically adjusts the working platform angle of the peanut harvester based on the prediction results to adapt to different terrains and ensure the stability of the machine under various terrain conditions;

[0058] The dynamic control and adjustment module performs real-time adjustment and dynamic correction based on the adjusted working platform angle of the peanut harvester, combined with real-time working status data and workload, and outputs control instructions;

[0059] The power drive module drives the electric hydraulic unit or the robotic arm to perform automatic adjustment according to the output control instructions;

[0060] Through the above content, adaptive leveling and stable control of the peanut harvester in complex terrain are realized. It can not only respond to terrain changes in real time and ensure the stability of the working platform, but also drive automatic adjustment through precise control instructions, thereby improving the efficiency and stability of the harvesting operation. The structural design of the system optimizes the functional division of each module, avoids repeated calculations, improves operational accuracy, and has strong adaptability, and can operate stably in changeable hilly and mountainous environments.

[0061] The data acquisition module includes:

[0062] Tilt angle acquisition: Use acceleration sensors and gyroscopes to collect longitudinal and lateral tilt angle data of the peanut harvester in real time;

[0063] Ground slope collection: Use LiDAR to scan the working ground and obtain ground slope data in real time;

[0064] Through the above content, the integration of acceleration sensors, gyroscopes and lidar can accurately collect the longitudinal and lateral tilt angles of the peanut harvester and the slope information of the working ground in real time, effectively overcoming the errors that may be caused by a single sensor and providing high-precision, real-time working status data.

[0065] The data preprocessing module includes:

[0066] Denoising: The mean denoising method (moving average method) is used to denoise the collected working status data, which can be expressed as:

[0067] ;

[0068] in, is the i-th data point after denoising, N is the size of the sliding window, is the original data point, j is the index in the window;

[0069] Smoothing: The exponentially weighted moving average method is used to smooth the denoised working status data to reduce data fluctuations and ensure signal stability, which can be expressed as:

[0070] ;

[0071] in, is the i-th data point after smoothing, is the smoothing factor, and its value range is , is the working status data after denoising, is the i-1th data point after smoothing;

[0072] Filtering: The Kalman filter algorithm is used to filter the smoothed working status data to achieve dynamic filtering, which is expressed as:

[0073] ;

[0074] ;

[0075] in, is the state estimation, is the prior state estimate at the current moment k, is the Kalman gain, is the observed value, is the measurement matrix, is the error covariance matrix, I is the identity matrix, is the prior state estimation error covariance matrix at the current moment k;

[0076] Through the above content, environmental noise and sensor errors can be effectively removed. At the same time, the key trends and change characteristics of the data can be retained through smoothing and dynamic adjustment, ensuring high-quality data input when processing slope prediction and dynamic adjustment, thereby improving the response speed, stability and ability of the entire system to adapt to complex terrain, and ultimately improving the efficiency and accuracy of the peanut harvester in actual application.

[0077] The adaptive slope prediction and adjustment module includes:

[0078] Slope feature extraction: Perform multi-dimensional analysis on the pre-processed working status data to extract the slope characteristics of the current terrain, including the slope fluctuation range, change frequency, and steep slope distribution;

[0079] Slope trend prediction: Based on the extracted slope features, predict the changing trend of terrain slope;

[0080] Working platform adjustment: Based on the slope trend prediction results and the operating speed of the peanut harvester, the working platform angle of the peanut harvester is adjusted;

[0081] Through the above content, it is possible to accurately respond to dynamic changes in complex terrain, combine trend prediction to perceive slope changes in advance, and further dynamically adjust the working platform angle, so that the peanut harvester can quickly adapt to changes in terrain undulations and operating speeds. This not only improves the stability and accuracy of operations, but also reduces the risk of operation interruptions caused by terrain changes, providing important guarantees for the efficient operation of peanut harvesters in complex hilly and mountainous environments.

[0082] Slope feature extraction includes:

[0083] Slope fluctuation range calculation: Use the maximum and minimum values ​​of the terrain slope data to calculate the slope fluctuation range R, which is expressed as:

[0084] ;

[0085] in, represents the slope value of the i-th sampling point, R represents the range of the slope, is the maximum value of the slope data, is the minimum value of the slope data;

[0086] Slope change frequency calculation: Count the number of slope value changes per unit time to reflect the frequency characteristics of slope changes, and use fast Fourier transform to extract the frequency components of slope data. , expressed as:

[0087] ;

[0088] in, is the frequency component, is the slope value of the i-th sampling point, and N is the total number of data points;

[0089] Steep slope distribution detection: The slope value exceeds the predetermined threshold T (steep slope standard is Defined as a steep slope area, the occurrence frequency and distribution location of the steep slope are counted to form a set S of steep slope points, which can be expressed as:

[0090] ;

[0091] Among them, S is the set of steep slope points;

[0092] Through the above content, the key features of the terrain are effectively extracted, including the slope fluctuation range, change frequency and steep slope distribution, which provides basic support for the accurate identification and prediction of complex terrain. The maximum and minimum values ​​are used to calculate the fluctuation range, quantify the terrain complexity, and analyze the slope change frequency through fast Fourier transform to perceive the terrain fluctuation trend in advance. Threshold detection is used to identify steep slope areas and optimize the responsiveness of platform adjustment. It can comprehensively and accurately describe the current terrain characteristics and improve the adaptability and accuracy of subsequent adjustment modules, thereby ensuring the smooth and efficient operation of the peanut harvester under complex terrain conditions.

[0093] Slope trend prediction includes:

[0094] Feature input: The extracted slope features are used as input variables and combined with historical slope data to form multiple input variables;

[0095] Slope prediction: Use multivariate regression model to model multiple input variables and predict the slope value at the next moment , expressed as:

[0096] ;

[0097] in, is the predicted slope value at the next moment, is the slope value at the current moment, 、 、 are the slope characteristic values ​​at the current moment, 、 、 、 are the corresponding weight coefficients, is the error term;

[0098] Output slope change rate: based on the predicted slope value at the next moment , calculate the slope change rate , used to describe the magnitude of the trend change, expressed as:

[0099] ;

[0100] in, is the slope change rate, is the predicted slope value at the next moment, is the slope value at the current moment, is the time interval;

[0101] Through the above content, the accuracy and real-time performance of terrain slope change trends are effectively improved, and the terrain complexity and dynamic change laws can be fully considered, making the prediction results more accurate and stable. By perceiving terrain change trends in advance, the adaptability and operating efficiency of peanut harvesters in complex terrain environments are greatly improved, while reducing the risk of instability caused by terrain changes.

[0102] Work platform adjustments include:

[0103] Calculate target adjustment angle: Based on predicted future slope values and the current slope value , combined with the peanut harvester's operating speed v, calculate the target adjustment angle of the working platform , expressed as:

[0104] ;

[0105] in, Adjust the angle for the target of the work platform, is the predicted slope value at the next moment, is the current slope value, v is the operating speed of the peanut harvester, 、 is the adjustment coefficient;

[0106] Smooth target angle: Use the exponentially weighted moving average (EWMA) method to smooth the target adjustment angle to ensure smooth and continuous adjustment action, expressed as:

[0107] ;

[0108] in, To adjust the angle after smoothing, Adjust the angle for the currently calculated target, is the adjustment angle of the previous moment, w is the smoothing factor, and its value range is 0 <w<1;

[0109] Through the above content, it is ensured that the platform can quickly adapt to complex terrain changes and dynamic requirements of operating speed. At the same time, smoothing processing avoids frequent adjustments caused by data fluctuations, ensures the stability and continuity of adjustment actions, improves the terrain adaptability and operating stability of the peanut harvester, effectively reduces unnecessary energy consumption and equipment wear, and provides a solid guarantee for efficient and precise operations.

[0110] The dynamic control and adjustment module includes:

[0111] Real-time adjustment: Based on the smoothed adjustment angle and the current working platform angle, a real-time adjustment signal is generated to ensure rapid platform response.

[0112] Dynamic correction: Combine real-time working status data and workload to dynamically correct real-time adjustment signals and optimize control effects;

[0113] Through the above content, efficient control and precise optimization of the working platform are achieved. Based on the smoothed adjustment angle, the adjustment signal is quickly generated to ensure that the platform can respond to slope changes in a timely manner. Further combined with real-time working status data and environmental changes, the adjustment signal is dynamically optimized to enhance the adaptability and stability of the system. It effectively balances the speed and precision of adjustment, adapts to complex terrain and dynamic environmental changes, avoids unnecessary energy consumption and instability caused by frequent adjustments, and provides important guarantees for the efficient operation of the peanut harvester.

[0114] Real-time adjustments include:

[0115] Error calculation: calculate the current platform angle Adjustment angle after smoothing The error between them is expressed as:

[0116] ;

[0117] in, is the current angle error;

[0118] Real-time adjustment: Based on the angle error, a proportional-integral-derivative (PID) control algorithm is used to generate a real-time adjustment signal , expressed as:

[0119] ;

[0120] in, To adjust the signal in real time, 、 、 are proportional, integral and differential control parameters respectively, is the angle error;

[0121] Through the above content, the angle error is calculated in real time and the adjustment signal is generated to ensure that the platform can quickly respond to changing needs. By using the proportional-integral-differential control algorithm, the adjustment speed and control accuracy can be balanced, the angle deviation is eliminated and the stability of the platform is maintained. The working platform can be adjusted in time under dynamic terrain and working conditions, significantly improving the operating efficiency and stability of the system.

[0122] Dynamic corrections include:

[0123] Workload monitoring: Monitor the workload in real time and when the workload exceeds the load threshold When , it is necessary to correct the real-time adjustment signal;

[0124] Correction signal generation: Dynamically adjust the real-time regulation signal according to the monitored load changes , generating the corrected regulation signal , expressed as:

[0125] ;

[0126] in, is the corrected regulation signal, For the original real-time adjustment signal, is the load correction factor, is the current workload, is the load threshold;

[0127] Load threshold Based on historical data settings, specifically including:

[0128] Collect historical data: monitor and record the operating load data of peanut harvesters under different terrains and operating conditions;

[0129] Statistical load distribution: Statistical analysis is performed on historical load data to extract statistical features, including average load value and standard deviation, expressed as:

[0130] ;

[0131] ;

[0132] in, is the average load value, is the standard deviation, n is the total number of historical data, is the load value of the i-th operation;

[0133] Set load threshold: Set load threshold based on statistical characteristics , expressed as:

[0134] ;

[0135] in, is the adjustment coefficient (the value range is 1~2);

[0136] Through the above content, the situation where the load exceeds the threshold can be accurately identified, and a correction signal can be dynamically generated based on the load change to optimize the adjustment effect. Through the dynamic adjustment of the correction signal, the impact of load changes on the stability of the working platform can be effectively compensated, avoiding tilting or instability during operation, providing reliable guarantee for the stable operation of the peanut harvester under high-load operating conditions, while reducing unnecessary energy consumption and mechanical load.

[0137] The present invention encompasses any alternatives, modifications, equivalents, and solutions that fall within the spirit and scope of the present invention. To provide a thorough understanding of the present invention, specific details are described in detail below in connection with the preferred embodiments of the present invention, but those skilled in the art will be able to fully understand the present invention without these detailed descriptions. Furthermore, to avoid unnecessary confusion regarding the essence of the present invention, well-known methods, processes, procedures, components, and circuits have not been described in detail.

[0138] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. An automatic leveling system for peanut harvesters in hilly and mountainous areas, characterized in that: It includes data acquisition module, data preprocessing module, adaptive slope prediction and adjustment module, dynamic control adjustment module and power drive module, among which; The data acquisition module collects the working status data of the peanut harvester in real time, including the longitudinal and lateral tilt angles of the peanut harvester and the slope data of the working ground; The data preprocessing module preprocesses the collected working status data, including denoising, smoothing and filtering; The adaptive slope prediction and adjustment module predicts the slope change trend of the working area based on the pre-processed working status data, and dynamically adjusts the working platform angle of the peanut harvester according to the prediction result; The dynamic control and adjustment module performs real-time adjustment and dynamic correction based on the adjusted working platform angle of the peanut harvester in combination with real-time working status data and workload, and outputs control instructions; The power drive module drives the electric hydraulic unit or the mechanical arm to perform automatic adjustment according to the output control instructions; The adaptive slope prediction and adjustment module includes: Slope feature extraction: Perform multi-dimensional analysis on the pre-processed working status data to extract the slope characteristics of the current terrain, including the slope fluctuation range, change frequency, and steep slope distribution; Slope trend prediction: Based on the extracted slope features, predict the changing trend of terrain slope; Working platform adjustment: Based on the slope trend prediction results and the operating speed of the peanut harvester, the working platform angle of the peanut harvester is adjusted; The slope feature extraction includes: Slope fluctuation range calculation: Use the maximum and minimum values ​​of the terrain slope data to calculate the slope fluctuation range R; Slope change frequency calculation: Count the number of slope value changes per unit time to reflect the frequency characteristics of slope changes, and use fast Fourier transform to extract the frequency components of slope data. ; Steep slope distribution detection: The threshold detection method is used to extract the area where the slope value exceeds the predetermined threshold T, and the number of occurrences and distribution locations of steep slopes are counted to form a set S of steep slope points; The slope trend prediction includes: Feature input: The extracted slope features are used as input variables and combined with historical slope data to form multiple input variables; Slope prediction: Use multivariate regression model to model multiple input variables and predict the slope value at the next moment ; Output slope change rate: based on the predicted slope value at the next moment , calculate the slope change rate , used to describe the magnitude of trend changes; The dynamic control and adjustment module includes: Real-time adjustment: Generate real-time adjustment signals based on the smoothed adjustment angle and the current working platform angle; Dynamic correction: Combine real-time working status data and workload to dynamically correct the real-time adjustment signal and optimize the control effect.

2. The automatic leveling system for peanut harvesters in hilly and mountainous areas according to claim 1, characterized in that: The data acquisition module includes: Tilt angle acquisition: Use acceleration sensors and gyroscopes to collect the longitudinal and lateral tilt angle data of the peanut harvester in real time; Ground slope collection: Use lidar to scan the working ground and obtain ground slope data in real time.

3. The automatic leveling system for peanut harvesters in hilly and mountainous areas according to claim 1, characterized in that: The data preprocessing module includes: Denoising: The mean denoising method is used to denoise the collected working status data; Smoothing: Use the exponentially weighted moving average method to smooth the denoised working status data; Filtering: The Kalman filter algorithm is used to filter the smoothed working status data.

4. The automatic leveling system for peanut harvesters in hilly and mountainous areas according to claim 1, characterized in that: The working platform adjustment includes: Calculate target adjustment angle: Based on predicted future slope values and the current slope value , combined with the peanut harvester's operating speed v, calculate the target adjustment angle of the working platform ; Smooth Target Angle: Uses an exponentially weighted moving average to smooth the target adjustment angle.

5. The automatic leveling system for peanut harvesters in hilly and mountainous areas according to claim 4, characterized in that: The real-time adjustment includes: Error calculation: calculate the current platform angle Adjustment angle after smoothing The error between Real-time adjustment: Based on the angle error, a proportional-integral-differential control algorithm is used to generate a real-time adjustment signal .

6. The automatic leveling system for peanut harvesters in hilly and mountainous areas according to claim 5, characterized in that: The dynamic correction includes: Workload monitoring: Monitor the workload in real time and when the workload exceeds the load threshold When , it is necessary to correct the real-time adjustment signal; Correction signal generation: Dynamically adjust the real-time regulation signal according to the monitored load changes , generating the corrected regulation signal .

Images