Grain depot grain condition prediction method and system based on big data

Abstract

The invention discloses a grain depot grain condition prediction method and system based on big data, and relates to the technical field of grain condition prediction. The method comprises the following steps: acquiring multi-modal data based on Internet of Things equipment; determining whether the operation state of the grain depot equipment is normal based on the operation data of the grain depot equipment, and if not, performing early warning; under the condition that the operation state of the grain depot equipment is normal, whether the current grain depot grain condition is normal or not is determined based on the meteorological data, the operation data of the grain depot equipment and the grain depot grain condition data, if not, a regulation and control strategy is obtained for regulation and control, and an optimal control strategy is obtained; if the grain condition of the grain depot is normal, acquiring grain condition prediction data of the grain depot based on the trained LSTM multi-output regression model, judging whether the grain condition of the grain depot is normal or not based on the grain condition prediction data of the grain depot, and if the grain condition of the grain depot is abnormal, acquiring an optimal control strategy for regulation and control. And equipment operation state monitoring, grain condition real-time evaluation and prediction and accurate regulation and control are inconvenient to realize.

Description

Technical Field

[0001] The present invention relates to the technical field of grain condition prediction, and particularly to a method and system for predicting grain conditions in a granary based on big data. Background Art

[0002] Data analysis plays a crucial role in grain condition monitoring. With the technological progress and wide application of grain condition measurement and control systems, tens of thousands of granaries across the country have accumulated a large amount of grain condition data. By deeply analyzing these data, the state and its changing trend of the grain in the warehouse can be predicted in advance, potential risks can be warned in a timely manner, and the safety of grain storage can be ensured. This method has become an important research field for improving the safety of grain storage.

[0003] A Chinese patent application with the publication number CN119578614A discloses a method and device for predicting grain condition data, which relates to the field of grain technology. It includes performing data cleaning processing on the original grain condition data to generate an optimal attribute set of grain condition data; training the optimal attribute set of grain condition data through a radial basis function (RBF) neural network to generate a grain condition data prediction model; outputting predicted grain condition data within a specified time step through the optimal attribute set of grain condition prediction and the grain condition data prediction model, and giving a warning according to the comparison result between the predicted grain condition data and a preset critical value for safe grain storage. The present invention predicts the future development or changing trend of grain conditions through various types of grain condition data, so as to warn of possible dangerous grain conditions to ensure the safety of grain storage.

[0004] However, in the process of granary management, the existing methods for predicting grain conditions in granaries have problems that it is inconvenient to monitor the operation state of equipment, conduct real-time evaluation and prediction of grain conditions, and perform precise regulation. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides a method and system for predicting grain conditions in a granary based on big data, which can solve the problems that in the process of granary management, the existing methods for predicting grain conditions in granaries are inconvenient to monitor the operation state of equipment, conduct real-time evaluation and prediction of grain conditions, and perform precise regulation.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for predicting the grain situation in a granary based on big data, comprising the following steps: obtaining multi-modal data based on Internet of Things devices, including grain situation data in the granary and operation data of granary equipment; determining whether the operation status of the granary equipment is normal based on the operation data of the granary equipment, and if it is not normal, giving an early warning; when the operation status of the granary equipment is normal, obtaining meteorological data, and determining whether the current grain situation in the granary is normal based on the meteorological data, the operation data of the granary equipment and the grain situation data in the granary. If it is not normal, obtaining a regulation strategy for regulation and optimizing the regulation strategy to obtain an optimal control strategy; if it is normal, obtaining grain situation prediction data based on the trained LSTM multi-output regression model, and judging whether the grain situation in the granary is normal based on the grain situation prediction data. If it is not normal, obtaining the optimal control strategy for regulation, and if it is normal, continuing the prediction.

[0007] Further, determining whether the operation status of the granary equipment is normal based on the operation data of the granary equipment includes the following steps: obtaining the actual values of the performance indicators of each granary equipment based on the operation data of the granary equipment , the current power value , the current action status , the variance of the power supply current fluctuation , the variance of the equipment temperature and the response time of the operation instruction , which are recorded as the operation indicators of each granary equipment ; obtaining the current operation setting data of each granary equipment stored in the database , including the set values of the performance indicators of each equipment , the set value of the current power , the set status of the current action , the required variance of the power supply current fluctuation , the required variance of the equipment temperature and the required response time of the operation instruction ; judging whether the operation status of each granary equipment is normal one by one based on the operation indicators of each granary equipment and the current operation setting data of each granary equipment. If the operation status of a certain granary equipment is not normal, giving an early warning to the granary equipment; if the operation status of all granary equipment is normal, obtaining a comprehensive judgment index. If the comprehensive judgment index is greater than the comprehensive index threshold set in the database, giving a comprehensive status early warning.

[0008] Further, the method for obtaining the comprehensive judgment index is as follows: ; wherein, is the comprehensive judgment index, i is the number of the granary equipment, is the operation status coefficient of the i-th granary equipment, is Weight coefficient

[0009] Furthermore, the method for obtaining the comprehensive judgment index is as follows: ; In the formula, is the operation status coefficient of the i-th grain depot equipment, is and similarity function, and are transfer functions, is and cosine similarity function. The action status includes the open or closed state of each switch, where open is 1 and closed is 0, and e is the natural constant; If is greater than the operation status threshold of the corresponding grain depot equipment, the operation status of the grain depot equipment is abnormal.

[0010] Furthermore, based on meteorological data, grain depot equipment operation data, and grain depot grain condition data, determine whether the current grain depot grain condition is normal, including the following steps: Obtain the comprehensive judgment index based on the grain depot equipment operation data, and combine the comprehensive judgment index with the meteorological data to form deviation matching data; Obtain the grain depot grain condition allowable deviation data from the database based on the deviation matching data; Obtain the grain depot grain condition requirement data required at the current time stored in the database; Judge whether the current grain depot grain condition is normal based on the grain depot grain condition data, the grain depot grain condition allowable deviation data, and the grain depot grain condition requirement data.

[0011] Furthermore, obtaining the grain depot grain condition allowable deviation data from the database based on the deviation matching data includes the following steps: Compare the deviation matching data with each matching data stored in the database one by one to obtain the comparison coefficient: ; In the formula, is the comparison coefficient between the deviation matching data and the j-th matching data, is the comprehensive judgment index, is the comprehensive judgment index matching value of the j-th matching data, is the meteorological data in the deviation matching data, is the matching meteorological data in the j-th matching data, is weight factor, is weight factor, is and cosine similarity function; Determine the matching data corresponding to the minimum comparison coefficient, and obtain the allowable deviation data of the grain depot grain condition corresponding to the matching data by using the matching data - allowable deviation mapping table stored in the database.

[0012] Furthermore, based on the grain depot grain condition data, the allowable deviation data of the grain depot grain condition and the requirement data of the grain depot grain condition, determine whether the current grain depot grain condition is normal, including the following steps: Based on the evaluation model, obtain the evaluation index, where the evaluation model is: ; Where, is the evaluation index, is the temperature data in the grain depot grain condition data, is the temperature requirement data in the grain depot grain condition requirement data, is and 's cosine similarity function, is the temperature allowable deviation value in the grain depot grain condition allowable deviation data; is the humidity data in the grain depot grain condition data, is the humidity requirement data in the grain depot grain condition requirement data, is and 's cosine similarity function, is the humidity allowable deviation value in the grain depot grain condition allowable deviation data; is the gas data in the grain depot grain condition data, is the gas requirement data in the grain depot grain condition requirement data, is and 's cosine similarity function, is the gas allowable deviation value in the grain depot grain condition allowable deviation data; is the pest data in the grain depot grain condition data, is the pest requirement data in the grain depot grain condition requirement data, is and 's cosine similarity function, is the pest allowable deviation value in the grain depot grain condition allowable deviation data; If is greater than the grain depot grain condition evaluation threshold stored in the database, the current grain depot grain condition is abnormal.

[0013] Further, optimize and select the regulation strategies to obtain the optimal control strategy, including the following steps: construct a digital twin model of the grain depot based on digital twin technology, after data connection and synchronization, apply the regulation strategy to the digital twin model of the grain depot, and obtain simulation data in real time, including the compliance rate of each performance and the compliance rate of energy consumption optimization of each grain depot equipment; compare the control parameters of the regulation strategy with the control parameters of the current state of the grain depot equipment to obtain parameter characteristic amplitude data, including the numerical parameter adjustment deviation and the number of action instruction adjustments; obtain the optimization evaluation coefficient of each regulation strategy based on the simulation data and the parameter characteristic amplitude data; determine the regulation strategy corresponding to the largest optimization evaluation coefficient and record it as the optimal control strategy.

[0014] Further, the method for obtaining the optimization evaluation coefficient is as follows: ; In the formula, is the optimization evaluation coefficient, and are guiding functions, is the compliance rate of the a-th performance, A is the total number of performances, is 's weight factor, is the compliance rate of energy consumption optimization of the i-th grain depot equipment, is 's weight factor, is the adjustment deviation of the c-th numerical parameter, is 's weight factor, is the number of action instruction adjustments.

[0015] A grain depot grain condition prediction system based on big data, which is applied to the above-mentioned grain depot grain condition prediction method based on big data, includes a data acquisition module, a grain depot equipment operation status evaluation module, a grain depot grain condition status evaluation module, and an optimization strategy acquisition module, where: the data acquisition module is used to acquire multi-modal data based on Internet of Things devices, including grain depot grain condition data and grain depot equipment operation data; the grain depot equipment operation status evaluation module is used to determine whether the operation status of the grain depot equipment is normal based on the grain depot equipment operation data, and issue a warning if it is not normal; the grain depot grain condition status evaluation module is used to obtain meteorological data when the operation status of the grain depot equipment is normal, and determine whether the current grain depot grain condition is normal based on the meteorological data, the grain depot equipment operation data, and the grain depot grain condition data; the optimization strategy acquisition module is used to obtain a control strategy for regulation when the current grain depot grain condition is abnormal, and optimize the control strategy to obtain an optimal control strategy; it is also used to obtain grain depot grain condition prediction data based on the trained LSTM multi-output regression model when the current grain depot grain condition is normal, and judge whether the grain depot grain condition is normal based on the grain depot grain condition prediction data. If it is not normal, obtain the optimal control strategy for regulation. If it is normal, continue the prediction.

[0016] The present invention has the following beneficial effects: The grain depot grain condition prediction method and system based on big data can, by acquiring multi-modal data, grasp the operation status of grain depot equipment in real time, discover abnormalities in time and issue warnings to avoid the impact of equipment failures on grain conditions; use meteorological, equipment, and grain condition data to determine whether the current grain condition is normal. When it is abnormal, it can obtain and optimize the control strategy to achieve precise regulation; when it is normal, it predicts the grain condition with the trained LSTM multi-output regression model, discovers potential problems in advance and regulates them, thereby ensuring the safety of grain storage, reducing losses, and improving the intelligent management level of grain depots.

[0017] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of the grain depot grain condition prediction method based on big data of the present invention.

[0019] Figure 2 It is a flow block diagram of the grain depot grain condition prediction system based on big data of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0020] Please refer to Figure 1, an embodiment of the present invention provides a technical solution: a method for predicting the grain situation in a granary based on big data, including the following steps: A method for predicting the grain situation in a granary based on big data, including the following steps: Obtain multimodal data based on Internet of Things devices, including grain situation data in the granary and operating data of granary equipment; Determine whether the operating status of the granary equipment is normal based on the operating data of the granary equipment, and give an early warning if it is not normal.

[0021] Obtain the actual values of the performance indicators of each granary equipment based on the operating data of the granary equipment (including but not limited to the detection accuracy, detection range, etc. of monitoring equipment; the ventilation volume, ventilation uniformity, control accuracy, etc. of the ventilation system; the gas concentration control accuracy, gas conditioning time, etc. of the gas conditioning system; the fumigation uniformity, drug residue, etc. of the circulation fumigation system; the temperature control accuracy, energy consumption ratio, etc. of the temperature control system; the illumination intensity and illumination uniformity of the lighting system; the recognition accuracy and response time of the access control management system), the current power value , the current action status (the status of the relevant switches of each granary equipment, open or closed), the variance of the power supply current fluctuation , the variance of the equipment temperature and the response time of the operation instruction , denoted as the operation indicators of each granary equipment .

[0022] Obtain the current operation setting data of each granary equipment stored in the database , including the set values of the performance indicators of each equipment , the current power set value , the current action set status , the required variance of the power supply current fluctuation , the required variance of the equipment temperature and the required response time of the operation instruction ; Comparing the actual operation indicators with the set data provides a clear reference standard for judging whether the equipment operation status is normal. Taking the temperature control system as an example, by comparing the actual value and the set value of the temperature control accuracy, it can be quickly found whether the temperature control system achieves the expected temperature control effect. If the deviation between the actual control accuracy and the set value is large, the problems existing in the equipment can be detected in time.

[0023] Based on the operating indicators of each grain depot equipment and the current operating set data of each grain depot equipment, judge whether the operating status of each grain depot equipment is normal one by one. If the operating status of a certain grain depot equipment is abnormal, give an early warning to this grain depot equipment; based on the operating indicators and the current operating set data, judge whether the operating status of each grain depot equipment is normal one by one, and give an early warning to the abnormal equipment. This way of judging one by one can accurately locate the equipment with problems, send out early warning signals in time, facilitate the staff to quickly take measures for repair or adjustment, and avoid the further deterioration of equipment failures, affecting the overall operation of the grain depot and the stability of the grain situation. For example, when the detection accuracy of a certain monitoring equipment is abnormal, timely early warning can enable the staff to calibrate or replace the equipment in time to ensure the accuracy of the grain situation monitoring data.

[0024] If the operating status of all grain depot equipment is normal, obtain the comprehensive judgment index. If the comprehensive judgment index is greater than the set comprehensive index threshold in the database, conduct a comprehensive status early warning.

[0025] Collect equipment operation data comprehensively from multiple dimensions. These data can intuitively reflect the real-time working conditions of the equipment, providing rich and key basis for accurately judging the operating status of the equipment subsequently. For example, by monitoring the actual values of performance indicators such as the ventilation volume and ventilation uniformity of the ventilation system, it can be judged whether the ventilation system is working properly. If the ventilation volume is insufficient, it may affect the air circulation in the grain depot and further affect the grain situation.

[0026] The method for obtaining the comprehensive judgment index is as follows: ; Among them, is the comprehensive judgment index, i is the number of the grain depot equipment, is the operating status coefficient of the i-th grain depot equipment, is 's weight coefficient.

[0027] Convert the operating conditions of each equipment into specific values to realize the quantitative evaluation of the operating status of each equipment. This makes the judgment of the equipment operating status more accurate and objective, avoiding the errors of subjective judgment. Considering the comprehensive situation of the operating status of multiple equipment, it avoids the situation where a single equipment is normal but there are potential risks in the overall system being ignored. Even if the individual operating indicators of each equipment seem normal, there may be problems in collaborative work or potential risks when combined. These problems can be effectively discovered through the comprehensive judgment index and early warnings can be issued in advance to ensure the overall safety of the grain depot operation.

[0028] The method for obtaining the comprehensive judgment index is as follows: ; In the formula, is the operating status coefficient of the i-th grain depot equipment, is and similarity function, and is a transfer function, is and cosine similarity function. The action state includes the on or off state of each switch, where on is 1 and off is 0, and e is the natural constant; if is greater than the operating state threshold of the corresponding grain depot equipment, the operating state of the grain depot equipment is abnormal.

[0029] Convert the complex operating parameters of the equipment into a quantified operating state coefficient to more accurately measure the difference between the actual operating state and the ideal state of the equipment, and can better reflect the true operating situation of the equipment than simple threshold judgment.

[0030] When the operating state of the grain depot equipment is normal, obtain meteorological data (including but not limited to temperature data, humidity data, precipitation data, and sunshine data). Based on the meteorological data, grain depot equipment operating data, and grain depot grain condition data (including but not limited to grain pile temperature, grain pile humidity, various gas concentrations, pest species, pest density), determine whether the current grain depot grain condition is normal. If it is not normal, obtain a regulation strategy for regulation and optimize the regulation strategy to obtain an optimal control strategy; the comprehensive judgment index reflects the overall operating condition of the grain depot equipment, and the meteorological data takes into account the impact of external environmental factors on the grain condition. Combining the two can comprehensively analyze the grain condition from two key aspects of equipment operation and external environment, making the judgment basis more comprehensive.

[0031] Obtain a comprehensive judgment index based on the grain depot equipment operating data, and combine the comprehensive judgment index with the meteorological data to form deviation matching data; obtain the allowable deviation data of the grain depot grain condition from the database based on the deviation matching data; obtain the required data of the grain depot grain condition required at the current time stored in the database; determine whether the current grain depot grain condition is normal based on the grain depot grain condition data, the allowable deviation data of the grain depot grain condition, and the required data of the grain depot grain condition. Obtaining the allowable deviation data of the grain depot grain condition from the database based on the deviation matching data provides a reasonable reference range for judging whether the grain condition is normal. Under different equipment operating states and meteorological conditions, the allowable fluctuation range of the grain condition is different. The allowable deviation data obtained in this way is more in line with the actual situation, avoiding misjudgment that may occur when using a fixed standard to judge the grain condition and improving the accuracy of the judgment.

[0032] Obtain the allowable deviation data of the grain depot grain condition from the database based on the deviation matching data, including the following steps: Compare the deviation matching data with each matching data stored in the database one by one to obtain a comparison coefficient: ; In the formula, is the comparison coefficient between the deviation matching data and the j-th matching data, is the comprehensive judgment index, is the comprehensive judgment index matching value of the j-th matching data, is the meteorological data in the deviation matching data, is the matching meteorological data in the j-th matching data, is the weight factor of is the weight factor of is and the cosine similarity function of Determine the matching data corresponding to the smallest comparison coefficient, and obtain the allowable deviation data of the grain depot's grain condition corresponding to this matching data by using the matching data - allowable deviation mapping table stored in the database. According to the actual equipment operation and meteorological conditions, accurately obtain the most suitable grain condition allowable deviation data from the database, providing a reliable reference basis for accurately judging whether the grain condition is normal in the follow-up, avoiding misjudgment of the grain condition caused by inaccurate allowable deviation data, and ensuring the correctness of the grain depot management decision.

[0033] Based on the grain depot's grain condition data, the allowable deviation data of the grain depot's grain condition, and the required data of the grain depot's grain condition, judge whether the current grain depot's grain condition is normal, including the following steps: Based on the evaluation model, obtain the evaluation index, where the evaluation model is: ; where, is the evaluation index, is the temperature data in the grain depot's grain condition data, is the temperature requirement data in the required data of the grain depot's grain condition, is and the cosine similarity function of is the temperature allowable deviation value in the allowable deviation data of the grain depot's grain condition; is the humidity data in the grain depot's grain condition data, is the humidity requirement data in the required data of the grain depot's grain condition, is and the cosine similarity function of is the humidity allowable deviation value in the allowable deviation data of the grain depot's grain condition; is the gas data in the grain depot's grain condition data, is the gas requirement data in the required data of the grain depot's grain condition, is and The cosine similarity function, is the gas allowable deviation value in the allowable deviation data of the grain depot grain condition; is the pest data in the grain depot grain condition data, is the pest requirement data in the grain depot grain condition requirement data, is and The cosine similarity function, is the pest allowable deviation value in the allowable deviation data of the grain depot grain condition; If is greater than the grain depot grain condition evaluation threshold stored in the database, the current grain depot grain condition is abnormal. The temperature, humidity, gas, and pest data in the grain depot grain condition data, as well as the corresponding requirement data and allowable deviation values, are comprehensively considered. This multi-dimensional evaluation method comprehensively covers the key factors affecting the grain condition and can more accurately reflect the actual situation of the grain condition compared with single-index judgment.

[0034] Obtain the grain depot grain condition requirement data required by the current time stored in the database, and judge whether the current grain depot grain condition is normal based on the grain depot grain condition data, the grain depot grain condition allowable deviation data, and the grain depot grain condition requirement data. By comparing the actual grain condition data with the requirement data and combining the allowable deviation range, it is possible to accurately judge whether the grain condition is in a normal state. If the grain condition is abnormal, corresponding measures can be taken in a timely manner, such as adjusting the equipment operation parameters, ventilating and dehumidifying, etc., to ensure the safety of grain storage.

[0035] Optimize the control strategies to obtain the optimal control strategy, including the following steps: Based on the digital twin technology, construct a grain depot digital twin model. After data connection and synchronization, apply the control strategies to the grain depot digital twin model to obtain real-time simulation data, including the performance compliance rate and the optimization compliance rate of the energy consumption of each grain depot equipment; Compare the control parameters of the control strategies with the control parameters of the current grain depot equipment status to obtain the parameter characteristic amplitude data, including the numerical parameter adjustment deviation and the number of action instruction adjustments; Obtain the optimization evaluation coefficient of each control strategy based on the simulation data and the parameter characteristic amplitude data; Determine the control strategy corresponding to the largest optimization evaluation coefficient and record it as the optimal control strategy.

[0036] The digital twin model can highly simulate the real grain depot environment. By testing different control strategies in the model, it is possible to intuitively understand in advance the impact of each strategy on the grain depot performance and equipment energy consumption. For example, when adjusting the ventilation strategy, it is possible to quickly know through the model the changes in temperature and humidity inside the grain depot and the increase or decrease in equipment energy consumption, avoiding blind attempts in actual operations and reducing resource waste.

[0037] The method for obtaining the optimization evaluation coefficient is as follows: ; In the formula, To optimize the evaluation coefficient, and is the guiding function, is the performance compliance rate of the a-th performance, A is the total number of performances, is 's weight factor, is the energy consumption optimization compliance rate of the i-th grain depot equipment, is 's weight factor, is the adjustment deviation of the c-th numerical parameter (the adjustment deviation is the absolute value of the difference between the current parameter and the parameter corresponding to the control strategy), is 's weight factor, is the number of action instruction adjustments (such as the number of changes in the switch state). Convert factors of different natures into unified quantitative indicators to comprehensively and accurately reflect the influence degree of each factor on the optimization effect of the control strategy.

[0038] Compare the control parameters of the control strategy with the control parameters of the current grain depot equipment state to obtain parameter characteristic amplitude data such as the adjustment deviation of numerical parameters and the number of action instruction adjustments. These data can clearly reflect the degree of change of different control strategies on the equipment state, and help managers understand the difficulty of strategy implementation and the influence range on the equipment. For example, when adjusting the parameters of the temperature control system, the rationality of the adjustment can be judged according to the parameter adjustment deviation to avoid over-adjustment causing damage to the equipment.

[0039] Based on the simulation data and parameter characteristic amplitude data, obtain the optimization evaluation coefficient of each control strategy, and determine the control strategy corresponding to the maximum optimization evaluation coefficient as the optimal control strategy. This comprehensive evaluation method takes into account both the control effect (performance compliance rate, energy consumption optimization compliance rate) and the feasibility of strategy implementation (parameter adjustment deviation, number of action instruction adjustments), ensuring that the selected control strategy can not only effectively solve the grain situation problem but also be efficiently implemented in actual operation to achieve the optimized management of grain depot operation.

[0040] If normal, obtain the grain situation prediction data of the grain depot based on the trained LSTM multi-output regression model, and judge whether the grain situation of the grain depot is normal based on the grain situation prediction data of the grain depot. If not normal, obtain the optimal control strategy for regulation. If normal, continue the prediction.

[0041] A grain depot grain situation prediction system based on big data, applied to the above-mentioned grain depot grain situation prediction method based on big data, such as Figure 2As shown in the figure, it includes a data acquisition module, a grain depot equipment operation status evaluation module, a grain depot grain condition status evaluation module, and an optimization strategy acquisition module, where: the data acquisition module is used to acquire multi-modal data based on Internet of Things devices, including grain depot grain condition data and grain depot equipment operation data; the grain depot equipment operation status evaluation module is used to determine whether the operation status of the grain depot equipment is normal based on the grain depot equipment operation data, and give an early warning if it is not normal; the grain depot grain condition status evaluation module is used to acquire meteorological data when the operation status of the grain depot equipment is normal, and determine whether the current grain depot grain condition is normal based on the meteorological data, the grain depot equipment operation data, and the grain depot grain condition data; the optimization strategy acquisition module is used to acquire a control strategy for regulation when the current grain depot grain condition is abnormal, and optimize the control strategy to obtain an optimal control strategy; it is also used to obtain grain depot grain condition prediction data based on the trained LSTM multi-output regression model when the current grain depot grain condition is normal, and determine whether the grain depot grain condition is normal based on the grain depot grain condition prediction data. If it is not normal, an optimal control strategy is acquired for regulation. If it is normal, the prediction continues.

[0042] An electronic device includes: a processor; and a memory in which computer program instructions are stored, and when the computer program instructions are run by the processor, the processor is caused to execute the above-mentioned method for predicting grain depot grain condition based on big data.

[0043] A computer-readable storage medium is used to store a program, and when the program is executed by a processor, it implements the above-mentioned method for predicting grain depot grain condition based on big data.

[0044] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0045] The present invention is described with reference to the flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the process Figure 1 one process or multiple processes and / or blocks Figure 1means for the functions specified in one or more boxes.

[0046] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions specified in one Figure 1 or more processes and / or boxes Figure 1 or more boxes.

[0047] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one Figure 1 or more processes and / or boxes Figure 1 or more boxes.

[0048] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0049] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for predicting the grain condition in a granary based on big data, characterized in that, It includes the following steps: Obtain multimodal data based on Internet of Things devices, including grain depot condition data and grain depot equipment operation data; Determine whether the operation status of grain depot equipment is normal based on the grain depot equipment operation data. If it is not normal, give an alarm; When the operation status of grain depot equipment is normal, obtain meteorological data. Based on the meteorological data, grain depot equipment operation data and grain depot condition data, determine whether the current grain depot condition is normal. If it is not normal, obtain a regulation strategy for regulation and optimize the regulation strategy to obtain an optimal control strategy; If it is normal, obtain grain depot condition prediction data based on the trained LSTM multi-output regression model, and judge whether the grain depot condition is normal based on the grain depot condition prediction data. If it is not normal, obtain the optimal control strategy for regulation. If it is normal, continue with the prediction.

2. The method for predicting the grain condition in a grain depot based on big data according to claim 1, wherein Determine whether the operation status of grain depot equipment is normal based on the grain depot equipment operation data, including the following steps: Obtain the actual values of the performance indicators of each grain depot equipment based on the operation data of the grain depot equipment , the current power value , the current action status , the variance of the power supply current fluctuation , the variance of the equipment temperature and the operation instruction response time , which are recorded as the operation indicators of each grain depot equipment ; Obtain the current operating setting data of each grain depot equipment stored in the database , including the set values of the performance indicators of each equipment , the current power set value , the current action setting status , the variance of the power supply current fluctuation requirement , the variance of the equipment temperature requirement and the response time required for the operation instruction ; Judging whether the operation status of each grain depot equipment is normal one by one based on the operation indexes of each grain depot equipment and the current operation setting data of each grain depot equipment. If the operation status of a certain grain depot equipment is not normal, give an alarm for that grain depot equipment; If the operation status of all grain depot equipment is normal, obtain a comprehensive judgment index. If the comprehensive judgment index is greater than the comprehensive index threshold set in the database, give a comprehensive status alarm.

3. A method for predicting the grain condition in a grain depot based on big data according to claim 2, characterized in that, The method for obtaining the comprehensive judgment index is as follows: ； Among them, is the comprehensive judgment index, i is the number of the grain depot equipment, is the operating status coefficient of the i-th grain depot equipment, is the weight coefficient of.

4. A method for predicting the grain condition in a grain depot based on big data according to claim 3, characterized in that, The method for obtaining the comprehensive judgment index is as follows: ； Wherein, is the operating status coefficient of the i-th grain depot equipment, is and similarity function, and are transfer functions, is and cosine similarity function. The action status includes the open or closed status of each switch, with open being 1 and closed being 0, and e being the natural constant; If is greater than the operating status threshold of the corresponding grain depot equipment, the operating status of the grain depot equipment is abnormal.

5. A method for predicting the grain situation in a grain depot based on big data according to claim 1, characterized in that Determine whether the current grain depot condition is normal based on meteorological data, grain depot equipment operation data and grain depot condition data, including the following steps: Obtain a comprehensive judgment index based on the grain depot equipment operation data, and combine the comprehensive judgment index with the meteorological data to form deviation matching data; Obtain the grain depot condition allowable deviation data from the database based on the deviation matching data; Obtain the grain depot condition requirement data required at the current time stored in the database; Judge whether the current grain depot condition is normal based on the grain depot condition data, grain depot condition allowable deviation data and grain depot condition requirement data.

6. The method for predicting the grain condition in a granary based on big data according to claim 5, wherein, Obtain the grain depot condition allowable deviation data from the database based on the deviation matching data, including the following steps: Compare the deviation matching data with each matching data stored in the database one by one to obtain a comparison coefficient: ； In the formula, is the comparison coefficient between the deviation matching data and the j-th matching data, is the comprehensive judgment index, is the comprehensive judgment index matching value of the j-th matching data, is the meteorological data in the deviation matching data, is the matching meteorological data in the j-th matching data, is 's weight factor, is 's weight factor, is and 's cosine similarity function; Determine the matching data corresponding to the smallest comparison coefficient, and use the matching data - allowable deviation mapping table stored in the database to obtain the grain depot condition allowable deviation data corresponding to the matching data.

7. A method for predicting the grain situation in a granary based on big data according to claim 5, characterized in that, Judge whether the current grain depot condition is normal based on the grain depot condition data, grain depot condition allowable deviation data and grain depot condition requirement data, including the following steps: Obtain an evaluation index based on the evaluation model, where the evaluation model is: ; Among them, is the evaluation index, is the temperature data in the grain depot grain condition data, is the temperature requirement data in the grain depot grain condition requirement data, is and is the cosine similarity function of, is the temperature allowable deviation value in the grain depot grain condition allowable deviation data; is the humidity data in the grain depot grain condition data, is the humidity requirement data in the grain depot grain condition requirement data, is and is the cosine similarity function of; is the humidity allowable deviation value in the grain depot grain condition allowable deviation data; is the gas data in the grain depot grain condition data, is the gas requirement data in the grain depot grain condition requirement data, is and the cosine similarity function of, is the gas allowable deviation value in the grain depot grain condition allowable deviation data; For the pest data in the grain depot grain condition data, For the pest requirement data in the grain depot grain condition requirement data, Is And The cosine similarity function of The pest allowable deviation value in the grain depot grain condition allowable deviation data; If is greater than the grain depot grain condition evaluation threshold stored in the database, the current grain depot grain condition is abnormal.

8. A method for predicting the grain condition in a granary based on big data according to claim 1, characterized in that, Optimize the regulation strategy to obtain an optimal control strategy, including the following steps: Build a grain depot digital twin model based on digital twin technology. After data connection and synchronization, apply the regulation strategy to the grain depot digital twin model to obtain simulation data in real time, including various performance compliance rates and various grain depot equipment energy consumption optimization compliance rates; Compare the control parameters of the regulation strategy with the control parameters of the current grain depot equipment status to obtain parameter characteristic amplitude data, including numerical parameter adjustment deviation and the number of action instruction adjustments; Obtain the optimization evaluation coefficients of each regulation strategy based on simulation data and parameter characteristic amplitude data; Determine the regulation strategy corresponding to the maximum optimization evaluation coefficient and record it as the optimal control strategy.

9. A method for predicting the grain situation in a grain depot based on big data according to claim 8, characterized in that, The method for obtaining the optimization evaluation coefficient is as follows: ； In the formula, is the optimization evaluation coefficient, and are the guiding functions, is the performance compliance rate of the a-th performance, and A is the total number of performances, is 's weight factor, is the energy consumption optimization compliance rate of the i-th grain depot equipment, is 's weight factor, is the adjustment deviation of the c-th numerical parameter, is 's weight factor, is the number of action instruction adjustments.

10. A grain depot grain condition prediction system based on big data, which is applied to a grain depot grain condition prediction method according to any one of claims 1-9, and is characterized in that, It includes a data acquisition module, a grain depot equipment operation status evaluation module, a grain depot grain condition status evaluation module, and an optimization strategy acquisition module, where: The data acquisition module is used to obtain multi-modal data based on Internet of Things devices, including grain depot grain condition data and grain depot equipment operation data; The grain depot equipment operation status evaluation module is used to determine whether the operation status of the grain depot equipment is normal based on the grain depot equipment operation data. If it is not normal, an alarm is issued; The grain depot grain condition status evaluation module is used to obtain meteorological data when the operation status of the grain depot equipment is normal, and determine whether the current grain depot grain condition is normal based on the meteorological data, grain depot equipment operation data, and grain depot grain condition data; The optimization strategy acquisition module is used to obtain a regulation strategy for regulation when the current grain depot grain condition is abnormal, and optimize the regulation strategy to obtain the optimal control strategy; It is also used to obtain grain depot grain condition prediction data based on the trained LSTM multi-output regression model when the current grain depot grain condition is normal, and judge whether the grain depot grain condition is normal based on the grain depot grain condition prediction data. If it is not normal, obtain the optimal control strategy for regulation. If it is normal, continue the prediction.

Images