Intelligent agricultural equipment management system and method based on Internet of Things

Abstract

The invention relates to the technical field of data reasoning, and discloses an intelligent agricultural equipment management system and method based on the Internet of Things, and the system comprises a data collection module, an equipment feature extraction module, an equipment health evaluation module, a health mapping module, a strategy generation module and a strategy optimization module, and is connected with a plurality of agricultural equipment through an Internet gateway. Obtaining an original data set; extracting real-time environment characteristics in the cleaned original data and the degradation trend of the agricultural equipment; performing adaptive health assessment on the historical performance data of the agricultural equipment to obtain a fault probability and residual service life assessment report; generating a predicted health index of the agricultural equipment; adjusting a working sequence and resource allocation among the agricultural equipment to obtain an initial scheduling strategy of the agricultural equipment; performing scheduling optimization on the initial scheduling strategy to obtain an equipment scheduling strategy of the agricultural equipment; the intelligent agricultural equipment management efficiency can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data reasoning, and in particular to a smart agricultural equipment management system and method based on Internet of Things. BACKGROUND

[0002] In the field of smart agriculture, the existing equipment management technology cannot efficiently integrate the raw data of multiple agricultural equipment through Internet of Things, and the precision of data cleaning and feature extraction is insufficient, which cannot quickly capture real-time environmental features and equipment degradation trends, resulting in a lack of reliable basis for subsequent equipment state analysis based on data, and difficulty in fully reflecting the actual operation status of the equipment.

[0003] The existing health assessment method lacks adaptive adjustment capability, and fails to fully combine the equipment degradation trend and real-time environmental features to dynamically optimize the evaluation benchmark and weight coefficient, resulting in a large deviation of the prediction results of the failure probability and the remaining useful life. At the same time, the scheduling strategy does not effectively take into account the matching degree of the predicted health indicators of the equipment and the agricultural operation demand, and the work sequence planning and resource allocation lack the cooperation of global consensus and local decision-making, which is prone to time conflicts and resource competition problems, seriously affecting the overall efficiency of smart agricultural equipment management. SUMMARY

[0004] The present application provides a smart agricultural equipment management system and method based on Internet of Things to solve the problems raised in the background art.

[0005] To achieve the above-mentioned purpose, the present application provides a smart agricultural equipment management system based on Internet of Things, characterized in that the system comprises a data acquisition module, an equipment feature extraction module, an equipment health assessment module, a health mapping module, a strategy generation module and a strategy optimization module, wherein:

[0006] The data acquisition module is used to connect multiple agricultural equipment through an Internet gateway to obtain a raw data collection of the agricultural equipment;

[0007] The equipment feature extraction module is used to extract real-time environmental features and degradation trends of the agricultural equipment from the cleaned raw data;

[0008] The equipment health assessment module is used to perform adaptive health assessment on the historical performance data of the agricultural equipment according to the degradation trend and the real-time environmental features, and obtain a failure probability and a remaining useful life assessment report of the agricultural equipment;

[0009] The health mapping module is used to generate a predicted health indicator of the agricultural equipment according to the failure probability and the remaining useful life assessment report;

[0010] The strategy generation module is configured to adjust work sequences and resource allocation among the agricultural devices according to the predicted health indicators and agricultural operation requirements, and obtain an initial scheduling strategy of the agricultural devices.

[0011] The strategy optimization module is configured to perform scheduling optimization on the initial scheduling strategy according to local decisions and global consensus in the agricultural device scheduling process, and obtain a device scheduling strategy of the agricultural devices, and send the device scheduling strategy to the corresponding agricultural devices through the Internet gateway.

[0012] In a preferred embodiment, the data collection module is configured to, when performing connection of multiple agricultural devices through the Internet gateway to obtain a raw data set of the agricultural devices, specifically:

[0013] sending a connection request to the agricultural devices;

[0014] receiving device identifiers and initial state data returned by the agricultural devices based on the Internet gateway to obtain a secure communication link of the agricultural devices;

[0015] periodically collecting operation data and environmental parameters of the agricultural devices through the Internet gateway, and transmitting and encapsulating the operation data and environmental parameters through the secure communication link and to an Internet platform.

[0016] In a preferred embodiment, the device feature extraction module is configured to, when performing extraction of real-time environmental features in the cleaned raw data and degradation trends of the agricultural devices, specifically:

[0017] identifying key environmental factors and change rules in the cleaned raw data to obtain real-time environmental features of the agricultural devices;

[0018] comparing and analyzing a current operation state time sequence of the agricultural devices with historical benchmark parameters to obtain a parameter deviation mode of the agricultural devices;

[0019] based on the parameter deviation mode, matching a pre-stored mode in a typical device degradation feature library to determine a degradation trend of the agricultural devices.

[0020] In a preferred embodiment, the device health evaluation module is configured to, when performing adaptive health evaluation of historical performance data of the agricultural devices according to the degradation trend and the real-time environmental features to obtain a failure probability and a remaining service life evaluation report of the agricultural devices, specifically:

[0021] generating a multi-dimensional health evaluation benchmark of the agricultural devices based on historical performance data of the agricultural devices according to device types and working environments;

[0022] According to the real-time environmental characteristics, a performance threshold range of the agricultural equipment is obtained by matching the device performance record of the agricultural equipment under similar working conditions with the multi-dimensional health assessment benchmark;

[0023] A predicted device performance change path of the agricultural equipment is obtained by trend extrapolation of the degradation trend and the performance threshold range;

[0024] According to the relevance of the predicted device performance change path and the real-time environmental characteristics, a health assessment weight coefficient of the agricultural equipment is dynamically adjusted;

[0025] Based on the adjusted health assessment weight coefficient, the operating state and historical performance data of the agricultural equipment are fused to generate a failure probability and remaining service life assessment report of the agricultural equipment.

[0026] In a preferred embodiment, when the device health assessment module executes the fusion of the operating state and historical performance data of the agricultural equipment based on the adjusted health assessment weight coefficient to generate the failure probability and remaining service life assessment report of the agricultural equipment, it is specifically used for:

[0027] The operating state and historical performance data are mapped to corresponding positions in a multi-dimensional state space of the agricultural equipment to obtain device state coordinates of the agricultural equipment;

[0028] Based on the health assessment weight coefficient, an influence factor of each dimension is determined in the multi-dimensional state space of the agricultural equipment to obtain a health state evolution trajectory of the agricultural equipment;

[0029] A health threshold boundary is set in the multi-dimensional state space of the agricultural equipment, and a current health state deviation of the agricultural equipment is evaluated according to the relative position relationship between the device state coordinates and the health threshold boundary;

[0030] Based on the health state evolution trajectory, a dynamic trajectory simulation of the device state of the agricultural equipment is performed to obtain a risk intersection point of the agricultural equipment;

[0031] According to the distribution density of the risk intersection point and the current health state deviation, a failure probability and remaining service life assessment report of the agricultural equipment is generated.

[0032] In a preferred embodiment, when the health mapping module executes the generation of the predicted health index of the agricultural equipment according to the failure probability and remaining service life assessment report, it is specifically used for:

[0033] The failure probability is mapped to a health risk coefficient, and the remaining service life assessment report is mapped to a device performance coefficient;

[0034] determining a basic health level of the agricultural equipment based on the health risk coefficient and the equipment performance coefficient;

[0035] dynamically correcting the basic health level based on current environmental characteristics to obtain an environmental adaptability health index of the agricultural equipment;

[0036] comparing the environmental adaptability health index with historical state data of the equipment to obtain a health state evolution pattern of the agricultural equipment;

[0037] based on the health state evolution pattern, performing health development trend evaluation on the agricultural equipment to obtain a predicted health indicator of the agricultural equipment.

[0038] In a preferred embodiment, when the health mapping module performs health development trend evaluation on the agricultural equipment based on the health state evolution pattern to obtain a predicted health indicator of the agricultural equipment, it is specifically used for:

[0039] arranging the health states of the agricultural equipment in chronological order to obtain a health state sequence of the agricultural equipment;

[0040] extracting key change characteristics from the health state sequence to obtain health dynamic parameters of the agricultural equipment;

[0041] based on the health dynamic parameters, calculating a trend health value of the agricultural equipment, wherein the calculation formula of the trend health value is as follows:

[0042] ;

[0043] wherein, the trend health value, a state change rate in the health dynamic parameters, a change acceleration in the health dynamic parameters, a preset state change rate weight, an environmental adaptability factor in the health state sequence, a preset change rate weight, a preset change acceleration weight;

[0044] mapping the trend health value and the current running state of the agricultural equipment into the predicted health indicator of the agricultural equipment.

[0045] In a preferred embodiment, when the strategy generation module performs adjustment on the work sequence and resource allocation among the agricultural equipment according to the predicted health indicator and agricultural operation requirements to obtain an initial scheduling strategy of the agricultural equipment, it is specifically used for:

[0046] generating a task priority list of the agricultural equipment based on the urgency of the agricultural operation demand and the device health status in the predicted health index;

[0047] performing matching degree analysis on the predicted health index and resource requirements of tasks to be performed to obtain a device-task matching degree matrix of the agricultural equipment;

[0048] based on the device-task matching degree matrix, ensuring that the device workload of the agricultural equipment matches the health status to obtain a workload allocation scheme of the agricultural equipment;

[0049] by task reordering and resource reallocation, eliminating time conflicts and resource competition in the workload allocation scheme to obtain a conflict-free work sequence of the agricultural equipment;

[0050] integrating the task priority list, the device workload allocation scheme and the conflict-free work sequence to obtain an initial scheduling strategy of the agricultural equipment.

[0051] In a preferred embodiment, when the strategy optimization module performs local decision-making and global consensus during the agricultural equipment scheduling process, the initial scheduling strategy is optimized to obtain a device scheduling strategy of the agricultural equipment, and the method is specifically used for:

[0052] based on the health status and execution capacity of the agricultural equipment, making local optimization suggestions for task allocation in the initial scheduling strategy;

[0053] integrating the local optimization suggestions of the agricultural equipment through multiple rounds of information exchange to obtain a collaborative work willingness graph between the agricultural equipment;

[0054] according to the real-time device state changes and task execution progress of the agricultural equipment, continuously optimizing the collaborative work willingness graph;

[0055] according to the continuously optimized collaborative work willingness graph, feedback adjusting the initial scheduling strategy to obtain a device scheduling strategy of the agricultural equipment.

[0056] In order to solve the above problems, the application also provides a smart agricultural equipment management method based on Internet of Things, which comprises:

[0057] S1, connecting multiple agricultural equipment through an Internet gateway to obtain a raw data set of the agricultural equipment;

[0058] S2, extracting real-time environmental features and degradation trends of the agricultural equipment from the cleaned raw data;

[0059] S3, performing adaptive health assessment on the historical performance data of the agricultural equipment according to the degradation trend and the real-time environmental characteristics, to obtain a failure probability and remaining service life evaluation report of the agricultural equipment;

[0060] S4, generating a predictive health index of the agricultural equipment according to the failure probability and remaining service life evaluation report;

[0061] S5, adjusting a work sequence and resource allocation among the agricultural equipment according to the predictive health index and agricultural operation demand, to obtain an initial scheduling strategy of the agricultural equipment;

[0062] S6, performing scheduling optimization on the initial scheduling strategy according to local decision and global consensus in the scheduling process of the agricultural equipment, to obtain a device scheduling strategy of the agricultural equipment, and sending the device scheduling strategy to the corresponding agricultural equipment through the Internet gateway.

[0063] Compared with the prior art, the present application has the following beneficial effects:

[0064] 1. The present application can accurately obtain the data required for agricultural equipment management and realize deep analysis through the cooperation of multiple modules: the data acquisition module establishes a secure communication link with multiple agricultural equipment through the Internet gateway, periodically acquires operation data and environmental parameters, and ensures the comprehensiveness and security of the original data; the equipment feature extraction module can effectively identify key environmental factors and change rules, analyze parameter deviation patterns to determine the equipment degradation trend; the health assessment module performs adaptive assessment combined with the degradation trend and real-time environmental characteristics, and the health mapping module further generates a predictive health index, which can accurately grasp the equipment failure probability, remaining service life and health development trend, providing accurate data support for equipment management and avoiding potential operation risks in advance.

[0065] 2. The present application has significant advantages in device scheduling strategy formulation and optimization: the strategy generation module generates a task priority list, a device-task adaptation matrix and a work load allocation scheme according to the predictive health index and agricultural operation demand, eliminates time conflicts and resource competition, and ensures that the device work load and health status are matched; the strategy optimization module integrates local optimization suggestions of the equipment, continuously optimizes the collaborative work willingness graph and feeds back the adjusted scheduling strategy, realizes the cooperation of local decision and global consensus, effectively improves the rationality of work sequence and resource allocation among agricultural equipment, and finally significantly improves the overall efficiency of intelligent agricultural equipment management, ensuring the stable and orderly development of agricultural operation. BRIEF DESCRIPTION OF DRAWINGS

[0066] Figure 1 A system architecture diagram of an intelligent agricultural equipment management system based on the Internet of Things is provided for an embodiment of the present application;

[0067] Figure 2 A flowchart of a smart agricultural equipment management method based on the Internet of Things is provided for an embodiment of the present application.

[0068] The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0069] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments belong to some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0070] The terms used in the embodiments of the present application are merely for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms “the” and “said” used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. “Plural” generally includes at least two.

[0071] Depending on the context, the word “if” or “if” as used herein can be interpreted as “when” or “upon” or “in response to determining” or “in response to detecting”. Similarly, depending on the context, the phrase “if determined” or “if detecting (a stated condition or event)” can be interpreted as “when determined” or “in response to determining” or “when detecting (a stated condition or event)” or “in response to detecting (a stated condition or event)”.

[0072] In addition, the step sequence in each of the following method embodiments is only an example and is not strictly limited.

[0073] In fact, the server device deployed by the smart agricultural equipment management system based on the Internet of Things can be composed of one or more devices. The smart agricultural equipment management system based on the Internet of Things can be implemented as a business instance, a virtual machine, or a hardware device. For example, the smart agricultural equipment management system based on the Internet of Things can be implemented as a business instance deployed on one or more devices in a cloud node. In short, the smart agricultural equipment management system based on the Internet of Things can be understood as a software deployed on a cloud node, which is used to provide a smart agricultural equipment management system based on the Internet of Things for each user end. Alternatively, the smart agricultural equipment management system based on the Internet of Things can also be implemented as a virtual machine deployed on one or more devices in a cloud node. The virtual machine has application software for managing each user end. Alternatively, the smart agricultural equipment management system based on the Internet of Things can also be implemented as a server composed of a plurality of same or different types of hardware devices, and one or more hardware devices are provided to provide a smart agricultural equipment management system based on the Internet of Things for each user end.

[0074] In an implementation form, the smart agricultural equipment management system based on the Internet of Things and the user end are mutually adapted. That is, the smart agricultural equipment management system based on the Internet of Things is installed as an application on a cloud service platform, and the user end is a client that establishes a communication connection with the application; or the smart agricultural equipment management system based on the Internet of Things is implemented as a website, and the user end is implemented as a webpage; or the smart agricultural equipment management system based on the Internet of Things is implemented as a cloud service platform, and the user end is implemented as an applet in an instant messaging application.

[0075] As shown in Figure 1 FIG. 1 is a system architecture diagram of a smart agricultural equipment management system based on the Internet of Things according to an embodiment of the present application.

[0076] The smart agricultural equipment management system based on the Internet of Things 100 can be set in a cloud server, and in an implementation form, can be one or more service devices, or can be installed as an application on a cloud (such as a server of a mobile service operator, a server cluster, etc.), or can be developed as a website. According to the functions implemented, the smart agricultural equipment management system based on the Internet of Things 100 can include a data acquisition module 101, a device feature extraction module 102, a device health assessment module 103, a health mapping module 104, a strategy generation module 105, and a strategy optimization module 106. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, and are stored in the memory of the electronic device.

[0077] In the embodiment of the present application, each of the above modules can be independently implemented and called by other modules. The calling here can be understood as that a module can be connected to multiple modules of another type and provide corresponding services for the connected multiple modules. The embodiment of the present application provides a smart agricultural equipment management system based on Internet of Things, which can adjust the application range of the architecture of the smart agricultural equipment management system based on Internet of Things by increasing modules and directly calling without modifying program codes, realizes cluster horizontal expansion, and achieves the purpose of quickly and flexibly expanding the smart agricultural equipment management system based on Internet of Things. In actual application, the above modules can be arranged in the same device or different devices, or in a virtual device, such as a service instance in a cloud server.

[0078] The following will describe each component and specific work flow of the smart agricultural equipment management system based on Internet of Things in combination with specific embodiments.

[0079] The data acquisition module 101 is configured to connect multiple agricultural equipment through an Internet gateway to obtain a raw data set of the agricultural equipment.

[0080] In the embodiment of the present application, when the data acquisition module connects multiple agricultural equipment through an Internet gateway to obtain a raw data set of the agricultural equipment, it is specifically configured to:

[0081] send a link request to the agricultural equipment;

[0082] receive device identification and initial state data returned by the agricultural equipment based on the Internet gateway to obtain a secure communication link of the agricultural equipment;

[0083] periodically collect running data and environmental parameters of the agricultural equipment through the Internet gateway, and transmit and encapsulate the running data and environmental parameters through the secure communication link and to an Internet platform.

[0084] Specifically, the Internet platform organizes link request data containing a connection intention in a protocol format based on a TCP / IP protocol, and sends out the data through a forwarding channel of the Internet gateway, and directly directs to the target agricultural equipment.

[0085] Further, the Internet platform receives feedback data of the agricultural equipment forwarded by the Internet gateway, which explicitly contains device identification and initial state data. The platform compares and confirms the consistency of the received device identification and the pre-stored agricultural equipment identity information, and confirms that the device is ready for communication based on the initial state data. Then, the platform establishes a dedicated encrypted transmission channel through the Internet gateway, which is the secure communication link of the agricultural equipment.

[0086] Further, the Internet platform sends collection instructions to the Internet gateway at preset fixed time intervals, the Internet gateway establishes a temporary data interaction connection with the agricultural equipment after receiving the instructions, extracts the operation data and environmental parameters recorded in real time by the agricultural equipment, then arranges these data into a fixed format data packet according to the transmission specification of the secure communication link, encodes and converts the data packet content using a symmetric encryption method to complete encapsulation, and then continuously transmits the encapsulated data packet to the Internet platform through the established secure communication link.

[0087] In general, connecting multiple agricultural equipment through the Internet gateway to obtain a collection of raw data has many significant beneficial effects. It can break down the communication barriers between different agricultural equipment, realize the centralized access of various equipment through multi-protocol compatibility, eliminate the "device island" problem, ensure the comprehensive convergence of data of different types of equipment such as soil sensors, irrigation equipment, servo machinery, and form a complete data foundation covering the running state of the equipment and environmental parameters.

[0088] In general, the stable communication characteristics of the gateway ensure the real-time and integrity of the raw data, and the edge side data preprocessing capability can eliminate abnormal fluctuation data, greatly improve the data efficiency, and provide accurate data source for subsequent feature extraction, health assessment and other links. At the same time, the gateway is designed to adapt to the wide temperature and anti-interference of the complex agricultural environment, can maintain long-term stable data collection, and the encryption transmission mechanism can guarantee data security, laying a core data support for the precision and intelligence of intelligent agricultural equipment management.

[0089] The device feature extraction module 102 is configured to extract real-time environmental features and degradation trends of the agricultural equipment from the cleaned raw data.

[0090] In the embodiment of the present application, when the device feature extraction module extracts real-time environmental features and degradation trends of the agricultural equipment from the cleaned raw data, it is specifically used for:

[0091] Identifying key environmental factors and change rules in the cleaned raw data to obtain real-time environmental features of the agricultural equipment.

[0092] Comparing and analyzing the current running state time sequence of the agricultural equipment with historical benchmark parameters to obtain a parameter offset mode of the agricultural equipment.

[0093] Based on the parameter offset mode, matching a pre-stored mode in a typical device degradation feature library to determine the degradation trend of the agricultural equipment.

[0094] Specifically, the environmental data in the original data after cleaning is classified and sorted, and the environmental data items directly related to the operation of the agricultural equipment are screened out as key environmental factors. The numerical increase and decrease direction, fluctuation amplitude and duration of these key environmental factors are sorted in chronological order. The key environmental factors and their changes are integrated to form the real-time environmental characteristics of the agricultural equipment.

[0095] Further, the operation state data recorded in chronological order by the agricultural equipment is extracted to form a time sequence, and the historical data accumulated during the normal operation stage of the equipment is retrieved as a historical reference parameter. The data in the time sequence is compared with the data in the historical reference parameter corresponding to each time period, and the differences in the numerical value and change rhythm are recorded. The differences are systematically integrated to obtain the parameter deviation mode of the agricultural equipment.

[0096] Further, a pre-constructed typical equipment degradation feature library is retrieved, which stores the equipment operation parameter change mode corresponding to different degradation stages. The obtained parameter deviation mode is compared with all pre-stored modes in the library one by one, and the pre-stored mode that completely matches the core features is found. According to the equipment degradation stage corresponding to the matched pre-stored mode, the degradation trend of the agricultural equipment is determined.

[0097] In summary, by identifying the key environmental factors and changes in the original data after cleaning to obtain real-time environmental characteristics, the dynamic changes of the environment in which the equipment is located can be accurately captured, providing accurate environmental dimension basis for the subsequent health assessment module to match similar working conditions and determine the performance threshold range. Ensure that the influence of environmental factors on the health status of the equipment is fully considered in the evaluation system, and avoid inaccurate health assessment due to missing or biased environmental information.

[0098] In summary, by comparing the time sequence of the current operation state of the equipment with the historical reference parameter to obtain the parameter deviation mode, and matching the typical equipment degradation feature library to determine the degradation trend, the specific direction and degree of performance degradation of the equipment can be accurately located, and the evolution trajectory of the performance of the equipment from normal to degradation can be clearly presented. Provide core trend data support for the subsequent prediction of equipment performance change path, generation of failure probability and remaining useful life evaluation report, help to perceive potential performance risks of the equipment in advance, and lay a reliable foundation for subsequent equipment scheduling and maintenance decision-making.

[0099] The device health assessment module 103 is configured to perform adaptive health assessment on the historical performance data of the agricultural equipment according to the degradation trend and the real-time environmental characteristics, and obtain a failure probability and a remaining useful life evaluation report of the agricultural equipment.

[0100] In the embodiment of the present application, when the device health assessment module performs adaptive health assessment on historical performance data of the agricultural equipment according to the degradation trend and the real-time environmental characteristics, to obtain a failure probability and a remaining service life assessment report of the agricultural equipment, it is specifically used for:

[0101] generating a multi-dimensional health assessment benchmark of the agricultural equipment based on historical performance data of the agricultural equipment according to equipment types and working environments;

[0102] According to the real-time environmental characteristics, matching the device performance records of the agricultural equipment under similar working conditions with the multi-dimensional health assessment benchmark, to obtain a performance threshold range of the agricultural equipment;

[0103] trend extrapolation of the degradation trend and the performance threshold range, to obtain a predicted device performance change path of the agricultural equipment;

[0104] According to the relevance of the predicted device performance change path and the real-time environmental characteristics, dynamically adjusting the health assessment weight coefficient of the agricultural equipment;

[0105] Based on the adjusted health assessment weight coefficient, the running state and the historical performance data of the agricultural equipment are fused to generate a failure probability and a remaining service life assessment report of the agricultural equipment.

[0106] In the embodiment of the present application, when the device health assessment module performs adaptive health assessment on historical performance data of the agricultural equipment according to the degradation trend and the real-time environmental characteristics, to obtain a failure probability and a remaining service life assessment report of the agricultural equipment, it is specifically used for:

[0107] Mapping the running state and the historical performance data to corresponding positions in a multi-dimensional state space of agricultural equipment, to obtain a device state coordinate of the agricultural equipment;

[0108] Based on the health assessment weight coefficient, determining the influence factor of each dimension in the multi-dimensional state space of the agricultural equipment, to obtain a health state evolution track of the agricultural equipment;

[0109] Setting a health threshold boundary in the multi-dimensional state space of the agricultural equipment, and according to the relative position relationship between the device state coordinate and the health threshold boundary, assessing the current health state deviation of the agricultural equipment;

[0110] Based on the health state evolution track, dynamically simulating the device state of the agricultural equipment to obtain a risk intersection point of the agricultural equipment;

[0111] According to the distribution density of the risk intersection point and the current health state deviation degree, a failure probability and a remaining service life evaluation report of the agricultural equipment are generated.

[0112] Specifically, historical performance data of the agricultural equipment in the whole life cycle is called, classified according to the specific type of the equipment, and then grouped again according to the actual working environment conditions of the equipment. The core features of the data in each group are extracted from multiple dimensions such as running stability, component wear degree and environmental adaptability. These features are integrated according to a unified standard to form a multi-dimensional health evaluation benchmark of the agricultural equipment.

[0113] Further, the acquired real-time environmental features are compared with each type of working condition recorded in the multi-dimensional health evaluation benchmark one by one, and similar working conditions that completely match the current real-time environmental features are screened out. The corresponding complete equipment performance records under these similar working conditions are extracted, the performance extreme values and normal fluctuation intervals in these records are counted, and the performance threshold range of the agricultural equipment is determined accordingly.

[0114] Further, based on the degradation trend as the basis direction, combined with the upper and lower boundary limits of the performance threshold range, the possible values of the equipment performance in future different time periods are extended and deduced in time sequence. These deduced performance values are connected in time sequence to form a predicted equipment performance change path of the agricultural equipment.

[0115] Further, the mutual influence degree of each performance node in the predicted equipment performance change path and each factor in the real-time environmental features is analyzed. When the change of a factor in the real-time environmental features causes obvious fluctuation of the predicted performance, the weight coefficient of the corresponding health evaluation dimension of the factor is increased, otherwise the weight coefficient of the corresponding dimension is decreased, and the dynamic adjustment of the health evaluation weight coefficient is completed.

[0116] Further, based on the adjusted health evaluation weight coefficient, the current running state data and the historical performance data of the agricultural equipment are given corresponding influence weight. The current running state data reflects the immediate condition of the equipment, and the historical performance data provides long-term reference. The two are combined to judge the possibility of equipment failure and the length of time that the equipment can still work normally. These judgment results are systematically arranged to form a failure probability and a remaining service life evaluation report of the agricultural equipment.

[0117] Specifically, the current running state data and the historical performance data of the agricultural equipment are extracted, the definitions of each dimension of the multi-dimensional state space of the agricultural equipment are determined, each dimension corresponds to a core evaluation index of the equipment running, and the running state data and the historical performance data are respectively corresponded to each dimension of the multi-dimensional state space. The specific position of each data in the corresponding dimension is determined, and the position information in all dimensions is integrated to obtain the equipment state coordinates of the agricultural equipment.

[0118] Further, according to the adjusted health evaluation weight coefficient, dimensions with weight coefficients higher than a set standard are screened out as core influence dimensions, and specific data items directly related to the health state of the equipment in each core influence dimension are the influence factors of each dimension. The equipment state coordinates of different time periods are extracted in chronological order, and these coordinates are sequentially connected to form a continuous path, which is the health state evolution trajectory of the agricultural equipment.

[0119] Further, with reference to historical health running data of the agricultural equipment and industry standards, the normal value range of each dimension is determined in the multi-dimensional state space of the agricultural equipment. These ranges together constitute a closed health threshold boundary. The current obtained equipment state coordinates are compared with the health threshold boundary to determine whether the coordinates are inside, above or outside the boundary. The distance between the coordinates and the normal region of the boundary is quantitatively calculated, which is the current health state deviation of the agricultural equipment.

[0120] Further, based on the trend and rate of change of the health state evolution trajectory, the possible positions of the future equipment state coordinates are simulated in chronological order by extending the change law of the trajectory. The dynamic simulation trajectory is formed by sequentially connecting the simulated future state coordinates. The specific positions in the dynamic simulation trajectory that intersect with the health threshold boundary or enter the risk area outside the boundary are the risk intersection points of the agricultural equipment.

[0121] Further, the distribution density of the risk intersection points is obtained by counting the number of risk intersection points in a unit time. Combined with the size of the current health state deviation, the higher the distribution density, the greater the deviation, and the higher the possibility of failure. According to the time when the risk intersection point first appears in the dynamic simulation trajectory and the length of the subsequent extension of the trajectory, the time that the equipment can still maintain normal operation is determined. The system integrates the possibility of failure and the remaining service life to form a failure probability and remaining service life evaluation report of the agricultural equipment.

[0122] In summary, the adaptive health evaluation method has significant beneficial effects. It can deeply integrate degradation trend, real-time environmental characteristics and historical performance data to ensure accurate evaluation results that are consistent with the actual operation scenario of the equipment. It first generates multi-dimensional health evaluation benchmarks according to the type of equipment and working environment, and then matches the performance records of similar working conditions to determine the performance threshold range, avoiding evaluation deviation caused by deviation from the actual working conditions. By extrapolating the degradation trend and performance threshold range, the performance change path of the equipment can be clearly predicted. In addition, the health evaluation weight coefficient can be dynamically adjusted combined with real-time environmental characteristics to achieve efficient integration of running state and historical data.

[0123] In general, the finally generated failure probability and remaining service life evaluation report can accurately reflect the device health state and potential risks, provide reliable data support for the subsequent health mapping module to generate predicted health indicators, and provide key basis for subsequent scheduling strategy formulation, helping to perceive device failure hidden dangers in advance, guaranteeing stable operation of agricultural equipment, and improving the scientificity and forward-looking nature of intelligent agricultural equipment management.

[0124] The health mapping module 104 is configured to generate predicted health indicators of the agricultural equipment according to the failure probability and remaining service life evaluation report.

[0125] In the embodiment of the present application, when the health mapping module generates predicted health indicators of the agricultural equipment according to the failure probability and remaining service life evaluation report, it is specifically configured to:

[0126] The failure probability is mapped to a health risk coefficient, and the remaining service life evaluation report is mapped to a device performance coefficient;

[0127] The health risk coefficient and the device performance coefficient are used to determine the basic health level of the agricultural equipment;

[0128] The basic health level is dynamically corrected based on the current environmental characteristics to obtain an environmental adaptability health index of the agricultural equipment;

[0129] The environmental adaptability health index is compared with the historical state data of the device to obtain a health state evolution mode of the agricultural equipment;

[0130] Based on the health state evolution mode, the health development trend of the agricultural equipment is evaluated to obtain the predicted health indicators of the agricultural equipment.

[0131] In the embodiment of the present application, when the health mapping module generates predicted health indicators of the agricultural equipment based on the health state evolution mode, it is specifically configured to:

[0132] The health state of the agricultural equipment is arranged in chronological order to obtain a health state sequence of the agricultural equipment;

[0133] Key change features are extracted from the health state sequence to obtain health dynamic parameters of the agricultural equipment;

[0134] Based on the health dynamic parameters, a trend health value of the agricultural equipment is calculated, and the calculation formula of the trend health value is as follows:

[0135] ;

[0136] In the formula, a trend health value, a state change rate in the health dynamic parameter, a change acceleration in the health dynamic parameter, a preset state change rate weight, an environmental fitness factor in the health state sequence, a preset change rate weight, a preset change acceleration weight;

[0137] mapping a predicted health indicator of the agricultural equipment according to the trend health value and a current operation state of the agricultural equipment.

[0138] Specifically, a failure probability of the agricultural equipment is extracted, and different numerical values of the failure probability are corresponded to specific health risk coefficients according to a fixed mapping rule, and the higher the numerical value of the failure probability is, the greater the corresponding health risk coefficient is. Meanwhile, core data in a remaining service life evaluation report is extracted, and a corresponding relationship is set according to the length of the remaining service life, and the longer the remaining service life is, the higher the equipment performance coefficient is. The health risk coefficient and the equipment performance coefficient are obtained by completing the two mappings.

[0139] Further, a division standard of a basic health level is set, which clearly shows the level interval corresponding to the combination of different health risk coefficients and equipment performance coefficients. The obtained health risk coefficient and equipment performance coefficient are substituted into the division standard, and a completely matched level interval is found. The level corresponding to the interval is the basic health level of the agricultural equipment.

[0140] Further, the influence degree of each factor in the current environmental characteristics on the operation of the agricultural equipment is analyzed. If the current environment is a working condition suitable for the operation of the equipment, the value corresponding to the basic health level is appropriately increased. If the current environment has factors such as high temperature and high humidity that are not conducive to the operation of the equipment, the value corresponding to the basic health level is correspondingly reduced. After such adjustment, the environmental adaptability health index of the agricultural equipment is obtained.

[0141] Further, the health-related indices of each period in the historical state data of the agricultural equipment are retrieved, and are arranged in time sequence to form a historical health trend curve. The current environmental adaptability health index is embedded in the curve. The change direction and change rate of the current index and the historical index are compared, and the change rule of the health state of the equipment with time is summarized. The rule is the health state evolution mode of the agricultural equipment.

[0142] Further, according to the change trend of the health state evolution mode, the development logic of the mode is continued to deduce the possible values of the equipment health indices in future time periods. These deduced future health indices are integrated in time sequence to form the predicted health indicator of the agricultural equipment.

[0143] Specifically, the health state data actually recorded by the agricultural equipment in each period is extracted, arranged in the order of time of data recording, and ensured that each health state data corresponds to a unique time node, forming a continuous and complete health state sequence of the agricultural equipment.

[0144] Further, the numerical value change of the health state in the health state sequence is analyzed segment by segment, and the mutation point of the health state value, the change trend direction of the continuous rise or fall, the duration of the change, and the interval range of the stable fluctuation in the sequence are identified. These core information reflecting the dynamic change of the health state are integrated and refined to obtain the health dynamic parameters of the agricultural equipment.

[0145] Further, referring to the change trend direction in the health dynamic parameters, if the trend is health improvement, it is included in the positive influence factor, if the trend is health decline, it is included in the negative influence factor, the cumulative degree of influence is judged according to the duration of the change, the strength level of the influence is determined according to the change amplitude, and a specific value reflecting the overall health development trend is determined by comprehensively considering these factors. The value is the trend health value of the agricultural equipment.

[0146] Further, the corresponding mapping rule of the trend health value and the current running state of the agricultural equipment is set, the rule clearly defines the corresponding prediction results of different ranges of trend health values and different combinations of running states, the calculated trend health value is matched with the real-time collected current running state of the agricultural equipment, and the corresponding specific index is determined according to the matching result. The index is the predicted health index of the agricultural equipment.

[0147] Specifically, the state change rate comes from the health dynamic parameters, the change acceleration is obtained by extracting the key change characteristics from the health state sequence, the environment adaptability factor is directly obtained from the health state sequence, the change rate weight is a fixed value set in advance, and the change acceleration weight is also a fixed value set in advance.

[0148] Further, the state change rate in the health dynamic parameters is multiplied by the preset change rate weight, and then the change acceleration in the health dynamic parameters is multiplied by the preset change acceleration weight. The results of the two multiplications are added, and the added result is multiplied by the environment adaptability factor in the health state sequence. Through such continuous operation, the influences of the state change rate, the change acceleration, the environment adaptability factor, and the corresponding preset weights are integrated and integrated. Finally, the trend health value reflecting the development trend of the health of the agricultural equipment is obtained.

[0149] Further, when the state change rate increases in the direction of health improvement, the trend health value will increase accordingly, when the change acceleration presents a positive direction and the value increases, it will further push the trend health value to increase, when the environmental fitness factor value increases, it will also increase the trend health value, when the change rate weight or the change acceleration weight is set higher, the corresponding state change rate or change acceleration will have a stronger influence on the trend health value, on the contrary, when the state change rate decreases in the direction of health decline, the change acceleration presents a negative direction and the value increases, or the environmental fitness factor value decreases, it will cause the trend health value to decrease.

[0150] In general, by mapping the failure probability to the health risk coefficient and the remaining service life evaluation report to the equipment performance coefficient, the standardized conversion of the evaluation results can be realized, and the judgment deviation caused by the dispersion of the original report information can be avoided, and then combined with the dynamic correction of the basic health level according to the current environmental characteristics, the health index can be fully adapted to the actual operation environment of the equipment, and the matching degree of the index and the real health state of the equipment is improved.

[0151] In general, by comparing and analyzing the health state evolution mode with the historical state data of the equipment, and calculating the trend health value based on the health dynamic parameters, the dynamic prediction of the health state of the equipment can be realized, instead of only being limited to the current state evaluation, and the health change law can be perceived in advance.

[0152] In general, the generated predicted health index can directly provide accurate data support for the task priority of the strategy generation module, the equipment, the task adaptation scheme and the work load allocation, guarantee the scientific and reasonable subsequent equipment scheduling strategy, and help to improve the forward-looking and effectiveness of intelligent agricultural equipment management.

[0153] The strategy generation module 105 is configured to adjust the work sequence and resource allocation among the agricultural equipment according to the predicted health index and the agricultural operation demand, to obtain an initial scheduling strategy of the agricultural equipment.

[0154] In the embodiment of the present application, when the strategy generation module executes the adjustment of the work sequence and resource allocation among the agricultural equipment according to the predicted health index and the agricultural operation demand, to obtain the initial scheduling strategy of the agricultural equipment, it is specifically used for:

[0155] generating a task priority list of the agricultural equipment based on the urgency of the agricultural operation demand and the equipment health state in the predicted health index;

[0156] performing matching degree analysis on the predicted health index and the resource demand of the to-be-executed task, to obtain a device-task adaptation degree matrix of the agricultural equipment;

[0157] Based on the device-task adaptability matrix, the device workload of the agricultural device is ensured to match the health state, so as to obtain a workload allocation scheme of the agricultural device;

[0158] By task reordering and resource reallocation, time conflicts and resource competition in the workload allocation scheme are eliminated to obtain a conflict-free work sequence of the agricultural device;

[0159] The task priority list, the device workload allocation scheme and the conflict-free work sequence are integrated to obtain an initial scheduling strategy of the agricultural device.

[0160] Specifically, the urgency level of each agricultural operation requirement is determined according to the agricultural time requirement and operation timeliness of agricultural production, the device health state reflecting the current stable operation of the device is extracted from the predicted health index, the operation requirement with high urgency level is preferentially matched with the agricultural device with good health state, and the operation requirement with low urgency level is correspondingly matched with the device with suitable health state. All tasks to be executed are arranged in order of urgency level from high to low and device health state adaptability from strong to weak to form a task priority list of the agricultural device.

[0161] Further, the resource types required by the tasks to be executed are sorted, including power output requirement operation time and demand environment tolerance range, the device capability data related to resource demand in the predicted health index is extracted, each resource demand of each task to be executed is compared with the corresponding capability of the health index of the agricultural device, the fitting degree of the two is judged and the adaptation result is determined, and the adaptation results of all tasks and devices are arranged in row and column form, with row and column corresponding to the dimensions of the tasks to be executed and the device capability respectively, to form a device-task adaptability matrix of the agricultural device.

[0162] Further, according to the adaptation results of each task and device in the device-task adaptability matrix, the maximum workload that the device can bear is determined in combination with the health state of the agricultural device, the task with high adaptability degree and moderate load is allocated to the device with good health state, the task with standard adaptability degree and low load is allocated to the device with general health state, the device is prevented from bearing work beyond the bearing range of the health state, the corresponding device and the allocated load proportion of each task are determined, and a workload allocation scheme of the agricultural device is formed.

[0163] Further, the execution time and required resources of each task in the work load allocation scheme are checked one by one, time conflicts of multiple tasks performed by the same device in the same time period and resource competition of multiple tasks simultaneously competing for the same resource are identified, the execution order of the tasks is adjusted according to the order of the task priority list, the resource demand of the high-priority task is preferentially guaranteed, the execution time and required resources of the low-priority task are re-allocated, it is ensured that each device only performs one task at the same time and the resource supply does not conflict, and a conflict-free work sequence of the agricultural device arranged in time sequence is arranged.

[0164] Further, the task priority list is integrated with the task importance sorting, the device load allocation determined by the work load allocation scheme, the time arrangement and resource configuration planned by the conflict-free work sequence, to ensure that the three are completely consistent in task execution order and load bearing resource supply, and a complete content including task execution order, device load allocation standard, time arrangement and detailed resource configuration scheme is formed. The content is the initial scheduling strategy of the agricultural device.

[0165] In summary, the task priority list is generated based on the urgency of agricultural operation demand and the health status of the device, which can ensure that critical agricultural operations are prioritized, while avoiding devices with poor health status from bearing high load tasks; the device is constructed by matching the predicted health index and task resource demand, and the task adaptation degree matrix can accurately correspond the device capacity and task demand, reducing resource waste and task execution deviation.

[0166] In summary, the work load allocation scheme is formulated according to the adaptation degree matrix and the health status of the device, which can effectively avoid the risk of device failure caused by overload operation and prolong the service life of the device; the conflict-free work sequence is formed by eliminating time conflicts and resource competition, which can guarantee the orderliness of multi-device collaborative work and avoid scheduling confusion affecting the progress of agricultural operation. The final integrated initial scheduling strategy provides a reasonable basis for subsequent strategy optimization, helps to improve the accuracy and efficiency of intelligent agricultural device scheduling, and ensures the stable progress of agricultural production.

[0167] The strategy optimization module 106 is configured to perform scheduling optimization on the initial scheduling strategy according to local decisions and global consensus in the agricultural device scheduling process, to obtain a device scheduling strategy of the agricultural device, and send the device scheduling strategy to the corresponding agricultural device through the Internet gateway.

[0168] In the embodiment of the present application, when the strategy optimization module performs scheduling optimization on the initial scheduling strategy according to local decisions and global consensus in the agricultural device scheduling process to obtain a device scheduling strategy of the agricultural device, it is specifically used for:

[0169] Based on the self-health state and execution ability of the agricultural equipment, local optimization suggestions are proposed for task allocation in the initial scheduling strategy;

[0170] Through multiple rounds of information exchange, the local optimization suggestions of the agricultural equipment are integrated to obtain a collaborative work willingness graph among the agricultural equipment;

[0171] According to the real-time equipment state changes and task execution progress of the agricultural equipment, the collaborative work willingness graph is continuously optimized;

[0172] According to the continuously optimized collaborative work willingness graph, feedback adjustment is performed on the initial scheduling strategy to obtain the equipment scheduling strategy of the agricultural equipment.

[0173] Specifically, actual execution feedback and real-time operation adjustment requirements of each local work area in the agricultural equipment scheduling process are collected, which constitute local decisions, and overall agricultural production targets and resource allocation principles are summarized to form global consensus. The initial scheduling strategy is compared with the local decisions, and the contents inconsistent with the actual execution conditions are revised. The revised contents are audited according to the global consensus to ensure that they meet the overall production planning and resource allocation requirements. After local adaptation and global calibration, the equipment scheduling strategy of the agricultural equipment is obtained.

[0174] Further, the equipment scheduling strategy is classified and arranged according to the unique identifier of each agricultural equipment to ensure that the scheduling strategy content corresponding to each equipment is complete and accurate. The classified scheduling strategy is converted into a standard transmission format according to the transmission specification of the Internet gateway, and the converted scheduling strategy data is sent to the Internet gateway through the established secure communication link. After receiving the data, the Internet gateway queries the corresponding network address according to the equipment identifier and forwards the scheduling strategy to the corresponding agricultural equipment, ensuring that the equipment successfully receives the complete scheduling strategy.

[0175] In summary, the optimization of scheduling strategy by combining local decisions and global consensus and the accurate delivery have multiple key beneficial effects. From the individual dimension of the equipment, based on the self-health state and execution ability of the agricultural equipment, local optimization suggestions are proposed, which can make the scheduling adjustment deeply adapt to the actual operation requirements of single equipment, avoid overloading operation or idle capacity caused by ignoring individual differences of equipment in unified scheduling, and ensure the safety of equipment operation and the adaptability of task execution.

[0176] Overall, from the multi-device collaboration dimension, through multiple rounds of information exchange, the local suggestions of each device are integrated to form a collaborative work willingness graph, which can effectively resolve the resource competition and task connection contradictions between devices, achieve global optimal allocation of tasks and resources, and avoid scheduling chaos caused by local decision fragmentation. At the same time, combined with the real-time state change of the device and the continuous optimization of the task execution progress, the graph is fed back and adjusted, which can make the scheduling scheme dynamically adapt to the working condition fluctuation and avoid the lag problem of static strategy. Finally, through the Internet gateway, the optimized scheduling strategy is accurately issued to ensure that the scheme is efficiently implemented and effectively improve the flexibility, collaboration and execution efficiency of intelligent agricultural equipment scheduling, and ensure the stable and orderly progress of agricultural operation.

[0177] Referring to Figure 2 The flowchart of the intelligent agricultural equipment management method provided by an embodiment of the application is shown. In this embodiment, the intelligent agricultural equipment management method based on the Internet of Things comprises the following steps:

[0178] S1, connecting multiple agricultural devices through an Internet gateway to obtain a raw data set of the agricultural devices;

[0179] S2, extracting real-time environmental features and degradation trends of the agricultural devices from the cleaned raw data;

[0180] S3, performing adaptive health assessment on historical performance data of the agricultural devices according to the degradation trends and the real-time environmental features, to obtain a failure probability and a remaining service life evaluation report of the agricultural devices;

[0181] S4, generating a predicted health index of the agricultural devices according to the failure probability and the remaining service life evaluation report;

[0182] S5, adjusting the work sequence and resource allocation among the agricultural devices according to the predicted health index and the agricultural operation demand, to obtain an initial scheduling strategy of the agricultural devices;

[0183] S6, performing scheduling optimization on the initial scheduling strategy according to local decisions and global consensus during the scheduling process of the agricultural devices, to obtain a device scheduling strategy of the agricultural devices, and sending the device scheduling strategy to the corresponding agricultural devices through the Internet gateway.

[0184] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0185] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. The artificial intelligence is a theory, method, technology and application system for simulating, extending and expanding human intelligence by using a digital computer or a machine controlled by a digital computer, perceiving an environment, acquiring knowledge and using the knowledge to obtain optimal results.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An Internet of Things-based intelligent agricultural equipment management system, characterized in that, The system comprises a data collection module, a device feature extraction module, a device health evaluation module, a health mapping module, a strategy generation module and a strategy optimization module, wherein: The data collection module is configured to connect multiple agricultural devices through an Internet gateway to obtain a raw data set of the agricultural devices; The device feature extraction module is configured to extract real-time environmental features and degradation trends of the agricultural devices from the cleaned raw data; The device health evaluation module is configured to perform adaptive health evaluation on historical performance data of the agricultural devices according to the degradation trends and the real-time environmental features, to obtain a failure probability and a remaining service life evaluation report of the agricultural devices; The health mapping module is configured to generate a predicted health index of the agricultural devices according to the failure probability and the remaining service life evaluation report; The strategy generation module is configured to adjust the work sequence and resource allocation among the agricultural devices according to the predicted health index and agricultural operation requirements, to obtain an initial scheduling strategy of the agricultural devices; The strategy optimization module is configured to perform scheduling optimization on the initial scheduling strategy according to local decisions and global consensus in the agricultural device scheduling process, to obtain a device scheduling strategy of the agricultural devices, and transmit the device scheduling strategy to the corresponding agricultural devices through the Internet gateway.

2. The smart agriculture device management system based on the Internet of Things according to claim 1, wherein, When the data collection module is executed to connect multiple agricultural devices through an Internet gateway to obtain a raw data set of the agricultural devices, it is specifically configured to: send a link request to the agricultural devices; receive device identifiers and initial state data returned by the agricultural devices based on the Internet gateway to obtain a secure communication link of the agricultural devices; periodically collect running data and environmental parameters of the agricultural devices through the Internet gateway, and transmit the running data and environmental parameters to an Internet platform through the secure communication link.

3. The IoT-based smart agriculture equipment management system of claim 1, wherein When the device feature extraction module is executed to extract real-time environmental features and degradation trends of the agricultural devices from the cleaned raw data, it is specifically configured to: identify key environmental factors and change patterns in the cleaned raw data to obtain real-time environmental features of the agricultural devices; compare and analyze the current running state time sequence of the agricultural devices with historical benchmark parameters to obtain a parameter deviation mode of the agricultural devices; based on the parameter deviation mode, match a pre-stored mode in a typical device degradation feature library to determine the degradation trend of the agricultural devices.

4. The smart agriculture device management system based on the Internet of Things of claim 1, wherein, When the device health evaluation module is executed to perform adaptive health evaluation on historical performance data of the agricultural devices according to the degradation trends and the real-time environmental features, to obtain a failure probability and a remaining service life evaluation report of the agricultural devices, it is specifically configured to: generate a multi-dimensional health evaluation benchmark of the agricultural devices based on the historical performance data of the agricultural devices according to device types and working environments; according to the real-time environmental features, match device performance records of the agricultural devices under similar working conditions with the multi-dimensional health evaluation benchmark to obtain a performance threshold range of the agricultural devices; trend extrapolation of the degradation trend and the performance threshold range, to obtain a predicted device performance change path of the agricultural equipment; dynamic adjustment of a health evaluation weight coefficient of the agricultural equipment according to relevance between the predicted device performance change path and the real-time environmental feature; generating a failure probability and a remaining service life evaluation report of the agricultural equipment based on the adjusted health evaluation weight coefficient, and fusing the running state and the historical performance data of the agricultural equipment.

5. The IoT-based smart agriculture equipment management system of claim 4, wherein In the execution of generating the failure probability and the remaining service life evaluation report of the agricultural equipment based on the adjusted health evaluation weight coefficient, and fusing the running state and the historical performance data of the agricultural equipment, the device health evaluation module is specifically used for: mapping the running state and the historical performance data to corresponding positions in an agricultural equipment multi-dimensional state space, to obtain a device state coordinate of the agricultural equipment; determining an influence factor of each dimension in the agricultural equipment multi-dimensional state space based on the health evaluation weight coefficient, to obtain a health state evolution track of the agricultural equipment; setting a health threshold boundary in the agricultural equipment multi-dimensional state space, and evaluating a current health state deviation of the agricultural equipment according to a relative positional relationship between the device state coordinate and the health threshold boundary; dynamically simulating a device state of the agricultural equipment based on the health state evolution track, to obtain a risk intersection point of the agricultural equipment; generating the failure probability and the remaining service life evaluation report of the agricultural equipment according to a distribution density of the risk intersection point and the current health state deviation.

6. The IoT-based smart agriculture equipment management system of claim 1, wherein In the execution of generating a predicted health index of the agricultural equipment according to the failure probability and the remaining service life evaluation report, the health mapping module is specifically used for: mapping the failure probability as a health risk coefficient, and mapping the remaining service life evaluation report as a device efficiency coefficient; determining a basic health level of the agricultural equipment based on the health risk coefficient and the device efficiency coefficient; dynamically correcting the basic health level based on a current environmental feature, to obtain an environmental adaptability health index of the agricultural equipment; comparing the environmental adaptability health index with device historical state data in a trend, to obtain a health state evolution mode of the agricultural equipment; performing a health development trend evaluation on the agricultural equipment based on the health state evolution mode, to obtain the predicted health index of the agricultural equipment.

7. The IoT-based smart agriculture equipment management system of claim 6, wherein In the execution of performing the health development trend evaluation on the agricultural equipment based on the health state evolution mode, to obtain the predicted health index of the agricultural equipment, the health mapping module is specifically used for: arranging health states of the agricultural equipment in chronological order, to obtain a health state sequence of the agricultural equipment; extracting key change features from the health state sequence, to obtain health dynamic parameters of the agricultural equipment; calculating a trend health value of the agricultural equipment based on the health dynamic parameters, wherein a calculation formula of the trend health value is as follows: ； wherein, is the trend health value, is a rate of state change in the health dynamic parameter, is an acceleration of change in the health dynamic parameter, is a preset rate of state change weight, is an environmental fitness factor in the health state sequence, is a preset rate of change weight, a preset acceleration of change weight; mapping the trend health value and a current running state of the agricultural equipment as the predicted health index of the agricultural equipment. 8.The IoT-based smart agriculture device management system of claim 1, wherein, The strategy generation module, when performing adjustment on the work sequence and resource allocation among the agricultural devices according to the predicted health indicators and agricultural operation requirements to obtain an initial scheduling strategy of the agricultural devices, is specifically configured to: generate a task priority list of the agricultural devices based on the urgency of the agricultural operation requirements and the device health status in the predicted health indicators; perform matching degree analysis on the predicted health indicators and resource requirements of tasks to be executed to obtain a device-task adaptability matrix of the agricultural devices; ensure that the device workloads of the agricultural devices are matched with the health status based on the device-task adaptability matrix to obtain a work load allocation scheme of the agricultural devices; eliminate time conflicts and resource competitions in the work load allocation scheme through task reordering and resource reallocation to obtain a conflict-free work sequence of the agricultural devices; and integrate the task priority list, the device work load allocation scheme, and the conflict-free work sequence to obtain the initial scheduling strategy of the agricultural devices. 9.The IoT-based smart agriculture device management system of claim 1, wherein, The strategy optimization module, when performing scheduling optimization on the initial scheduling strategy according to local decisions and global consensus in the scheduling process of the agricultural devices to obtain a device scheduling strategy of the agricultural devices, is specifically configured to: propose local optimization suggestions for task allocation in the initial scheduling strategy based on the self-health status and execution capability of the agricultural devices; integrate local optimization suggestions of the agricultural devices through multiple rounds of information exchange to obtain a collaborative work willingness graph among the agricultural devices; continuously optimize the collaborative work willingness graph according to real-time device status changes and task execution progress of the agricultural devices; and perform feedback adjustment on the initial scheduling strategy according to the continuously optimized collaborative work willingness graph to obtain the device scheduling strategy of the agricultural devices. 10.A method for managing intelligent agricultural equipment based on an Internet of Things, characterized in that, The method comprises: S1, connecting multiple agricultural devices through an Internet gateway to obtain a raw data set of the agricultural devices; S2, extracting real-time environmental features and degradation trends of the agricultural devices from the cleaned raw data; S3, performing adaptive health assessment on historical performance data of the agricultural devices according to the degradation trends and the real-time environmental features to obtain a failure probability and a remaining useful life evaluation report of the agricultural devices; S4, generating predicted health indicators of the agricultural devices according to the failure probability and the remaining useful life evaluation report; S5, adjusting the work sequence and resource allocation among the agricultural devices according to the predicted health indicators and agricultural operation requirements to obtain an initial scheduling strategy of the agricultural devices; S6, performing scheduling optimization on the initial scheduling strategy according to local decisions and global consensus in the scheduling process of the agricultural devices to obtain a device scheduling strategy of the agricultural devices, and sending the device scheduling strategy to the corresponding agricultural devices through the Internet gateway.

Images