Traveling track establishment method based on intelligent agricultural machine

Abstract

The invention relates to the field of intelligent agricultural machinery, in particular to an intelligent agricultural machinery-based driving track establishment method, which comprises the following steps of: S1, acquiring a time sequence operation land parcel data source set; s2, classifying the plane coordinate data set; s3, carrying out classified statistics on the road driving data and the field operation data; s4, judging an in-field operation behavior, an in-field turning behavior and an in-field turning behavior of the field operation data; s5, judging an output result of the agricultural machine driving track analysis model; s6, adjusting an output result of the agricultural machine driving track analysis model; s7, optimizing an output result of the agricultural machine driving track analysis model; step S8, performing real-time monitoring and warning on the operation process of the agricultural machine; and step S9, adjusting the alarm behavior in the operation process of the agricultural machine. By monitoring the driving state of the agricultural machine in real time, the driving track of the agricultural machine is established, and optimal configuration and economical use of agricultural resources are facilitated.

Description

Technical Field

[0001] The present invention relates to the field of intelligent agricultural machinery, and in particular to a method for establishing a driving trajectory based on intelligent agricultural machinery. Background Art

[0002] At present, the manual labeling of agricultural machinery driving behavior mainly relies on on-site manual recording. That is, during the driving process of agricultural machinery, the operator or assistants record the current location information and driving behavior of the agricultural machinery in real time on site. This on-site manual labeling method can directly utilize the agricultural machinery operation scene information, but it is very time-consuming and labor-intensive, especially when the agricultural machinery is in a state of long-term driving, it is very easy to cause data errors or inaccuracies.

[0003] Chinese Patent Publication No.: CN113641773A discloses a method for visually labeling agricultural machinery behaviors for driving trajectories, comprising the following steps: Step 1: data acquisition; according to the data format of agricultural machinery trajectories, agricultural machinery data is acquired; Step 2: data cleaning; data with Beidou terminal sampling errors is cleaned; Step 3: preliminary labeling of field and road segmentation; according to the cleaned data in step 2, preliminary labeling of field and road segmentation is performed; Step 4: amplifying the data with inaccurate preliminary labeling in step 3 and making minor adjustments; Step 5: uploading the accurately labeled field and road segmentation data and labeling the agricultural machinery driving behaviors in the field. The present invention can perform manual labeling of agricultural machinery behaviors offline, effectively solving the problems of cumbersome and inaccurate manual recording on site, and achieving the purpose of saving time and effort; It can be seen that the method for visually labeling agricultural machinery behaviors for driving trajectories has the following problems: the field and road segmentation labeling relies on manual judgment, which may lead to inconsistent labeling between different labelers, affecting the objectivity and repeatability of the labeling results. Summary of the invention

[0004] To this end, the present invention provides a method for establishing a driving trajectory based on intelligent agricultural machinery, so as to overcome the problems in the prior art of inaccurate and time-consuming manual labeling, lack of judgment on the operating behavior of agricultural machinery in the field, and lack of real-time monitoring of the driving status of agricultural machinery.

[0005] To achieve the above object, the present invention provides a method for establishing a driving trajectory based on an intelligent agricultural machine, comprising:

[0006] Step S1, collecting the operation plot source data of the intelligent agricultural machinery equipment, obtaining a time-series operation plot data source set, converting the longitude and latitude data in the time-series operation plot data source set into plane coordinate data, and recording the plane coordinate data into a plane coordinate data set;

[0007] Step S2, classifying the plane coordinate data set according to the density data classification algorithm to obtain a classification set of agricultural machinery labels;

[0008] Step S3, classifying and counting the road driving data and the field operation data according to the agricultural machinery label classification set and the time-series operation plot data source set, to obtain the road driving data and the field operation data;

[0009] Step S4, judging the field operation behavior, field turning behavior and field turning behavior of the field operation data according to the agricultural machinery driving trajectory analysis model;

[0010] Step S5, judging the output result of the agricultural machinery driving trajectory analysis model according to the number of confusions between the in-field U-turn behavior and the in-field turning behavior in the agricultural machinery driving trajectory analysis model;

[0011] Step S6, adjusting the output result of the agricultural machinery driving trajectory analysis model according to the turning radius of the agricultural machinery during operation;

[0012] Step S7, judging the parallel operation and overlapping operation in the field according to the direction angle of the agricultural machinery driving trajectory, and optimizing the output result of the agricultural machinery driving trajectory analysis model according to the judgment result;

[0013] Step S8, real-time monitoring and alarming of the agricultural machinery operation process based on the road driving data and the plot operation data;

[0014] Step S9, adjusting the alarm behavior of the agricultural machinery operation process according to the time when the agricultural machinery exceeds the agricultural machinery operation range and the difference between the agricultural machinery operation range data collected in real time and the preset operation range data.

[0015] Furthermore, in the step S1, when collecting the work plot source data of the intelligent agricultural machinery, a work plot data source set in the order of collection time is formed, which is used as a time series work plot data source set; the time series work plot data source set is traversed to obtain the longitude and latitude data in each data in the set, and recorded as a longitude and latitude data set; the longitude and latitude data set is traversed, the input coordinate system is set to WGS84, and the output coordinate system is obtained by Gaussian projection, using the Gaussian projection formula: Among them, k0 is the scale factor, N is the radius of curvature of the zodiac circle, λ is the longitude, λ0 is the longitude of the central meridian, To normalize the latitude, the high-order terms are the terms of the square and fourth power of the longitude difference, t is the flattening coefficient of the ellipsoid, and the longitude and latitude data (α, φ) in the spherical coordinate system are converted into plane coordinate data (x, y), x = R·α·cosφ, y = R·φ, R is the radius of the earth, and the plane coordinate data (x, y) is recorded as a plane coordinate data set.

[0016] Further, in step S2, when classifying the plane coordinate data set, the plane coordinate data set is input into the density data classification algorithm, the labels of the plane coordinate data output by the density data classification algorithm are obtained, and stored in the label classification set, the neighborhood radius in the density data classification algorithm is set to 20, the minimum number of samples is set to 120, and the plane coordinate data set is classified according to the labels of the plane coordinate data in the label classification set, wherein:

[0017] When the label of the plane coordinate data (x1, y1) in the label classification set is -1, the plane coordinate data (x1, y1) is determined to be a label that does not conform to the classification data;

[0018] When the label of the plane coordinate data (x2, y2) in the label classification set is other non-negative integers, the plane coordinate data (x2, y2) is determined to be a label that conforms to the classification data, and the agricultural machinery label classification set is obtained.

[0019] Furthermore, in step S3, when classifying and counting the road travel data and the field operation data, the labels of the plane coordinate data in the agricultural machinery label classification set are matched with the longitude and latitude coordinates in the time series operation plot data source set, and the longitude and latitude coordinates in the time series operation plot data source set are marked according to the labels of the plane coordinate data in the agricultural machinery label classification set, wherein:

[0020] When the label of the plane coordinate data in the agricultural machinery label classification set is -1, the longitude and latitude coordinates in the corresponding time series operation plot data source set are marked as road driving data;

[0021] When the label of the classified data in the agricultural machinery label classification set is other integers, the longitude and latitude coordinates in the corresponding time series operation plot data source set are marked as field operation data.

[0022] Furthermore, in step S4, when judging the in-field operation behavior, in-field U-turn behavior and in-field turning behavior of the field operation data according to the agricultural machinery driving trajectory analysis model, the data of the agricultural machinery motion trajectory, motion speed and motion acceleration are input into the agricultural machinery driving trajectory analysis model to obtain the output result of the agricultural machinery driving trajectory analysis model, which includes the in-field operation behavior, in-field U-turn behavior and in-field turning behavior, and is used as the in-field driving trajectory of the agricultural machinery.

[0023] Furthermore, in step S5, when judging the output result of the agricultural machinery driving trajectory analysis model, the test set data of the agricultural machinery motion trajectory, motion speed and motion acceleration are input into the agricultural machinery driving trajectory analysis model, and the predicted labels are collected, a confusion matrix is ​​generated according to the real labels and the predicted labels, the confusion number is output, the confusion number S is compared with the preset confusion number S0, and the output result of the agricultural machinery driving trajectory analysis model is judged according to the comparison result, wherein:

[0024] When S>S0, the output result of the agricultural machinery driving trajectory analysis model is determined to be abnormal, and a new characteristic turning radius is introduced into the agricultural machinery driving trajectory analysis model;

[0025] When S≤S0, it is determined that the output result of the agricultural machinery driving trajectory analysis model is normal.

[0026] Furthermore, in step S6, when adjusting the output result of the agricultural machinery driving trajectory analysis model, the turning radius R during the operation of the agricultural machinery is compared with the preset turning radius R0, and the output result of the agricultural machinery driving trajectory analysis model is adjusted according to the comparison result, wherein:

[0027] When R>R0, the output result of the agricultural machinery driving trajectory analysis model is adjusted to the agricultural machinery turning behavior in the field;

[0028] When R≤R0, the output result of the agricultural machinery driving trajectory analysis model is adjusted to the turning behavior of the agricultural machinery in the field.

[0029] Furthermore, in step S7, when judging the field operation behavior in the agricultural machinery driving trajectory analysis model, the parallel operation and the overlapping operation in the field are judged according to the direction angle of the agricultural machinery driving trajectory. (x i ,y i ) is the coordinate of the track point, and the direction angle θ of the agricultural machinery driving track i Compare with the preset direction angle θ0, and judge the parallel operation and overlapping operation in the field according to the comparison results, and optimize the output results of the agricultural machinery driving trajectory analysis model according to the judgment results, where:

[0030] When θ i >θ0, the agricultural machinery driving trajectory is determined to be an overlapping operation in the field, and the output result of the agricultural machinery driving trajectory analysis model is added to include overlapping operations in the field, and the output result added to the agricultural machinery driving trajectory analysis model is an overlapping operation in the field, and the agricultural machinery driving trajectory is dynamically adjusted;

[0031] When θ iWhen ≤θ0, the agricultural machinery driving trajectory is determined to be parallel operation in the field, and the output results of the agricultural machinery driving trajectory analysis model are added to include parallel operation in the field, and the agricultural machinery driving trajectory is dynamically adjusted to keep a consistent spacing when the agricultural machinery is operating in parallel in the field.

[0032] Furthermore, in step S8, when the agricultural machinery operation process is monitored and alarmed in real time, the agricultural machinery operation range is obtained according to the road driving data and the field operation data, the agricultural machinery operation data Y collected in real time is compared with the preset operation range data Y0, and the agricultural machinery operation range is monitored in real time according to the comparison result, wherein:

[0033] When Y>Y0, it is determined that the agricultural machinery is beyond the agricultural machinery operation range, and an agricultural machinery beyond-range alarm is issued;

[0034] When Y≤Y0, the agricultural machinery is determined to be within the agricultural machinery operating range, and no agricultural machinery exceeding alarm is issued.

[0035] Furthermore, in step S9, when adjusting the alarm behavior of the agricultural machinery operation process, wherein:

[0036] When the agricultural machinery exceeds the operating range, the time T that the agricultural machinery exceeds the operating range is compared with the preset exceeding time T0, and the alarm behavior is adjusted according to the comparison result, where:

[0037] If T>T0, it is determined that the agricultural machinery has exceeded the agricultural machinery operation range for an abnormal period of time, and an agricultural machinery exceeding alarm is issued;

[0038] If T≤T0, it is determined that the agricultural machinery has exceeded the agricultural machinery operation range for a normal period of time, and no agricultural machinery exceeding alarm is issued;

[0039] When the agricultural machinery is within the agricultural machinery operation range, the difference between the real-time collected agricultural machinery operation data Y and the preset operation range data Y0 is compared with the boundary threshold △Y, and the alarm behavior is adjusted according to the comparison result, where:

[0040] If Y-Y0≤Y, it is determined that the agricultural machinery operation is about to exceed the agricultural machinery operation range, and a boundary approach alarm is issued;

[0041] If Y-Y0>△Y, it is determined that the agricultural machinery operation does not exceed the agricultural machinery operation range, and no boundary approach alarm is issued.

[0042] Compared with the prior art, the beneficial effect of the present invention lies in that the driving trajectory establishment method is arranged in the control terminal of the intelligent agricultural machinery equipment, and is used to accurately analyze the driving trajectory of the agricultural machinery, and distinguish the road driving trajectory and the field operation driving trajectory by real-time monitoring of the driving status of the agricultural machinery, which is helpful to achieve the optimal allocation and economical use of agricultural resources, wherein the method processes and analyzes the operating plot source data through step S1, so as to accurately plan and manage the driving trajectory of the agricultural machinery; the method distinguishes the agricultural machinery label classification set from the plane coordinate data set through step S2, and lays the foundation for the subsequent distinction between road driving data and field operation data; the method accurately analyzes the operation conditions of the agricultural machinery equipment on the road and in the field through step S3, and paves the way for the subsequent establishment of the driving trajectory of the agricultural machinery; the method processes and analyzes the operating plot source data through step S1, so as to accurately plan and manage the driving trajectory of the agricultural machinery; Step S4 effectively classifies and manages the driving trajectory of agricultural machinery, making agricultural machinery operations more intelligent, efficient and accurate; the method enhances the judgment ability of the agricultural machinery driving trajectory analysis model through step S5; the method improves the accuracy of model prediction through step S6, making it closer to the actual operation situation; the method optimizes the operation path and operation time through step S7 to ensure the coordination and cooperation between multiple agricultural machinery so that the farmland can be fully processed; the method performs real-time data analysis through step S8 to promptly discover abnormal situations during the operation process and take measures to intervene or adjust to ensure the quality and efficiency of agricultural machinery operations; the method facilitates the operator to adjust the operation trajectory in advance through step S9 to avoid actually exceeding the operation range, and at the same time avoid triggering alarms due to short-term deviations, thereby reducing interference to the operator.

[0043] In particular, the step S1 collects the work plot source data of the intelligent agricultural machinery equipment, obtains the longitude and latitude data during operation, and converts them into plane coordinates to facilitate processing and analysis of the work plot source data, thereby accurately planning and managing the driving trajectory of the agricultural machinery.

[0044] In particular, the step S2 classifies the plane coordinate data set according to the density data classification algorithm, so as to distinguish the agricultural machinery label classification set from the plane coordinate data set, laying a foundation for the subsequent distinction between road driving data and field operation data.

[0045] In particular, the step S3 classifies and counts the road driving data and field operation data according to the agricultural machinery label classification set and the time-series operation plot data source set, so as to accurately analyze the operation conditions of agricultural machinery on the road and in the field, and lay the foundation for the establishment of subsequent agricultural machinery driving trajectories.

[0046] In particular, step S4 judges the field operation behavior, field U-turn behavior and field turning behavior according to the movement trajectory, movement speed and movement acceleration of the agricultural machinery, so as to effectively classify and manage the driving trajectory of the agricultural machinery, making the agricultural machinery operation more intelligent, efficient and accurate.

[0047] In particular, the step S5 judges the output result of the agricultural machinery driving trajectory analysis model according to the number of confusions between the in-field U-turn behaviors and the in-field turning behaviors in the agricultural machinery driving trajectory analysis model, so as to enhance the judgment ability of the agricultural machinery driving trajectory analysis model.

[0048] In particular, the step S6 adjusts the output result of the agricultural machinery driving trajectory analysis model according to the turning radius of the agricultural machinery during operation, so as to improve the accuracy of the model prediction and make it closer to the actual operation situation.

[0049] In particular, the step S7 judges the in-field operation behavior in the agricultural machinery driving trajectory analysis model, and judges the parallel operation and overlapping operation in the field according to the direction angle of the agricultural machinery driving trajectory, so as to optimize the operation path and operation time, ensure the coordination and cooperation between multiple agricultural machinery, and enable the farmland to be fully processed.

[0050] In particular, step S8 performs real-time monitoring and alarming of the agricultural machinery operation process based on the road driving data and the plot operation data, so as to facilitate real-time data analysis, timely discover abnormal situations in the operation process, and take measures to intervene or adjust to ensure the quality and efficiency of the agricultural machinery operation.

[0051] In particular, step S9 adjusts the alarm behavior of the agricultural machinery operation process so that the operator can adjust the operation trajectory in advance to avoid actually exceeding the operation range, and avoid triggering an alarm due to a brief deviation, thereby reducing interference to the operator. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a flow chart of the method for establishing a driving trajectory of an intelligent agricultural machinery according to this embodiment. DETAILED DESCRIPTION

[0053] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0054] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0055] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0056] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] See also Figure 1 As shown, it is a flow chart of a method for establishing a driving trajectory of an intelligent agricultural machine according to this embodiment, and the method includes:

[0058] Step S1, collecting the operation plot source data of the intelligent agricultural machinery equipment, obtaining a time-series operation plot data source set, converting the longitude and latitude data in the time-series operation plot data source set into plane coordinate data, and recording the plane coordinate data into a plane coordinate data set;

[0059] Step S2, classifying the plane coordinate data set according to the density data classification algorithm to obtain a classification set of agricultural machinery labels;

[0060] Step S3, classifying and counting the road driving data and the field operation data according to the agricultural machinery label classification set and the time-series operation plot data source set, to obtain the road driving data and the field operation data;

[0061] Step S4, judging the field operation behavior, field turning behavior and field turning behavior of the field operation data according to the agricultural machinery driving trajectory analysis model;

[0062] Step S5, judging the output result of the agricultural machinery driving trajectory analysis model according to the number of confusions between the in-field U-turn behavior and the in-field turning behavior in the agricultural machinery driving trajectory analysis model;

[0063] Step S6, adjusting the output result of the agricultural machinery driving trajectory analysis model according to the turning radius of the agricultural machinery during operation;

[0064] Step S7, judging the parallel operation and overlapping operation in the field according to the direction angle of the agricultural machinery driving trajectory, and optimizing the output result of the agricultural machinery driving trajectory analysis model according to the judgment result;

[0065] Step S8, real-time monitoring and alarming of the agricultural machinery operation process based on the road driving data and the plot operation data;

[0066] Step S9, adjusting the alarm behavior of the agricultural machinery operation process according to the time when the agricultural machinery exceeds the agricultural machinery operation range and the difference between the agricultural machinery operation range data collected in real time and the preset operation range data.

[0067] Specifically, the driving trajectory establishment method is set in the control terminal of the intelligent agricultural machinery equipment, which is used to accurately analyze the driving trajectory of the agricultural machinery, distinguish the road driving trajectory and the field operation driving trajectory by real-time monitoring of the driving status of the agricultural machinery, and help to achieve the optimal allocation and economical use of agricultural resources. Among them, the method processes and analyzes the operating plot source data through step S1, so as to accurately plan and manage the driving trajectory of the agricultural machinery; the method distinguishes the agricultural machinery label classification set from the plane coordinate data set through step S2, laying the foundation for the subsequent distinction between road driving data and field operation data; the method accurately analyzes the operation status of the agricultural machinery equipment on the road and in the field through step S3, paving the way for the subsequent establishment of the driving trajectory of the agricultural machinery; the method analyzes the operation status of the agricultural machinery equipment on the road and in the field through step S4, laying the foundation for the subsequent establishment of the driving trajectory of the agricultural machinery; The driving trajectories are effectively classified and managed, so that the agricultural machinery operation is more intelligent, efficient and accurate; the method enhances the judgment ability of the agricultural machinery driving trajectory analysis model through step S5; the method improves the accuracy of model prediction through step S6, so that it is closer to the actual operation situation; the method optimizes the operation path and operation time through step S7 to ensure the coordination and cooperation between multiple agricultural machines so that the farmland can be fully processed; the method performs real-time data analysis through step S8 to timely discover abnormal situations in the operation process and take measures to intervene or adjust to ensure the quality and efficiency of the agricultural machinery operation; the method facilitates the operator to adjust the operation trajectory in advance through step S9 to avoid actually exceeding the operation range and avoid triggering alarms due to short-term deviations, thereby reducing interference to the operator.

[0068] Specifically, in step S1, when collecting the work plot source data of the intelligent agricultural machinery equipment, a work plot data source set in the order of collection time is formed, which is used as a time series work plot data source set; the time series work plot data source set is traversed to obtain the longitude and latitude data in each data in the set, and recorded as a longitude and latitude data set; the longitude and latitude data set is traversed, the input coordinate system is set to WGS84, and the output coordinate system is obtained by Gaussian projection, using the Gaussian projection formula: Among them, k0 is the scale factor, N is the radius of curvature of the zodiac circle, λ is the longitude, λ0 is the longitude of the central meridian, To normalize the latitude, the high-order terms are the terms of the square and fourth power of the longitude difference, t is the flattening coefficient of the ellipsoid, and the longitude and latitude data (α, φ) in the spherical coordinate system are converted into plane coordinate data (x, y), x = R·α·cosφ, y = R·φ, R is the radius of the earth, and the plane coordinate data (x, y) is recorded as a plane coordinate data set.

[0069] Specifically, the work plot source data includes the movement trajectory, movement speed, movement acceleration, turning radius and direction angle of the agricultural machinery's driving trajectory. The WGS84 refers to the Earth-centered Earth-fixed coordinate system, whose origin is located at the center of mass of the earth. It is the coordinate system used by the global positioning system GPS. This embodiment does not limit the method for obtaining the output coordinate system. Those skilled in the art can freely set it according to actual conditions, as long as the coordinate conversion requirements are met. For example, a Gaussian projection can be set. The scale factor refers to the projection ratio. The radius of curvature of the ellipse refers to the radius of curvature describing the ellipse. The curvature of the sphere at a specific latitude, the central meridian longitude refers to the reference line in the map projection, and the naturalized latitude refers to the conversion of the actual latitude of the earth's ellipsoid into an equivalent latitude value through mathematical transformation. This embodiment does not limit the values ​​of the scale factor, central meridian longitude, naturalized latitude, and ellipsoid flattening coefficient. Technical personnel in this field can freely set them according to actual conditions as long as they meet the calculation requirements. For example, the scale factor can be set to 0.99, the central meridian longitude to 115°, the naturalized latitude to 40°, and the ellipsoid flattening coefficient to 0.6.

[0070] Specifically, step S1 collects the source data of the working plot of the intelligent agricultural machinery equipment, obtains the longitude and latitude data during operation, and converts them into plane coordinates to facilitate data processing and analysis, thereby accurately planning and managing the driving trajectory of the agricultural machinery.

[0071] Specifically, in step S2, when classifying the plane coordinate data set, the plane coordinate data set is input into the density data classification algorithm, the labels of the plane coordinate data output by the density data classification algorithm are obtained, and stored in the label classification set, the neighborhood radius in the density data classification algorithm is set to 20, the minimum number of samples is set to 120, and the plane coordinate data set is classified according to the labels of the plane coordinate data in the label classification set, wherein:

[0072] When the label of the plane coordinate data (x1, y1) in the label classification set is -1, the plane coordinate data (x1, y1) is determined to be a label that does not conform to the classification data;

[0073] When the label of the plane coordinate data (x2, y2) in the label classification set is other non-negative integers, the plane coordinate data (x2, y2) is determined to be a label that conforms to the classification data, and the agricultural machinery label classification set is obtained.

[0074] Specifically, the neighborhood radius refers to the plane coordinate data (x i ,y i ) neighborhood range, the minimum number of samples refers to the plane coordinate data (x i ,y i ) is regarded as the minimum number of neighboring points required for a point to be considered as a core point. The density data classification algorithm refers to a clustering analysis algorithm that organizes data points into high-density areas and low-density areas. Its English abbreviation is DBSCAN algorithm. This embodiment does not limit the labels of the classified data. Those skilled in the art can freely set them according to actual conditions, and only need to meet the requirements for distinguishing the labels of the classified data, such as setting 2.

[0075] Specifically, the step S2 classifies the plane coordinate data set according to the density data classification algorithm, so as to distinguish the agricultural machinery label classification set from the plane coordinate data set, laying a foundation for the subsequent distinction between road driving data and field operation data.

[0076] Specifically, in step S3, when classifying and counting the road travel data and the field operation data, the labels of the plane coordinate data in the agricultural machinery label classification set are matched with the longitude and latitude coordinates in the time series operation plot data source set, and the longitude and latitude coordinates in the time series operation plot data source set are marked according to the labels of the plane coordinate data in the agricultural machinery label classification set, wherein:

[0077] When the label of the plane coordinate data in the agricultural machinery label classification set is -1, the longitude and latitude coordinates in the corresponding time series operation plot data source set are marked as road driving data;

[0078] When the label of the classified data in the agricultural machinery label classification set is other integers, the longitude and latitude coordinates in the corresponding time series operation plot data source set are marked as field operation data.

[0079] Specifically, this embodiment does not limit the labels of the field operation data, and those skilled in the art can freely set them according to actual conditions, as long as they meet the requirements for distinguishing the field operation data, such as setting -3.

[0080] Specifically, step S3 classifies and counts the road driving data and field operation data according to the agricultural machinery label classification set and the time-series operation plot data source set, so as to accurately analyze the operation conditions of agricultural machinery on the road and in the field, and lay the foundation for the establishment of subsequent agricultural machinery driving trajectories.

[0081] Specifically, in step S4, when judging the field operation behavior, field U-turn behavior and field turning behavior of the field operation data according to the agricultural machinery driving trajectory analysis model, the data of the agricultural machinery motion trajectory, motion speed and motion acceleration are input into the agricultural machinery driving trajectory analysis model to obtain the output result of the agricultural machinery driving trajectory analysis model. The output result of the agricultural machinery driving trajectory analysis model includes the field operation behavior, field U-turn behavior and field turning behavior, which is used as the field driving trajectory of the agricultural machinery.

[0082] This embodiment does not limit the construction process of the agricultural machinery driving trajectory analysis model. Technical personnel in this field can freely set it according to actual conditions, and only need to meet the needs of intelligent analysis of the driving trajectory of agricultural machinery in the field. For example, the agricultural machinery movement trajectory, movement speed and movement acceleration can be set as indexes, and the data combination corresponding to the agricultural machinery driving trajectory in the field as the index content is used as the agricultural machinery driving trajectory analysis model construction data, 70% of the agricultural machinery driving trajectory analysis model construction data is divided into a model training set, and 30% of the agricultural machinery driving trajectory analysis model construction data is divided into a model test set. The convolutional neural network model is trained according to the model training set, and the trained convolutional neural network model is tested according to the model test set. When the test accuracy reaches 98%, the trained convolutional neural network model is output as the agricultural machinery driving trajectory analysis model. When the test accuracy does not reach 98%, the trained convolutional neural network model continues to be trained until the test accuracy reaches 98% and it is output as the agricultural machinery driving trajectory analysis model.

[0083] Specifically, step S4 judges the field operation behavior, field U-turn behavior and field turning behavior according to the movement trajectory, movement speed and movement acceleration of the agricultural machinery, so as to effectively classify and manage the agricultural machinery driving trajectory, making the agricultural machinery operation more intelligent, efficient and accurate.

[0084] Specifically, in step S5, when judging the output result of the agricultural machinery driving trajectory analysis model, the test set data of the agricultural machinery motion trajectory, motion speed and motion acceleration are input into the agricultural machinery driving trajectory analysis model, and the predicted labels are collected, a confusion matrix is ​​generated according to the real labels and the predicted labels, the confusion number is output, the confusion number S is compared with the preset confusion number S0, and the output result of the agricultural machinery driving trajectory analysis model is judged according to the comparison result, wherein:

[0085] When S>S0, the output result of the agricultural machinery driving trajectory analysis model is determined to be abnormal, and a new characteristic turning radius is introduced into the agricultural machinery driving trajectory analysis model;

[0086] When S≤S0, it is determined that the output result of the agricultural machinery driving trajectory analysis model is normal.

[0087] Specifically, the horizontal axis of the confusion matrix represents the true label, and the vertical axis represents the predicted label. The value of each cell represents the number of samples whose true label is predicted to be the label. The confused data refers to the samples of U-turn and turning behaviors that are incorrectly classified and screened out from the test set according to the results of the confusion matrix. This embodiment does not limit the identification method of the confused data. Technical personnel in this field can freely set it according to actual conditions, as long as the identification requirements of the confused data are met, such as setting the U-turn behavior to be incorrectly classified as turning behavior. The true label refers to the true and known output label of each sample in the test set of the agricultural machinery driving trajectory analysis model. The predicted label refers to the output label prediction generated by the agricultural machinery driving trajectory analysis model on the given input data. The confusion number refers to the number of samples that are incorrectly classified in the agricultural machinery driving trajectory analysis model. The preset confusion number refers to the threshold value pre-set for the confusion number.

[0088] Specifically, step S5 judges the output result of the agricultural machinery driving trajectory analysis model according to the number of confusions between the in-field U-turn behaviors and the in-field turning behaviors in the agricultural machinery driving trajectory analysis model, so as to enhance the judgment ability of the agricultural machinery driving trajectory analysis model.

[0089] Specifically, in step S6, when adjusting the output result of the agricultural machinery driving trajectory analysis model, the turning radius R during the operation of the agricultural machinery is compared with the preset turning radius R0, and the output result of the agricultural machinery driving trajectory analysis model is adjusted according to the comparison result, wherein:

[0090] When R>R0, the output result of the agricultural machinery driving trajectory analysis model is adjusted to the agricultural machinery turning behavior in the field;

[0091] When R≤R0, the output result of the agricultural machinery driving trajectory analysis model is adjusted to the turning behavior of the agricultural machinery in the field.

[0092] Specifically, the turning radius refers to the radius of the arc formed by the center of the agricultural machinery around the instantaneous steering center when the agricultural machinery is performing a turning operation. The center around the instantaneous steering center refers to the radius of the arc formed by the virtual center point around which all wheels rotate during the turning process. The preset turning radius refers to the preset value for the turning behavior and U-turn behavior of the agricultural machinery in the field.

[0093] Specifically, step S6 adjusts the output result of the agricultural machinery driving trajectory analysis model according to the turning radius of the agricultural machinery during operation, so as to improve the accuracy of the model prediction and make it closer to the actual operation situation.

[0094] Specifically, in step S7, when judging the field operation behavior in the agricultural machinery driving trajectory analysis model, the parallel operation and the overlapping operation in the field are judged according to the direction angle of the agricultural machinery driving trajectory. (x i ,y i ) is the coordinate of the track point, and the direction angle θ of the agricultural machinery driving track i Compare with the preset direction angle θ0, and judge the parallel operation and overlapping operation in the field according to the comparison results, and optimize the output results of the agricultural machinery driving trajectory analysis model according to the judgment results, where:

[0095] When θ i >θ0, the agricultural machinery driving trajectory is determined to be an overlapping operation in the field, and the output result of the agricultural machinery driving trajectory analysis model is added to include overlapping operations in the field, and the output result added to the agricultural machinery driving trajectory analysis model is an overlapping operation in the field, and the agricultural machinery driving trajectory is dynamically adjusted;

[0096] When θ i When ≤θ0, the agricultural machinery driving trajectory is determined to be parallel operation in the field, and the output results of the agricultural machinery driving trajectory analysis model are added to include parallel operation in the field, and the agricultural machinery driving trajectory is dynamically adjusted to keep a consistent spacing when the agricultural machinery is operating in parallel in the field.

[0097] Specifically, the parallel operation in the field refers to the operation performed by agricultural machinery along parallel tracks in the actual operation plot, and each operation covers a different area. The overlapping operation in the field refers to passing through and covering the same area multiple times in the actual operation plot. The direction angle of the agricultural machinery driving trajectory refers to the instantaneous driving direction angle of the agricultural machinery relative to the preset direction during the field operation. The preset direction refers to the setting by professionals in the field according to the actual operation plot. The preset direction angle refers to the reference angle set according to the geometric characteristics of the actual operation plot, such as setting θ0=10°. This embodiment does not limit the dynamic adjustment method, and technical personnel in this field can freely set it according to actual conditions, as long as the adjustment requirements for the agricultural machinery driving trajectory are met, such as setting a GPS navigation algorithm, using the GPS global positioning system to determine the position and driving trajectory of the agricultural machinery, and through the pre-planned path and real-time position data, the agricultural machinery can perform automatic navigation and trajectory adjustment.

[0098] Specifically, when judging the in-field operation behavior in the agricultural machinery driving trajectory analysis model, step S7 judges the parallel operation and overlapping operation in the field according to the direction angle of the agricultural machinery driving trajectory, so as to optimize the operation path and operation time, ensure the coordination and cooperation between multiple agricultural machinery, and enable the farmland to be fully processed.

[0099] Specifically, in step S8, when the agricultural machinery operation process is monitored and alarmed in real time, the agricultural machinery operation range is obtained according to the road driving data and the field operation data, the agricultural machinery operation data Y collected in real time is compared with the preset operation range data Y0, and the agricultural machinery operation range is monitored in real time according to the comparison result, wherein:

[0100] When Y>Y0, it is determined that the agricultural machinery is beyond the agricultural machinery operation range, and an agricultural machinery beyond-range alarm is issued;

[0101] When Y≤Y0, the agricultural machinery is determined to be within the agricultural machinery operating range, and no agricultural machinery exceeding alarm is issued.

[0102] Specifically, the agricultural machinery operation data refers to the data representation of the spatial range actually covered by the agricultural machinery during the actual operation process, and the preset operation range data refers to the preset value of the agricultural machinery operation range based on the road driving data and the field operation data.

[0103] Specifically, step S8 performs real-time monitoring and alarming of the agricultural machinery operation process based on road driving data and field operation data, so as to facilitate real-time data analysis, timely discover abnormal situations in the operation process, and take measures to intervene or adjust to ensure the quality and efficiency of agricultural machinery operations.

[0104] Specifically, in step S9, when adjusting the alarm behavior of the agricultural machinery operation process, wherein:

[0105] When the agricultural machinery exceeds the operating range, the time T that the agricultural machinery exceeds the operating range is compared with the preset exceeding time T0, and the alarm behavior is adjusted according to the comparison result, where:

[0106] If T>T0, it is determined that the agricultural machinery has exceeded the agricultural machinery operation range for an abnormal period of time, and an agricultural machinery exceeding alarm is issued;

[0107] If T≤T0, it is determined that the agricultural machinery has exceeded the agricultural machinery operation range for a normal period of time, and no agricultural machinery exceeding alarm is issued;

[0108] When the agricultural machinery is within the agricultural machinery operation range, the difference between the real-time collected agricultural machinery operation data Y and the preset operation range data Y0 is compared with the boundary threshold △Y, and the alarm behavior is adjusted according to the comparison result, where:

[0109] If Y-Y0≤Y, it is determined that the agricultural machinery operation is about to exceed the agricultural machinery operation range, and a boundary approach alarm is issued;

[0110] If Y-Y0>△Y, it is determined that the agricultural machinery operation does not exceed the agricultural machinery operation range, and no boundary approach alarm is issued.

[0111] Specifically, the preset excess time refers to the time during which the agricultural machinery is allowed to deviate briefly, and the boundary threshold refers to the preset value when the agricultural machinery approaches the boundary of the preset operating range.

[0112] Specifically, step S9 adjusts the alarm behavior of the agricultural machinery operation process so that the operator can adjust the operation trajectory in advance to avoid actually exceeding the operation range, and avoid triggering an alarm due to a brief deviation, thereby reducing interference to the operator.

[0113] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for establishing a driving trajectory based on intelligent agricultural machinery, characterized in that: include: Step S1, collecting the operation plot source data of the intelligent agricultural machinery equipment, obtaining a time-series operation plot data source set, converting the longitude and latitude data in the time-series operation plot data source set into plane coordinate data, and recording the plane coordinate data into a plane coordinate data set; Step S2, classifying the plane coordinate data set according to the density data classification algorithm to obtain a classification set of agricultural machinery labels; Step S3, classifying and counting the road driving data and the field operation data according to the agricultural machinery label classification set and the time-series operation plot data source set, to obtain the road driving data and the field operation data; Step S4, judging the field operation behavior, field turning behavior and field turning behavior of the field operation data according to the agricultural machinery driving trajectory analysis model; Step S5, judging the output result of the agricultural machinery driving trajectory analysis model according to the number of confusions between the in-field U-turn behavior and the in-field turning behavior in the agricultural machinery driving trajectory analysis model; Step S6, adjusting the output result of the agricultural machinery driving trajectory analysis model according to the turning radius of the agricultural machinery during operation; Step S7, judging the parallel operation and overlapping operation in the field according to the direction angle of the agricultural machinery driving trajectory, and optimizing the output result of the agricultural machinery driving trajectory analysis model according to the judgment result; Step S8, real-time monitoring and alarming of the agricultural machinery operation process based on the road driving data and the plot operation data; Step S9, adjusting the alarm behavior of the agricultural machinery operation process according to the time when the agricultural machinery exceeds the agricultural machinery operation range and the difference between the agricultural machinery operation range data collected in real time and the preset operation range data.

2. The method for establishing a driving trajectory based on an intelligent agricultural machine according to claim 1, characterized in that: In the step S1, when collecting the work plot source data of the intelligent agricultural machinery equipment, a work plot data source set in the order of collection time is formed, which is used as a time series work plot data source set; the time series work plot data source set is traversed to obtain the longitude and latitude data in each data in the set, and recorded as a longitude and latitude data set; the longitude and latitude data set is traversed, the input coordinate system is set to WGS84, and the output coordinate system is obtained by Gaussian projection, and the Gaussian projection formula is used: Among them, k0 is the scale factor, N is the radius of curvature of the zodiac circle, λ is the longitude, λ0 is the longitude of the central meridian, To normalize the latitude, the high-order terms are the terms of the square and fourth power of the longitude difference, t is the flattening coefficient of the ellipsoid, and the longitude and latitude data (α, φ) in the spherical coordinate system are converted into plane coordinate data (x, y), x = R·α·cosφ, y = R·φ, R is the radius of the earth, and the plane coordinate data (x, y) is recorded as a plane coordinate data set.

3. The method for establishing a driving trajectory based on an intelligent agricultural machine according to claim 2, characterized in that: In step S2, when classifying the plane coordinate data set, the plane coordinate data set is input into the density data classification algorithm, the labels of the plane coordinate data output by the density data classification algorithm are obtained, and stored in the label classification set, the neighborhood radius in the density data classification algorithm is set to 20, the minimum number of samples is set to 120, and the plane coordinate data set is classified according to the labels of the plane coordinate data in the label classification set, wherein: When the label of the plane coordinate data (x1, y1) in the label classification set is -1, the plane coordinate data (x1, y1) is determined to be a label that does not conform to the classification data; When the label of the plane coordinate data (x2, y2) in the label classification set is other non-negative integers, the plane coordinate data (x2, y2) is determined to be a label that conforms to the classification data, and the agricultural machinery label classification set is obtained.

4. The method for establishing a driving trajectory based on an intelligent agricultural machine according to claim 3, characterized in that: In step S3, when classifying and counting the road travel data and the field operation data, the labels of the plane coordinate data in the agricultural machinery label classification set are matched with the longitude and latitude coordinates in the time series operation plot data source set, and the longitude and latitude coordinates in the time series operation plot data source set are marked according to the labels of the plane coordinate data in the agricultural machinery label classification set, wherein: When the label of the plane coordinate data in the agricultural machinery label classification set is -1, the longitude and latitude coordinates in the corresponding time series operation plot data source set are marked as road driving data; When the label of the classified data in the agricultural machinery label classification set is other integers, the longitude and latitude coordinates in the corresponding time series operation plot data source set are marked as field operation data.

5. The method for establishing a driving trajectory based on an intelligent agricultural machine according to claim 4, characterized in that: In step S4, when judging the field operation behavior, field U-turn behavior and field turning behavior of the field operation data according to the agricultural machinery driving trajectory analysis model, the data of the agricultural machinery motion trajectory, motion speed and motion acceleration are input into the agricultural machinery driving trajectory analysis model to obtain the output result of the agricultural machinery driving trajectory analysis model, which includes the field operation behavior, field U-turn behavior and field turning behavior, and is used as the field driving trajectory of the agricultural machinery.

6. The method for establishing a driving trajectory based on an intelligent agricultural machine according to claim 5, characterized in that: In step S5, when judging the output result of the agricultural machinery driving trajectory analysis model, the test set data of the agricultural machinery motion trajectory, motion speed and motion acceleration are input into the agricultural machinery driving trajectory analysis model, and the predicted labels are collected, a confusion matrix is ​​generated according to the real labels and the predicted labels, the confusion number is output, the confusion number S is compared with the preset confusion number S0, and the output result of the agricultural machinery driving trajectory analysis model is judged according to the comparison result, wherein: When S>S0, the output result of the agricultural machinery driving trajectory analysis model is determined to be abnormal, and a new characteristic turning radius is introduced into the agricultural machinery driving trajectory analysis model; When S≤S0, it is determined that the output result of the agricultural machinery driving trajectory analysis model is normal.

7. The method for establishing a driving trajectory based on an intelligent agricultural machine according to claim 6, characterized in that: In step S6, when adjusting the output result of the agricultural machinery driving trajectory analysis model, the turning radius R during the operation of the agricultural machinery is compared with the preset turning radius R0, and the output result of the agricultural machinery driving trajectory analysis model is adjusted according to the comparison result, wherein: When R>R0, the output result of the agricultural machinery driving trajectory analysis model is adjusted to the agricultural machinery turning behavior in the field; When R≤R0, the output result of the agricultural machinery driving trajectory analysis model is adjusted to the turning behavior of the agricultural machinery in the field.

8. The method for establishing a driving trajectory based on an intelligent agricultural machine according to claim 7, characterized in that: In step S7, when judging the field operation behavior in the agricultural machinery driving trajectory analysis model, the parallel operation and the overlapping operation in the field are judged according to the direction angle of the agricultural machinery driving trajectory. (x i ,y i ) is the coordinate of the track point, and the direction angle θ of the agricultural machinery driving track i Compare with the preset direction angle θ0, and judge the parallel operation and overlapping operation in the field according to the comparison results, and optimize the output results of the agricultural machinery driving trajectory analysis model according to the judgment results, where: When θ i >θ0, the agricultural machinery driving trajectory is determined to be an overlapping operation in the field, and the output result of the agricultural machinery driving trajectory analysis model is added to include overlapping operations in the field, and the output result added to the agricultural machinery driving trajectory analysis model is an overlapping operation in the field, and the agricultural machinery driving trajectory is dynamically adjusted; When θ i When ≤θ0, the agricultural machinery driving trajectory is determined to be parallel operation in the field, and the output results of the agricultural machinery driving trajectory analysis model are added to include parallel operation in the field, and the agricultural machinery driving trajectory is dynamically adjusted to keep a consistent spacing when the agricultural machinery is operating in parallel in the field.

9. The method for establishing a driving trajectory based on an intelligent agricultural machine according to claim 8, characterized in that: In step S8, when the agricultural machinery operation process is monitored and alarmed in real time, the agricultural machinery operation range is obtained according to the road driving data and the field operation data, the agricultural machinery operation data Y collected in real time is compared with the preset operation range data Y0, and the agricultural machinery operation range is monitored in real time according to the comparison result, wherein: When Y>Y0, it is determined that the agricultural machinery is beyond the agricultural machinery operation range, and an agricultural machinery beyond-range alarm is issued; When Y≤Y0, the agricultural machinery is determined to be within the agricultural machinery operating range, and no agricultural machinery exceeding alarm is issued.

10. The method for establishing a driving trajectory based on an intelligent agricultural machine according to claim 9, characterized in that: In step S9, when adjusting the alarm behavior of the agricultural machinery operation process, wherein: When the agricultural machinery exceeds the operating range, the time T that the agricultural machinery exceeds the operating range is compared with the preset exceeding time T0, and the alarm behavior is adjusted according to the comparison result, where: If T>T0, it is determined that the agricultural machinery has exceeded the agricultural machinery operation range for an abnormal period of time, and an agricultural machinery exceeding alarm is issued; If T≤T0, it is determined that the agricultural machinery has exceeded the agricultural machinery operation range for a normal period of time, and no agricultural machinery exceeding alarm is issued; When the agricultural machinery is within the agricultural machinery operation range, the difference between the real-time collected agricultural machinery operation data Y and the preset operation range data Y0 is compared with the boundary threshold △Y, and the alarm behavior is adjusted according to the comparison result, where: If Y-Y0≤Y, it is determined that the agricultural machinery operation is about to exceed the agricultural machinery operation range, and a boundary approach alarm is issued; If Y-Y0>△Y, it is determined that the agricultural machinery operation does not exceed the agricultural machinery operation range, and no boundary approach alarm is issued.

Images