LU500256B1 - Agricultural Machinery Operation Area Calculation Method Based on Positioning Drift Calculation Model - Google Patents
Agricultural Machinery Operation Area Calculation Method Based on Positioning Drift Calculation Model Download PDFInfo
- Publication number
- LU500256B1 LU500256B1 LU500256A LU500256A LU500256B1 LU 500256 B1 LU500256 B1 LU 500256B1 LU 500256 A LU500256 A LU 500256A LU 500256 A LU500256 A LU 500256A LU 500256 B1 LU500256 B1 LU 500256B1
- Authority
- LU
- Luxembourg
- Prior art keywords
- trajectory
- area
- agricultural machinery
- positioning
- calculation model
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/28—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring areas
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An agricultural machinery operation area calculation method based on a positioning drift calculation model, comprising the following steps: step 1, collecting and preprocessing moving trajectory points of agricultural machinery, involving: preprocessing sensor data, screening out agricultural machinery operation state information, constructing a trajectory point time sequence conforming to an operation state; step 2, constructing a positioning trajectory and operation trajectory, and establishing a polygon according to an operation width; step 3, calculating a coverage area of the operation trajectory, involving: calculating a trajectory area, coverage area and blank area of the operation trajectory from different angles; step 4, constructing a positioning drift calculation model by using extracted core features, and training a sample to learn model parameters; step 5, calculating an agricultural machinery operation area, involving: inputting an operation trajectory and operation area to be calculated into the positioning drift calculation model to obtain an accurate agricultural machinery operation area.
Description
Description 500256 Agricultural Machinery Operation Area Calculation Method Based on Positioning Drift Calculation Model Technical Field The present disclosure relates to an agricultural machinery operation area calculation method based on a positioning drift calculation model. Background Art Deep loosening and land preparation operations of agricultural machinery are of great significance in realizing soil moisture conservation and relieving farmland hardening. By installing digital technology navigation devices such as geographic information systems and spatial positioning systems on the agricultural machinery and combining with a background service system, the requirements of remote monitoring and management of deep loosening and land preparation operations of the agricultural machinery can be met, and accurate operations of cultivation, seeding and harvesting of agricultural production can be realized. Novel agricultural machinery management and market-oriented service modes are becoming more and more mature. Both supply and demand parties require agricultural machinery operation services to provide high- accuracy, high-reliability, real-time and convenient agricultural machinery operation area calculation results.
Existing agricultural machinery operation area calculation methods mainly include distance methods, buffer area methods, grid methods, etc. These methods are limited by the following two aspects: when the positioning accuracy of the agricultural machinery moving trajectory points is poor due to drift, interference and the like of a low-cost Global Positioning System (GPS), there will be great errors in the operation area calculation results; and when there are multiple operation types in the agricultural machinery farming process and overlapping areas and non-operation areas are generated, the calculation accuracy is low.
Therefore, how to accurately calculate the operation area of the agricultural machinery with the low-cost GPS in a complicated operating environment has become a technical problem needing to be solved urgently. 500256 Summary of the Invention The objective of the present disclosure is to provide an agricultural machinery operation area calculation method based on a positioning drift calculation model, so as to solve the problem of low calculation accuracy of an agricultural machinery operation area caused when there are multiple operation types in an agricultural machinery farming process and overlapping areas and non-operation areas are generated in the prior art.
The agricultural machinery operation area calculation method based on a positioning drift calculation model includes the following steps: step 1, collecting and preprocessing moving trajectory points of agricultural machinery, involving: preprocessing data of a positioning sensor and an attitude sensor of the agricultural machinery, screening out agricultural machinery operation state information, and constructing a trajectory point time sequence conforming to an operation state; step 2, constructing a positioning trajectory and an operation trajectory, involving: sequentially connecting positioning points conforming to an operation state, and establishing a broken line path of the operation trajectory; and at the same time, generating a quadrangle by every two points respectively according to an operation width, and establishing a polygon by performing logic operation on a plurality of quadrangles; step 3, calculating a coverage area of the operation trajectory, involving: calculating a trajectory area, coverage area and blank area of the operation trajectory from different angles; step 4, constructing a positioning drift calculation model, involving: analyzing different trajectory coverage types, extracting core features of trajectory coverage area calculation, and constructing the positioning drift calculation model by using extracted core features; and training a sample to learn model parameters; and step 5, calculating an agricultural machinery operation area, involving: inputting an operation trajectory and operation area to be calculated into the positioning drift 500256 calculation model to obtain an accurate agricultural machinery operation area.
Preferably, the step 1 specifically includes the following steps: step 1.1, receiving data transmitted back per second by a GPS sensor and the attitude sensor mounted on the agricultural machinery; step 1.2, screening out too close or too far positioning points of agricultural machinery positioning points within the interval time; and step 1.3, remaining trajectory points with a ploughing depth reaching deep ploughing requirements of China after screening to be used as agricultural machinery operation effective trajectory points which are put into a set, and building a trajectory point time sequence.
Preferably, the step 2 specifically includes the following steps: step 2.1, sequentially connecting the positioning points conforming to an operation state in the step 1, and building a broken line path of the operation trajectory; step 2.2, calculating an azimuth angle between two time-sequence-adjacent trajectory points P1 and P2 on the agricultural machinery operation trajectory according to coordinates of the two trajectory points; step 2.3, calculating an azimuth angle of the agricultural machinery on the trajectory between the two adjacent trajectory points according to the fact that the agricultural machinery is perpendicular to the trajectory; step 2.4, obtaining four extending points L1, L2, L3 and LA of the trajectory points P1 and P2 according to the azimuth angle of the agricultural machinery and a plough length R to further form a quadrangle S1 of this section of trajectory operation coverage area, and by parity of reasoning, calculating all quadrangles S1 to Sn on the trajectory path; step 2.5, performing logical operation on the quadrangles S1to Sn obtained in the step 2.4 to build a total operation area polygon.
Preferably, the step 3 specifically includes the following steps: step 3.1, calculating a theoretical trajectory area of the operation, involving: sequentially connecting the positioning points conforming to an operation state,
respectively calculating a distance of each section of trajectory, and counting a 500256 trajectory coverage area according to an operation width; and step 3.2, calculating a theoretical coverage area of the operation, involving: performing graphics-based calculation on the polygon obtained through logic operation on small quadrangles formed by operation points in pairs, and counting the theoretical coverage area, an external outline area and an internal blank area.
Preferably, the step 4 specifically includes the following steps: step 4.1, determining elements reflecting coordinate positioning drift, and further extracting core features for realizing blank area analysis, wherein the core features are respectively a local overlap degree, a global overlap degree and a global coverage degree; step 4.2, optimizing parameters of the core features, involving: training the parameters of the core features according to sample data, and mapping the core features to a specific unified interval [0,1]; and step 4.3, constructing a positioning drift calculation model, involving: building the positioning drift calculation model by using the optimized parameters of the core features and using a machine learning method.
Preferably, the step 4.1 specifically includes the following steps: step 4.1.1, determining the elements reflecting the coordinate positioning drift, involving: taking and expressing an area of a finite envelope area of the operation trajectory on a map as an external area Sexternal, €Xpressing the effective coverage area formed by merging the quadrangles formed by the trajectory points in the finite envelope area as an internal area Sinternal, €Xpressing a difference value between Sexternal and Sinternal, 1.€., an internal blank area as Spjank; and calling a trajectory coverage area formed through calculation by combining a trajectory length with a plough width R as a trajectory area Strajectory; and step 4.1.2, extracting the local overlap degree, the global overlap degree and the global coverage degree of the core features for realizing blank area analysis, wherein the local overlap degree is defined as a ratio of the trajectory area to the internal area, and is expressed by a, 7500256 = Zelte dE [1,00).
The local overlap degree a expresses the degree of local overlap in the trajectory, the denser the trajectory and the more concentrated the overlap area, the greater the local overlap degree. Ideally, the local overlap degree approaches to 1, which indicates that the trajectory has no drift and the operation is normal.
The global overlap degree is defined as a ratio of the trajectory area to the external area, and is expressed by J, pen eon The global overlap degree ß expresses an integral scattering degree in the trajectory, the more uniform the track point distribution and the more scattered the overlap area, the greater the global overlap degree. Ideally, the global overlap degree of a complete operation trajectory approaches to 1.
The global coverage degree is defined as a ratio of the internal area to the external area, and is expressed by y, ype ye 0,1], The global coverage degree y expresses the coverage degree of a practical operation area in the operation area. The more normative the operation and the more uniform the trajectory, the greater the global coverage degree; and if the operation is abnormal, and the overlap is concentrated, the global coverage degree is smaller.
Preferably, the step 4.2 specifically includes the following steps: step 4.2.1, optimizing the parameters of the core features, and selecting a sigmod function to map the parameters to the interval [0,1]: K (a) = _ 2 —1, K,{o) € (0,1) +e vai | Ka) = rae 1 REO ra step 4.2.2, training the parameters x and y of the core features according to the sample data, and determining specific mapping functions K (and K=(8), Preferably, the step 4.3specifically includes the following steps:
step 4.3.1, constructing a positioning drift calculation model, and performing 500256 formal representation by the optimized parameters of the core features, wherein particularly, a structure of the blank Spjankis analyzed, Sabnormal IN Splank = Sdrift + Sabnormal 18 able to be specifically divided into two types: one type is a redundant portion, especially under the condition that the global overlap degree ß is smaller than 1, there will be other trajectories for filling in a subsequent process; and the other type is a non-operation blank portion, the blank area is generated due to non- coverage in the operation process, and the area is expressed as Spon-operation; in the method, a redundancy rate of the trajectory is defined as Oredundancy» indicating a proportion of the redundant operation area in the internal area of the operation trajectory: I =1-BBE (0,1) Oredundancy = 0,B € [1,) | the Sredundancy represents the corresponding redundant operation area, and / is the global overlap degree, then: Sredundancy”Predundancy X Sblanks at the same time, the blank rate Oplanr of the trajectory is defined as a proportion of the area of a blank generated by abnormal operation in the practical trajectory in the blank area after the redundant operation area is removed, then: Spon-operation Optank X (Sblank — Sredundancy): and Sabnormal 1S an operation non-coverage area generated by abnormal operation, and is expressed as follows according to the above analysis: Sabnormal=Sredundancy + Snon-operation: step 4.3.2, building a positioning drift calculation model based on the optimized parameters of the core features by using a machine learning method, wherein based on a trajectory of a test sample, a practical operation area is expressed as Shormaito obtain the following relation: Snormal=Sexternal — Sblank X f (0 B),
wherein f(a, B)is a calculation function of a ratio of SabnormallN Splank, and an HU500256 equation of the blank rate Op;anz1$ known, so a calculation model of 8,,,, also needs to be built; through tests, it is found that when keeps unchanged, the greatera, the greater a value of Opranr; When akeeps unchanged, the greater, the small era value of Opzank; according to the above conclusion, a calculation model of the blank rate 84, 1s built through a sigmod function: Optank = (1 — K,(B)1 9), by using a machine learning method, in conjunction with the specific sample trajectory, a clear representation of the positioning drift calculation model is established; based on the trajectory of the test sample, the practical operation area is expressed as Shormaito obtain the following relation: Snormal”Sexternal 7 Sabnormal» Le, Snormal”Sexternal 7 Fredundancy X Sblank 7 Opianr X (1 — Orequndancy) X Sblank and the positioning drift calculation model is thus built.
Preferably, the step 5 specifically includes the following steps: step 5.1, preprocessing the positioning points into a trajectory sequence, calculating values of different features and parameters, and generating a trajectory to be processed; and step 5.2, inputting the trajectory to be processed into the positioning drift calculation model to realize different classification of the trajectory, and correcting and compensating a drift area to obtain the practical operation area of the agricultural machinery.
The present disclosure has the following advantages that: After the collected moving trajectory points of the agricultural machinery are preprocessed, the operation area polygon is constructed by logic operations, the positioning drift calculation model is built by analyzing different trajectory coverage types and extracting core features of trajectory coverage area calculation, and the accurate agricultural machinery operation area is finally obtained. By adopting the machine learning method, the calculation model can be continuously corrected to 500256 improve the accuracy. There are two operation abnormal conditions, one condition is called as redundancy, under this condition, the subsequent global overlap degree is smaller than 1, and other trajectories are used for filling in the subsequent process; and the other condition is an uncovered blank area in the operation process caused by abnormal operation. The blank area generated by abnormal operation and the blank area displayed by positioning drift jointly form the blank region occurring during calculation. Aiming at the two abnormal operation conditions, the method provides the redundancy rate and the blank rate for calculation and analysis, and the blank rate which is not easy to calculate is continuously corrected through machine learning, so that an error portion generated by abnormal operation can be accurately calculated. Therefore, the problem of calculation error of the agricultural machinery operation area caused by low-cost GPS positioning drift, agricultural machinery operation offset and the like are solved, the measurement accuracy of the agricultural machinery operation area is improved, and a basis is provided for the accurate operation of the agricultural machinery and operation subsidies of agricultural machinery operators. Brief Description of the Drawings Figure 1 is a flow diagram of an agricultural machinery operation area calculation method based on a positioning drift calculation model of the present disclosure. Detailed Description of the Invention With reference to the drawings, the specific implementations of the present disclosure will be further illustrated in detail hereafter through the description of the embodiments to help those skilled in the art have a more complete, accurate and deep understanding on the inventive concept and technical solution of the present disclosure.
As shown in Figure 1, the present disclosure provides an agricultural machinery operation area calculation method based on a positioning drift calculation model, including the following steps: Step 1, moving trajectory points of agricultural machinery are collected and preprocessed: data of a positioning sensor and an attitude sensor of the agricultural 500256 machinery is preprocessed, agricultural machinery operation state information 1s screened out, and a trajectory point time sequence conforming to an operation state is constructed. The following specific steps are included: Step 1.1, data transmitted back per second by a GPS sensor and the attitude sensor mounted on the agricultural machinery is received.
Step 1.2, too close or too far positioning points of agricultural machinery positioning points within the interval time are screened out.
Step 1.3, trajectory points with a ploughing depth reaching deep ploughing requirements of China after screening are remained to be used as agricultural machinery operation effective trajectory points to be put into a set, and a trajectory point time sequence is built.
Step 2, a positioning trajectory and an operation trajectory are constructed: positioning points conforming to an operation state are sequentially connected, and a broken line path of an operation trajectory is built; and at the same time, a quadrangle is generated by every two points respectively according to an operation width, and a polygon is established by performing logic operation on a plurality of quadrangles. The following specific steps are included: Step 2.1, the positioning points conforming to an operation state in the step 1 are sequentially connected, and a broken line path of an operation trajectory is built.
Step 2.2, an azimuth angle between two time-sequence-adjacent trajectory points P1 and P2 on the agricultural machinery operation trajectory is calculated according to coordinates of the two trajectory points.
Step 2.3, an azimuth angle of the agricultural machinery on the trajectory between the two adjacent trajectory points is calculated according to the fact that the agricultural machinery is perpendicular to the trajectory.
Step 2.4, four extending points L1, L2, L3 and LA of the trajectory points P1 and P2 are obtained according to the azimuth angle of the agricultural machinery and a plough length R to further form a quadrangle S1 of this section of trajectory operation coverage area, and by parity of reasoning, all quadrangles S1 to Sn on the trajectory path are calculated. 500256 Step 2.5, logical operation is performed on the quadrangles S1 to Sn obtained in the step 2.4 to build a total operation area polygon. The total operation area polygon provides a basis for the subsequent area calculation.
Step 3, a coverage area of the operation trajectory is calculated: a trajectory area, coverage area and blank area of the operation trajectory are calculated from different angles. The following specific steps are included: Step 3.1, a theoretical trajectory area of the operation is calculated: the positioning points conforming to an operation state are sequentially connected, a distance of each section of trajectory is respectively calculated, a trajectory coverage area is counted according to an operation width, and this area includes overlap portions among all sections of trajectories.
Step 3.2, a theoretical coverage area of the operation is calculated: graphics-based calculation is performed on the polygon obtained through logic operation on small quadrangles formed by operation points in pairs, and the theoretical coverage area, an external outline area and an internal blank area are counted. The external outline area is an area enclosed by the external outline of the formed polygon, the blank area is an area of the blank portion in the external outline formed by the polygon, and the theoretical coverage area is a coverage area of the polygon itself. The above areas are provided for the constructed positioning drift calculation model to solve the practical operation area.
Step 4, a positioning drift calculation model is constructed: different trajectory coverage types are analyzed, core features for trajectory coverage area calculation are extracted, the positioning drift calculation model is constructed by using extracted core features, and a sample is trained to learn model parameters. The following specific steps are included: Step 4.1, elements reflecting coordinate positioning drift are determined, and core features for realizing blank area analysis, respectively a local overlap degree, a global overlap degree and a global coverage degree are further extracted. The following specific steps are included:
Step 4.1.1, the elements reflecting the coordinate positioning drift are determined: 500256 a finite envelope area of the operation trajectory on a map is taken and expressed as an external area Sexternal, the effective coverage area formed by merging the quadrangles formed by the trajectory points in the finite envelope area is expressed as an internal area Sinternal, a difference value between Sexternal and Sinternal, 1.€., an internal blank area is expressed as Spank, and a trajectory coverage area formed through calculation by combining a trajectory length with a plough width R is called as a trajectory area Strajectory- Step 4.1.2, the local overlap degree, the global overlap degree and the global coverage degree of the core features for realizing blank area analysis are extracted.
The local overlap degree is defined as a ratio of the trajectory area to the internal area, and is expressed by a, = el o € [1,00).
The local overlap degree a expresses the degree of local overlap in the trajectory, the denser the trajectory and the more concentrated the overlap area, the greater the local overlap degree. Ideally, the local overlap degree approaches to 1 which indicates that the trajectory has no drift and the operation is normal.
The global overlap degree is defined as a ratio of the trajectory area to the external area, and is expressed by J, potatos BE [0,c0), The global overlap degree f expresses an integral scattering degree in the trajectory, the more uniform the track point distribution and the more scattered the overlap area, the greater the global overlap degree. Ideally, the global overlap degree of a complete operation trajectory approaches to 1.
The global coverage degree is defined as a ratio of the internal area to the external area, and is expressed by y, tye 0) The global coverage degree y expresses the coverage degree of a practical operation area in the operation area. The more normative the operation and the more 500256 uniform the trajectory, the greater the global coverage degree; and if the operation is abnormal, and the overlap is concentrated, the global coverage degree is smaller. The above core features are all obtained through the area data calculated in step 3, and are important parameters required for solving the practical operation area. Different trajectory coverage types are determined according to the differences of the core features.
Step 4.2, parameters of the core features are optimized: the parameters of the core features are trained according to the sample data, and the core features are mapped to a specific unified interval [0,1]. The following specific steps are included: Step 4.2.1, the parameters of the core features are optimized, and a sigmod function is selected to map the parameters to the interval [0,1]: Kıla) = __: — 1, K,{u) € (0,1) 1 4e mais | © = 1 OD Step 4.2.2, the parameters x and y of the core features are trained according to the sample data, and specific mapping functions K, (€ and X2(8} are determined. The mapping functions are very important for the area analysis of the subsequent abnormal conditions.
Step 4.3, a positioning drift calculation model is constructed: the positioning drift calculation model is built by using the optimized parameters of the core features and using a machine learning method. The following specific steps are included: Step 4.3.1, a positioning drift calculation model is constructed, and formal representation is performed by the optimized parameters of the core features.
Particularly, a structure of the blank Splanr!S analyzed, Sabnormal IN Sblank = Sdrift + Sabnormal 1S able to be specifically divided into two types: one type is a redundant portion, especially under the condition that the global overlap degree ß is smaller than 1, there will be other trajectories for filling in a subsequent process; and the other type is a non-operation blank portion, the blank area is generated due to non-
coverage in the operation process, and the area is expressed as Snon-operation:
in the method, a redundancy rate of the trajectory is defined as O-edundancy: indicating a proportion of the redundant operation area in the internal area of the operation trajectory:
I =1-BBE (0,1) Oredundancy = 0,B € [1,) | the Sredundancy represents the corresponding redundant operation area, and / is the global overlap degree, then:
Sredundancy7Üredundancy X Sblank-
At the same time, the blank rate Opranæ of the trajectory is defined as a proportion of the area of a blank generated by abnormal operation in the practical trajectory in the blank area after the redundant operation area is removed, then:
Spon-operation Optank X (Sblank — Sredundancy): and
Sabnormal 1S an operation non-coverage area generated by abnormal operation, and is expressed as follows according to the above analysis: Sabnormal7Sredundancy + Snon-operation-
Step 4.3.2, a positioning drift calculation model is built based on the optimized parameters of the core features by using a machine learning method, wherein based on a trajectory of a test sample, a practical operation area is expressed as Shormaito obtain the following relation:
Snormal=Sexternal — Sblank X f (0 B),
wherein f(a, B)is a calculation function of a ratio of SabnormallN Splank, and an equation of the blank rate Op;anz1$ known, so a calculation model of Opranralso needs to be built;
through tests, it is found that when B keeps unchanged, the greatera, the greater a value of Opranr; When akeeps unchanged, the greater 3, the small era value of Opjank; according to the above conclusion, a calculation model of the blank rate 84, 1s built through a sigmod function:
Opiank = (1 — Kp(B)*~*1(®),
by using a machine learning method, in conjunction with the specific sample 500256 trajectory, a clear representation of the positioning drift calculation model is established; based on the trajectory of the test sample, the practical operation area is expressed as Shormaito obtain the following relation: Snormal”Sexternal 7 Sabnormal- Le, Snormal”Sexternal 7 redundancy X Sblank — Opianr X (1 — 9redundancy) X Sblank: and the positioning drift calculation model is thus built. Since the mapping functions K1(®) and KzP}have been determined through training of the core features according to the sample data, Sabnorma1Can also be accurately calculated to ensure the accuracy of the practical operation area.
Step 5, an agricultural machinery operation area is calculated: an operation trajectory and operation area to be calculated are input into the positioning drift calculation model to obtain an accurate agricultural machinery operation area. The following specific steps are included: Step 5.1, the positioning points are preprocessed into a trajectory sequence, values of different features and parameters are calculated, and a trajectory to be processed is generated.
Step 5.2, the trajectory to be processed is input into the positioning drift calculation model to realize different classification of the trajectory, and a drift area 1s corrected and compensated to obtain the practical operation area of the agricultural machinery.
According to the method, the blank portion area caused by abnormal conditions is removed from the results, and Sy. which is covered in practical operation but cannot be correctly displayed due to positioning drift during data acquisition is still included in the calculation results, so that the method of the present method can calculate the practical operation area, and overcomes the defect of low calculation accuracy of the agricultural machinery operation area caused when there are multiple operation types in an agricultural machinery farming process and overlapping areas and non-operation areas are generated in the prior art. In addition, the calculation of the practical operation area is less influenced by a positioning drift phenomenon.
The present disclosure is exemplarily described above with the reference to the 500256 drawings.
It is obvious that the specific implementations of the present disclosure are not limited by the above manners, various non-substantive improvements made by adopting the inventive concept and technical solutions of the present disclosure, or direct application of the concept and the technical solutions of the present disclosure to other occasions without improvements all fall within the protection scope of the present disclosure.
Claims (9)
1. An agricultural machinery operation area calculation method based on a positioning drift calculation model, comprising the following steps: step 1, collecting and preprocessing moving trajectory points of agricultural machinery, involving: preprocessing data of a positioning sensor and an attitude sensor of the agricultural machinery, screening out agricultural machinery operation state information, and constructing a trajectory point time sequence conforming to an operation state; step 2, constructing a positioning trajectory and an operation trajectory, involving: sequentially connecting positioning points conforming to an operation state, and establishing a broken line path of the operation trajectory; and at the same time, generating a quadrangle by every two points respectively according to an operation width, and establishing a polygon by performing logic operation on a plurality of quadrangles; step 3, calculating a coverage area of the operation trajectory, involving: calculating a trajectory area, coverage area and blank area of the operation trajectory from different angles; step 4, constructing a positioning drift calculation model, involving: analyzing different trajectory coverage types, extracting core features of trajectory coverage area calculation, and constructing the positioning drift calculation model by using extracted core features; and training a sample to learn model parameters; and step 5, calculating an agricultural machinery operation area, involving: inputting an operation trajectory and operation area to be calculated into the positioning drift calculation model to obtain an accurate agricultural machinery operation area.
2. The agricultural machinery operation area calculation method based on a positioning drift calculation model according to claim 1, wherein the step 1 specifically comprises the following steps: step 1.1, receiving data transmitted back per second by a GPS sensor and the attitude sensor mounted on the agricultural machinery;
step 1.2, screening out too close or too far positioning points of agricultural 500256 machinery positioning points within the interval time; and step 1.3, remaining trajectory points with a ploughing depth reaching deep ploughing requirements of China after screening to be used as agricultural machinery operation effective trajectory points which are put into a set, and building a trajectory point time sequence.
3. The agricultural machinery operation area calculation method based on a positioning drift calculation model according to claim 1, wherein the step 2 specifically comprises the following steps: step 2.1, sequentially connecting the positioning points conforming to an operation state in the step 1, and building a broken line path of the operation trajectory; step 2.2, calculating an azımuth angle between two time-sequence-adjacent trajectory points P1 and P2 on the agricultural machinery operation trajectory according to coordinates of the two trajectory points; step 2.3, calculating an azimuth angle of the agricultural machinery on the trajectory between the two adjacent trajectory points according to the fact that the agricultural machinery is perpendicular to the trajectory; step 2.4, obtaining four extending points L1, L2, L3 and LA of the trajectory points P1 and P2 according to the azimuth angle of the agricultural machinery and a plough length R to further form a quadrangle S1 of this section of trajectory operation coverage area, and by parity of reasoning, calculating all quadrangles S1 to Sn on the trajectory path; step 2.5, performing logical operation on the quadrangles S1 to Sn obtained in the step 2.4 to build a total operation area polygon.
4. The agricultural machinery operation area calculation method based on a positioning drift calculation model according to 1, wherein the step 3 specifically comprises the following steps: step 3.1, calculating a theoretical trajectory area of the operation, involving: sequentially connecting the positioning points conforming to an operation state, respectively calculating a distance of each section of trajectory, and counting a trajectory coverage area according to an operation width; and 500256 step 3.2, calculating a theoretical coverage area of the operation, involving: performing graphics-based calculation on the polygon obtained through logic operation on small quadrangles formed by operation points in pairs, and counting the theoretical coverage area, an external outline area and an internal blank area.
5. The agricultural machinery operation area calculation method based on a positioning drift calculation model according to claim 1, wherein the step 4 specifically comprises the following steps: step 4.1, determining elements reflecting coordinate positioning drift, and further extracting core features for realizing blank area analysis, wherein the core features are respectively a local overlap degree, a global overlap degree and a global coverage degree; step 4.2, optimizing parameters of the core features, involving: training the parameters of the core features according to sample data, and mapping the core features to a specific unified interval [0,1]; and step 4.3, constructing a positioning drift calculation model, involving: building the positioning drift calculation model by using the optimized parameters of the core features and using a machine learning method.
6. The agricultural machinery operation area calculation method based on a positioning drift calculation model according to claim 5, wherein the step 4.1 specifically comprises the following steps: step 4.1.1, determining the elements reflecting the coordinate positioning drift, involving: taking and expressing an area of a finite envelope area of the operation trajectory on a map as an external area Sexternal €Xpressing the effective coverage area formed by merging the quadrangles formed by the trajectory points in the finite envelope area as an internal area Sinternal, €Xxpressing a difference value between Sexternal and Sinternal, 1.€., an internal blank area as Spank, and calling a trajectory coverage area formed through calculation by combining a trajectory length with a plough width R as a trajectory area Strajectory; and step 4.1.2, extracting the local overlap degree, the global overlap degree and the 500256 global coverage degree of the core features for realizing blank area analysis, wherein the local overlap degree is defined as a ratio of the trajectory area to the internal area, and is expressed by a, the local overlap degree a expresses the degree of local overlap in the trajectory, the denser the trajectory and the more concentrated the overlap area, the greater the local overlap degree; ideally, the local overlap degree approaches to 1, which indicates that the trajectory has no drift and the operation is normal, the global overlap degree is defined as a ratio of the trajectory area to the external area, and is expressed by J, PL BE [0,co); the global overlap degree ß expresses an integral scattering degree in the trajectory, the more uniform the track point distribution and the more scattered the overlap area, the greater the global overlap degree; ideally, the global overlap degree of a complete operation trajectory approaches to 1; and the global coverage degree is defined as a ratio of the internal area to the external area, and is expressed by y, dye 0.1), the global coverage degree y expresses the coverage degree of a practical operation area in the operation area; the more normative the operation and the more uniform the trajectory, the greater the global coverage degree; and if the operation is abnormal, and the overlap is concentrated, the global coverage degree is smaller.
7. The agricultural machinery operation area calculation method based on a positioning drift calculation model according to claim 6, wherein the step 4.2 specifically comprises the following steps: step 4.2.1, optimizing the parameters of the core features, and selecting a sigmod function to map the parameters to the interval [0,1]:
. 2 LU500256 pee =e we (0,1) | =r RE OD step 4.2.2, training the parameters x and y of the core features according to the sample data, and determining specific mapping functions Kı (0) and K2(8),
8. The agricultural machinery operation area calculation method based on a positioning drift calculation model according to claim 7, wherein the step 4.3 specifically comprises the following steps: step 4.3.1, constructing a positioning drift calculation model, and performing formal representation by the optimized parameters of the core features, wherein particularly, a structure of the blank SpiankiS analyzed, SabnormallN Splank = Sdrift + Sabnormails able to be specifically divided into two types: one type is a redundant portion, especially under the condition that the global overlap degree ß is smaller than 1, there will be other trajectories for filling in a subsequent process; and the other type 1s a non-operation blank portion, the blank area is generated due to non- coverage in the operation process, and the area is expressed as Snon-operation: in the method, a redundancy rate of the trajectory is defined as O-edundancy: indicating a proportion of the redundant operation area in the internal area of the operation trajectory: I =1-BBE (0,1) Oredundancy = 0,B € [1,) | the Sredundancyrepresents the corresponding redundant operation area, and fis the global overlap degree, then: SredundancyTÜredundancy X Sblank: at the same time, the blank rate OpianrOf the trajectory is defined as a proportion of the area of a blank generated by abnormal operation in the practical trajectory in the blank area after the redundant operation area is removed, then: Snon-operation=0piank X (Sblank — Sredundancy)> and SabnormailS an operation non-coverage area generated by abnormal operation, and is expressed as follows according to the above analysis: 500256 Sabnormal=Sredundancy + Snon-operation; step 4.3.2, building a positioning drift calculation model based on the optimized parameters of the core features by using a machine learning method, wherein based on a trajectory of a test sample, a practical operation area is expressed as Snorma1to obtain the following relation: Snormal=Sexternal — Sblank X f (& B), wherein f(a, B)is a calculation function of a ratio of Sabnormal!N Splank.and an equation of the blank rate Opjanz18 known, so a calculation model of Opranralso needs to be built; through tests, it is found that when keeps unchanged, the greater a, the greater a value of Opranr; When akeeps unchanged, the greater, the smaller a value of Opzank; according to the above conclusion, a calculation model of the blank rate 84, 1s built through a sigmod function: Optank = (1 — K,(B)1 9), by using a machine learning method, in conjunction with the specific sample trajectory, a clear representation of the positioning drift calculation model is established; based on the trajectory of the test sample, the practical operation area is expressed asShormalto obtain the following relation: Snormal”Sexternal 7 Sabnormal» Le, Snormal”Sexternal 7 Fredundancy X Sblank 7 Opianr X (1 — Orequndancy) X Sblank and the positioning drift calculation model is thus built.
9. The agricultural machinery operation area calculation method based on a positioning drift calculation model according to claim 1, wherein the step 5 specifically comprises the following steps: step 5.1, preprocessing the positioning points into a trajectory sequence, calculating values of different features and parameters, and generating a trajectory to be processed; and step 5.2, inputting the trajectory to be processed into the positioning drift calculation model to realize different classification of the trajectory, and correcting and 500256 compensating a drift area to obtain the practical operation area of the agricultural machinery.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| LU500256A LU500256B1 (en) | 2019-10-11 | 2019-10-11 | Agricultural Machinery Operation Area Calculation Method Based on Positioning Drift Calculation Model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| LU500256A LU500256B1 (en) | 2019-10-11 | 2019-10-11 | Agricultural Machinery Operation Area Calculation Method Based on Positioning Drift Calculation Model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| LU500256B1 true LU500256B1 (en) | 2021-08-03 |
Family
ID=77125676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| LU500256A LU500256B1 (en) | 2019-10-11 | 2019-10-11 | Agricultural Machinery Operation Area Calculation Method Based on Positioning Drift Calculation Model |
Country Status (1)
| Country | Link |
|---|---|
| LU (1) | LU500256B1 (en) |
-
2019
- 2019-10-11 LU LU500256A patent/LU500256B1/en active IP Right Grant
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111868566B (en) | Agricultural machinery operation area measuring and calculating method based on positioning drift measuring and calculating model | |
| CN109813273B (en) | Agricultural machinery repeated operation area judgment method based on spatial analysis | |
| CN106990401B (en) | full-waveform airborne laser radar data-based two-class elevation error correction method | |
| CN107462208A (en) | Agricultural machine and agricultural machine operation area measuring device and measuring method | |
| CN109556529A (en) | A kind of tunnel deformation method for monitoring and analyzing based on Grid Projection points cloud processing technology | |
| CN105303063A (en) | Leaf area index inversion method and system of merged phenological data and remote sensing data | |
| CN109063553A (en) | Field-crop growth defect area's remote sensing fast diagnosis method after a kind of land control | |
| CN206609463U (en) | Monitoring System for Dam Safety based on the Big Dipper | |
| CN103136393A (en) | Area coverage rate calculating method based on mesh division | |
| CN108334476B (en) | Method, device and system for detecting flatness of agricultural machine operation | |
| CN110619649A (en) | Operation area determination method and device and terminal | |
| CN104318089A (en) | Threshold value determining method for local enhanced system completeness monitoring | |
| CN113762090A (en) | Disaster monitoring and early warning method for extra-high voltage intensive power transmission channel | |
| CN109006749B (en) | Row resistance-based field canopy density detection system and calibration method thereof | |
| CN108427741B (en) | DEM relative error evaluation method based on large number of high-precision control points | |
| CN111078953B (en) | Method for directly reconstructing SEGY data coordinates based on navigation file | |
| LU500256B1 (en) | Agricultural Machinery Operation Area Calculation Method Based on Positioning Drift Calculation Model | |
| CN105651311A (en) | Method for measuring satellite navigation autopilot accuracy of agricultural machinery operation | |
| CN117724059A (en) | Multi-source sensor fusion track correction method based on Kalman filtering algorithm | |
| CN110130168A (en) | A kind of railroad track control net triangulated height data correction processing method | |
| CN114184179B (en) | Outdoor geographical survey and drawing management and control system based on internet | |
| CN109446497A (en) | One kind is grown up tunnel traverse survey record and data processing method | |
| CN103837130B (en) | For data processing method and the device of airborne lidar system | |
| CN111340055B (en) | Parking identification method for agricultural machinery vehicle | |
| CN112945078B (en) | Based on MIMO slope deformation monitoring early warning system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FG | Patent granted |
Effective date: 20210803 |