Agricultural machinery operation technical index evaluation method based on multi-source data fusion

Abstract

The invention relates to the technical field of agricultural technical index evaluation, in particular to an agricultural machinery operation technical index evaluation method based on multi-source data fusion, which innovatively constructs two characteristics with clear engineering physical significance, namely roller specific torque and cleaning specific power consumption, and further fuses the two characteristics into cleaning load factors. And the margin of distance cleaning overload of the current operation system is dynamically quantified. Three working conditions of margin sufficiency, critical balance and overload risk identified based on cleaning load factors respectively represent different environment operation difficulties. According to the method, the scoring caliber is successfully converted from direct statistical weighting of speed, loss and oil consumption into evaluation according to working conditions under explainable working condition constraints, so that interference of strong coupling among the operation speed, the loss rate and the oil consumption on an evaluation result is weakened, and fairness, stability and explainability of technical index evaluation are improved.

Description

Technical Field

[0001] This invention relates to the field of agricultural technical indicator evaluation technology, and in particular to a method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion. Background Technology

[0002] With the rapid development of precision agriculture and intelligent agricultural machinery, the need for refined management and quantitative performance evaluation of agricultural machinery operations is becoming increasingly urgent. The evaluation of agricultural machinery operation technical indicators is of great significance for optimizing agricultural machinery scheduling, improving operational efficiency, reducing operating costs, and implementing scientific operator assessments. Currently, acquiring agricultural machinery operation data is relatively convenient, mainly through vehicle-mounted BeiDou / GNSS positioning systems and various operation quality sensors (such as grain loss sensors and yield / flow sensors).

[0003] Existing technologies typically employ evaluation methods based on single-dimensional statistical indicators. These methods involve independently calculating macroscopic statistics such as total operating area, total fuel consumption, average speed, and average loss rate, and then making simple comparisons or comparisons with historical averages. Alternatively, they may use operation guidance and evaluation methods based on fixed thresholds. These methods set recommended operating speed ranges or maximum loss rate alarm thresholds for different crops based on experience. When real-time data exceeds the threshold, a prompt is issued, and this is used as the basis for evaluation.

[0004] The above method completely ignores the strong physical coupling relationship between operating efficiency (speed), fuel consumption (fuel consumption), and operating quality (loss rate). For example, high operating speed may lead to a high loss rate, while simply pursuing a low loss rate may force the operator to reduce speed and sacrifice efficiency. This evaluation method cannot distinguish whether the quality of the operation evaluation result is due to improper operation by the operator or due to the environmental difficulty of the field itself (such as differences in crop density and humidity), resulting in distorted evaluation results. It fails to analyze and quantify the chain coupling relationship of operating speed-feeding resistance-cleaning energy consumption-grain loss from the physical essence of agricultural machinery operation, and thus cannot effectively separate objective environmental factors from the operator's subjective operation, resulting in distorted comprehensive operation technical indicator evaluation results.

[0005] Therefore, there is an urgent need to propose an evaluation method for agricultural machinery operation technical indicators based on multi-source data fusion. Summary of the Invention

[0006] The main objective of this invention is to provide an evaluation method for agricultural machinery operation technical indicators based on multi-source data fusion. It innovatively constructs two features with clear engineering and physical significance: drum specific torque and cleaning specific power consumption, and further integrates them into a cleaning load factor, dynamically quantifying the margin of the current operating system from cleaning overload. Based on the cleaning load factor, three operating conditions are identified: sufficient margin, critical balance, and overload risk, each representing different environmental operating difficulties. Efficiency is evaluated only under the most challenging critical balance condition, and quality is assessed by comparing the actual loss rate with the expected loss rate based on the current cleaning load factor. This successfully transforms the scoring caliber from directly statistically weighting speed, loss, and fuel consumption to evaluating under interpretable operating condition constraints, thereby reducing the interference of the strong coupling between operating speed, loss rate, and fuel consumption on the evaluation results and improving the stability and interpretability of the operation evaluation results.

[0007] The technical solution of the present invention is as follows: A method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion is proposed. This method includes the following steps: S1. Construct a time-series dataset, which includes the agricultural machinery operating speed, engine output power, engine speed, instantaneous fuel consumption rate, threshing drum torque, number of loss pulses, and grain yield flow rate at each moment within a preset collection period, and obtain the grain loss rate. S2. Based on the agricultural machinery operating speed and threshing drum torque, the drum specific torque is calculated to characterize the feeding resistance per unit speed. An empirical model based on energy distribution is used to obtain the power consumption of the cleaning system, and then the cleaning specific power consumption is obtained to characterize the power consumption of the cleaning system per unit grain yield. S3. Based on the drum torque ratio, a linear model is constructed to calculate the critical cleaning ratio power consumption. The cleaning load factor is further calculated. Based on the value of the cleaning load factor, the agricultural machinery operation status at each moment within the preset collection period is divided into working condition categories and the working condition category identifier is output. Specifically, these include sufficient margin working condition, critical balance working condition, and overload risk working condition. S4. Based on the cleaning load factor and working condition category identifier, calculate the efficiency score, quality score and fuel consumption score respectively, and then obtain the comprehensive operating performance score.

[0008] A further improvement of this invention is that the grain loss rate in S1 is calculated based on the calibration coefficient of the grain loss sensor, and the calculation formula is as follows: ; in, for Grain loss rate at any given time This refers to the calibration coefficients of the grain loss sensor, in units of... / pulse, for The number of lost pulses at each moment, for Grain yield flow rate at any given time, in units of To prevent division by zero, the constant is set to a value of , where i is the time index.

[0009] A further improvement of the present invention is that step S2 includes the following specific steps: S21. Based on the agricultural machinery's operating speed and the threshing drum torque, calculate the drum specific torque, which characterizes the feeding resistance per unit speed. The calculation formula is as follows: ; in, for The roller torque at any given moment for The torque of the threshing drum at any given time, in units of for The speed of agricultural machinery operation at any given moment, in units of To prevent division by zero, the constant is set to a value of ; S22. The power consumption of the cleaning system is calculated using an empirical model based on energy allocation. The calculation formula is as follows: ; in, for Engine output power at any given time, in kW. The ratio of engine power allocated to the cleaning system. The power coefficient of the walking system, in units of The power coefficient of the threshing system. The value represents the rotational speed of the threshing drum, in rpm. 9549 is a power conversion factor. for The power consumption of the cleaning system at any given time, in kW; S23. Further calculate the power consumption of the cleaning system, which characterizes the unit grain yield, using the following formula: ;in, for Cleaning power consumption at any given time, in units of .

[0010] A further improvement of the present invention is that step S3 includes the following specific steps: S31. Based on the drum specific torque, a linear model is constructed to calculate the critical cleaning ratio power consumption. The linear model expression is as follows: ; in, Basic cleaning ratio power consumption, in units of The load sensitivity coefficient is used for cleaning, and the unit is... for Critical cleaning ratio power consumption at time , in units of ; S32. Further calculate the cleaning load factor, the calculation method is as follows: ; in, for The cleaning load factor at any given time is used to classify the agricultural machinery operation status at each moment within the preset collection period into different working condition categories based on the value of the cleaning load factor. At that time, mark The time is always under conditions of sufficient margin. ;when At that time, mark The time is the critical equilibrium condition. ;when At that time, mark This is a constant state of overload risk. for The operating condition category identifier at any given time.

[0011] A further improvement of the present invention is that the calculation of the efficiency score in S4 includes the following specific steps: S411. Calculate the area-weighted average velocity under the critical equilibrium condition. The calculation formula is as follows: ; in, For the working width, This refers to the data collection time interval; S412, Computational Efficiency Score This represents the theoretically optimal operating speed.

[0012] A further improvement of the present invention is that the calculation of the quality score in S4 includes the following specific steps: S421, targeting At any given time, calculate the loss control deviation. ;in, express Expected grain loss rate under the current cleaning load factor value express Loss control deviation at any given moment; S422. Calculate the area-weighted average deviation for all times within the preset acquisition period. The formula is: ; Calculate quality score This is the scaling parameter.

[0013] A further improvement of the present invention is that the calculation of the fuel consumption score in S4 includes the following specific steps: S431, targeting At any time, extract engine output power and engine speed This leads to the engine output torque. ; S432, targeting Calculate the instantaneous fuel efficiency coefficient at each time point. ;in, for Instantaneous fuel consumption rate at any given moment This represents the theoretical minimum fuel consumption rate under current operating conditions. S433. Calculate the area-weighted average efficiency coefficient for all times within the preset acquisition period. The formula is: This leads to a fuel consumption score. .

[0014] A further improvement of this invention is that the formula for calculating the comprehensive operational performance score in S4 is as follows: ; in, To calculate the overall performance score, As a weighting factor for efficiency scoring, As a weighting factor for quality scoring, As a weighting factor for fuel consumption rating, .

[0015] The technical effects of this invention are as follows: A method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion was constructed. This method innovatively establishes two features with clear engineering and physical significance: drum specific torque and cleaning specific power consumption, and further integrates them into a cleaning load factor, dynamically quantifying the margin of the current operating system from cleaning overload. Based on the cleaning load factor, three operating conditions—sufficient margin, critical balance, and overload risk—are identified, each representing different environmental operational difficulties. Efficiency is evaluated only under the most challenging critical balance condition, and quality is assessed by comparing the actual loss rate with the expected loss rate based on the current cleaning load factor. This successfully transforms the scoring caliber from directly statistically weighting speed, loss, and fuel consumption to evaluating under interpretable operating condition constraints, thereby reducing the interference of the strong coupling between operating speed, loss rate, and fuel consumption on the evaluation results and improving the stability and interpretability of the operation evaluation results. Attached Figure Description

[0016] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart illustrating the evaluation method for agricultural machinery operation technical indicators based on multi-source data fusion according to Embodiment 1 of the present invention. Detailed Implementation

[0017] Example 1: This example proposes an evaluation method for agricultural machinery operation technical indicators based on multi-source data fusion. It innovatively constructs two features with clear engineering physical significance: drum specific torque and cleaning specific power consumption, and further integrates them into a cleaning load factor, dynamically quantifying the margin of the current operating system from cleaning overload. Based on the cleaning load factor, three operating conditions are identified: sufficient margin, critical balance, and overload risk, each representing different environmental operating difficulties. Efficiency is evaluated only under the most challenging critical balance condition, and quality is assessed by comparing the actual loss rate with the expected loss rate based on the current cleaning load factor. This successfully transforms the scoring caliber from directly statistically weighting speed, loss, and fuel consumption to evaluating under interpretable operating condition constraints, thereby reducing the interference of the strong coupling between operating speed, loss rate, and fuel consumption on the evaluation results and improving the stability and interpretability of the operation evaluation results. Specifically, as shown... Figure 1 As shown, the evaluation method for agricultural machinery operation technical indicators based on multi-source data fusion proposed in this embodiment includes the following specific steps: S1. Construct a time-series dataset, which includes the agricultural machinery operating speed, engine output power, engine speed, instantaneous fuel consumption rate, threshing drum torque, loss pulse number, and grain yield flow rate at each moment within a preset collection period, and obtain the grain loss rate.

[0018] In this embodiment, the grain loss rate in S1 is calculated based on the calibration coefficient of the grain loss sensor, and the calculation formula is as follows: ; in, for Grain loss rate at any given time This refers to the calibration coefficients of the grain loss sensor, in units of... / pulse, for The number of lost pulses at each moment, for Grain yield flow rate at any given time, in units of To prevent division by zero, the constant is set to a value of , where i is the time index.

[0019] In this embodiment, the calculation of the grain loss rate is derived from the core logic that loss rate = mass lost per unit time / total output mass per unit time. To avoid the calculation failing due to the total output mass per unit time being zero, a very small constant needs to be introduced. The calibration coefficients for the grain loss sensor are obtained through a standard weight calibration experiment. Specifically, corn grain samples with different weight gradients are selected, and each sample passes through the sensor's detection area. The number of pulses corresponding to each sample is recorded, and a linear regression method is used to fit the data to obtain the grain mass corresponding to each pulse. The unit is 1 / 2 wt%. / pulse.

[0020] S2. Based on the agricultural machinery's operating speed and the threshing drum torque, the drum specific torque is calculated to characterize the feeding resistance per unit speed. An empirical model based on energy distribution is used to obtain the power consumption of the cleaning system, and then the cleaning specific power consumption is obtained to characterize the power consumption of the cleaning system per unit grain yield.

[0021] In this embodiment, S2 includes the following specific steps: S21. Based on the agricultural machinery's operating speed and the threshing drum torque, calculate the drum specific torque, which characterizes the feeding resistance per unit speed. The calculation formula is as follows: ; in, for The roller torque at any given moment for The torque of the threshing drum at any given time, in units of for The speed of agricultural machinery operation at any given moment, in units of To prevent division by zero, the constant is set to a value of ; S22. The power consumption of the cleaning system is calculated using an empirical model based on energy allocation. The calculation formula is as follows: ; in, for Engine output power at any given time, in kW. The ratio of engine power allocated to the cleaning system. The power coefficient of the walking system, in units of The power coefficient of the threshing system. The value represents the rotational speed of the threshing drum, in rpm. 9549 is a power conversion factor. for The power consumption of the cleaning system at any given time, in kW; S23. Further calculate the power consumption of the cleaning system, which characterizes the unit grain yield, using the following formula: ;in, for Cleaning power consumption at any given time, in units of .

[0022] In this embodiment, the drum torque ratio is used to reflect the feeding resistance characteristics, and the cleaning power consumption ratio is used to reflect the energy efficiency of the cleaning system, laying the foundation for subsequent load assessment. The derivation logic for calculating the drum torque ratio in step S21 is that the feeding resistance is positively correlated with the threshing drum torque. However, the faster the agricultural machinery travels, the greater the feeding amount per unit time, and the less accurate the characterization of the feeding resistance under the same torque becomes. Therefore, it is necessary to eliminate the interference of speed on the characterization of feeding resistance by using the ratio of torque to speed, while introducing a minimal constant. To avoid the calculation failing due to zero speed.

[0023] In this embodiment, the design of step S22, which calculates the power consumption of the cleaning system, is based on the distribution characteristics of the engine's output power. The power generated by the engine is mainly distributed to the cleaning system, the traveling system, and the threshing system. Therefore, the power consumption of the cleaning system can be obtained by subtracting the power consumption of the traveling system and the threshing system from the total output power of the engine. Based on this, an empirical model based on energy distribution is derived. The power distribution ratio of the engine to the cleaning system is determined by measuring the engine output power and the actual power consumed by the cleaning system under no-load and full-load cleaning conditions in bench tests. The power distribution ratio is obtained by linear fitting, and the preferred value range is 0.15-0.25. The power coefficient of the walking system, in units of The calibration method involves allowing the agricultural machinery to travel at different speeds under no-load conditions, measuring the power consumption of the travel system at each speed, fitting a linear relationship between power and speed, and the slope of the relationship is the calibration result. The power coefficient of the threshing system is calibrated by measuring the power consumption at different drum speeds under no-load operation of the threshing system, establishing a relationship model between power, torque, and speed, and fitting the model to obtain the power coefficient. .

[0024] In this embodiment, the derivation logic for calculating the cleaning power consumption ratio in step S23 is that the energy efficiency of the cleaning system needs to be evaluated in conjunction with the output. Only the cleaning energy consumption per unit grain yield can accurately reflect the working efficiency of the cleaning system. Therefore, the ratio of the power consumed by the cleaning system to the grain yield flow rate is used for calculation, while also introducing... To avoid calculation failure due to zero output flow rate.

[0025] S3. Based on the drum specific torque, construct a linear model to calculate the critical cleaning specific power consumption, further calculate the cleaning load factor, and classify the agricultural machinery operation status at each moment within the preset collection period into working condition categories and output the working condition category identifier according to the value of the cleaning load factor. Specifically, these include working condition with sufficient margin, critical balance working condition, and overload risk working condition.

[0026] In this embodiment, S3 includes the following specific steps: S31. Based on the drum specific torque, a linear model is constructed to calculate the critical cleaning ratio power consumption. The linear model expression is as follows: ; in, Basic cleaning ratio power consumption, in units of The load sensitivity coefficient is used for cleaning, and the unit is... for Critical cleaning ratio power consumption at time , in units of ; S32. Further calculate the cleaning load factor, the calculation method is as follows: ; in, for The cleaning load factor at any given time is used to classify the agricultural machinery operation status at each moment within the preset collection period into different working condition categories based on the value of the cleaning load factor. At that time, mark The time is always under conditions of sufficient margin. ;when At that time, mark The time is the critical equilibrium condition. ;when At that time, mark This is a constant state of overload risk. for The operating condition category identifier at any given time.

[0027] In this embodiment, the critical cleaning ratio power consumption and cleaning load factor are calculated, and the working conditions are classified. The design principle is that the load state of the cleaning system directly determines the balance between work quality and efficiency. By constructing a critical cleaning ratio power consumption as a load threshold and combining it with the actual cleaning ratio power consumption to calculate the load factor, the margin of the cleaning system from overload can be quantified, thereby classifying different working conditions and providing a basis for decoupling subsequent work performance scoring. The derivation logic of step S31, which constructs a linear model to calculate the critical cleaning ratio power consumption, is that the critical load capacity of the cleaning system is positively correlated with the feeding resistance, and the drum torque has accurately represented the feeding resistance. Therefore, the critical cleaning ratio power consumption and the drum torque are linearly related, thus a linear model is constructed. Basic cleaning ratio power consumption, in units of The energy consumption per unit grain yield of the cleaning system when there is no feeding resistance is characterized. The calibration method is to allow the agricultural machinery to operate at a very low feeding rate (approximately no feeding resistance) in a standard test field, measure the cleaning power and yield flow rate at different times, and calculate the average value of the basic cleaning power consumption. The load sensitivity coefficient is used for cleaning, and the unit is... The method of calibration is to characterize the influence of feeding resistance on critical cleaning ratio power consumption. In a standard test field, the agricultural machinery is controlled to operate at different speeds to obtain the cleaning ratio power consumption and the corresponding grain loss rate under different drum torques. The critical point where the loss rate begins to rise nonlinearly (i.e., critical cleaning ratio power consumption) is found. The critical point data is linearly fitted with the corresponding drum torque to obtain the value of k.

[0028] In this embodiment, the derivation logic of step S32 for calculating the cleaning load factor is that the ratio of the actual cleaning power consumption to the critical cleaning power consumption can intuitively reflect the degree of the actual load of the cleaning system relative to the critical state. A ratio less than 1 indicates that the load has not reached the critical state, and a ratio greater than 1 indicates that the load exceeds the critical state. The division of working conditions is based on the influence law of the cleaning load factor on the work quality. The thresholds of 0.85 and 1.05 are determined through statistical analysis of experimental data to ensure that the division of working conditions can accurately reflect the correspondence between work quality and load.

[0029] S4. Based on the cleaning load factor and working condition category identifier, calculate the efficiency score, quality score and fuel economy score respectively, and then obtain the comprehensive operating performance score.

[0030] In this embodiment, the calculation of the efficiency score in S4 includes the following specific steps: S411. Calculate the area-weighted average velocity under the critical equilibrium condition. The calculation formula is as follows: ; in, For the working width, This refers to the data collection time interval; S412, Computational Efficiency Score This represents the theoretically optimal operating speed.

[0031] In this embodiment, the calculation of the quality score in S4 includes the following specific steps: S421, targeting At any given time, calculate the loss control deviation. ;in, express Expected grain loss rate under the current cleaning load factor value express Loss control deviation at any given moment; S422. Calculate the area-weighted average deviation for all times within the preset acquisition period. The formula is: ; Calculate quality score This is the scaling parameter.

[0032] In this embodiment, the calculation of the fuel consumption score in S4 includes the following specific steps: S431, targeting At any time, extract engine output power and engine speed This leads to the engine output torque. ; S432, targeting Calculate the instantaneous fuel efficiency coefficient at each time point. ;in, for Instantaneous fuel consumption rate at any given moment This represents the theoretical minimum fuel consumption rate under current operating conditions. S433. Calculate the area-weighted average efficiency coefficient for all times within the preset acquisition period. The formula is: This leads to a fuel consumption score. .

[0033] In this embodiment, the formula for calculating the overall job performance score in S4 is as follows: ; in, To calculate the overall performance score, As a weighting factor for efficiency scoring, As a weighting factor for quality scoring, As a weighting factor for fuel consumption rating, .

[0034] In this embodiment, step S4 calculates various scores and a comprehensive operational performance score based on the cleaning load factor and working condition category identifier. The design logic is that traditional technical indicator evaluations couple the objective environmental load difficulty with the operator's subjective operational level, leading to distorted evaluation results. Therefore, by separating the influence of different load environments through working condition category identifiers and quantifying the environmental difficulty by combining the cleaning load factor, a fair assessment of the operator's operational level is achieved. Simultaneously, a scoring system is constructed from three core dimensions: efficiency, quality, and fuel consumption, comprehensively reflecting operational performance. The design idea for calculating the efficiency score in step S41 is that the cleaning system load is moderate under critical equilibrium working conditions, ensuring both operational quality and fully utilizing the operational efficiency of the agricultural machinery. The operating speed at this point best reflects the operator's true operational efficiency; therefore, it is selected... The efficiency score for calculating critical equilibrium condition data.

[0035] In this embodiment, step S411 calculates the area-weighted average speed under critical equilibrium conditions. The derivation logic is that the contribution of the working area to overall efficiency differs at different times; the larger the working area, the more significant the impact of the corresponding speed on overall efficiency. Therefore, a weighted average is performed using the working area as the weight. The working area is calculated from the working width (in meters), the working speed (in meters per second), and the data collection time interval (in seconds). In step S412, the theoretically optimal working speed is obtained by calibrating the technical parameters provided by the agricultural machinery manufacturer in conjunction with agronomic requirements.

[0036] In this embodiment, the design idea behind step S42, which calculates the quality score, is that the core of operational quality is grain loss rate control, and the loss rate is significantly affected by the cleaning load factor. Therefore, the impact of environmental load difficulty is eliminated by calculating the loss control deviation. A positive deviation indicates that the actual loss rate is lower than expected, and the operator's operation is better than the benchmark. A negative deviation indicates that the operation is worse than the benchmark. The overall quality control level is then quantified by the average deviation and converted into a score. The derivation logic of step S421, which calculates the loss control deviation, is that different cleaning load factors correspond to different expected loss rates. An expected loss rate function is constructed using historical operational data. The function is constructed by collecting a large amount of operational data under different cleaning load factors, and then... Interval grouping was performed, the average loss rate of each group was calculated, and a quadratic polynomial fitting was used to obtain the result. Step S422, which calculates the area-weighted average deviation, follows the same logic as the area-weighted method in the efficiency score, using the work area as the weight to quantify the overall deviation level. The scaling parameter is determined based on the common loss rate deviation range to ensure that the scores are distributed within a reasonable range.

[0037] In this embodiment, fuel consumption depends on the optimization level of the engine operating point. By comparing the actual fuel consumption rate with the theoretical minimum fuel consumption rate, the optimization level of the engine operating point is quantified, and then a fuel consumption score is obtained by combining the operating area weight. The derivation logic for calculating the engine output torque in step S431 is based on the physical relationship between power, torque, and speed, and the torque is derived from the engine output power and speed. The derivation logic for calculating the instantaneous fuel efficiency coefficient in step S432 is that the theoretical minimum fuel consumption rate is the optimal fuel consumption level under the current engine speed and torque, which can be found in the universal characteristic curve data table provided by the engine manufacturer. The closer the instantaneous fuel efficiency coefficient is to 1, the closer the engine operating point is to the optimal efficiency zone. The logic for calculating the area-weighted average efficiency coefficient in step S433 is consistent with the aforementioned area-weighted method.

[0038] It is worth noting that by innovatively constructing two features with clear engineering and physical significance—drum specific torque and cleaning specific power consumption—and further integrating them into a cleaning load factor, the margin of the current operating system from cleaning overload is dynamically quantified. Based on the cleaning load factor, three operating conditions are identified: sufficient margin, critical balance, and overload risk, each representing different environmental operational difficulties. Efficiency is evaluated only under the most challenging critical balance condition, and quality is assessed by comparing the actual loss rate with the expected loss rate based on the current cleaning load factor. This successfully transforms the scoring method from directly statistically weighting speed, loss, and fuel consumption to evaluating under interpretable operating condition constraints, thereby reducing the interference of the strong coupling between operating speed, loss rate, and fuel consumption on the evaluation results and improving the stability and interpretability of the operation evaluation results.

[0039] Example 2: This example provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion by calling the computer program stored in the memory.

[0040] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the agricultural machinery operation technical indicator evaluation method based on multi-source data fusion provided in the above-described embodiment. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Details will not be elaborated upon in this embodiment.

[0041] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0042] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0043] This invention is described with reference to flowchart illustrations and block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and block diagrams, as well as combinations of blocks in the flowchart illustrations and block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0044] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and boxes Figure 1 The steps of the function specified in one or more boxes.

[0045] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion, characterized in that: The specific steps include the following: S1. Construct a time-series dataset, which includes the agricultural machinery operating speed, engine output power, engine speed, instantaneous fuel consumption rate, threshing drum torque, number of loss pulses, and grain yield flow rate at each moment within a preset collection period, and obtain the grain loss rate. S2. Based on the agricultural machinery operating speed and threshing drum torque, the drum specific torque is calculated to characterize the feeding resistance per unit speed. An empirical model based on energy distribution is used to obtain the power consumption of the cleaning system, and then the cleaning specific power consumption is obtained to characterize the power consumption of the cleaning system per unit grain yield. S3. Based on the drum torque ratio, a linear model is constructed to calculate the critical cleaning ratio power consumption. The cleaning load factor is further calculated. Based on the value of the cleaning load factor, the agricultural machinery operation status at each moment within the preset collection period is divided into working condition categories and the working condition category identifier is output. Specifically, these include sufficient margin working condition, critical balance working condition, and overload risk working condition. S4. Based on the cleaning load factor and working condition category identifier, calculate the efficiency score, quality score and fuel consumption score respectively, and then obtain the comprehensive operating performance score.

2. The method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion according to claim 1, characterized in that: The grain loss rate in S1 is calculated based on the calibration coefficient of the grain loss sensor, and the calculation formula is as follows: ； in, for Grain loss rate at any given time This refers to the calibration coefficients of the grain loss sensor, in units of... / pulse, for The number of lost pulses at each moment, for Grain yield flow rate at any given time, in units of To prevent division by zero, the constant is set to a value of , where i is the time index.

3. The method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion according to claim 2, characterized in that: S2 includes the following specific steps: S21. Based on the agricultural machinery's operating speed and the threshing drum torque, calculate the drum specific torque, which characterizes the feeding resistance per unit speed. The calculation formula is as follows: ； in, for The roller torque at any given moment for The torque of the threshing drum at any given time, in units of for The speed of agricultural machinery operation at any given moment, in units of To prevent division by zero, the constant is set to a value of ; S22. The power consumption of the cleaning system is calculated using an empirical model based on energy allocation. The calculation formula is as follows: ； in, for Engine output power at any given time, in kW. The ratio of engine power allocated to the cleaning system. The power coefficient of the walking system, in units of The power coefficient of the threshing system. The value represents the rotational speed of the threshing drum, in rpm. 9549 is a power conversion factor. for The power consumption of the cleaning system at any given time, in kW; S23. Further calculate the power consumption of the cleaning system, which characterizes the unit grain yield, using the following formula: ;in, for Cleaning power consumption at any given time, in units of .

4. The method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion according to claim 3, characterized in that: S3 includes the following specific steps: S31. Based on the drum specific torque, a linear model is constructed to calculate the critical cleaning ratio power consumption. The linear model expression is as follows: ； in, Basic cleaning ratio power consumption, in units of The load sensitivity coefficient is used for cleaning, and the unit is... for Critical cleaning ratio power consumption at time , in units of ; S32. Further calculate the cleaning load factor, the calculation method is as follows: ； in, for The cleaning load factor at any given time is used to classify the agricultural machinery operation status at each moment within the preset collection period into different working condition categories based on the value of the cleaning load factor. At that time, mark The time is always under conditions of sufficient margin. ;when At that time, mark The time is the critical equilibrium condition. ;when At that time, mark This is a constant state of overload risk. for The operating condition category identifier at any given time.

5. The method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion according to claim 4, characterized in that: The calculation of the efficiency score in S4 includes the following specific steps: S411. Calculate the area-weighted average velocity under the critical equilibrium condition. The calculation formula is as follows: ； in, For the working width, This refers to the data collection time interval; S412, Computational Efficiency Score This represents the theoretically optimal operating speed.

6. The method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion according to claim 5, characterized in that: The calculation of the quality score in S4 includes the following specific steps: S421, targeting At any given time, calculate the loss control deviation. ;in, express Expected grain loss rate under the current cleaning load factor value express Loss control deviation at any given moment; S422. Calculate the area-weighted average deviation for all times within the preset acquisition period. The formula is: ; Calculate quality score This is the scaling parameter.

7. The method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion according to claim 6, characterized in that: The calculation of the fuel consumption score in S4 includes the following specific steps: S431, targeting At any time, extract engine output power and engine speed This leads to the engine output torque. ; S432, targeting Calculate the instantaneous fuel efficiency coefficient at each time point. ;in, for Instantaneous fuel consumption rate at any given moment This represents the theoretical minimum fuel consumption rate under current operating conditions. S433. Calculate the area-weighted average efficiency coefficient for all times within the preset acquisition period. The formula is: This leads to a fuel consumption score. .

8. The method for evaluating agricultural machinery operation technical indicators based on multi-source data fusion according to claim 7, characterized in that: The formula for calculating the comprehensive performance score in S4 is as follows: ； in, To calculate the overall performance score, As a weighting factor for efficiency scoring, As a weighting factor for quality scoring, As a weighting factor for fuel consumption rating, .

Images