Weeding machine operation soil compaction degree distinguishing method based on machine tool real-time parameters

Abstract

The invention discloses a weeding machine operation soil compaction degree judgment method based on machine tool real-time parameters, and belongs to the technical field of agricultural machine intelligent operation optimization. The existing electronic monitoring means cannot effectively analyze the multi-parameter synergistic effect and cannot judge the soil compaction degree on line. Collecting data, including weeding machine operation data and soil monitoring data, performing standardization processing on the weeding machine operation data to obtain processed weeding machine operation data, and performing optimization processing on the soil monitoring data to obtain processed soil monitoring data; performing key factor screening on the processed weeding machine operation data to obtain key factors; obtaining a weighted response value by using the key factor, and obtaining an increased compaction index by using the processed soil monitoring data; obtaining a soil compaction risk prediction value by using the weighted response value and the increased compaction index, so as to obtain an early warning priority index; and according to the early warning priority index, judging a soil compaction risk grade. The method is used for judging the soil compaction degree.

Description

Technical Field

[0001] This invention belongs to the field of intelligent operation optimization technology for agricultural machinery. Background Technology

[0002] In modern mechanized agricultural production, soil compaction caused by heavy machinery operations such as weeders is becoming increasingly prominent. This leads to soil structure damage, deterioration of permeability, and the formation of compacted layers, severely restricting crop root development and nutrient absorption, and posing a significant threat to sustainable agricultural production. Currently, the industry relies on manual observation or offline monitoring after operations. The former has limitations such as strong subjectivity and delayed judgment, while the latter requires interruption of operations and cannot fully reflect the compaction status of the plot. Existing electronic monitoring methods still cannot effectively analyze the synergistic effects of multiple parameters, lack the ability to adapt to dynamic changes in the soil environment, and cannot determine the degree of soil compaction online. There is an urgent need for an online soil compaction assessment method based on real-time machine parameters to achieve dynamic risk assessment and immediate intervention during continuous operations. Summary of the Invention

[0003] The purpose of this invention is to address the problems that existing electronic monitoring methods cannot effectively analyze the synergistic effects of multiple parameters, lack adaptability to dynamic changes in the soil environment, and cannot determine the degree of soil compaction online. This invention proposes a method for determining the degree of soil compaction during weeding operations based on real-time parameters of the machinery.

[0004] A method for determining the degree of soil compaction during weeding operations based on real-time machine parameters, the method comprising the following:

[0005] Step 1: Collect data, including weeding machine operation data and soil monitoring data. Standardize the weeding machine operation data to obtain processed weeding machine operation data. Optimize the soil monitoring data to obtain processed soil monitoring data.

[0006] Step 2: Screen key factors from the processed weeding machine operation data to obtain key factors;

[0007] Step 3: Utilize key factors to obtain weighted response values, and use the processed soil monitoring data to obtain the increased compaction index;

[0008] Step 4: Use the weighted response value and increase the compaction index to obtain the predicted value of soil compaction risk;

[0009] Step 5: Obtain the early warning priority index based on the predicted soil compaction risk value;

[0010] Step 6: Determine the soil compaction risk level based on the early warning priority index;

[0011] When the warning priority index is greater than or equal to the upper limit threshold, a Level 1 warning is issued;

[0012] When the warning priority index is greater than or equal to the lower threshold and less than the upper threshold, a Level 2 warning is issued.

[0013] When the warning priority index is less than the lower limit threshold, a Level 3 warning is issued.

[0014] Preferably, the weeding machine operation data includes ground pressure, vibration frequency offset, slip rate, operating height variation coefficient, and cutter head load fluctuation; soil monitoring data includes effective soil moisture content.

[0015] Preferably, in step 1, the weeding machine operation data is standardized, specifically as follows:

[0016] According to the standardized formula:

[0017]

[0018] Standardize the weeding machine operation data to obtain processed weeding machine operation data;

[0019] In the formula, x i For the processed data of the i-th weed cutter, i = 1, 2, 3, 4, 5 correspond to grounding specific voltage, vibration dominant frequency offset, travel slip rate, working height variation coefficient, and cutter head load fluctuation, respectively. σ i Let X be the standard deviation of the i-th parameter. i For the i-th weeding machine's operation data, μ i Let be the historical mean of the i-th weeding machine operation data.

[0020] Preferably, in step 1, the soil monitoring data is optimized, specifically as follows:

[0021] According to the formula:

[0022]

[0023] Obtain the processed soil monitoring data,

[0024] In the formula, x6 is the effective soil moisture content after treatment, and X6 is the effective soil moisture content.

[0025] Preferably, in step 2, the key factors include mutual information, Spearman correlation coefficient, and initial weights;

[0026] Mutual information:

[0027]

[0028] In the formula, I(Y; x) i For mutual information, p(y,x) i () represents the specific sample values ​​y and x of the soil compaction index Y.i The probability of simultaneous occurrence, p(y), is the probability that a specific sample value y of the soil compaction index Y appears in a specific value range, p(x) i ) represents the machine parameter x i The probability of appearing in a specific value range;

[0029] Filter out set S = {x i |I(Y;x i )≥0.25};

[0030] Spearman correlation coefficient:

[0031]

[0032] In the formula, d k For sample k, the soil compaction index Y and x i The rank difference; n is the number of samples in the current work cycle; p i Spearman correlation coefficient;

[0033] Initial weights:

[0034]

[0035] In the formula, These are the initial weights.

[0036] Preferably, in step 3, the weighted response value is:

[0037]

[0038] In the formula, z is the weighted response value, β0 is the regression intercept term, and β i The regression slope coefficient, X is the standardized parameter matrix, λ is the regularization intensity, I is the identity matrix, and Y is the soil compaction index. Let be a vector, where the first row of the vector contains β0 and the second row contains β. i ;

[0039] Increase the compaction index:

[0040]

[0041] In the formula, δ is the increased compaction index, and x6 is the effective moisture content of the soil after treatment;

[0042] Predicted value of soil compaction risk:

[0043]

[0044] In the formula, The compaction index;

[0045] Early warning priority index:

[0046]

[0047] In the formula, P is the warning priority index, and Δt is the time interval between two adjacent data samplings.

[0048] Preferably, the method further includes step 7:

[0049] Based on the processed weeder operation data, the state deviation entropy value is obtained, and the weeder data is adjusted according to the warning priority index and the state deviation entropy value.

[0050] Preferably, the state deviation entropy value H:

[0051]

[0052] In the formula, x is the deviation weight of parameter i. i,opt Let x be the historical best value of parameter i. k,opt Let x be the historical optimal value of parameter k in S. k Let be the k-th parameter in S.

[0053] Preferably, the weeder data is adjusted based on the early warning priority index and the state deviation entropy value, specifically as follows:

[0054] When the warning priority index is less than the lower limit threshold and the state deviation entropy value is any value, the current operation data is maintained and the data is continuously monitored.

[0055] When the warning priority index is greater than or equal to the lower limit threshold and less than the upper limit threshold, and the state deviation entropy value is less than the lower limit deviation threshold, the parameter with the largest deviation is inspected.

[0056] When the warning priority index is greater than or equal to the lower limit threshold and less than the upper limit threshold, and the state deviation entropy value is greater than or equal to the lower limit deviation threshold and less than the upper limit deviation threshold, optimize the multi-parameter operation data.

[0057] When the warning priority index is greater than or equal to the lower limit threshold and less than the upper limit threshold, and the state deviation entropy value is greater than or equal to the upper limit deviation threshold, system maintenance of the whole machine shall be arranged.

[0058] When the warning priority index is greater than or equal to the high limit threshold and the state deviation entropy value is less than the low limit deviation threshold, the machine should be stopped immediately for repair of the specific faulty component.

[0059] When the warning priority index is greater than or equal to the upper limit threshold, and the state deviation entropy value is greater than or equal to the lower limit deviation threshold and less than the upper limit deviation threshold, the system is shut down to perform full parameter calibration.

[0060] When the warning priority index is greater than or equal to the upper limit threshold, and the state deviation entropy value is greater than or equal to the upper limit deviation threshold, the plant is sent back for major repairs and soil remediation is carried out, while rotary tillage and loosening operations are carried out simultaneously.

[0061] Preferably, the lower threshold is 0.4 and the upper threshold is 0.6;

[0062] The lower limit deviation threshold is 0.3, and the upper limit deviation threshold is 0.8.

[0063] The beneficial effects of this invention are:

[0064] This invention achieves online quantitative assessment and graded early warning of soil compaction risk by real-time collection of multi-source machine status parameters (including ground pressure, vibration characteristics, slip ratio, working height stability, load fluctuation, and soil moisture content) during weeding operations, combined with data-driven modeling and dynamic optimization techniques. This method provides core technical support for soil protection, precise parameter adjustment, and preventative decision-making in agricultural machinery operations, and is applicable to weeding management in complex farmland scenarios such as dryland and wetlands.

[0065] This invention innovatively integrates real-time parameters of multi-source machinery with dynamic modeling technology, and has the following advantages:

[0066] The systematic nature of multidimensional collaborative analysis capabilities: A six-dimensional feature fusion system is established, encompassing ground pressure, cutterhead vibration spectrum shift, dynamic slip rate, coefficient of variation of working height, hydraulic load fluctuation, and soil moisture content. Through standardized processing and a two-level screening mechanism of mutual information and rank correlation, the synergistic effect of vibration energy transfer and slip compaction during machine operation is accurately captured, revealing the nonlinear coupling law of soil compression deformation. This technology fundamentally solves the shortcomings of isolated parameter analysis in manual experience-based judgment, providing a new analytical paradigm for the study of compaction mechanisms.

[0067] Accurate discrimination of the environmental adaptive model: To address the dynamic influence of soil type and moisture content, a differentiated recovery capacity correction mechanism is proposed. Based on the irreversible characteristics of clay compaction, a high-intensity correction coefficient (a = 0.8) is set, while for the elastic recovery characteristics of sandy soil, a low-intensity correction coefficient (a = 0.3) is adopted. The ridge regression penalty term and the weighted quadratic response algorithm are integrated to effectively suppress multicollinearity interference. The model significantly improves the discrimination robustness under complex working conditions such as alternating wet and dry conditions and abrupt changes in soil type.

[0068] A revolutionary innovation in intelligent early warning and decision-making system: By continuously quantifying the real-time soil compression state through a compaction index, and simultaneously combining it with state entropy values ​​to diagnose abnormal distribution patterns, a dual-dimensional understanding of risk level and fault nature is formed. Based on the synergistic construction of dual indicators, a graded response mechanism is established, realizing a closed-loop decision-making process from continuous monitoring and dynamic parameter optimization to targeted maintenance. This system elevates fault location accuracy to a new level, significantly optimizes maintenance resource allocation efficiency through intelligent analysis of abnormal patterns, and reconstructs the paradigm of agricultural machinery health management. Attached Figure Description

[0069] Figure 1 This is a flowchart of a method for judging the degree of soil compaction during weeding operations based on real-time machine parameters. Detailed Implementation

[0070] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0071] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0072] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, but this is not intended to limit the scope of the invention.

[0073] Example:

[0074] A method for determining the degree of soil compaction during weeding operations based on real-time machine parameters, the method comprising the following:

[0075] Step 1: Collect data, including weeding machine operation data and soil monitoring data. Standardize the weeding machine operation data to obtain processed weeding machine operation data. Optimize the soil monitoring data to obtain processed soil monitoring data.

[0076] Step 2: Screen key factors from the processed weeding machine operation data to obtain key factors;

[0077] Step 3: Utilize key factors to obtain weighted response values, and use the processed soil monitoring data to obtain the increased compaction index;

[0078] Step 4: Use the weighted response value and increase the compaction index to obtain the predicted value of soil compaction risk;

[0079] Step 5: Obtain the early warning priority index based on the predicted soil compaction risk value;

[0080] Step 6: Determine the soil compaction risk level based on the early warning priority index;

[0081] When the warning priority index is greater than or equal to the upper limit threshold, a Level 1 warning is issued;

[0082] When the warning priority index is greater than or equal to the lower threshold and less than the upper threshold, a Level 2 warning is issued.

[0083] When the warning priority index is less than the lower limit threshold, a Level 3 warning is issued.

[0084] Further, the weeding machine operation data includes ground pressure, vibration frequency offset, slip rate, operating height variation coefficient, and cutter head load fluctuation; soil monitoring data includes effective soil moisture content.

[0085] Specifically, feature definition and classification:

[0086]

[0087]

[0088] Further specifying, in step 1, the weeding machine operation data is standardized, specifically as follows:

[0089] According to the standardized formula:

[0090]

[0091] Standardize the weeding machine operation data to obtain processed weeding machine operation data;

[0092] In the formula, x i For the processed data of the i-th weed cutter, i = 1, 2, 3, 4, 5 correspond to grounding specific voltage, vibration dominant frequency offset, travel slip rate, working height variation coefficient, and cutter head load fluctuation, respectively. σ i Let X be the standard deviation of the i-th parameter. i For the i-th weeding machine's operation data, μ i Let be the historical mean of the i-th weeding machine operation data.

[0093] Specifically, to eliminate dimensional differences while preserving the parameter distribution characteristics and avoid distortion in subsequent weight calculations caused by dimensional differences, all parameters are standardized into unitless values ​​after standardization, facilitating fair comparisons and weight calculations.

[0094] Further specifying, in step 1, the soil monitoring data is optimized, specifically as follows:

[0095] According to the formula:

[0096]

[0097] Obtain the processed soil monitoring data,

[0098] In the formula, x6 is the effective soil moisture content after treatment, and X6 is the effective soil moisture content.

[0099] Specifically, 15% is the plastic limit of soil in agricultural soil science. When the soil is too dry, changes in moisture content have almost no effect on compaction, so it is set to 0. The higher the moisture content, the easier the soil is to compact. 35% is the empirical threshold for saturated moisture content. "Otherwise" means otherwise.

[0100] Further specifying, in step 2, the key factors include mutual information, Spearman correlation coefficient, and initial weights;

[0101] Mutual information:

[0102]

[0103] In the formula, I(Y; x) i For mutual information, p(y,x) i () represents the specific sample values ​​y and x of the soil compaction index Y. i The probability of simultaneous occurrence, p(y), is the probability that a specific sample value y of the soil compaction index Y appears in a specific value range, p(x) i ) represents the machine parameter x i The probability of appearing in a specific value range;

[0104] Filter out set S = {x i |I(Y;x i )≥0.25};

[0105] Spearman correlation coefficient:

[0106]

[0107] In the formula, d k For sample k, the soil compaction index Y and x i The rank difference; n is the number of samples in the current work cycle; p i Spearman correlation coefficient;

[0108] Initial weights:

[0109]

[0110] In the formula, These are the initial weights.

[0111] Specifically, the key factor screening involves using nonparametric methods to select factors that are strongly correlated with compaction, thereby avoiding multicollinearity from interfering with the stability of the subsequent regression model.

[0112] First, mutual information filtering is used to quantize the parameter x. i The nonlinear correlation strength between the soil compaction index Y and the soil compaction index Y.

[0113] p(y) is the probability that the soil compaction index y appears in a specific value range (ignoring x). i ), p(x i ) represents the machine parameter x i The probability of appearing in a specific value range (ignoring y).

[0114] The initial weight calculation is a dynamic weight allocation: based on the correlation strength between the parameters and compaction (p... i The absolute value is used to assign initial weights to the elements in subsequent models. The stronger the correlation, the higher the weight, and the greater the contribution to the final compaction index.

[0115] Further specifying, in step 3, the weighted response value:

[0116]

[0117] In the formula, z is the weighted response value, β0 is the regression intercept term, and β i The regression slope coefficient, X is the standardized parameter matrix, λ is the regularization intensity, I is the identity matrix, and Y is the soil compaction index. Let be a vector, where the first row of the vector contains β0 and the second row contains β. i ;

[0118] Increase the compaction index:

[0119]

[0120] In the formula, δ is the increased compaction index, and x6 is the effective moisture content of the soil after treatment;

[0121] Predicted value of soil compaction risk:

[0122]

[0123] In the formula, This represents the predicted risk value for soil compaction.

[0124] Specifically, the predicted value of soil compaction risk Compressing the weighted response value z and the correction term δ into the [0, 1] interval visually represents the compaction risk;

[0125] The nonlinear coupling effect of quantified equipment parameters on compaction is introduced to correct for soil resilience, thereby improving the accuracy of wetland operation identification.

[0126] Ridge regression coefficient solution: A stable solution for the regression slope coefficient β when multicollinearity (high correlation between parameters) exists. i Traditional regression fails under collinearity; ridge regression addresses this issue by introducing a λ penalty term.

[0127] X: Standardized parameter matrix (rows are sample size, columns are the filtered parameters); λ: Regularization strength (default is 0.1). β0: Regression intercept term, representing the regression intercept when all standardized parameters x... i When β = 0, it represents the foundation response value of soil compaction. i : Regression slope coefficient, representing the filtered parameter x i The unit influence intensity on the soil compaction index Y.

[0128] Purpose of weighted response value calculation: to quantify the nonlinear coupling effect of equipment parameters on soil compaction.

[0129] Soil restoration correction: When the soil moisture content is high, clay is more difficult to restore than sand (it is more prone to compaction after compaction), so the compaction index needs to be increased.

[0130] Further defining the warning priority index:

[0131]

[0132] In the formula, P is the warning priority index, and Δt is the time interval between two adjacent data samplings.

[0133] Specifically, the soil compaction index output compresses the weighted response value z and the correction term δ into the [0, 1] interval, intuitively representing the compaction risk.

[0134] Further specifying, the method also includes step 7:

[0135] Based on the processed weeder operation data, the state deviation entropy value is obtained, and the weeder data is adjusted according to the warning priority index and the state deviation entropy value.

[0136] Further specifying, the state deviation entropy value H:

[0137]

[0138] In the formula, x is the deviation weight of parameter i. i,opt Let x be the historical best value of parameter i. k,opt Let x be the historical optimal value of parameter k in S. k Let be the k-th parameter in S.

[0139] Specifically, the state deviation entropy value H represents the degree of disorder in which multiple parameters simultaneously deviate from their optimal values.

[0140] Further specifying, the weeder data is adjusted based on the early warning priority index and the state deviation entropy value, specifically as follows:

[0141] When the warning priority index is less than the lower limit threshold and the state deviation entropy value is any value, the current operation data is maintained and the data is continuously monitored.

[0142] When the warning priority index is greater than or equal to the lower limit threshold and less than the upper limit threshold, and the state deviation entropy value is less than the lower limit deviation threshold, the parameter with the largest deviation is inspected.

[0143] When the warning priority index is greater than or equal to the lower limit threshold and less than the upper limit threshold, and the state deviation entropy value is greater than or equal to the lower limit deviation threshold and less than the upper limit deviation threshold, optimize the multi-parameter operation data.

[0144] When the warning priority index is greater than or equal to the lower limit threshold and less than the upper limit threshold, and the state deviation entropy value is greater than or equal to the upper limit deviation threshold, system maintenance of the whole machine shall be arranged.

[0145] When the warning priority index is greater than or equal to the high limit threshold and the state deviation entropy value is less than the low limit deviation threshold, the machine should be stopped immediately for repair of the specific faulty component.

[0146] When the warning priority index is greater than or equal to the upper limit threshold, and the state deviation entropy value is greater than or equal to the lower limit deviation threshold and less than the upper limit deviation threshold, the system is shut down to perform full parameter calibration.

[0147] When the warning priority index is greater than or equal to the upper limit threshold, and the state deviation entropy value is greater than or equal to the upper limit deviation threshold, the plant is sent back for major repairs and soil remediation is carried out, while rotary tillage and loosening operations are carried out simultaneously.

[0148] Further restrictions are imposed, with a lower threshold of 0.4 and a higher threshold of 0.6.

[0149] The lower limit deviation threshold is 0.3, and the upper limit deviation threshold is 0.8.

[0150] Specifically, the hierarchical strategy:

[0151]

[0152]

[0153] This table is based on the joint decision-making of the compaction early warning index (P) and the state deviation entropy (H):

[0154] P-value: quantifies the risk level of soil compaction; the higher the value, the more urgent the risk. H-value: diagnoses abnormal distribution patterns; the lower the value, the more likely it is a single point of failure, and the higher the value, the more likely it is a systemic problem.

[0155] While the invention has been described herein with reference to specific embodiments, it should be understood that these embodiments are merely examples of the principles and applications of the invention. Therefore, it should be understood that many modifications can be made to the exemplary embodiments, and other arrangements can be designed without departing from the spirit and scope of the invention as defined by the appended claims. It should be understood that different dependent claims and features described herein can be combined in ways different from those described in the original claims. It is also understood that features described in conjunction with individual embodiments can be used in other described embodiments.

Claims

1. A method for determining the degree of soil compaction during weeding operations based on real-time machine parameters, characterized in that, The method includes the following: Step 1: Collect data, including weeding machine operation data and soil monitoring data. Standardize the weeding machine operation data to obtain processed weeding machine operation data. Optimize the soil monitoring data to obtain processed soil monitoring data. Step 2: Screen key factors from the processed weeding machine operation data to obtain key factors; Step 3: Utilize key factors to obtain weighted response values, and use the processed soil monitoring data to obtain the increased compaction index; Step 4: Use the weighted response value and increase the compaction index to obtain the predicted value of soil compaction risk; Step 5: Obtain the early warning priority index based on the predicted soil compaction risk value; Step 6: Determine the soil compaction risk level based on the early warning priority index; When the warning priority index is greater than or equal to the upper limit threshold, a Level 1 warning is issued; When the warning priority index is greater than or equal to the lower threshold and less than the upper threshold, a Level 2 warning is issued. When the warning priority index is less than the lower limit threshold, a Level 3 warning is issued.

2. The method for determining the degree of soil compaction during weeding operations based on real-time machine parameters according to claim 1, characterized in that, The weeding machine's operational data includes ground pressure, vibration frequency offset, slip rate, coefficient of variation of working height, and blade load fluctuation; soil monitoring data includes effective soil moisture content.

3. The method for determining the degree of soil compaction during weeding operations based on real-time machine parameters according to claim 1 or 2, characterized in that, In step 1, the weeding machine operation data is standardized, specifically as follows: According to the standardized formula: Standardize the weeding machine operation data to obtain processed weeding machine operation data; In the formula, x i For the processed data of the i-th weed cutter, i = 1, 2, 3, 4, 5 correspond to grounding specific voltage, vibration dominant frequency offset, travel slip rate, working height variation coefficient, and cutter head load fluctuation, respectively. σ i Let X be the standard deviation of the i-th parameter. i For the i-th weeding machine's operation data, μ i Let be the historical mean of the i-th weeding machine operation data.

4. The method for determining the degree of soil compaction during weeding operations based on real-time machine parameters according to claim 3, characterized in that, In step 1, the soil monitoring data is optimized, specifically as follows: According to the formula: Obtain the processed soil monitoring data, In the formula, x6 is the effective soil moisture content after treatment, and X6 is the effective soil moisture content.

5. The method for determining the degree of soil compaction during weeding operations based on real-time machine parameters according to claim 1 or 4, characterized in that, In step 2, the key factors include mutual information, Spearman correlation coefficient, and initial weights; Mutual information: In the formula, I(Y; x) i For mutual information, p(y,x) i () represents the specific sample values ​​y and x of the soil compaction index Y. i The probability of simultaneous occurrence, p(y), is the probability that a specific sample value y of the soil compaction index Y appears in a specific value range, p(x) i ) represents the machine parameter x i The probability of appearing in a specific value range; Filter out set S = {x i |I(Y;x i )≥0.25}; Spearman correlation coefficient: In the formula, d k For sample k, the soil compaction index Y and x i The rank difference; n is the number of samples in the current work cycle; p i Spearman correlation coefficient; Initial weights: In the formula, These are the initial weights.

6. The method for determining the degree of soil compaction during weeding operations based on real-time machine parameters according to claim 5, characterized in that, In step 3, the weighted response value is: In the formula, z is the weighted response value, β0 is the regression intercept term, and β i The regression slope coefficient, X is the standardized parameter matrix, λ is the regularization intensity, I is the identity matrix, and Y is the soil compaction index. Let be a vector, where the first row of the vector contains β0 and the second row contains β. i ; Increase the compaction index: In the formula, δ is the increased compaction index, and x6 is the effective moisture content of the soil after treatment; Predicted value of soil compaction risk: In the formula, This represents the predicted risk value for soil compaction. Early warning priority index: In the formula, P is the warning priority index, and Δt is the time interval between two adjacent data samplings.

7. The method for determining the degree of soil compaction during weeding operations based on real-time machine parameters according to claim 6, characterized in that, The method further includes step 7: Based on the processed weeder operation data, the state deviation entropy value is obtained, and the weeder data is adjusted according to the warning priority index and the state deviation entropy value.

8. The method for determining the degree of soil compaction during weeding operations based on real-time machine parameters according to claim 7, characterized in that, State deviation entropy value H: In the formula, x is the deviation weight of parameter i. i,opt Let x be the historical best value of parameter i. k,opt Let x be the historical optimal value of parameter k in S. k Let be the k-th parameter in S.

9. The method for determining the degree of soil compaction during weeding operations based on real-time machine parameters according to claim 8, characterized in that, Based on the early warning priority index and the state deviation entropy value, the weed trimmer data is adjusted as follows: When the warning priority index is less than the lower limit threshold and the state deviation entropy value is any value, the current operation data is maintained and the data is continuously monitored. When the warning priority index is greater than or equal to the lower limit threshold and less than the upper limit threshold, and the state deviation entropy value is less than the lower limit deviation threshold, the parameter with the largest deviation is inspected. When the warning priority index is greater than or equal to the lower limit threshold and less than the upper limit threshold, and the state deviation entropy value is greater than or equal to the lower limit deviation threshold and less than the upper limit deviation threshold, optimize the multi-parameter operation data. When the warning priority index is greater than or equal to the lower limit threshold and less than the upper limit threshold, and the state deviation entropy value is greater than or equal to the upper limit deviation threshold, system maintenance of the whole machine shall be arranged. When the warning priority index is greater than or equal to the high limit threshold and the state deviation entropy value is less than the low limit deviation threshold, the machine should be stopped immediately for repair of the specific faulty component. When the warning priority index is greater than or equal to the upper limit threshold, and the state deviation entropy value is greater than or equal to the lower limit deviation threshold and less than the upper limit deviation threshold, the system is shut down to perform full parameter calibration. When the warning priority index is greater than or equal to the upper limit threshold, and the state deviation entropy value is greater than or equal to the upper limit deviation threshold, the plant is sent back for major repairs and soil remediation is carried out, while rotary tillage and loosening operations are carried out simultaneously.

10. The method for determining the degree of soil compaction during weeding operations based on real-time machine parameters according to claim 9, characterized in that, The lower threshold is 0.4, and the upper threshold is 0.

6. The lower limit deviation threshold is 0.3, and the upper limit deviation threshold is 0.8.

Images