A method and system for monitoring electric agricultural machinery operations based on the Internet of Things

Abstract

This invention relates to a method and system for monitoring the operation of electric agricultural machinery based on the Internet of Things (IoT), belonging to the field of intelligent monitoring and IoT technology for agricultural equipment. The invention addresses the problem of complex hardware configurations in existing methods that rely on multiple dedicated sensors to monitor the operational status of agricultural machinery. The method includes: collecting multi-source data to construct an agricultural machinery operation status vector, and then preprocessing it to obtain an agricultural machinery operation feature vector; pre-determining the agricultural machinery's no-load speed range and no-load reference power to determine the final operational status of the agricultural machinery; accumulating the actual operational time of the agricultural machinery based on the final operational status; calculating the actual operational energy consumption; statistically analyzing the set of actual operational trajectory points; calculating the operational coverage area based on the final operational status and the set of actual operational trajectory points; calculating the actual operational intensity based on the actual operational energy consumption and actual operational time; and simultaneously calculating the corresponding operational load response and operational load stability based on the final operational status, thereby achieving agricultural machinery operation monitoring. This invention is used for monitoring the operational status of agricultural machinery.

Description

Technical Field

[0001] This invention relates to a method and system for monitoring the operation of electric agricultural machinery based on the Internet of Things (IoT), belonging to the field of intelligent monitoring of agricultural equipment and IoT technology. Background Technology

[0002] With the continuous improvement of agricultural mechanization and informatization, digital monitoring of agricultural operations has become a crucial foundational technology for agricultural production management and socialized service settlement. In recent years, electric agricultural machinery, due to its low emissions and ease of control, has been gradually applied and promoted in facility agriculture, park operations, plant protection, and light-duty operations. Compared to traditional fuel-powered agricultural machinery, electric agricultural machinery typically uses a motor and power controller to form an electric drive system. Parameters such as current, voltage, power, and energy consumption generated during operation can be directly collected by the control system, exhibiting a relatively rapid and obvious response to load changes, providing new technical conditions for the refined perception of the operational process.

[0003] In agricultural production management, the core needs of agricultural machinery operation monitoring are no longer limited to determining whether agricultural machinery is in operation or has reached a certain location. Instead, the focus has shifted to whether the machinery has actually performed tillage, sowing, and plant protection operations, whether the operations occurred on designated plots within specified timeframes, and whether the operation process was continuous and effective. However, existing agricultural machinery operation monitoring solutions are simple in structure and low in cost, primarily relying on BeiDou or Global Positioning System (GPS) terminals to obtain the machinery's trajectory and infer the operation status based on information such as speed. However, due to the lack of direct perception of the workload and the working status of the implements, situations such as field relocation or unloaded driving are easily misjudged as actual operations, or missed during lightly loaded operations. To improve recognition accuracy, some solutions integrate GNSS positioning, PTO speed sensors, hydraulic pressure sensors, or work load sensors, and combine them with rule or algorithm models to distinguish work status. However, such solutions usually require the configuration of multiple dedicated sensors, making system integration and maintenance complex, hardware costs high, and strong adaptability requirements for different models of agricultural machinery and implements. Furthermore, they are easily affected by data noise and sensor stability in weak communication environments and complex working conditions in farmland, making it difficult to deploy them universally in large-scale agricultural production scenarios.

[0004] Existing agricultural machinery operation monitoring technologies still have significant limitations in practical applications. On the one hand, although operation monitoring schemes based on positioning trajectories and driving speeds have simple system structures and low deployment costs, they lack direct perception of the workload and working status of the machinery, making it difficult to stably and accurately distinguish between actual operation, relocation operation, and no-load operation. On the other hand, while fusion schemes relying on multiple dedicated sensors can improve recognition accuracy to some extent, they generally suffer from complex hardware configurations, high system integration and maintenance costs, and strong adaptability requirements, making it difficult to meet the needs of large-scale agricultural production scenarios for promotion and application.

[0005] In summary, the core contradiction currently facing the field of agricultural machinery operation monitoring is that high-precision solutions are difficult to popularize, while popular solutions struggle to accurately distinguish operational states. Especially with the gradual promotion of electric agricultural machinery, how to fully utilize the inherent sensing capabilities of electric agricultural machinery to achieve reliable operation monitoring without significantly increasing hardware costs has become an urgent technical problem to be solved. Summary of the Invention

[0006] To address the issue of complex hardware configurations in existing methods that rely on multiple dedicated sensors to monitor the operational status of agricultural machinery, this invention provides an Internet of Things-based method and system for monitoring the operation of electric agricultural machinery.

[0007] The present invention provides an Internet of Things-based method for monitoring the operation of electric agricultural machinery, comprising:

[0008] Collecting multi-source data at time t constitutes the agricultural machinery operating state vector. The data is then preprocessed to obtain the time-synchronized agricultural machinery operation feature vector. ;

[0009] ,

[0010] In the formula Let be the motor input power at time t. Let t be the speed of the agricultural machinery. Let t represent the working state of the agricultural machinery. Let t be the x-coordinate of the agricultural machinery in the plane coordinate system at time t. Let t be the ordinate of the agricultural machinery in the plane coordinate system at time t;

[0011] ,

[0012] In the formula For preprocessing functions, This represents the smoothed power characteristic at time t after being filtered by the moving average. Let be the characteristic quantity of the agricultural machinery's travel speed at time t. Let be the characteristic quantity of the agricultural machinery's working state at time t. Let t be the x-coordinate of the agricultural machinery after preprocessing. The ordinate of the agricultural machinery after preprocessing at time t;

[0013] Predetermine the no-load speed range and no-load reference power of the agricultural machinery, and base the characteristic quantities of the agricultural machinery's working state at time t. The characteristic quantity of agricultural machinery travel speed at time t Determine whether the agricultural machinery is in an unloaded state; if the agricultural machinery is in an unloaded state, update the unloaded reference power based on the smoothing coefficient;

[0014] For agricultural machinery in non-idle conditions, the current idle reference power and the smoothed power characteristic at time t are used as the basis. Calculate the current job load response, and then based on Determine the current position of the agricultural machinery, and then make a preliminary judgment on whether the agricultural machinery is in operation at time t;

[0015] Set continuous window Determine the agricultural machinery in the continuous window The inner part represents the count of the working status, and the final working status of the agricultural machinery at time t is determined based on the count.

[0016] The actual operating time of agricultural machinery is accumulated based on the final operating status; this is then combined with the smoothed power characteristic at time t. Calculate the actual energy consumption of the operation; statistically analyze the set of actual operation trajectory points; calculate the operation coverage area based on the final operation status and the set of actual operation trajectory points; calculate the actual operation intensity based on the actual operation energy consumption and actual operation duration; and calculate the corresponding operation load response and operation load stability based on the final operation status, thereby realizing agricultural machinery operation monitoring.

[0017] According to the present invention, a method for monitoring electric agricultural machinery operation based on the Internet of Things, the method for obtaining the smoothed power characteristic at time t is as follows:

[0018] Set smooth window length ,like , ;

[0019] like , .

[0020] According to the present invention, an IoT-based method for monitoring the operation of electric agricultural machinery, the no-load speed range of the agricultural machinery is expressed as follows: ,

[0021] ,

[0022] In the formula This is the minimum unloaded speed. This represents the maximum unloaded speed. For low quantile parameters quantile function, For higher quantile parameters quantile function, Agricultural machinery is not in operation. Characteristic quantities of agricultural machinery travel speed;

[0023] like and At that time, the agricultural machinery was determined to be in an unloaded state;

[0024] Define an idle update indicator variable :

[0025] ,

[0026] No-load reference power at time t for:

[0027] ,

[0028] In the formula For smoothing coefficients, .

[0029] According to the present invention, an IoT-based method for monitoring the operation of electric agricultural machinery, the operation load response is expressed as: :

[0030] ;

[0031] Set target work area set Define the region indicator variable :

[0032] ;

[0033] Set adaptive job load threshold Calculate the job status determination variables :

[0034] ,

[0035] but At that time, it was initially determined that the agricultural machinery was in operation at time t.

[0036] According to the present invention, an Internet of Things-based method for monitoring the operation of electric agricultural machinery,

[0037] like , ;

[0038] like , ;

[0039] In the formula The length of the continuous test window;

[0040] The count of the job status is represented as :

[0041] ;

[0042] The final operating state of the agricultural machinery at time t is represented as: :

[0043] ,

[0044] In the formula This is the minimum duration threshold.

[0045] According to the present invention, an IoT-based method for monitoring the operation of electric agricultural machinery expresses the actual operation time of the agricultural machinery as follows: :

[0046] ,

[0047] In the formula The work status remains unchanged. The end time point, The interval between adjacent phase points;

[0048] Express the actual energy consumption of the operation as :

[0049] .

[0050] According to the present invention, an IoT-based method for monitoring the operation of electric agricultural machinery represents the set of real operation trajectory points as follows: :

[0051] .

[0052] According to the present invention, an IoT-based method for monitoring electric agricultural machinery operations represents the operational coverage area as... :

[0053] ,

[0054] In the formula This represents the total number of spatial units. For the first One spatial unit;

[0055] when At that time, trajectory point The spatial unit that falls into the cover unit is denoted as the covered unit, and after deduplication, we get... .

[0056] According to the present invention, an IoT-based method for monitoring electric agricultural machinery operations expresses the actual workload as... :

[0057] ;

[0058] The stability of the workload is expressed as :

[0059] ,

[0060] In the formula This represents the total number of valid sampling points during agricultural machinery operation. for Load response under certain conditions The arithmetic mean;

[0061] , .

[0062] This invention also provides an Internet of Things-based monitoring system for electric agricultural machinery operations, comprising:

[0063] The data acquisition module is used to collect multi-source data at time t to form the agricultural machinery operating state vector. :

[0064] ,

[0065] In the formula Let be the motor input power at time t. Let t be the speed of the agricultural machinery. Let t represent the working state of the agricultural machinery. Let t be the x-coordinate of the agricultural machinery in the plane coordinate system at time t. Let t be the ordinate of the agricultural machinery in the plane coordinate system at time t;

[0066] The preprocessing module is used to process the agricultural machinery operating state vector. Preprocessing is performed to obtain the preprocessed time-synchronized agricultural machinery operation feature vector. ;

[0067] ,

[0068] In the formula For preprocessing functions, This represents the smoothed power characteristic at time t after being filtered by the moving average. Let be the characteristic quantity of the agricultural machinery's travel speed at time t. Let be the characteristic quantity of the agricultural machinery's working state at time t. Let t be the x-coordinate of the agricultural machinery after preprocessing. The ordinate of the agricultural machinery after preprocessing at time t;

[0069] The operation monitoring and management module is used to pre-determine the no-load speed range and no-load reference power of agricultural machinery, based on the characteristic quantities of the agricultural machinery's working status at time t. The characteristic quantity of agricultural machinery travel speed at time t Determine whether the agricultural machinery is in an unloaded state; if the agricultural machinery is in an unloaded state, update the unloaded reference power based on the smoothing coefficient;

[0070] For agricultural machinery in non-idle conditions, the current idle reference power and the smoothed power characteristic at time t are used as the basis. Calculate the current job load response, and then based on Determine the current position of the agricultural machinery, and then make a preliminary judgment on whether the agricultural machinery is in operation at time t;

[0071] Set continuous window Determine the agricultural machinery in the continuous window The inner part represents the count of the working status, and the final working status of the agricultural machinery at time t is determined based on the count.

[0072] The actual operating time of agricultural machinery is accumulated based on the final operating status; this is then combined with the smoothed power characteristic at time t. Calculate the actual energy consumption of the operation; compile the set of actual operation trajectory points; calculate the operation coverage area based on the final operation status and the set of actual operation trajectory points; calculate the actual operation intensity based on the actual operation energy consumption and actual operation duration; and calculate the corresponding operation load response and operation load stability based on the final operation status.

[0073] The beneficial effects of this invention are as follows: This invention addresses the management needs of electric agricultural machinery in operations such as tillage, sowing, plant protection, and harvesting. It utilizes the perceptible and quantifiable electrical parameters of the electric drive system of the agricultural machinery, combined with the status and spatial location data of the implements, to achieve operation authenticity detection, operation stage identification, and operation quality quantification. It fully leverages the characteristics of the operating parameters of the electric drive system, achieving reliable detection of agricultural machinery operation authenticity and effective quantification of the operation process without significantly increasing system complexity.

[0074] This invention, without adding extra complex work load sensors or significantly increasing system integration and maintenance costs, utilizes the significant response differences in power and other parameters of electric agricultural machinery drive systems under actual and non-operational states to construct an operation monitoring method based on the electric drive load response characteristics. This enables reliable determination of whether agricultural machinery operation behavior has actually occurred, and allows for stage identification, continuous verification, and effective quantitative monitoring of the operation process. Thus, it provides objective and verifiable technical support for agricultural machinery operation verification, socialized services, and management decisions. Attached Figure Description

[0075] Figure 1This is a flowchart of an IoT-based method for monitoring the operation of electric agricultural machinery, as described in this invention. Detailed Implementation

[0076] 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.

[0077] Specific Implementation Method 1: Combination Figure 1 As shown, this embodiment provides a method for monitoring the operation of electric agricultural machinery based on the Internet of Things, including:

[0078] Collecting multi-source data at time t constitutes the agricultural machinery operating state vector. The data is then preprocessed to obtain the time-synchronized agricultural machinery operation feature vector. ;

[0079] ,

[0080] In the formula Let be the motor input power at time t. Let t be the speed of the agricultural machinery. Let t represent the working state of the agricultural machinery. Let t be the x-coordinate of the agricultural machinery in the plane coordinate system at time t. Let t be the ordinate of the agricultural machinery in the plane coordinate system at time t;

[0081] ,

[0082] In the formula For preprocessing functions, This represents the smoothed power characteristic at time t after being filtered by the moving average. Let be the characteristic quantity of the agricultural machinery's travel speed at time t. Let be the characteristic quantity of the agricultural machinery's working state at time t. Let t be the x-coordinate of the agricultural machinery after preprocessing. The ordinate of the agricultural machinery after preprocessing at time t;

[0083] Predetermine the no-load speed range and no-load reference power of the agricultural machinery, and base the characteristic quantities of the agricultural machinery's working state at time t. The characteristic quantity of agricultural machinery travel speed at time t Determine whether the agricultural machinery is in an unloaded state; if the agricultural machinery is in an unloaded state, update the unloaded reference power based on the smoothing coefficient;

[0084] For agricultural machinery in non-idle conditions, the current idle reference power and the smoothed power characteristic at time t are used as the basis. Calculate the current job load response, and then based on Determine the current position of the agricultural machinery, and then make a preliminary judgment on whether the agricultural machinery is in operation at time t;

[0085] Set continuous window Determine the agricultural machinery in the continuous window The inner part represents the count of the working status, and the final working status of the agricultural machinery at time t is determined based on the count.

[0086] The actual operating time of agricultural machinery is accumulated based on the final operating status; this is then combined with the smoothed power characteristic at time t. Calculate the actual energy consumption of the operation; statistically analyze the set of actual operation trajectory points; calculate the operation coverage area based on the final operation status and the set of actual operation trajectory points; calculate the actual operation intensity based on the actual operation energy consumption and actual operation duration; and calculate the corresponding operation load response and operation load stability based on the final operation status, thereby realizing agricultural machinery operation monitoring.

[0087] Furthermore, in discrete time series The system collects multi-source data in real time during the operation of electric agricultural machinery, constructing a real-time monitoring system for the machinery. Operating state vector: collectable Cumulative energy consumption over time As a system-level energy consumption record, it is used to ensure the continuity of energy consumption statistics in the event of communication instability or data loss, and to perform consistency verification on the operation energy consumption results obtained based on power integration.

[0088] Indicates that the machine is working. This indicates that the machine is not working; It is usually obtained from the BeiDou or GPS positioning system.

[0089] Preprocessing is performed to address issues such as time asynchrony and noise interference in multi-source data. Preprocessing includes time alignment: mapping data from different sampling frequencies to a unified time scale. Noise filtering: performing noise filtering on the collected operating data, with a focus on smoothing power parameters reflecting changes in workload to suppress the impact of instantaneous fluctuations on job judgment results.

[0090] The method for obtaining the smoothed power characteristic at time t is as follows:

[0091] Set smooth window length ,like , ;

[0092] like , .

[0093] For every moment The smoothed power value below, that is, the power value for the most recent Instantaneous power within each sampling time point Take the average value; The number of most recent sampling times used in the averaging process when calculating the smoothed power at the current time.

[0094] Outlier handling is also performed: abnormal data points that exceed the physically reasonable range are removed. Through data preprocessing, the continuous and stable electric drive parameters used for job determination are ensured, avoiding interference from instantaneous fluctuations in load identification.

[0095] No-load reference state determination: When the working implements are not turned on and the agricultural machinery is in a non-operational state, the no-load or non-operational reference power state of the electric agricultural machinery is determined, providing a reference for subsequent operation load determination, and can adapt to different machine models and operating conditions.

[0096] No-load sample determination: To adaptively determine the non-operational speed range for different machine models and operating conditions, statistical analysis is performed on the operating speed of agricultural machinery when the implements are not activated. At discrete sampling times, the agricultural machinery's travel speed is acquired, and indicators that satisfy the implement's operating status are selected. The historical samples constitute the non-operational speed sample set, and the distribution of the non-operational speed samples is statistically analyzed, taking the first... quantiles and the Quantiles serve as the lower and upper limits of the non-operational speed range; the agricultural machinery no-load speed range is represented as follows: ,

[0097] ,

[0098] In the formula This is the minimum unloaded speed. This represents the maximum unloaded speed. For low quantile parameters quantile function, For higher quantile parameters quantile function, Agricultural machinery is not in operation. Characteristic quantities of agricultural machinery travel speed; and They are used to obtain the sample number respectively. and The value at the quantile; ;

[0099] like and At that time, the agricultural machinery was determined to be in an unloaded state;

[0100] Define an idle update indicator variable :

[0101] ,

[0102] No-load reference power at time t for:

[0103] ,

[0104] In the formula For smoothing coefficients, .

[0105] in, For a moment No-load / non-operation reference power, initialization , This indicates an update.

[0106] The workload response is expressed as The difference between the current power and the no-load reference power is the core physical quantity for determining the operating load.

[0107] ;

[0108] Set target work area set Define the region indicator variable :

[0109] ;

[0110] It can determine whether the current location of the agricultural machinery is within the operating area;

[0111] Set adaptive job load threshold Calculate the job status determination variables :

[0112] ,

[0113] but At time t, the agricultural machinery is initially determined to be in an operational state. When the increase in the agricultural machinery load exceeds the threshold, the implement is in an operational state and located within the target operational area, and is instantly determined to be in an operational state.

[0114] This determination method is based directly on the physical response characteristics of the electric drive system to the work load, avoiding reliance on trajectory or speed for empirical judgment, thereby improving the reliability of work authenticity identification.

[0115] To avoid misjudgments caused by short-term power fluctuations or instantaneous impacts and to eliminate occasional interference, a time continuity constraint is introduced into the job judgment results.

[0116] like , ;

[0117] like , ;

[0118] In the formula The length of the continuous testing window, i.e., the number of sampling time points;

[0119] The count of the job status is represented as :

[0120] ;

[0121] The final operating state of the agricultural machinery at time t is represented as: :

[0122] ,

[0123] In the formula This is the minimum duration threshold.

[0124] The actual operating time of agricultural machinery is expressed as :

[0125] ,

[0126] In the formula The work status remains unchanged. The end time point, The interval between adjacent phase points;

[0127] The operation time is only counted for valid operation segments that pass the operation judgment and continuity verification, effectively eliminating the interference of relocation operations, empty driving, and short-term abnormal operating conditions on the statistical results. In practical applications, the operation time results can be directly used for operation time settlement in agricultural socialized services and for agricultural machinery operation performance evaluation, providing management departments and service providers with objective and verifiable time basis, thereby avoiding disputes and errors caused by manual reporting or simple trajectory statistics.

[0128] Express the actual energy consumption of the operation as :

[0129] .

[0130] The energy consumption results reflect the total electrical energy consumed by electric agricultural machinery under actual operating conditions, and are an important quantitative indicator that distinguishes electric agricultural machinery from traditional fuel-powered agricultural machinery. In practical applications, these operation time results can be directly used for operation time settlement in agricultural socialized services and for agricultural machinery operation performance evaluation, providing management departments and service providers with objective and verifiable time data, thereby avoiding disputes and errors caused by manual reporting or simple trajectory statistics.

[0131] The set of actual operation trajectory points is represented as :

[0132] .

[0133] By filtering all operational trajectories, only spatial location points under operational status are retained to form a set of true operational trajectories, thus obtaining an operational trajectory that highly matches the actual operational behavior. This trajectory automatically excludes trajectory information corresponding to non-operational behaviors such as site transfers, U-turns, and waiting. In practical applications, this result can be used for spatial verification and visualization of operational behavior, supporting management departments in verifying whether operations occurred within designated plots, and also providing reliable spatial evidence for operational quality assessment, operational process retrospection, and dispute resolution.

[0134] Furthermore, the area covered by the operation is expressed as... :

[0135] ,

[0136] In the formula This represents the total number of spatial units. For the first One spatial unit; , The side length of the spatial unit;

[0137] when At that time, trajectory point The spatial unit that falls into the cover unit is denoted as the covered unit, and after deduplication, we get... .

[0138] The operational coverage area obtained by further statistical analysis based on the actual operational trajectory can quantify the actual operational range completed by electric agricultural machinery during operation. In practical applications, this operational coverage area result can be directly used in operation settlement scenarios where area is the basis for measurement, such as tillage and plant protection spraying. At the same time, it can also provide quantitative basis for management departments, avoiding judgments based solely on trajectory or manual reporting.

[0139] The actual workload is expressed as :

[0140] ;

[0141] It can be used to compare the intensity of work load under different plots of land and different working conditions.

[0142] Work intensity reflects the load level during a work process in terms of energy consumption per unit of work time. This indicator integrates work duration and energy consumption information, enabling comparability between different work tasks. In practical applications, work intensity can be used to analyze differences in work load under different site conditions, different work modes, or different equipment configurations, providing decision support for optimizing work plans, rationally arranging work rhythms, and improving energy utilization efficiency.

[0143] The stability of the workload is expressed as :

[0144] ,

[0145] In the formula This represents the total number of valid sampling points during agricultural machinery operation. for Load response under certain conditions The arithmetic mean;

[0146] , .

[0147] Specific Implementation Method Two: This implementation method also provides an Internet of Things-based electric agricultural machinery operation monitoring system, including:

[0148] The data acquisition module is used to collect multi-source data at time t to form the agricultural machinery operating state vector. :

[0149] ,

[0150] In the formula Let be the motor input power at time t. Let t be the speed of the agricultural machinery. Let t represent the working state of the agricultural machinery. Let t be the x-coordinate of the agricultural machinery in the plane coordinate system at time t. Let t be the ordinate of the agricultural machinery in the plane coordinate system at time t;

[0151] The preprocessing module is used to process the agricultural machinery operating state vector. Preprocessing is performed to obtain the preprocessed time-synchronized agricultural machinery operation feature vector. ;

[0152] ,

[0153] In the formula For preprocessing functions, This represents the smoothed power characteristic at time t after being filtered by the moving average. Let be the characteristic quantity of the agricultural machinery's travel speed at time t. Let be the characteristic quantity of the agricultural machinery's working state at time t. Let t be the x-coordinate of the agricultural machinery after preprocessing. The ordinate of the agricultural machinery after preprocessing at time t;

[0154] The operation monitoring and management module is used to pre-determine the no-load speed range and no-load reference power of agricultural machinery, based on the characteristic quantities of the agricultural machinery's working status at time t. The characteristic quantity of agricultural machinery travel speed at time t Determine whether the agricultural machinery is in an unloaded state; if the agricultural machinery is in an unloaded state, update the unloaded reference power based on the smoothing coefficient;

[0155] For agricultural machinery in non-idle conditions, the current idle reference power and the smoothed power characteristic at time t are used as the basis. Calculate the current job load response, and then based on Determine the current position of the agricultural machinery, and then make a preliminary judgment on whether the agricultural machinery is in operation at time t;

[0156] Set continuous window Determine the agricultural machinery in the continuous window The inner part represents the count of the working status, and the final working status of the agricultural machinery at time t is determined based on the count.

[0157] The actual operating time of agricultural machinery is accumulated based on the final operating status; this is then combined with the smoothed power characteristic at time t. Calculate the actual energy consumption of the operation; compile the set of actual operation trajectory points; calculate the operation coverage area based on the final operation status and the set of actual operation trajectory points; calculate the actual operation intensity based on the actual operation energy consumption and actual operation duration; and calculate the corresponding operation load response and operation load stability based on the final operation status.

[0158] During the operation of electric agricultural machinery, when the machinery is only moving between sites or traveling unloaded, its motor is under low or stable load, and the changes in electric drive power and energy consumption are relatively small. However, when the machinery is actually performing tillage, sowing, plant protection, and other operations, the implements interact with the soil or the workpiece, and the workload is directly reflected in the continuous changes in electric drive parameters such as motor power. Therefore, this experiment constructs an operation monitoring model based on electric drive parameters, combined with information on the machinery's working status, speed, and spatial location, to comprehensively determine the operation behavior and form a scheme suitable for monitoring the authenticity of electric agricultural machinery operations.

[0159] The data acquisition module is used to acquire raw data reflecting the operating status, work status, and spatial location of the electric agricultural machinery, and is the foundation of the entire operation monitoring. The data acquisition module is installed on the electric agricultural machinery itself and is used to collect multi-source data reflecting the machinery's operating and work status, including but not limited to:

[0160] Motor operating parameters, such as current, voltage, power and energy consumption; operating status parameters, such as motor speed and travel speed; work equipment status parameters, such as the on or off status of the work device; travel status parameters, such as speed and heading; location information parameters, such as Beidou or GPS positioning coordinates; the above parameters are collected in real time through the vehicle controller, sensors and IoT interface, and output with a unified timestamp to provide input for subsequent model calculations.

[0161] The preprocessing module, deployed at the agricultural machinery or nearby edge computing devices, is used to preprocess and analyze the collected multi-source data in real time. This module performs data time alignment, noise filtering, and feature calculation, and makes a preliminary judgment on the operating status based on the response characteristics of the electric drive load, thus enabling real-time identification of the operating status even in environments with weak communication or network outages.

[0162] A communication module is used to realize data interaction between the agricultural machinery and the cloud platform. It supports cellular communication, narrowband IoT or other communication methods suitable for agricultural scenarios. It is used to upload preprocessed results and raw or summarized data to the cloud and receive parameter configuration or control commands issued by the cloud.

[0163] The operation monitoring and management module is used to centrally store, statistically analyze and manage operation monitoring data from multiple electric agricultural machines, generate operation records, operation quality assessment results and abnormal operation prompts, and provide support for management and decision-making.

[0164] The application display module is used to intuitively show users the status of agricultural machinery operation, operation time, operation area and related statistical results, and supports access via web page or mobile terminal.

[0165] Example 1: Light load (transfer / light operation, insufficient load increase, no operation triggered)

[0166] Parameter settings: Sampling period Total duration Continuous window Minimum duration threshold Job load threshold Smooth window Smoothing coefficient .

[0167] The sampled data (same vehicle, same voltage) are shown in Table 1:

[0168] Table 1

[0169]

[0170] I. Calculation of moving average power:

[0171] ;

[0172] II. Recursive derivation of no-load reference power:

[0173] ,initialization ;

[0174] The no-load condition is met: ;

[0175] The no-load condition is met: ;

[0176] The equipment operation will no longer be updated: .

[0177] III. Load Increment Calculation:

[0178] Job load increment ;

[0179] Job load increment ;

[0180] Job load increment .

[0181] IV. Instantaneous Operation Judgment:

[0182] Due to threshold , judgment condition ;

[0183] determination .

[0184] V. Continuity Verification:

[0185] Continuous window Minimum duration threshold ,by For example:

[0186] Job count within the window ;

[0187] VI. Final Assessment of the Assignment:

[0188] .

[0189] Conclusion (light load): The final job assignment is determined to be 0, and the actual job duration / energy consumption is not output.

[0190] Example 2: Overload (real job, the load increment exceeds the threshold, triggering the job).

[0191] Parameter settings: Sampling period Total duration Continuous window Minimum duration threshold Job load threshold Smooth window Smoothing coefficient .

[0192] The sampled data (current changes only during the heavy load phase) are shown in Table 2:

[0193] Table 2

[0194]

[0195] I. Calculation of moving average power:

[0196] ;

[0197] II. Recursive derivation of no-load reference power:

[0198] ,initialization ;

[0199] The no-load condition is met: ;

[0200] The no-load condition is met: ;

[0201] The equipment operation will no longer be updated: .

[0202] III. Load Increment Calculation:

[0203] Job load increment ,

[0204] Job load increment ,

[0205] Job load increment .

[0206] IV. Instantaneous Operation Judgment:

[0207] Due to threshold , judgment condition

[0208] determination

[0209] V. Continuity Verification:

[0210] Continuous window Minimum duration threshold ,by For example:

[0211] Job count within the window

[0212] VI. Final Assessment of the Assignment:

[0213] ;

[0214] At the same time, due to The window counts are 1 and 2 (less than 3), therefore

[0215] VII. Monitoring Results Output:

[0216] Actual assignment duration:

[0217] ;

[0218] Actual operating energy consumption:

[0219] ;

[0220] Work intensity:

[0221] ;

[0222] Coverage area:

[0223] Pick Then the area of ​​each unit ;

[0224] when At that time, trajectory point It falls into a certain grid cell and is recorded. After deduplicating all recorded cells, the count is... .

[0225] In this embodiment, only Therefore, after deduplication, only one cell was recorded: .

[0226] Coverage area ;

[0227] Load stability:

[0228] Minimum Duration Threshold ,satisfy ,only A point, therefore , This indicates that no calculable load fluctuations were detected.

[0229] 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 method for monitoring the operation of electric agricultural machinery based on the Internet of Things, characterized in that, include: Collecting multi-source data at time t constitutes the agricultural machinery operating state vector. The data is then preprocessed to obtain the time-synchronized agricultural machinery operation feature vector. ; ， In the formula Let be the motor input power at time t. Let t be the speed of the agricultural machinery. Let t represent the working state of the agricultural machinery. Let t be the x-coordinate of the agricultural machinery in the plane coordinate system at time t. Let t be the ordinate of the agricultural machinery in the plane coordinate system at time t; ， In the formula For preprocessing functions, This represents the smoothed power characteristic at time t after being filtered by the moving average. Let be the characteristic quantity of the agricultural machinery's travel speed at time t. Let be the characteristic quantity of the agricultural machinery's working state at time t. Let t be the x-coordinate of the agricultural machinery after preprocessing. The ordinate of the agricultural machinery after preprocessing at time t; Predetermine the no-load speed range and no-load reference power of the agricultural machinery, and base the characteristic quantities of the agricultural machinery's working state at time t. The characteristic quantity of agricultural machinery travel speed at time t Determine whether the agricultural machinery is in an unloaded state; if the agricultural machinery is in an unloaded state, update the unloaded reference power based on the smoothing coefficient; For agricultural machinery in non-idle conditions, the current idle reference power and the smoothed power characteristic at time t are used as the basis. Calculate the current job load response, and then based on Determine the current position of the agricultural machinery, and then make a preliminary judgment on whether the agricultural machinery is in operation at time t; Set continuous window Determine the agricultural machinery in the continuous window The inner part represents the count of the working status, and the final working status of the agricultural machinery at time t is determined based on the count. The actual operating time of agricultural machinery is calculated based on the final operating status. Combined with the smoothed power characteristic at time t Calculate the energy consumption of actual operations; Statistical analysis of the set of actual operation trajectory points; Calculate the operation coverage area based on the final operation status and the actual operation trajectory point set; Then, the actual operation intensity is calculated based on the actual operation energy consumption and actual operation duration; at the same time, the corresponding operation load response is calculated based on the final operation status and the operation load stability is calculated, thereby realizing agricultural machinery operation monitoring.

2. The method for monitoring electric agricultural machinery operations based on the Internet of Things according to claim 1, characterized in that, The method for obtaining the smoothed power characteristic at time t is as follows: Set smooth window length ,like , ; like , .

3. The method for monitoring electric agricultural machinery operations based on the Internet of Things according to claim 2, characterized in that, The no-load speed range of agricultural machinery is expressed as follows: , ， In the formula This is the minimum unloaded speed. This represents the maximum unloaded speed. For low quantile parameters quantile function, For higher quantile parameters quantile function, Agricultural machinery is not in operation. Characteristic quantities of agricultural machinery travel speed; like and At that time, the agricultural machinery was determined to be in an unloaded state; Define an idle update indicator variable : ， No-load reference power at time t for: ， In the formula For smoothing coefficients, .

4. The method for monitoring electric agricultural machinery operations based on the Internet of Things according to claim 3, characterized in that, The workload response is expressed as : ； Set target work area set Define the region indicator variable : ； Set adaptive job load threshold Calculate the job status determination variables : ， but At that time, it was initially determined that the agricultural machinery was in operation at time t.

5. The method for monitoring electric agricultural machinery operations based on the Internet of Things according to claim 4, characterized in that, like , ; like , ; In the formula The length of the continuous test window; The count of the job status is represented as : ； The final operating state of the agricultural machinery at time t is represented as: : ， In the formula This is the minimum duration threshold.

6. The method for monitoring electric agricultural machinery operations based on the Internet of Things according to claim 5, characterized in that, The actual operating time of agricultural machinery is expressed as : ， In the formula The work status remains unchanged. The end time point, The interval between adjacent phase points; Express the actual energy consumption of the operation as : 。 7. The method for monitoring electric agricultural machinery operations based on the Internet of Things according to claim 6, characterized in that, The set of actual operation trajectory points is represented as : 。 8. The method for monitoring electric agricultural machinery operations based on the Internet of Things according to claim 7, characterized in that, The area covered by the operation is represented as : ， In the formula This represents the total number of spatial units. For the first One spatial unit; when At that time, trajectory point The spatial unit that falls into the cover unit is denoted as the covered unit, and after deduplication, we get... .

9. A method for monitoring the operation of electric agricultural machinery based on the Internet of Things according to claim 8, characterized in that, The actual workload is expressed as : ； The stability of the workload is expressed as : ， In the formula This represents the total number of valid sampling points during agricultural machinery operation. for Load response under certain conditions The arithmetic mean; ， 。 10. An Internet of Things-based monitoring system for electric agricultural machinery operations, characterized in that, include: The data acquisition module is used to collect multi-source data at time t to form the agricultural machinery operating state vector. : ， In the formula Let be the motor input power at time t. Let t be the speed of the agricultural machinery. Let t represent the working state of the agricultural machinery. Let t be the x-coordinate of the agricultural machinery in the plane coordinate system at time t. Let t be the ordinate of the agricultural machinery in the plane coordinate system at time t; The preprocessing module is used to process the agricultural machinery operating state vector. Preprocessing is performed to obtain the preprocessed time-synchronized agricultural machinery operation feature vector. ; ， In the formula For preprocessing functions, This represents the smoothed power characteristic at time t after being filtered by the moving average. Let be the characteristic quantity of the agricultural machinery's travel speed at time t. Let be the characteristic quantity of the agricultural machinery's working state at time t. Let t be the x-coordinate of the agricultural machinery after preprocessing. The ordinate of the agricultural machinery after preprocessing at time t; The operation monitoring and management module is used to pre-determine the no-load speed range and no-load reference power of agricultural machinery, based on the characteristic quantities of the agricultural machinery's working status at time t. The characteristic quantity of agricultural machinery travel speed at time t Determine whether the agricultural machinery is in an unloaded state; if the agricultural machinery is in an unloaded state, update the unloaded reference power based on the smoothing coefficient; For agricultural machinery in non-idle conditions, the current idle reference power and the smoothed power characteristic at time t are used as the basis. Calculate the current job load response, and then based on Determine the current position of the agricultural machinery, and then make a preliminary judgment on whether the agricultural machinery is in operation at time t; Set continuous window Determine the agricultural machinery in the continuous window The inner part represents the count of the working status, and the final working status of the agricultural machinery at time t is determined based on the count. The actual operating time of agricultural machinery is calculated based on the final operating status. Combined with the smoothed power characteristic at time t Calculate the energy consumption of actual operations; Statistical analysis of the set of actual operation trajectory points; Calculate the operation coverage area based on the final operation status and the actual operation trajectory point set; Then, the actual work intensity is calculated based on the actual work energy consumption and actual work duration; at the same time, the corresponding work load response is calculated based on the final work status, and the work load stability is calculated.

Images