Agricultural machine operation suitability evaluation method and system

Abstract

The present application belongs to the technical field of plot information extraction, and proposes a farmland machine operation suitability evaluation method, comprising: S1, based on remote sensing images and digital elevation models, extracting field block geometric features, road features, field obstacle features and terrain parameters, and calculating field block indexes; S2, calculating multi-dimensional environment correction factors, integrating obstacle influence functions and farmland machine operation efficiency loss, constructing a multi-parameter weighted farmland machine operation suitability evaluation model, and calculating a farmland machine operation suitability index. The present application also correspondingly proposes a farmland machine operation suitability evaluation system. The method of the present application not only reflects the direct influence of field obstacles on farmland machine operation, but also objectively quantifies the efficiency loss in actual operation through path planning, providing a scientific basis for farmland precision reconstruction and intelligent scheduling of agricultural machinery.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of plot information extraction, and particularly relates to a farmland operation suitability evaluation method and system. BACKGROUND

[0002] Agricultural mechanization is the core driving force of modern agricultural production, and its operation efficiency directly affects the grain production capacity, production cost and the level of sustainable development of agriculture. With the accelerated progress of agricultural modernization in China, agricultural equipment is developing towards large-scale and intelligentization, which puts higher requirements on the field operation environment. However, the obstacles such as power facilities, irrigation wells, trees, straw piles widely distributed in farmland, as well as the topographic features such as ridges and ditches seriously restrict the efficient and continuous operation of agricultural machinery. These obstacles not only cause the interruption of agricultural machinery operation path, the increase of turning and avoiding frequency and other non-operation operations, but also cause soil compaction and fuel waste due to repeated detours. Scientific evaluation of agricultural machinery operation suitability is an important basis for realizing intelligent management of agricultural machinery.

[0003] Existing agricultural machinery suitability evaluation systems are mostly based on ideal continuous plots, and do not fully consider the spatial distribution, density, type and avoidance difficulty of obstacles and other multi-dimensional constraint factors, resulting in deviations between theoretical evaluation results and actual operation efficiency.

[0004] A set of evaluation method system for hill and mountain farmland mechanization transformation (Doi:10.13733 / j.jcam.issn.2095-5553.2024.03.035) was developed by a team of Southwest University. The method determines the index weight by integrating AHP hierarchical analysis method and K-means clustering algorithm, selects six key limiting factors such as plot shape index and contiguity, and constructs a three-dimensional evaluation framework of "natural characteristics-land conditions-infrastructure". Based on the ArcGIS platform, the research team developed a comprehensive evaluation process including grid calculation, kernel density analysis, buffer analysis and other spatial analysis techniques, realizing the whole chain analysis from DEM data processing to fuzzy membership conversion.

[0005] A farmland suitability evaluation framework based on machine learning (Doi:10.3389 / fpls.2023.1084886) was proposed by a team of China Agricultural University. The method constructs a comprehensive evaluation system including natural resource endowment, agricultural machinery accessibility, social and economic level and ecological restriction of four dimensions and 15 indexes, objectively determines the weight of each index by introducing random forest model, and evaluates the suitability of farmland for agricultural machinery after land consolidation, providing a new research paradigm and technical path for systematic evaluation of farmland operation conditions in hilly areas.

[0006] The existing agricultural machinery operation suitability evaluation system has obvious shortcomings, and the core problem is that the evaluation model generally fails to fully consider the impact of field obstacles. Current research mainly focuses on traditional factors such as field size, soil properties, road conditions, and terrain parameters, establishing a relatively complete "field-soil-road-terrain" evaluation framework, but ignoring the actual constraints of obstacles such as power facilities, irrigation wells, trees, etc. on the agricultural machinery operation process. Specifically, the existing evaluation method has the following main problems: first, the index system is mostly based on static geographic attributes, without integrating dynamic constraint factors such as obstacle type, distribution density, and spatial configuration, resulting in an inability to accurately reflect the constraints of obstacles on the continuous operation efficiency of agricultural machinery; second, there is a lack of coupling modeling mechanism between the spatial distribution of obstacles and the movement parameters of agricultural machinery (such as turning radius and operation width), making it difficult to quantify the efficiency loss caused by obstacles such as path interruption and increased detour. These defects result in insufficient applicability of the existing evaluation method in complex obstacle-distributed farmland environments, leading to a large deviation between the evaluation results and the actual operation efficiency.

[0007] Therefore, it is urgent to introduce multi-dimensional obstacle influence factors into the existing evaluation system and to build an evaluation model that dynamically interacts with agricultural machinery behavior, in order to establish a more comprehensive and accurate agricultural machinery operation suitability evaluation method. Precise identification and quantification of the spatial characteristics of field obstacles, as well as suitability evaluation under obstacle constraints, have important theoretical and practical significance for improving the economic efficiency and operation precision of agricultural machinery, as well as the scientificity and practicality of the evaluation model. SUMMARY

[0008] The present invention aims to address the problem of the existing agricultural machinery operation suitability evaluation system generally ignoring the impact of field obstacles, and proposes a dynamic evaluation method and system for field-level agricultural machinery operation suitability based on multi-dimensional environmental correction factors and path simulation.

[0009] The method first extracts key indicators such as field geometric features, road boundaries, obstacle spatial distribution, and terrain parameters based on high-resolution remote sensing images, providing a data foundation for subsequent evaluation. Then, multi-dimensional environmental correction factors such as field, road, and terrain are constructed to quantify the constraints of static environment on agricultural machinery operation. On this basis, a dynamic influence function (OEI) that integrates obstacle spatial distribution and agricultural machinery movement parameters is established to accurately represent the degree of interference of obstacles on the operation process. Then, an improved path planning algorithm (GA-TSPCPP) is used to simulate the operation path of agricultural machinery in the field, and the efficiency loss (PD) of agricultural machinery is calculated to objectively evaluate the efficiency loss. Finally, the calculation results of the obstacle influence function and the agricultural machinery operation efficiency loss are integrated to construct an agricultural machinery operation suitability index (CSI) evaluation model, realizing the precise grading evaluation of field agricultural machinery operation suitability, and providing reliable decision support for farmland mechanization and farmland management.

[0010] The application provides a farmland operation suitability evaluation method, comprising the following steps: S1, calculating a field index based on remote sensing images and a digital elevation model, extracting field geometric features, road features and terrain parameters; S2, calculating a multi-dimensional environment correction factor, comprehensively considering an obstacle influence function and an agricultural machinery operation efficiency loss, constructing a multi-parameter weighted agricultural machinery operation suitability evaluation model, and calculating an agricultural machinery operation suitability index.

[0011] The application also provides a farmland operation suitability evaluation system, comprising a computer executable program, and the program can realize the method as described above.

[0012] The application combines the obstacle influence function and the agricultural machinery operation efficiency loss, constructs an operation suitability index (CSI), realizes multi-dimensional dynamic quantitative evaluation of the agricultural machinery operation suitability, reflects the direct influence of field obstacles on the agricultural machinery operation, and objectively quantifies the efficiency loss in actual operation through path planning, so that a scientific basis is provided for farmland precision reconstruction and agricultural machinery intelligent scheduling.

[0013] In order to further enhance the adaptability of the model to complex farmland environment, the application also innovatively introduces a field correction factor, a road correction factor and a terrain correction factor, dynamically integrates multi-dimensional environment parameters such as fields, roads and terrains, and makes up for the shortcomings of traditional evaluation models in the description of environmental heterogeneity. Each correction factor has scene self-adaptive ability, can be flexibly adjusted according to actual farmland conditions, and thus the accuracy and robustness of the evaluation result are greatly improved. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to make the application easier to understand, the application will be described in more detail by referring to the specific embodiments shown in the drawings. These drawings only depict typical embodiments of the application and should not be considered as limiting the scope of protection of the application.

[0015] Figure 1 Flow chart of one embodiment of the method of the application.

[0016] Figure 2 Technical roadmap of the method of the application.

[0017] Figure 3 Schematic diagram of a sample test area.

[0018] Figure 4 Schematic diagram of a wheat field block and its circumscribed rectangle in a sample area.

[0019] Figure 5 Schematic diagram of whether the road in a sample area directly reaches a wheat field block.

[0020] Figure 6Fig. 2 is a schematic diagram of field obstacles of a sample area.

[0021] Figure 7 Fig. 3 is a schematic diagram of elevation of a sample area.

[0022] Figure 8 Fig. 4 shows part of the field path planning results of a sample area.

[0023] Figure 9 Fig. 5 shows the classification results of the agricultural machinery operation suitability index of a sample area. DETAILED DESCRIPTION

[0024] Embodiments of the present application will be described below with reference to the accompanying drawings so that those skilled in the art can better understand the present application and implement it, but the listed embodiments are not intended to limit the present application, and the embodiments described below and the technical features in the embodiments can be combined with each other without conflict, wherein the same components are denoted by the same reference numerals.

[0025] The embodiments of the present application will be described below with reference to the accompanying drawings. Figure 1 and Figure 2 The embodiments shown in the drawings describe the present application.

[0026] S1, based on high-resolution remote sensing images and digital elevation models (DEM), extract field geometric features, road features, field obstacle features and terrain parameters, and calculate related indexes.

[0027] S1.1, for remote sensing images, based on deep learning, image processing and geographic spatial analysis techniques, through block processing, multi-model collaboration and iterative optimization, efficient and accurate farmland field extraction is realized, field indexes are calculated, and basic data is provided for subsequent field feature analysis. The specific calculation method is as follows.

[0028] 1) Calculate the size of the field: calculate the area of the field ( ) in hectares. The area can be calculated by the contour point coordinates of the field boundary.

[0029] 2) Calculate the field shape index ( ): The field shape index is the product of the aspect ratio ( ) and the ratio of the area of the field to the area of its minimum circumscribed rectangle ( ), which is used to quantify the influence of field shape regularity on agricultural machinery operation efficiency.

[0030] (1),

[0031] wherein the aspect ratio is the ratio of the length to the width of the smallest enclosing rectangle of the field. A reasonable aspect ratio is conducive to the agricultural machine covering more land and improving the operation efficiency; the ratio of the area of the field to the area of the smallest enclosing rectangle of the field is used to evaluate the regularity of the shape of the field, and the closer the value is to 1, the more regular the shape is.

[0032] S1.2, obtain the field road information in the remote sensing image, and the connection information of the field and the road.

[0033] In an embodiment, the field road in the remote sensing image is subjected to semantic segmentation and vectorization processing. Then, the road centerline is obtained through a skeleton extraction algorithm, and the average width of each road is calculated in combination with a morphological method; at the same time, the number of roads connected to the field is counted, and a road topology network is constructed; on this basis, it is judged whether the field is connected to the road through spatial analysis, and the width of the widest road in all the connected roads is calculated.

[0034] (2),

[0035] wherein, represents the average width of the road connected to the field, represents the total number of roads connected to the field.

[0036] S1.3, detect and extract the boundary of the field obstacle, and identify the position, number, area and type of the obstacle.

[0037] In an embodiment, the LSR-YOLO model is used to detect and extract the boundary of the field obstacle (such as power poles, line towers, trees and field infrastructure, etc.), and identify the position (spatial distribution feature), number and type of the obstacle. Based on the obstacle extraction result, the number of obstacles ( ) and the number of each type are calculated.

[0038] S1.4, in combination with the DEM and the field extraction result, the slope ( ) and the elevation standard deviation ( ) of each field are calculated through a terrain analysis algorithm.

[0039] (3),

[0040] wherein, is the elevation value of the pixel j, is the average elevation of the field, is the total number of pixels in the field.

[0041] S2, integrate the obstacle influence function ( ) and the loss of agricultural machine operation efficiency ( ​​), a multi-parameter weighted agricultural machinery operation suitability evaluation model is constructed, and an agricultural machinery operation suitability index is calculated. This step specifically includes S2.1-S2.4 sub-steps.

[0042] S2.1, based on the field block geometric features, road features and terrain parameters extracted in step S1, the field block correction factor, the road correction factor and the terrain correction factor are calculated by dynamic weighting algorithm, and a multi-dimensional environment correction factor model is constructed. The calculation formula of each correction factor is determined based on a large amount of experimental data and after multiple iterations and optimization.

[0043] (1) Field block correction factor (F1):

[0044] (4),

[0045] wherein, is the standard shape index, is the field block shape index, is the standard field block area, is the field block area. The value range is 0.4-1.

[0046] (2) Road correction factor (F2):

[0047] (5), wherein,

[0048] is the effective width of the widest road connected to the field block, is the width of the agricultural machinery body. The value range is 0.4-1.

[0049] (3) Terrain correction factor (F3):

[0050] (6), wherein,

[0051] is the standard deviation of the field block elevation, is the average slope of the field block, The value range is 0-1. S2.2, construct a dynamic influence function of obstacles based on multi-parameter fusion (F4).

[0052] Based on the number, area and spatial distribution characteristics of field obstacles extracted in step S1, combined with the multi-dimensional environment correction factor, an obstacle influence function (F4) is constructed.

[0053]

[0054] ​​​​​The function comprehensively considers the coupling relationship of the type weight of field obstacles, the distribution dispersion, and the turning radius of agricultural machinery, and introduces a multi-dimensional environment correction factor including a field correction factor, a road correction factor, and a terrain correction factor, so as to realize dynamic quantitative evaluation of the influence of field obstacles on the operation efficiency of agricultural machinery.

[0055] (7),

[0056] wherein, is the weight coefficient of the first class obstacle, is the number of the first class obstacle, is the field area, is the area occupied by the first class obstacle, is the standard deviation of the obstacle distance, reflecting the dispersion of the spatial distribution, is the turning radius of agricultural machinery, , , are the field correction factor, the road correction factor, and the terrain correction factor, respectively.

[0057] S2.3, based on the field geometric features, road features, and terrain parameters extracted in step S1, calculate the loss of agricultural machinery operation efficiency (E) ).

[0058] In one embodiment, this step uses an improved path planning model (GA-TSPCPP) to simulate the full coverage reciprocating operation route of agricultural machinery in a complex field obstacle environment. The GA-TSPCPP algorithm is an optimization method based on genetic algorithm (GA) for solving the integrated problem of traveling salesman problem (TSP) and coverage path planning (CPP). This algorithm efficiently searches for the global optimal path by simulating natural selection and genetic mechanisms, and can dynamically adjust the driving direction, turning radius, and obstacle avoidance strategy of agricultural machinery during path planning, thereby significantly reducing the length of non-productive paths and improving operation efficiency.

[0059] (1) Calculate the actual operation efficiency: based on the geometric boundaries of the field and obstacles, the field after removing the obstacles is regarded as the effective operation area, the actual obstacle avoidance path (E ) is generated by using the GA-TSPCPP model, and the corresponding number of turns is counted. This path strictly meets the operational restrictions in the actual operation of agricultural machinery while achieving global coverage.

[0060] (2) Calculate the theoretical operation efficiency: under the condition of no obstacles, the theoretical optimal path (E ) and its number of turns are generated based on the geometric features of the field by using the GA-TSPCPP model.

[0061] (3) Quantification of efficiency loss: By comparing the actual operating efficiency ( ) and theoretical operating efficiency under unobstructed conditions ( ), calculate the efficiency loss of agricultural machinery operation ( This allows for the dynamic quantification of the impact of field obstacles on agricultural machinery operation efficiency.

[0062] (8),

[0063] (9),

[0064] (10)

[0065] in, The length of the obstacle avoidance path for agricultural machinery. This represents the theoretically optimal path length for agricultural machinery. To improve the speed of agricultural machinery operations, This refers to the actual number of turns made by the agricultural machinery. The theoretical number of turns for agricultural machinery. This refers to the time it takes for the agricultural machinery to make a single turn. The effective operating area of ​​the field. This refers to the area of ​​the field.

[0066] S2.4: Based on the results of steps S2.2 and S2.3, construct the agricultural machinery operation suitability index ( We conducted a multi-dimensional quantitative analysis of the suitability of agricultural machinery operations.

[0067] (11),

[0068] in, , Weighting coefficients ( + =1), which can be dynamically adjusted according to different types of agricultural machinery (such as harvesters / seeders). This index quantifies the suitability of a field for cultivation using a percentage system; the lower the value, the more significant the constraint effect of obstacles.

[0069] S3: Based on the agricultural machinery operation suitability index obtained from S2, the fields are classified into grades to intuitively reflect the suitability of agricultural machinery operations for each field. The specific classification criteria are as follows:

[0070] 1) Suitable ( >85): Excellent field working conditions, with few and reasonably distributed obstacles, suitable for efficient agricultural machinery operation;

[0071] 2) Generally suitable (75 < ≤ 85): the field operation condition is good, there are a small amount of field obstacles, which have certain influence on agricultural machinery operation, but the overall is still suitable for agricultural machinery operation;

[0072] 3) generally unsuitable (60 < S < 75): the field operation condition is general, the number of obstacles is more or the distribution is unreasonable, which has obviously affected the efficiency of agricultural machinery operation, it is suggested to improve the operation condition through path optimization or local reconstruction; ≤ 75): the field operation condition is general, the number of obstacles is more or the distribution is unreasonable, which has obviously affected the efficiency of agricultural machinery operation, it is suggested to improve the operation condition through path optimization or local reconstruction;

[0073] 4) unsuitable (S ≤ 60): the field operation condition is poor, the obstacles are dense or the distribution is seriously unreasonable, which is not suitable for direct agricultural machinery operation, and the farmland comprehensive improvement should be implemented preferentially. ≤ 60): the field operation condition is poor, the obstacles are dense or the distribution is seriously unreasonable, which is not suitable for direct agricultural machinery operation, and the farmland comprehensive improvement should be implemented preferentially.

[0074] The classification system provides scientific and quantitative decision basis for agricultural machinery operation scheduling, path planning and farmland reconstruction.

[0075] The application also provides a kind of agricultural machinery operation suitability evaluation system, including computer executable program, the program can realize the method as described above.

[0076] The application will be further described in detail through specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application. In addition, the technical features involved in each embodiment of the application described below can be combined with each other as long as they do not conflict with each other.

[0077] (1) A certain winter wheat planting area is taken as an experimental area (as shown in FIG. 1), the area is 267.64 hectares, the farmland is distributed with field obstacles such as power facilities, trees, irrigation well house, the field block shape is irregular, the road network is complex, and the efficiency of agricultural machinery operation is significantly affected by the field obstacles, which is typical and representative. The terrain of the experimental area is mainly plain, and there is local micro-terrain fluctuation. A Lvyu Gu Shen GE80 agricultural machine is selected for the experiment, the machine body width is 3.08 m, and the minimum turning radius is 5.8 m. Figure 3 (2) Based on the spatial resolution of 0.3 meters of the remote sensing image obtained based on the Google Earth platform, combined with the DEM (ALOS PALSAR DEM) with a spatial resolution of 12.5 meters as the basic data, the field block boundary, road boundary, field obstacle boundary and terrain information (as shown in FIG. 2) are extracted, and the specific steps are as follows:

[0078] Figures 4-7 1) The field block boundary is extracted, the field block area (as shown in FIG. 3) and the minimum circumscribed rectangle (as shown in FIG. 4) are calculated through the contour point coordinates, and the field block shape index (as shown in FIG. 5) is further calculated.

[0079] 1) The field block boundary is extracted, the field block area (as shown in FIG. 3) and the minimum circumscribed rectangle (as shown in FIG. 4) are calculated through the contour point coordinates, and the field block shape index (as shown in FIG. 5) is further calculated. Figure 3 1) The field block boundary is extracted, the field block area (as shown in FIG. 3) and the minimum circumscribed rectangle (as shown in FIG. 4) are calculated through the contour point coordinates, and the field block shape index (as shown in FIG. 5) is further calculated. ​​The specific calculation is shown in formula (1) above.

[0080] 2) Based on the road vector file, determine whether each field is connected to a road to assess the accessibility of the field (e.g., Figure 5 (As shown). Then, the centerline of the road was extracted to calculate the average width of each road. In the experimental area, some fields were not connected to roads, or the roads were not wide enough (<3.08 meters), resulting in poor accessibility and making it impossible for agricultural machinery to pass.

[0081] 3) Detection of field obstacles based on remote sensing images (such as...) Figure 6 As shown in the figure, identify and count the types, quantities, and area occupied by obstacles such as utility poles, towers, trees, and irrigation wells.

[0082] 4) Calculate the standard deviation of field slope and elevation based on DEM data (e.g., Figure 7 (As shown).

[0083] (3) Based on the extracted field, road, and terrain data, according to formula (4), the standard field area ( =2.0 hectares) and standard shape index ( Using 4.0 as the baseline, the field correction factor for each field is calculated.

[0084] According to formula (5), the width of the agricultural machinery body ( Using 3.08 meters as a benchmark, the road correction factor is calculated in conjunction with the road width.

[0085] According to formula (6), the terrain correction factor is calculated by combining the slope and elevation standard deviation.

[0086] (4) Based on the extracted obstacle data, taking into account the number, area, spatial distribution dispersion, turning radius of agricultural machinery, and correction factor of obstacles in each field, the obstacle impact index of each field is calculated using formula (7). ).

[0087] During the calculation process, differentiated weighting coefficients were set for the main obstacle types in the experimental area based on expert experience: power facilities (including power line towers) =0.85, utility pole =0.50), irrigation well house ( =0.70) and trees ( =0.40), these weighting coefficients fully consider the spatial occupancy characteristics of different field obstacles and the difficulty of agricultural machinery avoiding them in the experimental area.

[0088] (5) The improved GA-TSPCPP model was used to simulate the agricultural machinery operation path. The deviation rate between the actual operation efficiency and the theoretical operation efficiency under unobstructed conditions was calculated according to formulas (8)-(10). The agricultural machinery operation paths for some fields are as follows: Figure 8 As shown.

[0089] (6) and Substituting the calculation results into formula (11), the agricultural machinery operation suitability index for each field is generated. ).

[0090] The results of the calculation of the suitability index for agricultural machinery operation in some fields are shown in Table 1.

[0091] Table 1 shows the calculation results of the suitability index for agricultural machinery operations in some fields.

[0092]

[0093] (7) According to The grading criteria were used to classify the experimental field plots, and the results are as follows: Figure 9 As shown.

[0094] The embodiments described above are merely preferred embodiments of the present invention. The terms "in one embodiment," "in another embodiment," "in yet another embodiment," or "in still another embodiment" used in this specification all refer to one or more of the same or different embodiments according to this disclosure. Ordinary variations and substitutions made by those skilled in the art within the scope of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for evaluating suitability of agricultural work, characterized by, Comprising: S1, based on remote sensing images and digital elevation models, extracting field block geometric features, road features, field obstacle features and terrain parameters, and calculating field block indicators, including: S1.1, extracting the field block boundary in the remote sensing image, and calculating the field block indicators, the field block indicators including: field block area and field block shape index; S1.2, obtaining the field road information in the remote sensing image, and the connection information of the field block and the road; S1.3, detecting and extracting the boundary of the field obstacle, and identifying the position, number, area and type of the obstacle; S1.4, combining the digital elevation model and the field block extraction result, calculating the slope and elevation standard deviation of each field block through terrain analysis algorithm; S2, calculating multi-dimensional environmental correction factors, integrating obstacle influence function and agricultural machinery operation efficiency loss, constructing a multi-parameter weighted agricultural machinery operation suitability evaluation model, and calculating the agricultural machinery operation suitability index, including: S2.1, based on the field block geometric features, road features and terrain parameters extracted in step S1, calculating the field block correction factor, the road correction factor and the terrain correction factor through a dynamic weighting algorithm, and constructing a multi-dimensional environmental correction factor model; S2.2, based on the position, number, area and type of the field obstacle extracted in step S1, combining the multi-dimensional environmental correction factor, and constructing a multi-parameter fusion-based obstacle dynamic influence function; S2.3, based on the field block geometric features and the field obstacle boundary extracted in step S1, calculating the agricultural machinery operation efficiency loss; S2.4, based on the results of steps S2.2 and S2.3, constructing the agricultural machinery operation suitability index; Wherein, step S2.3 includes: 1) calculating the actual operation efficiency: based on the geometric boundary of the field block and the obstacle, taking the field block after removing the obstacle as the effective operation area, generating the actual obstacle avoidance path, and counting the corresponding turning number; 2) calculating the theoretical operation efficiency: under the condition of no obstacle, generating the theoretical optimal path and its turning number based on the field block geometric features; 3) efficiency loss quantification: by comparing the actual operation efficiency with the theoretical operation efficiency under the condition of no obstacle, calculating the agricultural machinery operation efficiency loss; Step S3: Based on the agricultural machinery operation suitability index obtained in S2, the field is evaluated and classified according to The field is evaluated and classified according to the classification criteria.

2. The farm work suitability evaluation method according to claim 1, characterized by, In step S2.1, the field correction factor is calculated by the following equation : ， wherein, is a standard shape index, is a field shape index, is a standard field area, is a field area, has a value in the range of 0.4-1; The road correction factor is calculated by the following equation : ， wherein, is the effective width of the widest road connecting the field, is the width of the body of the agricultural machine, has a value in the range 0.4-1; The terrain correction factor is calculated by the following equation : ， wherein, is the standard deviation of the elevation of the field, is the average slope of the field, has a value in the range 0-1.

3. The farm work suitability evaluation method according to claim 2, characterized by, In step S2.2, the obstacle dynamic influence function is constructed by the following equation : ， wherein, is the weight coefficient of the th type of obstacle, is the number of the th type of obstacle, is the area of the field, is the area of the th type of obstacle, is the standard deviation of the distance between obstacles, reflecting the dispersion of spatial distribution, is the turning radius of the agricultural machine, , , are the field correction factor, the road correction factor and the terrain correction factor, respectively.

4. The farm work suitability evaluation method according to claim 3, characterized by, In step S2.3, the actual work efficiency is calculated by the following equation theoretical work efficiency under no obstacle condition loss of work efficiency of agricultural machine : ， ， ， wherein, is the length of the optimal path for the agricultural machine to avoid obstacles, is the length of the optimal path for the agricultural machine to travel in theory, is the working speed of the agricultural machine, is the actual number of turns of the agricultural machine, is the theoretical number of turns of the agricultural machine, is the time for a single turn of the agricultural machine, is the effective working area of the field, is the area of the field.

5. The farm work suitability evaluation method according to claim 4, characterized by, In step S2.4, the agricultural machine work suitability index is calculated by the following equation : ， wherein , is a weight coefficient, + = 1.​ 6. A suitability evaluation system for agricultural machinery operations, characterized in that, Computer executable program, the program can realize the method as claimed in any one of the preceding claims 1-5. Computer executable program, the program can realize the method as claimed in any one of the preceding claims 1-5.

Images