Grain collection and storage agricultural machinery intelligent management system based on agricultural machinery ecologicalization

Abstract

The invention relates to a grain collection and storage agricultural machinery intelligent management system based on agricultural machinery ecologicalization, and relates to the technical field of grain storage agricultural machinery coordinated management. Comprising an object classification input module for classifying agricultural machine core components and inputting parameters, a data acquisition module for acquiring operation parameters in real time, and a data monitoring and early warning module for performing curve graph construction display and early warning management and control on real-time data, the abnormity coordination management module is used for automatically adjusting upstream and downstream working rhythms; and the health management operation and maintenance module is used for monitoring and early warning the service life of each core component of the agricultural machine. The problems that in the prior art, agricultural machinery lacks service life tracking analysis on core components, resulting in sudden abnormity, production is affected, ecology is caught in disorder after sudden abnormity, correlation and coordination among multiple agricultural machinery cannot be achieved, and the production takt of upstream and downstream procedures cannot be controlled are solved. The agricultural machinery ecology is in a life control state, the occurrence frequency of sudden abnormity is reduced, and the working stability of the whole system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of coordinated management of grain storage and agricultural machinery, and specifically to an intelligent management system for grain storage and agricultural machinery based on the ecology of agricultural machinery. Background Art

[0002] With the rapid development of modern agricultural technology, the ecologicalization of agricultural machinery has become an important way to improve agricultural production efficiency, optimize resource allocation, and reduce environmental pollution. In the process of grain storage, grain storage agricultural machinery screens, samples, transports and stores grain. The whole process constitutes a continuous and complete fully automatic storage process.

[0003] However, the working rhythm of existing grain storage agricultural machinery (such as screening machines, belt conveyors, sampling machines, etc.) is generally operated according to the set gear power, and its working rhythm can only be controlled by manually adjusting the operating gear; in the actual production process, when a certain agricultural machinery has a risk of failure or an unplanned shutdown due to force majeure, the entire storage process will be stagnant, and grain will accumulate in a certain storage process. After resuming work, the entire production chain cannot be restarted immediately. In addition, the existing agricultural machinery lacks monitoring and life management of core components, so it is impossible to evaluate the working status and performance of agricultural machinery, and the coordination and cooperation of various agricultural machinery in the entire agricultural machinery production chain is out of the question; in this case, the production chain is easily disturbed by potential risks, making the entire storage process unsmooth. To this end, we propose an intelligent management system for grain storage agricultural machinery based on agricultural machinery ecology. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent management system for grain storage agricultural machinery based on the ecologicalization of agricultural machinery.

[0005] The technical problems solved by the present invention are:

[0006] (1) To solve the problem of how to quickly handle sudden abnormalities of core components of agricultural machinery and automatically and specifically adjust the work rhythm of upstream and downstream work in the existing technology;

[0007] (2) Solve the problem of lack of life health control and early warning for core components of agricultural machinery in existing technologies;

[0008] The present invention can be implemented through the following technical solutions: an intelligent management system for grain storage and agricultural machinery based on the ecologicalization of agricultural machinery, comprising:

[0009] The object classification and input module builds the agricultural machinery ecosystem and divides the core components of each agricultural machinery in the ecosystem into drive providing components, power transmission components and function realization components, and inputs their working parameters and limit thresholds respectively;

[0010] The data acquisition module obtains the operating parameters of the corresponding core components in the working state based on various monitoring sensors installed at the core components and generates a log form for storage in the data storage module;

[0011] The data monitoring and warning module constructs a time-series change curve graph of the operating parameters of the core components based on the updated log form, monitors the time-series change curve, analyzes the curve trend in case of anomalies, and adjusts the operating status of the relevant core components in a timely manner according to the analysis results;

[0012] The abnormal coordination and management module calculates the output efficiency of each upstream process within the abnormal handling time according to the process where the abnormal component is located and the size of its buffer area, combined with its abnormal handling time; at the same time, constructs an inequality to empty the buffer area within the set time period, and obtains the upper limit value of the output efficiency of the upstream bottleneck process after the anomaly is eliminated;

[0013] The health management and operation and maintenance module analyzes and predicts the remaining service life of the core components in a dynamic cycle, so as to obtain the ranking of the remaining service life of each core component in the entire agricultural machinery ecosystem, compares the remaining service life with the threshold value, triggers an alarm and notifies the operation and maintenance personnel to handle it. The duration of the dynamic cycle is negatively correlated with the normal continuous influence time of the relevant components.

[0014] A further technical improvement of the present invention lies in that: the data monitoring and warning module listens to the log form, and the data entries of the log form are set with labels corresponding to the agricultural machinery and its core components.

[0015] A further technical improvement of the present invention lies in that: the data monitoring and warning module sets a variable limit threshold line interval in the time-series change curve graph. When the time-series change curve exceeds this interval range, a timer is started to time, and according to the first derivative and the second derivative of the time-series change curve in the time neighborhood at the current moment, the curve inflection point is determined and the time of the regression interval range of the time-series change curve is predicted;

[0016] Compare the timing duration, the abnormal regression prediction time with the abnormal tolerance time limit of the corresponding core component:

[0017] When the timing duration > the abnormal tolerance time limit, the core component starts stop protection;

[0018] When the abnormal regression prediction time < the abnormal tolerance time limit, the core component maintains its current working state;

[0019] When the timing duration < the abnormal tolerance time limit < the abnormal regression prediction time, reduce the operating power of the core component until the abnormal regression prediction time is less than the abnormal tolerance time limit.

[0020] A further technical improvement of the present invention lies in that: when the regression change of the time sequence change curve is within the limit threshold line interval or the timing duration > the abnormal tolerance duration, the timer stops timing, records the timing duration and resets it to zero.

[0021] A further technical improvement of the present invention lies in that: the specific steps for the abnormal coordination management module to coordinate and control the working beats of the upstream and downstream processes include:

[0022] Associate the operation and maintenance group, the warehousing group and the procurement group, and calculate the time required to handle the current abnormality, that is, the abnormal handling time;

[0023] Calculate the controllable output efficiency according to the buffer area size of the abnormal process and the abnormal handling time, and select the smaller value between the controllable output efficiency and the maximum output efficiency of the upstream process as the initial coordinated output efficiency of the previous process;

[0024] Determine the process with the lowest output efficiency among the upstream processes, calculate the output efficiency of the previous process of the process where the abnormality is located according to the maximum output efficiency of this process, and compare it with the initial coordinated output efficiency, and select the smaller value as the final coordinated output efficiency of the previous process of the abnormal process;

[0025] According to the bottleneck processes in the upstream and downstream processes, in order to empty the buffer area within the set time period after the abnormal process resumes operation, construct an inequality to obtain the upper limit value of the upstream bottleneck process, and obtain the time for the entire process to resume normal operation, that is, the continuous impact time of the abnormality.

[0026] A further technical improvement of the present invention lies in that: the inequality constructed to empty the buffer area within the set time period is: the maximum output efficiency of the downstream bottleneck process * the compensation time period ≥ the final coordinated output efficiency of the upstream bottleneck process * the abnormal handling time + the compensation output efficiency of the upstream bottleneck process * the compensation time period; where the compensation time period ≤ the set time period;

[0027] When the upper limit value of the compensation output efficiency of the upstream bottleneck process when the above inequality is satisfied is less than 0, stop the operation of the upstream process within the set time period.

[0028] A further technical improvement of the present invention lies in that: the continuous impact time of the abnormality is specifically the sum of the abnormal handling time and the duration of the short time period.

[0029] A further technical improvement of the present invention lies in that: the specific process of the health management operation and maintenance module for predicting and analyzing the operation risks of the core components within the dynamic cycle includes:

[0030] Calculate the remaining service life of the current risk prediction and analysis cycle according to the remaining life of each core component in the previous sub-line prediction and analysis cycle;

[0031] Sort the remaining service lives of each core component in the current risk prediction period from short to long, generate a form and display it;

[0032] Set an alarm threshold for the remaining service life of each core component. After the form is generated, compare it with the latest obtained remaining life of the corresponding component, and generate an on-site operation and maintenance signal for the core component that reaches the alarm threshold and send it to the operation and maintenance group for detection and processing.

[0033] A further technical improvement of the present invention lies in: the calculation formula for calculating the remaining service life in the current risk prediction analysis period is:

[0034]

[0035] where i represents the core component number, j represents the operating parameter number of the corresponding core component, e represents the natural constant in mathematics, T represents the cycle duration of this risk prediction analysis period, a, b, and c respectively represent the abnormal duration impact factor, parameter stability impact factor, and abnormal frequency predictability impact factor, and 1 > a > c > b > 0; N i,j represents the number of times that the operating parameter j of the core component i appears abnormal in this risk prediction analysis period, T i,j represents the corresponding average abnormal duration, α i,j represents the influence weight factor of the operating parameter j on the core component i; the stability of the operating parameter j of the core component i in this risk prediction analysis period is expressed as The change rate ε of the abnormal occurrence frequency of the operating parameter j compared with the previous cycle i,j .

[0036] A further technical improvement of the present invention lies in: the risk prediction analysis period is a dynamic period. The longer the average continuous influence time when an abnormality occurs in the corresponding core component, the shorter the risk prediction analysis period.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. The present invention constructs a time series change curve of the operating parameters of the core components through the data monitoring and early warning module, analyzes the operating status of the corresponding core components according to the curve trend, and self-adjusts the working status based on the time that the corresponding parameters continuously stay in the abnormal range; at the same time, the abnormal coordination and management module automatically associates the operation and maintenance group, the warehousing group, and the procurement group based on the location where the abnormality occurs, determines the abnormal handling time, and at the same time, according to the size of the buffer area of the abnormal occurrence process, determines the output efficiency that does not exceed the buffer area size and the upstream and downstream working beats for emptying the buffer area within the set time period, ensuring that the entire work process can continue normally as much as possible in the event of an abnormality, and ensuring the stability of the storage process.

[0039] 2. The present invention dynamically manages the risk prediction analysis cycle based on the length of the abnormal continuous influence time of each core component, shortens the risk prediction analysis cycle for the core component with a long continuous influence time, calculates the remaining service life of the core component within each risk prediction analysis cycle, so as to have data support for the monitoring and early warning of the remaining life of the core component, reduces the frequency of sudden abnormalities occurring during the use of the core component, makes the agricultural machinery ecosystem have better stability during the working process, and enables the agricultural machinery components to be maintained in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings.

[0041] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0042] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will describe in detail the specific implementation manners, structures, features and their effects of the present invention in conjunction with the accompanying drawings and preferred embodiments.

[0043] Please refer to Figure 1 As shown, a smart management system for grain storage agricultural machinery based on agricultural machinery ecologicalization includes an object classification and input module, a data acquisition module, a data monitoring and early warning module, an abnormal coordination management module, and a health management and operation and maintenance module.

[0044] The object classification and input module classifies the core components of agricultural machinery into:

[0045] Drive-providing components, such as motors, cylinders, hydraulic cylinders, etc.;

[0046] Power transmission components, such as transmission gears, transmission chains (belts), rotating shafts, etc.;

[0047] Function-implementing components, such as the vibration screening assembly of the screening machine, the positioning assembly and sampling assembly of the sampling machine, the belt of the conveyor, etc.;

[0048] The object classification and input module takes the agricultural machinery for grain storage as an ecological whole, classifies the core components of each agricultural machinery in this ecosystem, and respectively inputs the parameters (such as vibration conditions, temperature, pressure, rotation speed, voltage and current conditions) when they are in the normal working state. At the same time, the variation limit thresholds and service lives of each parameter are input according to the regulations of agricultural machinery manufacturers or expert experience;

[0049] The data acquisition module includes various monitoring sensors fixedly installed at the above-mentioned core components. When the corresponding agricultural machinery is in operation, it automatically collects data and generates a log form, which is sent to the data storage module for storage. To facilitate data differentiation, the data entries in the log form are set with labels corresponding to the agricultural machinery and its core components.

[0050] The data monitoring and warning module monitors the log forms in the data storage module. When the log form is updated, the data monitoring and prediction module separately plots a time-series change curve for each monitoring parameter of a certain agricultural machinery core component, and sets a change limit threshold line for the corresponding parameter in the curve. When the change curve is within the range of the change limit threshold line, it indicates that the real-time parameter value is normal. When the change curve exceeds the range of the change limit threshold line, it indicates that the real-time parameter value is abnormal, and an abnormal warning signal is generated.

[0051] When the change curve exceeds the range of the change limit threshold line, a timer is started, and the first derivative and the second derivative of the change curve in the time neighborhood of the current moment are calculated in real time. When the second derivative becomes zero, it means that the inflection point of the change curve appears, and the change curve has a tendency to callback into the range of the change limit threshold line. At this time, the moment when the change curve returns to the range of the change limit threshold line is predicted according to the average first derivative of each time point in the right neighborhood of the moment where the inflection point is located, and compared with the start time of the timer, so as to obtain the abnormal regression prediction time. When the change curve returns to the range of the change limit threshold line, the timer stops timing, records the timing duration and resets it to zero.

[0052] The timing duration of the timer and the abnormal regression prediction time are respectively compared with the abnormal tolerance time limit of the corresponding component. When the timing duration of the timer exceeds the abnormal tolerance time limit, stop protection is started for the corresponding component, and the timer stops timing and resets to zero; when the abnormal regression prediction time is less than the abnormal tolerance time limit, the corresponding component maintains the current working state; when the abnormal regression prediction time exceeds the abnormal tolerance time limit and the timer is still in the timing state, the operating power of the corresponding component is reduced until the abnormal regression prediction time is less than the abnormal tolerance time limit.

[0053] The abnormal coordination and management module determines the process position where the abnormal component is located and evaluates the continuous influence time of the abnormal component, and coordinates and controls the working rhythm of any upstream or downstream process. Specifically:

[0054] Step 1: When an abnormal warning signal is recognized, the information platforms of the operation and maintenance group, the warehousing group, and the procurement group are automatically associated:

[0055] According to the current distribution location and task execution situation of the operation and maintenance group personnel, determine the time for the operation and maintenance group personnel to reach the abnormal occurrence location fastest, and the average time for handling the abnormal corresponding parameters of this component in the historical records.

[0056] Query the storage status of abnormal parts in the storage group to see if there are normal parts that can be replaced. If not, directly generate the corresponding purchase order and send it to the purchasing group. The purchasing group will evaluate the time required for procurement and provide feedback.

[0057] According to the time required for each of the above steps, the time required to handle the current exception is obtained and marked as the exception handling time;

[0058] Step 2: To reduce the handling cost and match the size of the buffer area of ​​the current abnormal process, the size of the buffer area is calculated based on machine vision technology, and then the output of the upstream process that can be temporarily stored in the buffer area is evaluated according to the size of the buffer area. The output is compared with the abnormal handling time to obtain the controllable output efficiency of the upstream process. The smaller value between the controllable output efficiency and the maximum output efficiency of the upstream process is selected as the initial coordinated output efficiency of the previous process;

[0059] Step 3: Determine the process with the lowest output efficiency among the upstream processes. Assuming that the process runs at the maximum output efficiency, calculate the output efficiency of the downstream process of the process when it runs at the output efficiency. Compare the coordinated output efficiency of the previous process of the abnormal process with the calculated output efficiency, and select the smaller value as the final coordinated output efficiency of the previous process of the abnormal process. Continue to calculate the output efficiency of the previous process, thereby completing the work rhythm adjustment of the entire upstream process of the abnormal process.

[0060] Step 4: Obtain the processes with the lowest output efficiency in the upstream and downstream processes of the abnormal process respectively, and mark them as the upstream bottleneck process and the downstream bottleneck process respectively. To clear the buffer area within the set time period, let the maximum output efficiency of the downstream bottleneck process * compensation time period ≥ the final coordinated output efficiency of the upstream bottleneck process * abnormal handling time + the compensation output efficiency of the upstream bottleneck process * compensation time period, where the compensation time period ≤ the set time period, so as to obtain the upper limit value of the compensation output efficiency of the upstream bottleneck process in the compensation time period after the abnormal handling time. If the upper limit value is less than zero, the operation of the upstream process can be stopped within the set time period. The continuous impact time of the entire abnormality is the sum of the duration of the abnormal handling time and the compensation time period.

[0061] The duration of the impact is recorded in the operation and maintenance database as an indicator of the impact range of this sudden abnormality. The system also includes a health management operation and maintenance module for managing the health status of the entire agricultural machinery ecosystem. The health management operation and maintenance module is used to predict and analyze the operation risks of the above core components based on their operating status and remaining life, so as to provide early warning and eliminate fault risks during the operation and maintenance cycle, thereby reducing the frequency of sudden abnormalities during work and production;

[0062] The specific process of the health management operation and maintenance module for predicting and analyzing the operation risks of core components within a dynamic cycle includes:

[0063] S1: Obtain the remaining useful life previousRUL of the core components within the previous risk prediction and analysis cycle. i , based on the change curves constructed by the abnormal coordination management module for the relevant operation parameters of each core component, obtain the number of abnormal values N of the relevant operation parameters within this risk prediction and analysis cycle. i,j The average abnormal duration T i,j , the influence weight factor α of the relevant operation parameters relative to the component i,j (This influence weight factor is obtained based on the experience of equipment operation and maintenance personnel or experts), the stability of the relevant operation parameters during normal operation within this risk prediction and analysis cycle (i.e., the variance value ), and the change rate ε of the abnormal occurrence frequency of the relevant operation parameters compared to the previous cycle i,j , this value includes a sign;

[0064] Then calculate the remaining useful life currentRUL of the current risk prediction and analysis cycle i The calculation formula is:

[0065]

[0066] Among them, i represents the core component number, j represents the operation parameter number of the corresponding core component, e represents the natural constant in mathematics, T represents the cycle duration of this risk prediction and analysis cycle, a, b, and c respectively represent the abnormal duration influence factor, parameter stability influence factor, and abnormal frequency predictability influence factor, and 1 > a > c > b > 0;

[0067] S2: After obtaining the remaining useful life of the current risk prediction and analysis cycle in step S1, sort the remaining useful lives of each core component in ascending order and generate a sorting form for display, and set a dynamic risk prediction and analysis cycle according to the average continuous influence time when the corresponding core component has an abnormality. The longer the average continuous influence time, the shorter the risk prediction and analysis cycle, so as to pay closer attention to it;

[0068] S3: Set a remaining useful life alarm threshold for each core component. Each time the latest remaining useful life is obtained, it is compared with the alarm threshold. When the alarm threshold is reached, a on-site operation and maintenance signal is generated and sent to the operation and maintenance group. After the information platform of the operation and maintenance group receives the signal, it assigns operation and maintenance personnel to go to the site for inspection and handling.

[0069] The above are only the preferred embodiments of the present invention, and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments of equivalent changes within the scope of the technical solution of the present invention by using the above-disclosed technical content. However, as long as it does not depart from the content of the technical solution of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An intelligent management system for grain storage and agricultural machinery based on the ecologicalization of agricultural machinery, characterized in that: include: The object classification and input module builds the agricultural machinery ecosystem and divides the core components of each agricultural machinery in the ecosystem into drive providing components, power transmission components and function realization components, and inputs their working parameters and limit thresholds respectively; The data acquisition module obtains the operating parameters of the corresponding core components in the working state based on various monitoring sensors installed at the core components and generates a log form to store it in the data storage module; The data monitoring and early warning module constructs a time series change curve chart of the operating parameters of the core components based on the updated log form, monitors the time series change curve, analyzes the curve trend in abnormal situations, and makes timely adjustments to the operating status of related core components based on the analysis results; The abnormal coordination management module calculates the output efficiency of each upstream process within the abnormal handling time according to the process where the abnormal component is located and the size of its buffer area, combined with its abnormal handling time; at the same time, it constructs an inequality to clear the buffer area within the set time period and obtain the upper limit of the output efficiency of the upstream bottleneck process after the abnormality is eliminated; The health management operation and maintenance module analyzes and predicts the remaining service life of core components in a dynamic cycle, thereby obtaining the remaining service life ranking of each core component in the entire agricultural machinery ecosystem, comparing the remaining service life with the threshold, and notifying the operation and maintenance personnel to handle it after triggering an alarm. The duration of the dynamic cycle is negatively correlated with the normal continuous impact time of the relevant components.

2. According to claim 1, the intelligent management system for grain storage and agricultural machinery based on agricultural machinery ecology is characterized in that: The data monitoring and early warning module monitors the log form, and the data entries in the log form are provided with labels corresponding to the agricultural machinery and its core components.

3. According to claim 1, the intelligent management system for grain storage and agricultural machinery based on agricultural machinery ecology is characterized in that: The data monitoring and early warning module sets a change limit threshold line interval in the time series change curve diagram, starts a timer when the time series change curve exceeds the interval range, and determines the curve inflection point and predicts the time when the time series change curve returns to the interval range according to the first-order derivative and the second-order derivative of the time series change curve in the time neighborhood at the current moment; Compare the timing duration, the predicted time for abnormal regression, and the abnormal tolerance time limit of the corresponding core components: When the timing duration is greater than the abnormal tolerance time limit, the core components start to stop protection; When the abnormal regression prediction time is less than the abnormal tolerance time limit, the core components maintain the current working status; When the timing duration < abnormality tolerance time limit < abnormality regression prediction time, reduce the operating power of the core components until the abnormality regression prediction time is less than the abnormality tolerance time limit.

4. The intelligent management system for grain storage and agricultural machinery based on agricultural machinery ecology according to claim 3 is characterized in that: When the time series change curve regresses to the limit threshold line interval or the timing duration is greater than the abnormal tolerance time limit, the timer stops timing, records the timing duration and returns to zero.

5. The intelligent management system for grain storage and agricultural machinery based on agricultural machinery ecology according to claim 1 is characterized in that: The specific steps of the abnormal coordination management module coordinating and controlling the work rhythm of upstream and downstream processes include: Associate the operation and maintenance group, storage group, and procurement group to calculate the time required to handle the current exception, i.e., the exception handling time; The controllable output efficiency is calculated according to the buffer area size and the abnormal handling time of the abnormal process, and the smaller value between the controllable output efficiency and the maximum output efficiency of the upstream process is selected as the initial coordinated output efficiency of the previous process; Determine the process with the lowest output efficiency among the upstream processes, and calculate the output efficiency of the previous process of the abnormal process according to the maximum output efficiency of this process, and compare it with the initial coordinated output efficiency, and select the smaller value as the final coordinated output efficiency of the previous process of the abnormal process; According to the bottleneck process in the upstream and downstream processes, in order to meet the requirement of clearing the buffer area within the set time period after the abnormal process is restarted, an inequality is constructed to obtain the upper limit value of the upstream bottleneck process, and the time for the entire process to resume normal operation is obtained, that is, the continuous impact time of the abnormality.

6. The intelligent management system for grain storage and agricultural machinery based on agricultural machinery ecology according to claim 5 is characterized in that: The inequality constructed by clearing the buffer area within the set time period is: the maximum output efficiency of the downstream bottleneck process * compensation time period ≥ the final coordinated output efficiency of the upstream bottleneck process * abnormal handling time + the compensation output efficiency of the upstream bottleneck process * compensation time period; where the compensation time period ≤ the set time period; When the upper limit value of the compensation output efficiency of the upstream bottleneck process when the above inequality is satisfied is less than 0, the operation of the upstream process is stopped within a set time period.

7. The intelligent management system for grain storage and agricultural machinery based on agricultural machinery ecology according to claim 6 is characterized in that: The duration of the abnormal impact is specifically the sum of the abnormal handling time and the duration of the short-term period.

8. The intelligent management system for grain storage and agricultural machinery based on agricultural machinery ecology according to claim 5 is characterized in that: The specific process of the health management operation and maintenance module predicting and analyzing the operation risks of core components within the dynamic cycle includes: Calculate the remaining service life of the current risk prediction and analysis cycle based on the remaining service life of each core component in the previous line prediction and analysis cycle; Sort the remaining service life of each core component in the current risk prediction cycle from short to long and generate a table for display; Set a remaining service life alarm threshold for each core component. After the form is generated, compare it with the latest remaining service life of the corresponding component. Generate an on-site operation and maintenance signal for the core component that reaches the alarm threshold and send it to the operation and maintenance team for detection and processing.

9. The intelligent management system for grain storage and agricultural machinery based on ecological agricultural machinery according to claim 8 is characterized in that: The calculation formula for calculating the remaining useful life of the current risk prediction analysis cycle is: Where i represents the core component number, j represents the operating parameter number of the corresponding core component, e represents a natural constant in mathematics, T represents the cycle duration of this risk prediction analysis cycle, a, b, c represent the abnormal duration influencing factor, parameter stability influencing factor, abnormal frequency predictability influencing factor, and 1>a>c>b>0; N i,j represents the number of times that the operating parameter j of core component i appears abnormal value in this risk prediction analysis cycle, T i,j represents the corresponding average abnormal duration, α i,j represents the influence weight factor of operating parameter j on core component i; the stability of operating parameter j of core component i in this risk prediction analysis cycle is expressed as The change rate of the abnormal frequency of operating parameter j compared with the previous cycle ε i,j .

10. The intelligent management system for grain storage and agricultural machinery based on ecological agricultural machinery according to claim 8, characterized in that: The risk prediction and analysis cycle is a dynamic cycle. The longer the average continuous impact time when an abnormality occurs in the corresponding core component, the shorter the risk prediction and analysis cycle.

Images