A data-driven power implement and work implement matching method

Abstract

The application discloses a data-driven power machine and working machine matching method, and relates to the field of machine matching. The application is used to solve the problem of large subjectivity and experience of the existing power machine and working machine matching method, which causes inaccurate matching and power waste. The application takes real collaborative working history data as the core, counts the number of collaborative work of the power machine and the working machine in the preset historical time window, eliminates the virtual high phenomenon of the popular machine, corrects the virtual high number of collaborative work, uses the number of collaborative work to assign weights to the matching relationship, and hard filters the matching relationship to obtain the adaptation condition. According to the matching relationship, the weight of the matching relationship, the number of collaborative work and the adaptation condition, a machine matching recommendation table of the grid is generated to realize matching recommendation. The application is mainly used for matching recommendation of the power machine and the working machine for the grid field.

Description

Technical Field

[0001] This invention relates to the field of agricultural implement matching. Background Technology

[0002] With the rapid development of smart agriculture, agricultural big data encompasses an increasing variety and quantity of data, and is becoming more comprehensive. In agricultural operations, the efficient matching of power implements (such as tractors and diesel engines) with work implements (tillage machinery, seeding machinery, and cultivation machinery) is crucial for improving the efficiency of agricultural mechanization and reducing operating costs. Traditional methods for matching power implements with work implements often rely on simple calculations using power data and work implement data such as operating resistance, width, and operating time. This matching is often inaccurate. Other methods depend on operator experience and selection manuals, leading to wasted power. These problems urgently need to be addressed. Summary of the Invention

[0003] To address the issues of inaccurate matching and wasted power in existing methods for matching power tools with work tools, which are largely subjective and experience-based, this invention provides a data-driven method for matching power tools with work tools.

[0004] A data-driven method for matching power tools and work tools, comprising:

[0005] The farmland in the target area is divided into grids, and the operation records of each grid under the preset historical time window are obtained according to the operation trajectory and operation log.

[0006] The power tools and work tools appearing in the work records of each grid are respectively designated as power tool nodes and work tool nodes;

[0007] Based on the matching relationship between power tools and work tools in the work records of each grid, connect the power tool nodes and work tool nodes corresponding to that grid to obtain the matching relationship diagram of that grid;

[0008] The number of collaborative tasks corresponding to each line in the matching graph is counted, and the number of collaborative tasks exceeding the threshold is corrected.

[0009] Based on the number of collaborative operations on each connection in each grid in the matching graph, determine the weight of the matching relationship corresponding to each connection in that grid.

[0010] Based on the efficiency indicators of power tools and work tools in the work records of each grid, determine whether the matching relationship in the matching relationship diagram corresponding to that grid is suitable;

[0011] Based on the matching relationship between each power tool and the work tool corresponding to each grid, as well as the weight of the matching relationship, the number of collaborative operations, and the suitability, a tool matching recommendation table is generated for that grid. The matching relationships in the tool matching recommendation table are sorted from high to low according to the weight of the matching relationship.

[0012] Preferably, the work record for each grid includes the grid number, power tool name, work tool name, matching relationship between power tool and work tool, tool operation time, power tool efficiency index, and work tool efficiency index.

[0013] Preferably, the performance indicators of power tools and the performance indicators of work tools use the same categories of items, including work quality, efficiency, energy consumption, fault conditions, interface compatibility, PTO gear, power conditions, hydraulic flow and traction stability.

[0014] Preferably, the implementation method for correcting the number of collaborative operations exceeding the threshold is as follows:

[0015] The corrected number of collaborative work sessions is ,in, , The compression factor is 1. For the threshold, The first line corresponding to the current connection within the current grid. The power equipment and the first Number of times each working machine can work together and All are integers.

[0016] Preferably, the method for determining the weight of the matching relationship corresponding to each connection in each grid based on the number of collaborative operations on each connection in the matching relationship graph is as follows: for the matching relationship between the same working machine and its corresponding power equipment in the same grid, the weight of each matching relationship is calculated using a normalization method. ;

[0017] The first line corresponding to the current connection within the current grid. The power equipment and the first Number of times each working machine can work together The first line corresponding to the current connection within the current grid. The total number of times a power tool and all working tools work together. and All are integers.

[0018] Preferably, the method for determining whether the matching relationship in the matching relationship graph corresponding to each grid is suitable based on the efficiency indicators of power tools and work tools in the work records of each grid is as follows:

[0019] In the work records of each grid, under the matching relationship between each power tool and the work tool, if the data of all item types in the efficiency indicators of the power tool and the work tool meet the corresponding machine specifications, then the matching relationship is determined to be suitable; otherwise, the matching relationship is determined to be unsuitable.

[0020] The beneficial effects of this invention are:

[0021] This invention constructs a data-driven method for matching power equipment and work equipment by integrating historical operation data. Compared with existing matching methods that rely on manual experience, selection manuals, or simple power conversion, this invention has at least the following technical advantages: First, based on real collaborative operation data of the target area within a preset historical time window, a matching relationship diagram of power equipment and work equipment is established at the grid scale. This ensures that the recommended results are directly derived from historical operation facts in the actual farmland environment, more realistically reflecting the applicability of different equipment combinations in different areas and working conditions, thereby significantly improving matching accuracy. Second, by correcting abnormally high data in the number of collaborative operations, the abnormal amplification effect of "popular equipment" with strong versatility and high usage frequency on the matching results is weakened, making the recommended results more focused on stable and effective real matching relationships, avoiding bias propagation caused by historical usage habits. Third, by improving the quality and efficiency of operations... The invention employs hard-constraint filtering based on indicators such as efficiency, energy consumption, fault conditions, interface compatibility, PTO gear, power, hydraulic flow, and traction stability. This allows for the elimination of combinations with insufficient power, incompatible interfaces, unstable traction, or substandard operational quality before recommendations are made, reducing the risk of idling, high fuel consumption, low efficiency, and abnormal downtime caused by incorrect matching, thus minimizing power waste. Fourth, the generated implement matching recommendation table retains the number of collaborative operations, weights, and compatibility information, providing strong interpretability and facilitating review and retrieval by operators, managers, and scheduling systems. Fifth, the invention primarily utilizes historical data statistics, frequency correction, weight calculation, and rule filtering to complete recommendations, eliminating the need to reorganize large-scale field trials for each candidate combination. Consequently, it features low computational complexity, simple deployment, and rapid integration into existing agricultural machinery scheduling, monitoring, and smart agriculture platforms, ensuring recommendation reliability while reducing trial matching and decision-making costs.

[0022] This invention can automatically generate a recommended list of power equipment and operational machinery for different grids based on existing historical operation data, reducing the reliance on repeated manual comparisons, on-site trial matching, and experience-based judgments in traditional methods. Especially in application scenarios with large target areas, numerous equipment types, and frequent changes in operational tasks, this invention can output recommendation results in a shorter time, balancing computational efficiency and engineering practicality. Furthermore, through a combined mechanism of "historical collaborative operation facts + anomaly correction + adaptability hard filtering," the recommendation results can be used not only for static selection but also for rapid matching decisions before operation scheduling, thereby improving equipment utilization, reducing ineffective power consumption, and enhancing the overall organizational efficiency of agricultural mechanization operations. Attached Figure Description

[0023] Figure 1 This is a schematic diagram illustrating the principle of a data-driven matching method for power tools and work tools as described in this invention.

[0024] Figure 2 It is a schematic diagram of the matching relationship within any grid. Detailed Implementation

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0027] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, but this is not intended to limit the scope of the invention.

[0028] Origin of the Concept: This invention constructs a data-driven method for matching power equipment and operational machinery by integrating historical operational data. It collects existing operational data on power equipment and operational machinery. Specifically, it uses statistical patterns of "which power equipment + operational machinery combinations perform better in real farmland environments" for power equipment and operational machinery selection and matching. Furthermore, it abstracts "power equipment and operational machinery have previously worked together within a specific farmland grid" as an edge (connection) in the matching relationship graph, forming a "node-edge" matching relationship graph containing only two types of nodes (power equipment nodes and operational machinery nodes), with the occurrence of collaboration as the edge, for data-driven power equipment and operational machinery selection and matching. It generates a machinery matching recommendation table for each grid based on historical data, guiding subsequent power equipment and operational machinery matching recommendations for each farmland. The matching results are accurate, free from subjective and experience-based recommendations, and avoid energy waste. The specific implementation method is as follows:

[0029] Specific Implementation Method 1: Combination Figure 1 As shown, this embodiment provides a data-driven method for matching power tools and work tools, including:

[0030] S1. Divide the farmland in the target area into grids, and obtain the operation records of each grid under the preset historical time window based on the operation trajectory and operation log;

[0031] Furthermore, the work record for each grid includes the grid number, power tool name, work tool name, matching relationship between power tool and work tool, tool operation time, power tool efficiency index, and work tool efficiency index.

[0032] Furthermore, the performance indicators for power tools and work tools use the same categories of items, including work quality, efficiency, energy consumption, fault conditions, interface compatibility, PTO gear, power, hydraulic flow, and traction stability.

[0033] S2. The power tools and work tools appearing in the work records of each grid are respectively designated as power tool nodes and work tool nodes;

[0034] Based on the matching relationship between power tools and work tools in the work records of each grid, connect the power tool nodes and work tool nodes corresponding to that grid to obtain the matching relationship diagram of that grid;

[0035] S3. Count the number of collaborative operations corresponding to each line in the matching relationship graph, and correct the number of collaborative operations that exceeds the threshold.

[0036] The purpose of correcting the number of collaborative operations is to eliminate the inflated number of "popular equipment" and correct it to the normal range. This avoids the inflated number of "popular equipment" caused by subjective or empirical matching in historical operations, and provides an accurate data basis for the weight of subsequent matching relationships.

[0037] Furthermore, the implementation method for correcting the number of collaborative tasks exceeding the threshold is as follows: the corrected number of collaborative tasks is... ,in, , The compression factor is 1. For the threshold, The first line corresponding to the current connection within the current grid. The power equipment and the first Number of times each working machine can work together and All are integers.

[0038] The advantages of the above correction method are as follows: First, it keeps the original count unchanged for regular matching relationships that do not exceed the threshold, thus preserving the true information in historical data to the greatest extent. Second, for high-frequency matching relationships that exceed the threshold, it only compresses the excess part instead of directly truncating it, which avoids the weight distortion caused by the long-term high frequency of "popular machinery" and preserves the fact that it does have a high usage frequency. Third, the correction method is simple to calculate, involving only threshold judgment and linear compression, which is easy to implement quickly in edge devices, agricultural machinery management terminals, or cloud scheduling platforms. Fourth, by suppressing abnormally high numbers, the subsequent recommendation results can be more balanced and robust, which is conducive to discovering power machinery-operating machinery combinations that are masked by popular machinery but are actually more suitable in specific grids.

[0039] S4. Based on the number of collaborative operations on each connection within each grid in the matching relationship diagram, determine the weight of the matching relationship corresponding to each connection within that grid. Specifically, for the matching relationship between the same work machine and its corresponding power equipment within the same grid, a normalization method is used to calculate the weight of each matching relationship. , The first line corresponding to the current connection within the current grid. The power equipment and the first Number of times each working machine can work together The first line corresponding to the current connection within the current grid. The total number of times a power tool and all working tools work together. and All are integers.

[0040] The advantages of the above-mentioned weight transformation relationship are as follows: on the one hand, it can transform the number of collaborative operations with different matching relationships into relative weights under a unified dimension, which is convenient for horizontal comparison between different power equipment; on the other hand, the normalized weight sum is 1, and the result is intuitive and clear, which is convenient for direct use in recommendation ranking, system display and manual review; in addition, this weight calculation method can inherit the effect of the aforementioned number correction, so that the weight reflects the true historical degree of collaboration and is not monopolized by a few abnormally high-frequency combinations, thereby improving the stability, interpretability and engineering applicability of the recommendation results.

[0041] S5. Based on the efficiency indicators of power tools and work tools in the work records of each grid, determine whether the matching relationship in the matching relationship diagram corresponding to that grid is suitable; specifically:

[0042] In the work records of each grid, under the matching relationship between each power tool and the work tool, if the data of all item types in the efficiency indicators of the power tool and the work tool meet the corresponding machine specifications, then the matching relationship is determined to be suitable; otherwise, the matching relationship is determined to be unsuitable.

[0043] S6. Based on the matching relationship between each power tool and the working tool corresponding to each grid, as well as the weight of the matching relationship, the number of collaborative operations, and the suitability, generate a tool matching recommendation table for that grid. The matching relationships in the tool matching recommendation table are sorted from high to low according to the weight of the matching relationship.

[0044] This implementation method uses real historical collaborative operation data as its core. Within a preset historical time window, it statistically analyzes the number of collaborative operations between power tools and work tools according to a "grid × time" model, eliminating the inflated number of "popular tools" and correcting any inflated collaborative operation counts. It employs a weighted approach to assign values ​​to the collaborative operation counts based on matching relationships, simplifying deployment and maintenance while eliminating abnormally inflated data. Furthermore, it performs hard filtering on matching relationships (including operation quality, efficiency, energy consumption, fault conditions, interface compatibility, PTO gear, power, hydraulic flow, and traction stability) to avoid incompatible and unsafe combinations from the outset. The generated tool matching recommendation table is highly interpretable, clearly showing historical collaborative operation counts and matching relationship suitability, facilitating on-site verification. It naturally suppresses the bias towards "popular tools," highlighting genuine matching relationships.

[0045] This invention primarily utilizes sparse counting and table lookup, offering linear scalability, low resource consumption, and easy integration with existing scheduling / monitoring systems to provide accurate recommendation results. At the operational and maintenance levels, it can significantly reduce over- and under-allocation, improve job completion rates and quality stability, reduce trial-and-error and downtime, and enhance equipment utilization and decision-making efficiency.

[0046] In practical application, the operation data that occurred in the most recent operation quarter is organized by plot and time, and outputs a power equipment list and an operation equipment list. Two lists are constructed within this time window: a power equipment list and an operation equipment list. If a power equipment and an operation equipment have worked collaboratively in the same grid within this time window, a matching relationship diagram is drawn. The number of collaborations between power equipment nodes and operation equipment nodes in each matching relationship in the relationship diagram represents the connection strength. Through a "removal of popular equipment" correction, to prevent general-purpose equipment from inflating the score, a more appropriate score is obtained. Before the recommendation table is generated, incompatible combinations are filtered out using hard conditions, such as mismatched mounting interfaces or insufficient power. Finally, a recommendation list is generated, and recommended combinations are output according to the weight of the matching relationship from high to low.

[0047] As an example, Figure 2 The diagram provides a matching relationship graph for any grid, showing the matching relationships between power tools and working tools that have been used in the current grid. Figure 2 Displays the set of power tools that have been used in the current grid within the set historical time window. Set of number of working tools ,in, For the first One power tool, , For the first Each working tool , and These represent the total number of working machines and power machines within the current grid;

[0048] As an example, a recommended list of matching relationships between work equipment i4 and different power equipment within a grid is given in Table 1;

[0049] Table 1. Recommended list of matching relationships between work implement i4 and different power implements

[0050]

[0051] Specific Embodiment Two: A data-driven power tool and work tool matching device, comprising a storage device, a processor, and a computer program stored in the storage device and executable on the processor, characterized in that the processor executes the computer program to implement the data-driven power tool and work tool matching method. Specific Embodiment Three: A computer-readable storage device storing a computer program, characterized in that the computer program, when executed, implements the data-driven power tool and work tool matching method. Specific Embodiment Four: A computer program product, comprising a computer program, which, when executed by a processor, implements the data-driven power tool and work tool matching method.

[0052] While the invention has been described herein with reference to specific embodiments, it should be understood that these embodiments are merely examples of the principles and applications of the invention. Therefore, it should be understood that many modifications can be made to the exemplary embodiments, and other arrangements can be designed without departing from the spirit and scope of the invention as defined by the appended claims. It should be understood that different dependent claims and features described herein can be combined in ways different from those described in the original claims. It is also understood that features described in conjunction with individual embodiments can be used in other described embodiments.

Claims

1. A data-driven method for matching power tools and work tools, characterized in that, include: The farmland in the target area is divided into grids, and the operation records of each grid under the preset historical time window are obtained according to the operation trajectory and operation log. The power tools and work tools appearing in the work records of each grid are respectively designated as power tool nodes and work tool nodes; Based on the matching relationship between power tools and work tools in the work records of each grid, connect the power tool nodes and work tool nodes corresponding to that grid to obtain the matching relationship diagram of that grid; The number of collaborative tasks corresponding to each line in the matching graph is counted, and the number of collaborative tasks exceeding the threshold is corrected. Based on the number of collaborative operations on each connection in each grid in the matching graph, determine the weight of the matching relationship corresponding to each connection in that grid. Based on the efficiency indicators of power tools and work tools in the work records of each grid, determine whether the matching relationship in the matching relationship diagram corresponding to that grid is suitable; Based on the matching relationship between each power tool and the work tool corresponding to each grid, as well as the weight of the matching relationship, the number of collaborative operations, and the suitability, a tool matching recommendation table is generated for that grid. The matching relationships in the tool matching recommendation table are sorted from high to low according to the weight of the matching relationship.

2. The data-driven matching method for power tools and work tools according to claim 1, characterized in that, The work record for each grid includes the grid number, power tool name, work tool name, matching relationship between power tool and work tool, tool operation time, power tool efficiency index, and work tool efficiency index.

3. A data-driven method for matching power tools and work tools according to claim 1 or 2, characterized in that, The performance indicators for power tools and the performance indicators for work tools use the same categories of items, including work quality, efficiency, energy consumption, fault conditions, interface compatibility, PTO gear, power, hydraulic flow, and traction stability.

4. The data-driven matching method for power tools and work tools according to claim 1, characterized in that, The implementation method for correcting the number of collaborative tasks exceeding the threshold is as follows: The corrected number of collaborative work sessions is ,in, , The compression factor is 1. For the threshold, The first line corresponding to the current connection within the current grid. The power equipment and the first Number of times each working machine can work together and All are integers.

5. The data-driven matching method for power tools and work tools according to claim 1, characterized in that, The weight of each matching relationship corresponding to each connection in each grid is determined based on the number of collaborative operations on each connection in the matching relationship diagram. The method for determining the weight of each matching relationship is as follows: For the matching relationship between the same working machine and its corresponding power equipment within the same grid, a normalization method is used to calculate the weight of each matching relationship. ; The first line corresponding to the current connection within the current grid. The power equipment and the first Number of times each working machine can work together The first line corresponding to the current connection within the current grid. The total number of times a power tool and all working tools work together. and All are integers.

6. The data-driven matching method for power tools and work tools according to claim 1, characterized in that, The method for determining whether the matching relationship in the matching relationship graph corresponding to each grid is suitable, based on the efficiency indicators of power tools and work tools in the work records of each grid, is as follows: In the work records of each grid, under the matching relationship between each power tool and the work tool, if the data of all item types in the efficiency indicators of the power tool and the work tool meet the corresponding machine specifications, then the matching relationship is determined to be suitable; otherwise, the matching relationship is determined to be unsuitable.

Images