Grain variable temperature drying control system and method
By combining multi-source sensors and a grain drying-stress coupling dynamic model, intelligent and adaptive control of the grain drying process was achieved, solving the problems of low efficiency and unstable quality in the grain drying process, and reducing the rate of grain breakage and energy consumption.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HEILONGJIANG BAYI AGRICULTURAL UNIVERSITY
- Filing Date
- 2026-03-20
- Publication Date
- 2026-07-10
AI Technical Summary
Existing technologies lack real-time perception and dynamic response to the internal state of grain during the drying process, resulting in low drying efficiency and unstable grain quality, especially high breakage rate and severe heat damage.
The system employs multi-source sensors to monitor grain condition, combined with a grain drying-stress coupling dynamic model. The control module enables real-time prediction and dynamic adjustment of drying temperature. Distributed moisture sensors, infrared thermal imaging, and acoustic emission monitoring are used, along with multi-objective optimization algorithms and variable-temperature drying strategies, to achieve precise control.
It has enabled intelligent and adaptive grain drying processes, reduced the rate of grain breakage, improved drying efficiency and grain quality, and reduced energy consumption.
Smart Images
Figure CN122360091A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of post-harvest grain processing technology, specifically to a grain temperature-controlled drying control system and method. Background Technology
[0002] Grain drying is a crucial step in ensuring safe grain storage. Traditional grain drying technologies often employ constant-temperature drying, which involves maintaining the hot air temperature at a fixed set value throughout the drying process. While this method is simple to control, it has significant drawbacks: In the initial drying stage, when the grain has a high moisture content, high-temperature drying causes the surface moisture to evaporate rapidly, forming a hard crust. This hinders the migration of internal moisture, generating significant internal stress and leading to a sharp increase in the rate of grain cracking, severely reducing grain quality and germination rate. In the later stages of drying, maintaining high temperatures causes heat damage to the grain, which is already in a low-moisture state, and also results in low energy efficiency.
[0003] Existing technologies also include some variable-temperature drying methods, such as setting several fixed temperature stages based on experience. However, these methods lack real-time perception and dynamic response to the internal state of the grain (such as moisture gradient, temperature gradient, and internal stress) during the drying process. They cannot adaptively adjust according to the actual drying state of the grain, and the timing and magnitude of temperature changes depend on the operator's experience, resulting in unstable effects and difficulty in optimally ensuring grain quality while maintaining drying efficiency.
[0004] Therefore, there is an urgent need in this field for a control system and method that can sense the internal and external state of grain in real time, predict quality changes, and dynamically and accurately adjust the drying temperature accordingly, so as to achieve intelligent drying with high efficiency, high quality, and low loss. To this end, we propose a grain variable temperature drying control system and method to solve the above problems. Summary of the Invention
[0005] (a) Technical problems to be solved
[0006] To address the shortcomings of existing technologies, this invention provides a grain temperature-controlled drying system and method that enables intelligent, precise, and adaptive drying processes, thus solving the problems mentioned in the background section.
[0007] (II) Technical Solution
[0008] To achieve the above objectives, the present invention specifically adopts the following technical solution:
[0009] A grain temperature-controlled drying system includes:
[0010] An environmental parameter acquisition module is used to acquire environmental parameters inside the drying tower or drying chamber in real time. The environmental parameters include at least the inlet temperature, outlet temperature, ambient humidity, and medium flow rate of the drying medium.
[0011] The grain parameter acquisition module is used to acquire the state parameters of grain during the drying process in real time or near real time. The state parameters include at least the average moisture content of each layer of grain, the temperature distribution of grain, and the internal stress of grain.
[0012] The control module has its input terminals communicatively connected to the environmental parameter acquisition module and the grain parameter acquisition module, respectively, and is used to receive the environmental parameters and the status parameters.
[0013] The storage module is communicatively connected to the control module and stores at least the drying characteristic parameters of different grain varieties, the maximum allowable drying temperature, the moisture diffusion coefficient model, the cracking rate prediction model, and multiple preset variable temperature drying strategy templates.
[0014] An actuator module, the control terminal of which is communicatively connected to the output terminal of the control module; the actuator module is used to regulate the environment inside the drying tower or drying chamber.
[0015] Furthermore, the grain parameter acquisition module includes:
[0016] A distributed moisture sensor array, arranged in a three-dimensional grid within the drying equipment, is used to acquire moisture content data of grain at different depths and horizontal positions.
[0017] Infrared thermal imagers are used to acquire images of the temperature field distribution on the surface of grains during the drying process.
[0018] The acoustic emission monitoring unit is used to collect acoustic emission signals of micro-fractures generated by changes in internal stress during the drying process of grain, and to invert the risk coefficient of grain bursting based on these signals.
[0019] Furthermore, the control module is configured as follows:
[0020] Based on the received real-time parameters, the drying characteristic parameters and models in the storage module are called to perform rolling optimization prediction of the future drying process and quality changes of the grain in a preset prediction time domain.
[0021] Using drying energy consumption below a set threshold, moisture uniformity at the end of drying above a set threshold, and grain breakage rate below a set threshold as multi-objective optimization functions, combined with the variable temperature drying strategy template in the storage module, the optimal temperature control sequence in the control time domain is dynamically solved.
[0022] The optimal temperature control sequence is converted into control commands and sent to the actuator module to drive it to adjust the temperature of the drying medium.
[0023] Furthermore, the control module incorporates a prediction model, which is a grain drying-stress coupled dynamic model. This model describes the nonlinear relationship between grain moisture diffusion rate and temperature, the thermal stress caused by the internal temperature gradient of the grain, and the grain bursting mechanism under the combined action of moisture stress caused by the moisture gradient.
[0024] Furthermore, the variable temperature drying strategy template stored in the storage module includes:
[0025] Stepped heating template: Low temperature is used for preheating and tempering in the early stage of drying, and then the drying temperature is gradually increased in stages;
[0026] Pulse-type temperature-changing template: It adopts a pulse mode that combines periodic or non-periodic high-temperature short-time drying with low-temperature slow-release.
[0027] Adaptive tracking template: Based on the real-time predicted rate of moisture migration inside the grain, the temperature curve is dynamically adjusted so that the drying rate always approaches but does not exceed the critical rate of moisture migration inside the grain.
[0028] Furthermore, the actuator module includes:
[0029] A gas proportional valve is used to precisely adjust the burner's firepower, thereby controlling the hot air temperature.
[0030] The air mixing regulating valve is used to adjust the mixing ratio of cold air and hot air;
[0031] Steam heat exchange regulating valve, used to precisely regulate steam flow when steam heat exchange is used;
[0032] The control module outputs control signals through PID algorithm or fuzzy control algorithm to continuously or stepwise adjust the opening of the valve.
[0033] Furthermore, it also includes a cloud platform and a user interaction terminal, which are remotely connected to the control module;
[0034] The cloud platform is used to store historical drying data, optimize model parameters, and support remote diagnostics and strategy updates;
[0035] The user interaction terminal is used to display real-time drying curves, predicted quality indicators, system alarm information, and to receive user-defined manual intervention commands or drying target parameters.
[0036] A method for controlling grain temperature-controlled drying, the method being used based on the aforementioned grain temperature-controlled drying system, includes the following steps:
[0037] S1: Initialize the system by inputting the variety of grain to be dried, the initial average moisture content, and the target final moisture content, and by retrieving the corresponding drying characteristic parameters from the storage module.
[0038] S2: Start the drying equipment and obtain the dynamic parameters of the drying process in real time through the environmental parameter acquisition module and the grain condition parameter acquisition module;
[0039] S3: The control module, based on the parameters collected at the current time k, predicts in the time domain... , Internally, it uses a built-in predictive model to make rolling predictions about the future. Changes in grain moisture content, temperature, and breakage rate within a single step;
[0040] S4: In the control time domain , Within this process, based on the prediction results of step S3, a multi-objective optimization problem is solved. The objective function of this optimization problem aims to minimize drying energy consumption, maximize moisture uniformity, and minimize the rate of cracking, thereby obtaining the future... The optimal temperature setpoint sequence within each step ;
[0041] S5: Set the first value in the optimal temperature setpoint sequence. As the setpoint for the current control cycle, control commands are output to the actuator module to achieve precise adjustment of the drying medium temperature;
[0042] S6: In the next sampling period, repeat steps S2 to S5 to achieve rolling optimization and closed-loop control based on real-time feedback.
[0043] Furthermore, in step S3, the prediction model is a state-space model, whose state variables include at least the average moisture content of the grain, the core temperature of the grain, and the surface temperature of the grain. The prediction model predicts the evolution of the state variables by using the temperature of the drying medium as the control input.
[0044] Furthermore, in step S4, the solution of the multi-objective optimization problem adopts a constrained nonlinear programming algorithm, the constraints of which include: the temperature of the drying medium must not exceed the maximum allowable temperature of the grain variety, and the instantaneous drying rate at any position of the grain must not exceed the set safety factor of its internal moisture diffusion rate.
[0045] In step S2, the parameters acquired in real time include the acoustic emission signal collected by the acoustic emission monitoring unit. In step S3, based on the intensity and frequency of the acoustic emission signal, the prediction parameters of the bursting rate in the prediction model are corrected in real time to achieve adaptive correction of the grain drying-stress coupling dynamics model.
[0046] (III) Beneficial Effects
[0047] Compared with the prior art, the present invention provides a grain temperature-controlled drying control system and method, which has the following beneficial effects:
[0048] This invention integrates multi-source sensor information with a grain drying mechanism model to achieve advanced prediction of changes in the drying process and grain quality, thereby proactively intervening in the drying temperature and fundamentally resolving the contradiction between drying efficiency and grain quality. This invention provides an open and scalable intelligent drying platform that can integrate expert experience, historical data, and advanced algorithms to continuously optimize drying strategies, enabling intelligent, precise, and adaptive drying processes. Attached Figure Description
[0049] Figure 1 This is a schematic diagram of the overall system architecture of the present invention.
[0050] Figure 2 This is a schematic diagram of the method flow of the present invention. Detailed Implementation
[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0052] Example
[0053] like Figure 1 As shown, an embodiment of the present invention provides a grain temperature-controlled drying system, comprising:
[0054] An environmental parameter acquisition module is responsible for real-time monitoring of the macroscopic operating conditions of the drying process. This module includes at least temperature sensors, humidity sensors, and anemometers located at the inlet and outlet of the drying tower or drying chamber. It is used to collect real-time data on the inlet temperature, outlet temperature, ambient humidity, and flow rate of the drying medium. These parameters are fundamental for calculating the drying driving force and energy consumption. The module is used to collect real-time environmental parameters within the drying tower or drying chamber, including at least the inlet temperature, outlet temperature, ambient humidity, and flow rate of the drying medium.
[0055] The grain parameter acquisition module is responsible for deeply sensing changes in the microscopic state of the grain itself, which is crucial for achieving precise control. This module employs a multi-technology integrated, three-dimensional monitoring solution:
[0056] Distributed moisture sensor array: Embedded in a three-dimensional grid at different depths and horizontal positions within the drying equipment, thereby obtaining a three-dimensional spatial moisture distribution cloud map inside the grain, rather than just the average moisture content.
[0057] Infrared thermal imager: non-contact acquisition of temperature field distribution images of the entire grain pile surface, intuitively reflecting the uniformity of drying and thermal shock.
[0058] Acoustic emission monitoring unit: This is one of the innovative aspects of this invention. During the drying process, grains may experience micro-cracks due to internal stress exceeding their strength, generating acoustic emission signals. This unit collects these signals using a high-frequency acoustic sensor and, through analysis of signal characteristics (such as energy, count, and frequency), calculates the real-time risk factor of grain cracking, providing direct and rapid feedback for quality control.
[0059] This is used to collect state parameters of grain during the drying process in real time or near real time. The state parameters include at least the average moisture content of each layer of grain, the temperature distribution of grain, and the internal stress of grain.
[0060] The control module, whose input terminals are communicatively connected to the environmental parameter acquisition module and the grain parameter acquisition module respectively, is used to receive the environmental parameters and the state parameters. As the brain of the system, its core implements the model predictive control algorithm. The operation flow of this module is as follows:
[0061] State awareness and fusion: Receives all real-time data from environmental parameter and grain parameter acquisition modules.
[0062] Model Rolling Prediction: The grain drying-stress coupled dynamics model in the storage module is used as the internal prediction model. This model is not a simple empirical formula, but is based on physical mechanisms, describing two coupled processes: moisture diffusion and stress generation. It quantifies the nonlinear relationship between moisture diffusion rate and temperature (usually conforming to the Arrhenius equation) and integrates the internal stress induced by both temperature and moisture gradients, ultimately relating it to the prediction of the bursting rate. The control module uses this model to perform advanced simulations of changes in grain moisture, temperature, and bursting rate over a future time period (prediction time domain), starting from the current moment.
[0063] Multi-objective rolling optimization: In each control cycle, the controller solves a constrained optimization problem. Its objective function aims to simultaneously minimize drying energy consumption, maximize the uniformity of moisture content at the end of drying, and minimize the grain breakage rate. The optimization variables are a series of drying temperature setpoints over a short future period (control time domain). By combining variable-temperature drying strategy templates (such as stepped heating, pulsed temperature changes, etc.) stored in the module, the optimal temperature control sequence is dynamically solved.
[0064] The storage module, communicatively connected to the control module, stores at least the drying characteristic parameters of different grain varieties, the maximum allowable drying temperature, moisture diffusion coefficient models, bursting rate prediction models, and multiple preset variable-temperature drying strategy templates. As a support system, it stores rich prior knowledge and models. The physical property parameter library includes: elastic modulus, moisture expansion coefficient, and maximum allowable temperature for different grain varieties (e.g., rice, corn, wheat). The mechanism model library includes: moisture diffusion coefficient models, bursting rate prediction models, etc. The strategy template library contains multiple pre-stored, validated variable-temperature drying strategy templates, providing initial direction and constraints for optimization solutions.
[0065] The actuator module, whose control end is communicatively connected to the output end of the control module, is used to regulate the environment within the drying tower or drying chamber, translating the decisions of the control module into actual actions. It includes gas proportional valves, air mixing regulating valves, steam heat exchange regulating valves, etc., achieving rapid and stable control of the drying medium temperature through continuous or step-by-step precise adjustment of the valve openings. The control module can employ PID algorithms or fuzzy control algorithms to generate specific valve control signals.
[0066] The cloud platform and user interaction terminal extend the system's remote and intelligent capabilities. The cloud platform is used for big data storage, remote model parameter updates, and fault diagnosis; the user interaction terminal provides a human-computer interaction interface, displays various curves and alarm information, and allows experienced operators to perform necessary manual intervention.
[0067] This invention integrates multi-source sensor information with a grain drying mechanism model to achieve advanced prediction of changes in the drying process and grain quality, thereby proactively intervening in the drying temperature and fundamentally resolving the contradiction between drying efficiency and grain quality. This invention provides an open and scalable intelligent drying platform that can integrate expert experience, historical data, and advanced algorithms to continuously optimize drying strategies, enabling intelligent, precise, and adaptive drying processes.
[0068] like Figure 1 As shown, in some embodiments, the grain parameter acquisition module includes: a distributed moisture sensor array arranged in a three-dimensional grid within the drying equipment to acquire moisture content data of the grain at different depths and horizontal positions; an infrared thermal imager to acquire temperature field distribution images of the grain surface during the drying process; and an acoustic emission monitoring unit to acquire acoustic emission signals of micro-cracks generated by changes in internal stress during the drying process, and to invert the risk coefficient of grain bursting based on these signals.
[0069] like Figure 1 As shown, in some embodiments, the control module is configured to:
[0070] Based on the received real-time parameters, the drying characteristic parameters and models in the storage module are invoked to perform rolling optimization prediction of the future drying process and quality changes of the grain in a preset prediction time domain. Using drying energy consumption below a set threshold, moisture uniformity at the end of drying above a set threshold, and grain breakage rate below a set threshold as multi-objective optimization functions, combined with the variable temperature drying strategy template in the storage module, the optimal temperature control sequence in the control time domain is dynamically solved. The optimal temperature control sequence is converted into control commands and sent to the actuator module to drive it to adjust the temperature of the drying medium.
[0071] The control module has a built-in prediction model, which is a grain drying-stress coupled dynamic model. This model describes the nonlinear relationship between grain moisture diffusion rate and temperature, the thermal stress caused by the internal temperature gradient of the grain, and the grain bursting mechanism under the combined action of moisture stress caused by the moisture gradient.
[0072] The grain drying-stress coupled dynamics prediction model includes a moisture migration sub-model and a stress damage sub-model. The moisture migration sub-model is described by an unsteady diffusion equation. ;
[0073] in: Let t be the wet basis moisture content of the grain (%), t be the time (s), T be the absolute temperature of the grain (K), and D(T) be the moisture diffusion coefficient, which is a function of temperature T.
[0074] Represented as ,in Pre-exponential factor, Let be the activation energy for water diffusion (J / mol), and R be the ideal gas constant.
[0075] The stress damage sub-model is based on the assumption that grain particles are simplified into elastic spherical shells, with an internal moisture gradient. The induced stress σ is expressed as: ;
[0076] in, The elastic modulus (Pa) of grain. The coefficient of wet expansion is 1. Poisson's ratio;
[0077] The increment of the instantaneous burst rate CR is related to the degree to which the stress σ exceeds the tensile strength σ_threshold of the grain itself, and is expressed as: ;
[0078] in, H is the damage rate constant, and H(·) is the Heaviside step function.
[0079] When the control module performs rolling optimization, its objective function is... Defined as:
[0080] ;
[0081] in, This represents the summation over the entire prediction time domain;
[0082] The target moisture value is set;
[0083] The average moisture content of the grain predicted by the model;
[0084] The predicted rate of waist collapse by the model;
[0085] Set the temperature of the drying medium to be optimized;
[0086] , , These are weighting coefficients, used to weigh the importance of drying endpoint accuracy, quality retention, and energy consumption, respectively.
[0087] The optimization process is to satisfy Upper and lower limit constraints and Find the temperature set sequence that minimizes the objective function J, provided that the set value does not exceed the maximum allowable value.
[0088] like Figure 1 As shown, in some embodiments, the variable temperature drying strategy templates stored in the storage module include: a stepped heating template: using low temperature for preheating and tempering in the early stage of drying, and then gradually increasing the drying temperature in stages; a pulsed variable temperature template: using a pulsed mode that combines periodic or non-periodic high-temperature short-time drying with low-temperature tempering; and an adaptive tracking template: dynamically adjusting the temperature curve according to the real-time predicted internal moisture migration rate of the grain, so that the drying rate always approaches but does not exceed the critical rate of internal moisture migration of the grain.
[0089] like Figure 1 As shown, in some embodiments, the actuator module includes: a gas proportional valve for precisely adjusting the burner's firepower, thereby controlling the hot air temperature; a mixing regulating valve for adjusting the mixing ratio of cold air and hot air; and a steam heat exchange regulating valve for precisely adjusting the steam flow rate when steam heat exchange is used. The control module outputs control signals through a PID algorithm or a fuzzy control algorithm to continuously or stepwise adjust the opening of the above valves.
[0090] like Figure 1As shown, in some embodiments, a cloud platform and a user interaction terminal are also included, which are remotely connected to the control module; the cloud platform is used to store historical drying data, optimize model parameters, and support remote diagnosis and strategy updates; the user interaction terminal is used to display real-time drying curves, predict quality indicators, system alarm information, and receive user-set manual intervention instructions or drying target parameters.
[0091] like Figure 2 As shown, a method for controlling grain temperature-controlled drying, based on the aforementioned grain temperature-controlled drying system, includes the following steps:
[0092] S1: Initialize the system by inputting the variety of grain to be dried, the initial average moisture content, and the target final moisture content, and by retrieving the corresponding drying characteristic parameters from the storage module.
[0093] S2: Start the drying equipment and obtain the dynamic parameters of the drying process in real time through the environmental parameter acquisition module and the grain condition parameter acquisition module;
[0094] S3: The control module, based on the parameters collected at the current time k, predicts in the time domain... , Internally, it uses a built-in predictive model to make rolling predictions about the future. Changes in grain moisture content, temperature, and breakage rate within a single step;
[0095] S4: In the control time domain , Within this process, based on the prediction results of step S3, a multi-objective optimization problem is solved. The objective function of this optimization problem aims to minimize drying energy consumption, maximize moisture uniformity, and minimize the rate of cracking, thereby obtaining the future... The optimal temperature setpoint sequence within each step ;
[0096] S5: Set the first value in the optimal temperature setpoint sequence. As the setpoint for the current control cycle, control commands are output to the actuator module to achieve precise adjustment of the drying medium temperature;
[0097] S6: In the next sampling period, repeat steps S2 to S5 to achieve rolling optimization and closed-loop control based on real-time feedback.
[0098] like Figure 2 As shown, in some embodiments, in step S3, the prediction model is a state-space model, whose state variables include at least the average moisture content of the grain (M) and the core temperature of the grain. and grain surface temperature The prediction model uses the temperature of the drying medium. It serves as a control input to predict the evolution of state variables.
[0099] like Figure 2 As shown, in some embodiments, in step S4, the solution of the multi-objective optimization problem adopts a constrained nonlinear programming algorithm, the constraints of which include: the temperature of the drying medium shall not exceed the maximum allowable temperature of the grain variety, and the instantaneous drying rate at any position of the grain shall not exceed the set safety factor of its internal moisture diffusion rate.
[0100] In step S2, the parameters acquired in real time include the acoustic emission signal collected by the acoustic emission monitoring unit. In step S3, based on the intensity and frequency of the acoustic emission signal, the prediction parameters of the bursting rate in the prediction model are corrected in real time to achieve adaptive correction of the grain drying-stress coupling dynamics model.
[0101] In summary, compared with the prior art, the present invention has the following significant advantages:
[0102] 1. By using a grain drying-stress coupling dynamics model and direct acoustic emission monitoring, the key quality indicator of grain breakage can be predicted and controlled in a closed loop, which fundamentally reduces the breakage rate and maintains grain quality. The model predictive control can "foresee" future conditions and dynamically adjust the temperature, so that the drying process always proceeds on the optimal path that is close to but does not exceed the grain's tolerance limit, thus shortening the drying time and reducing energy consumption while ensuring quality.
[0103] 2. The model is calibrated online using real-time data such as acoustic emission signals, enabling the system to adapt to different varieties of grains in different initial states, as well as environmental changes. By combining distributed sensor arrays and thermal imaging technology, three-dimensional monitoring of the drying process is achieved, solving the problem of uneven drying and improving the uniformity of the final product. Expert experience, mechanism models, and advanced control algorithms are deeply integrated to form an intelligent decision-making system that can be continuously evolved and improved, reducing the reliance on operator experience.
[0104] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A grain temperature-controlled drying system, characterized in that, include: An environmental parameter acquisition module is used to acquire environmental parameters inside the drying tower or drying chamber in real time. The environmental parameters include at least the inlet temperature, outlet temperature, ambient humidity, and medium flow rate of the drying medium. The grain parameter acquisition module is used to acquire the state parameters of grain during the drying process in real time or near real time. The state parameters include at least the average moisture content of each layer of grain, the temperature distribution of grain, and the internal stress of grain. The control module has its input terminals communicatively connected to the environmental parameter acquisition module and the grain parameter acquisition module, respectively, and is used to receive the environmental parameters and the status parameters. The storage module is communicatively connected to the control module and stores at least the drying characteristic parameters of different grain varieties, the maximum allowable drying temperature, the moisture diffusion coefficient model, the cracking rate prediction model, and multiple preset variable temperature drying strategy templates. An actuator module, the control terminal of which is communicatively connected to the output terminal of the control module; the actuator module is used to regulate the environment inside the drying tower or drying chamber.
2. The grain temperature-controlled drying system according to claim 1, characterized in that: The grain parameter acquisition module includes: A distributed moisture sensor array, arranged in a three-dimensional grid within the drying equipment, is used to acquire moisture content data of grain at different depths and horizontal positions. Infrared thermal imagers are used to acquire images of the temperature field distribution on the surface of grains during the drying process. The acoustic emission monitoring unit is used to collect acoustic emission signals of micro-fractures generated by changes in internal stress during the drying process of grain, and to invert the risk coefficient of grain bursting based on these signals.
3. The grain temperature-controlled drying system according to claim 1, characterized in that: The control module is configured as follows: Based on the received real-time parameters, the drying characteristic parameters and models in the storage module are called to perform rolling optimization prediction of the future drying process and quality changes of the grain in a preset prediction time domain. Using drying energy consumption below a set threshold, moisture uniformity at the end of drying above a set threshold, and grain breakage rate below a set threshold as multi-objective optimization functions, combined with the variable temperature drying strategy template in the storage module, the optimal temperature control sequence in the control time domain is dynamically solved. The optimal temperature control sequence is converted into control commands and sent to the actuator module to drive it to adjust the temperature of the drying medium.
4. The grain temperature-controlled drying system according to claim 3, characterized in that: The control module has a built-in prediction model, which is a grain drying-stress coupled dynamic model. This model describes the nonlinear relationship between grain moisture diffusion rate and temperature, the thermal stress caused by the internal temperature gradient of the grain, and the grain bursting mechanism under the combined action of moisture stress caused by the moisture gradient.
5. A grain temperature-controlled drying system according to claim 1, characterized in that: The variable temperature drying strategy templates stored in the storage module include: Stepped heating template: Low temperature is used for preheating and tempering in the early stage of drying, and then the drying temperature is gradually increased in stages; Pulse-type temperature-changing template: It adopts a pulse mode that combines periodic or non-periodic high-temperature short-time drying with low-temperature slow-release. Adaptive tracking template: Based on the real-time predicted rate of moisture migration inside the grain, the temperature curve is dynamically adjusted so that the drying rate always approaches but does not exceed the critical rate of moisture migration inside the grain.
6. The grain temperature-controlled drying system according to claim 1, characterized in that: The actuator module includes: A gas proportional valve is used to precisely adjust the burner's firepower, thereby controlling the hot air temperature. The air mixing regulating valve is used to adjust the mixing ratio of cold air and hot air; Steam heat exchange regulating valve, used to precisely regulate steam flow when steam heat exchange is used; The control module outputs control signals through PID algorithm or fuzzy control algorithm to continuously or stepwise adjust the opening of the valve.
7. A grain temperature-controlled drying system according to any one of claims 1-6, characterized in that, It also includes a cloud platform and a user interaction terminal, which are remotely connected to the control module; The cloud platform is used to store historical drying data, optimize model parameters, and support remote diagnostics and strategy updates; The user interaction terminal is used to display real-time drying curves, predicted quality indicators, system alarm information, and to receive user-defined manual intervention commands or drying target parameters.
8. A method for controlling grain temperature-controlled drying, the method being used based on a grain temperature-controlled drying system according to any one of claims 1-7, characterized in that, Includes the following steps: S1: Initialize the system by inputting the variety of grain to be dried, the initial average moisture content, and the target final moisture content, and by retrieving the corresponding drying characteristic parameters from the storage module. S2: Start the drying equipment and obtain the dynamic parameters of the drying process in real time through the environmental parameter acquisition module and the grain condition parameter acquisition module; S3: The control module, based on the parameters collected at the current time k, predicts in the time domain... , Internally, it uses a built-in predictive model to make rolling predictions about the future. Changes in grain moisture, temperature, and breakage rate within a single step; S4: In the control time domain , Within this process, based on the prediction results of step S3, a multi-objective optimization problem is solved. The objective function of this optimization problem aims to minimize drying energy consumption, maximize moisture uniformity, and minimize the rate of cracking, thereby obtaining the future... The optimal temperature setpoint sequence within each step ; S5: Set the first value in the optimal temperature setpoint sequence. As the setpoint for the current control cycle, control commands are output to the actuator module to achieve precise adjustment of the drying medium temperature; S6: In the next sampling period, repeat steps S2 to S5 to achieve rolling optimization and closed-loop control based on real-time feedback.
9. The method for controlling grain temperature-controlled drying according to claim 1, characterized in that: In step S3, the prediction model is a state-space model, whose state variables include at least the average moisture content of the grain, the core temperature of the grain, and the surface temperature of the grain. The prediction model predicts the evolution of the state variables by using the temperature of the drying medium as the control input.
10. The method for controlling grain temperature-controlled drying according to claim 1, characterized in that: In step S4, the multi-objective optimization problem is solved using a constrained nonlinear programming algorithm, the constraints of which include: the temperature of the drying medium must not exceed the maximum allowable temperature for the grain variety, and the instantaneous drying rate at any location of the grain must not exceed the set safety factor of its internal moisture diffusion rate. In step S2, the parameters acquired in real time include the acoustic emission signal collected by the acoustic emission monitoring unit. In step S3, based on the intensity and frequency of the acoustic emission signal, the prediction parameters of the bursting rate in the prediction model are corrected in real time to achieve adaptive correction of the grain drying-stress coupling dynamics model.