Harvester operation speed control method

Abstract

The invention relates to the technical field of crop harvesting, and discloses a harvester operation speed control method, which comprises the following steps: constructing a three-dimensional grid of a to-be-detected crop harvesting area, uniformly dividing a three-dimensional grid unit into n grids, performing three-dimensional scanning on crops by using a laser radar, processing acquired radar data, and determining the operation speed of a harvester according to the processed radar data. Generating a radar image; according to the method, the three-dimensional grid of the to-be-detected crop harvesting area is constructed, the grid unit is further uniformly divided into a plurality of sub-grids, refined division of the harvesting area is realized, and the division mode is beneficial to more accurately evaluating the crop weight in each grid, so that the crop weight in the to-be-detected crop harvesting area can be accurately evaluated. Therefore, a better scheme is provided for adjusting the running speed of the harvester, in the subsequent steps, through correlation analysis of the weight of crops in the grids, the multiple grids are combined into fewer grids, the frequency of frequently adjusting the speed in the running process of the harvester is reduced, and the overall efficiency of harvesting operation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of crop harvesting, and in particular to a method for controlling the operating speed of a harvester. Background Art

[0002] In modern agricultural production, crop harvesting is a crucial step, with its efficiency and quality directly impacting agricultural yields and economic returns. Traditional crop harvesting operations rely primarily on manual experience, with the harvester's speed often adjusted based on the operator's subjective judgment. However, this approach has numerous drawbacks. For one thing, manual judgment struggles to accurately adapt to the actual growth conditions of crops in different regions, such as differences in height, density, and weight, which can easily lead to harvesting speeds that are too fast or too slow. Excessive speeds can result in incomplete harvesting and increased crop losses, while excessively slow speeds reduce harvesting efficiency and increase operating costs. Furthermore, with the increasing scale and intensification of agriculture, farmland continues to expand and crop variety is increasingly diverse. Traditional manual control methods are no longer able to meet the demands of large-scale, efficient harvesting. Summary of the Invention

[0003] In response to the deficiencies in the prior art, the present invention provides a method for controlling the operating speed of a harvester, which has the advantages of being easy to accurately control the operating speed of the harvester and having a high degree of intelligence, thereby solving the problems mentioned in the background technology.

[0004] In order to achieve the above-mentioned purpose of facilitating precise control of the operating speed of a harvester with a high degree of intelligence, the present invention provides the following technical solution: a method for controlling the operating speed of a harvester, comprising the following steps: S1: Construct a three-dimensional grid of the crop harvesting area to be measured and evenly divide the three-dimensional grid cells into n grids; S2: Use LiDAR to perform three-dimensional scanning of crops, process the collected radar data, and generate radar images; S3: Perform threshold segmentation on the radar image to segment the crops from the radar image and extract the height features of the crops from the segmented image. Within each grid, interpolate the known height features to obtain the height value of any point within the grid. S4: Calculate the volume V of crops in each grid n , through the crop volume V n Calculate the weight F of each grid crop n , the weight of each grid crop F n Both correspond to the harvester’s running speed γ; S5: Analyze the weight of each grid crop F αThe correlation between them is calculated, and n grids are merged according to the algorithm to obtain new n' grids, n'<n; S6: Control the running speed γ' of the harvester after merging the grids according to the weight of the crops in the new n' grids; S7: Analyze the weight uniformity (CWDU) of the crops based on the n grids before merging and the n' grids after merging.

[0005] Preferably, step S3 includes the following steps: S3.1: De-noise or enhance contrast of radar images to improve segmentation accuracy; S3.2: Use the threshold segmentation method to segment crops from the radar image. The expression is: Where f(x, y) is the pixel value at position (x, y) in the radar image, T is the set threshold, g(x, y) is the binary image after segmentation, 1 represents the crop area, and 0 represents the background area; S3.3: Extract the height features of crops in the segmented binary image g(x, y). The expression is: Where H(x, y) is the height value of the position (x, y) in the radar image, M is the mask of the crop area, and H is the height feature of the crop; S3.4: Use bilinear interpolation to interpolate the crop height characteristics within a single grid cell. Let (x0, y0) be the point to be interpolated, and (x1, y1), (x1, y2), (x2, y1), and (x2, y2) be the four known points around the point to be interpolated. The expression is: Among them, a, b, c, and d are interpolation coefficients.

[0006] Preferably, the step S4 specifically includes: S4.1: Based on the average height H of crops in the grid grid The area A of crops in the grid n *B n The volume of crops is obtained as follows: S4.2: According to the volume V α The weight of crops in each grid is calculated by the density of crops ρ α , the expression is: F n =V n *ρ Preferably, the step S5 specifically includes: S5.1: Analyze the correlation between the crop weights F of each grid using the Pearson correlation coefficient, and the expression is: n Between them, the expression is: Where i and j are any two grids, and their crop weights correspond to F i 、F j , And Respectively represent the average values of the crop weights of grid i and grid j; S5.2: And The expressions of are: S5.3: By calculating the Pearson correlation coefficient r between every two grids among n grids ij , a correlation coefficient matrix R can be obtained, and R(i, j) = r ij ; S5.4: According to the correlation coefficient matrix R and the merging threshold τ, merge the grids. For example, set τ = 0.8, which means that when the correlation coefficient of the crop weights of two grids is greater than 0.8, it is considered that the two grids have a strong correlation and can be considered for merging.

[0007] Preferably, the specific steps for merging the grids in step S5 are as follows: Step 1: Initialize, and regard each grid as an independent cluster; Step 2: According to the correlation coefficient matrix R, convert the correlation coefficient into a distance matrix D, and the distance matrix D(i, j) = 1 - |r ij |; Step 3: Find the two clusters C i And C j With the smallest distance in the distance matrix D. If the distance D(C i , C j ) < the merging threshold τ, then merge the two clusters into a new C new = C i ∪C j ; Step 4: After merging the clusters, recalculate the distances between the new cluster and other clusters, and update the distance matrix D'(C new [[ID=6​​​​​​​​​​k | are clusters C new and cluster C k The number of elements in Step 6: Loop steps 3 to 6 until there are no clusters with distance D less than the merging threshold τ that can be merged.

[0008] Preferably, the specific steps of step S7 are: Among them, θF' is the standard deviation of the crop weight in each grid after merging, is the weight of crops in the ith grid after merging, is the average weight of crops in all grids after merging; Calculate the weight uniformity CWDU of crops in the grid before and after merging. The expression is: Compared with the prior art, the present invention provides a method for controlling the operating speed of a harvester, which has the following beneficial effects: 1. This harvester operating speed control method constructs a three-dimensional grid of the crop harvesting area to be tested and further evenly divides the grid cells into multiple sub-grids, achieving a refined division of the harvesting area. This division method helps to more accurately assess the weight of the crops within each grid, thereby providing a better solution for adjusting the harvester's operating speed. In subsequent steps, through correlation analysis of the crop weight within the grid, multiple grids are merged into fewer grids, reducing the number of times the harvester needs to frequently adjust its speed during operation and improving the overall efficiency of the harvesting operation.

[0009] 2. This harvester speed control method uses a grid merging algorithm to merge grids of similar weight, allowing the harvester to maintain a relatively stable load within the merged grid. This even distribution helps reduce harvester failures and damage caused by uneven loads, improving harvesting quality. Precise harvesting control can also reduce crop losses during the harvesting process. For example, by adjusting the harvester's operating speed, crops can be prevented from being overly crushed or left in the field, thereby improving the harvest rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 The present invention provides a flow chart of a method for controlling the operating speed of a harvester. DETAILED DESCRIPTION

[0011] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 without making creative efforts are within the scope of protection of the present invention.

[0012] See also Figure 1 A method for controlling the operating speed of a harvester comprises the following steps: S1: Construct a three-dimensional grid of the crop harvesting area to be measured and evenly divide the three-dimensional grid cells into n grids; S2: Use LiDAR to perform three-dimensional scanning of crops, process the collected radar data, and generate radar images; S3: Perform threshold segmentation on the radar image to segment the crops from the radar image and extract the height features of the crops from the segmented image. Within each grid, interpolate the known height features to obtain the height value of any point within the grid. S4: Calculate the volume V of crops in each grid n , through the crop volume V n Calculate the weight F of each grid crop n , the weight of each grid crop F n Both correspond to the harvester’s running speed γ; S5: Analyze the weight of each grid crop F α The correlation between them is calculated, and n grids are merged according to the algorithm to obtain new n' grids, n'<n; S6: Control the running speed γ' of the harvester after merging the grids according to the weight of the crops in the new n' grids; S7: Analyze the weight uniformity (CWDU) of the crops based on the n grids before merging and the n' grids after merging.

[0013] Accurately calculate crop weight: LiDAR scans crops in three dimensions, generating radar images. Using threshold segmentation techniques, the crops are segmented from the image. Height features are then extracted and interpolated within each grid to obtain the height value of any point within the grid. Based on these height values, the volume and weight of the crops within each grid can be accurately calculated.

[0014] Dynamic Harvester Speed Adjustment: The harvester's operating speed is calculated based on the weight of the crops in each grid. During the harvesting process, the harvester automatically adjusts its speed based on the weight of the crops in the current grid, ensuring precise harvesting. This dynamic adjustment helps prevent harvesters from missing crops due to excessive speed or reducing efficiency due to excessive speed.

[0015] Evaluating the effectiveness of mesh merging: By calculating metrics such as the mesh reduction rate, crop weight distribution uniformity, and harvester speed stability, the effectiveness of the mesh merging algorithm can be comprehensively evaluated. These evaluation results can provide decision support for subsequent algorithm optimization and parameter adjustment.

[0016] Harvesting strategy guidance: Based on the distribution of crop weight and harvester speed, more appropriate harvesting strategies can be developed. For example, in areas with heavier crops, the harvester's operating time can be increased or harvesting efficiency can be improved; in areas with lighter crops, the harvester's operating time can be reduced or harvesting efficiency can be lowered.

[0017] Wherein, step S3 includes the following steps: S3.1: De-noise or enhance contrast of radar images to improve segmentation accuracy; S3.2: Use the threshold segmentation method to segment crops from the radar image. The expression is: Where f(x, y) is the pixel value at position (x, y) in the radar image, T is the set threshold, g(x, y) is the binary image after segmentation, 1 represents the crop area, and 0 represents the background area; S3.3: Extract the height features of crops in the segmented binary image g(x, y). The expression is: Where H(x, y) is the height value of the position (x, y) in the radar image, M is the mask of the crop area, and H is the height feature of the crop; S3.4: Use bilinear interpolation to interpolate the crop height characteristics within a single grid cell. Let (x0, y0) be the point to be interpolated, and (x1, y1), (x1, y2), (x2, y1), and (x2, y2) be the four known points around the point to be interpolated. The expression is: Among them, a, b, c, and d are interpolation coefficients.

[0018] Step S4 specifically includes: S4.1: Based on the average height H of crops in the grid gridThe area A of crops in the grid n *B n The volume of crops is obtained as follows: S4.2: According to the volume V α The weight of crops in each grid is calculated by the density of crops ρ α , the expression is: F n =V n *ρ Step S5 specifically includes: S5.1: Use Pearson correlation coefficient to analyze the crop weight F of each grid n The correlation between them is expressed as: Among them, i and j are any two grids, and their crop weights correspond to F i 、F j , and represent the average weight of crops in grid i and grid j respectively; S5.2: and The expression is: S5.3: By calculating the Pearson correlation coefficient r between each pair of n grids ij , we can get a correlation coefficient matrix R, R (i, j) = r ij ; S5.4: Merge the grids according to the correlation coefficient matrix R and the merging threshold τ.

[0019] The choice of the merging threshold τ directly affects the quality of clustering or segmentation. If τ is set too large, different categories that should be separate may be mistakenly merged together, resulting in over-merging, making the clustering results too coarse and losing detailed information in the data. Conversely, if τ is set too small, data that should belong to the same category may be split into multiple subcategories, resulting in under-merging, making the clustering results too trivial and unable to accurately reflect the inherent structure of the data.

[0020] Divide the possible value range of the τ value into a grid, and then conduct experiments on each τ value in the grid to calculate the corresponding performance metrics (such as internal metrics or external metrics). By comparing the performance metrics under different τ values, the τ value range that optimizes the metrics can be found. For example, assuming the value range of the τ value is [0, 1], this range can be divided into 100 equally spaced points, i.e., τ = 0.01, 0.02,..., 1.00, and then conduct clustering or segmentation experiments on each τ value and calculate the corresponding silhouette coefficient. Finally, select the intervals where several τ values with the highest silhouette coefficient are located as the candidate ranges.

[0021] If the quality of the clustering results changes little when the τ value varies within a certain range, it indicates that this range is a relatively stable candidate range; while if a slight change in the τ value leads to a significant change in the clustering results, then the selection of τ values within this range needs to be further carefully considered, or the candidate range needs to be adjusted.

[0022] This technical solution can be adjusted and optimized according to different harvesting areas and crop types. For example, in areas with high crop density, the number of grid divisions can be increased to improve the accuracy of evaluation; in areas with low crop density, the number of grid divisions can be reduced to simplify the calculation process.

[0023] The specific steps for merging the grid in step S5 are as follows: Step 1: Initialization, consider each grid as an independent cluster; Step 2: According to the correlation coefficient matrix R, convert the correlation coefficient into a distance matrix D, where the distance matrix D(i, j) = 1 - |r ij |; Step 3: Find the two clusters C i and C j with the smallest distance in the distance matrix D. If the distance D(C i , C j ) < the merging threshold τ, then merge the two clusters into a new C new = C i ∪C j ; Step 4: After merging the clusters, recalculate the distances between the new cluster and other clusters, and update the distance matrix D'(C new , C k ); Step 5: Calculate the distance between them using the average linkage method, and the expression is: where |C new | and |C k | are the numbers of elements in cluster C new and cluster C kThe number of elements in Step 6: Loop steps 3 to 6 until there are no clusters with distance D less than the merging threshold τ that can be merged.

[0024] The specific steps of step S7 are: Among them, θF' is the standard deviation of the crop weight in each grid after merging, is the weight of crops in the ith grid after merging, is the average weight of crops in all grids after merging; Calculate the weight uniformity CWDU of crops in the grid before and after merging. The expression is: The inverse form of the ratio of the standard deviation to the mean is used here to make the CWDU value larger when the uniformity is higher, which can more intuitively reflect the uniformity.

[0025] In summary, this harvester operating speed control method achieves a refined division of the harvesting area by constructing a three-dimensional grid of the crop harvesting area to be measured and further evenly dividing the grid cells into multiple subgrids. This division method helps to more accurately assess the weight of the crop within each grid, thereby providing a better solution for adjusting the harvester's operating speed. In subsequent steps, through correlation analysis of the crop weight within the grid, multiple grids are merged into a smaller number of grids, reducing the number of times the harvester needs to frequently adjust its speed during operation, thereby improving the overall efficiency of the harvesting operation. At the same time, the stable load distribution also reduces wear on key harvester components, reducing maintenance costs and downtime.

[0026] Furthermore, a grid merging algorithm combines grids of similar weight, allowing the harvester to maintain a relatively stable load within the merged grid. This even distribution helps reduce harvester failures and damage caused by uneven loads, improving harvesting quality. Precise harvesting control can also reduce crop losses during the harvesting process. For example, by adjusting the harvester's operating speed, crops can be prevented from being overly crushed or left in the field, thereby improving the harvest rate.

[0027] It should be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not preclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0028] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for controlling the operating speed of a harvester, characterized in that: The following steps are involved: S1: Construct a three-dimensional grid of the crop harvesting area to be measured and evenly divide the three-dimensional grid cells into n grids; S2: Use LiDAR to perform three-dimensional scanning of crops, process the collected radar data, and generate radar images; S3: Perform threshold segmentation on the radar image to segment the crops from the radar image and extract the height features of the crops from the segmented image. Within each grid, interpolate the known height features to obtain the height value of any point within the grid. S4: Calculate the volume V of crops in each grid n , through the crop volume V n Calculate the weight F of each grid crop n , the weight of each grid crop F n Both correspond to the harvester’s running speed γ; S5: Analyze the weight of each grid crop F α The correlation between them is calculated, and n grids are merged according to the algorithm to obtain new n' grids, n'<n; S6: Control the running speed γ' of the harvester after merging the grids according to the weight of the crops in the new n' grids; S7: Analyze the weight uniformity (CWDU) of the crops based on the n grids before merging and the n' grids after merging.

2. A harvester operating speed control method according to claim 1, characterized in that: The step S3 comprises the following steps: S3.1: De-noise or enhance contrast of radar images to improve segmentation accuracy; S3.2: Use the threshold segmentation method to segment crops from the radar image. The expression is: Where f(x, y) is the pixel value at position (x, y) in the radar image, T is the set threshold, g(x, y) is the binary image after segmentation, 1 represents the crop area, and 0 represents the background area; S3.3: Extract the height features of crops in the segmented binary image g(x, y). The expression is: Where H(x, y) is the height value of the position (x, y) in the radar image, M is the mask of the crop area, and H is the height feature of the crop; S3.4: Use bilinear interpolation to interpolate the crop height characteristics within a single grid cell. Let (x0, y0) be the point to be interpolated, and (x1, y1), (x1, y2), (x2, y1), and (x2, y2) be the four known points around the point to be interpolated. The expression is: Among them, a, b, c, and d are interpolation coefficients.

3. A harvester operating speed control method according to claim 1, characterized in that: The step S4 specifically includes: S4.1: Based on the average height H of crops in the grid grid The area A of crops in the grid n *B n The volume of crops is obtained as follows: S4.2: According to the volume V α The weight of crops in each grid is calculated by the density of crops ρ α , the expression is: F n =V n *r.

4. A harvester operation speed control method according to claim 1, characterized in that: The step S5 specifically includes: S5.1: Use Pearson correlation coefficient to analyze the crop weight F of each grid n The correlation between them is expressed as: Among them, i and j are any two grids, and their crop weights correspond to F i 、F j , and represent the average weight of crops in grid i and grid j respectively; S5.2: and The expression is: S5.3: By calculating the Pearson correlation coefficient r between each pair of n grids ij , we can get a correlation coefficient matrix R, R (i, j) = r ij ; S5.4: Merge the grids according to the correlation coefficient matrix R and the merging threshold τ.

5. A method for controlling the operating speed of a harvester according to claim 4, characterized in that: The specific steps of merging the grids in step S5 are: Step 1: Initialize and treat each grid as an independent cluster; Step 2: According to the correlation coefficient matrix R, convert the correlation coefficient into a distance matrix D, the distance matrix D (i, j) = 1-|r ij |; Step 3: Find the two clusters C with the smallest distance in the distance matrix D i and C j , if the distance D (C i , C j )<merging threshold τ, then merge the two clusters into a new C new =C i ∪C j ; Step 4: After merging the clusters, recalculate the distance between the new cluster and other clusters and update the distance matrix D' (C new , C k ); Step 5: Use the average link method to calculate the distance between them. The expression is: where, |C new | and |C k | are the numbers of elements in cluster C new and cluster C k respectively; Step 6: Loop steps 3 to 6 until there are no clusters with distance D less than the merging threshold τ that can be merged.

6. A harvester operation speed control method according to claim 1, characterized in that: The specific steps of step S7 are: Among them, θF' is the standard deviation of the crop weight in each grid after merging, is the weight of crops in the ith grid after merging, is the average weight of crops in all grids after merging; Calculate the weight uniformity CWDU of crops in the grid before and after merging. The expression is: 。

Images