Intelligent drying control system for compound seasoning production

Abstract

The invention discloses an intelligent drying control system for compound seasoning production, which is characterized in that an acquisition module is used for acquiring a two-dimensional heat map, a temperature field distribution map and a wind speed distribution map, and a control module is used for dynamically adjusting the opening and closing angle of a diverging flow guide pipeline, optimizing the position of a conical flow divider through Kalman filtering, adjusting the heating power and the rotating speed of a fan, and controlling the temperature field distribution map and the wind speed distribution map. The compound seasoning is protected when the temperature and flavor risks are too high in the drying process; the optimization module is used for constructing an energy consumption-quality multi-objective optimization model and optimizing the energy consumption-quality multi-objective optimization model through an improved genetic algorithm; and the execution module is used for performing linkage control on the execution layer equipment. By means of multi-sensor fusion, dynamic cooperative control, a multi-target optimization algorithm and an inert gas protection strategy, intelligent upgrading of the compound seasoning drying process is achieved, and the method has remarkable advantages in the aspects of energy consumption reduction, flavor retention, quality stability and system robustness and is suitable for efficient production requirements of industries such as food processing.

Description

Technical Field

[0001] This invention relates to the technical field of drying control, and more particularly to an intelligent drying control system for the production of compound seasonings. Background Technology

[0002] The production of compound seasonings typically requires the removal of moisture from raw materials to ensure product stability, extend shelf life, and maintain flavor concentration. Drying processes not only remove moisture but also ensure that seasoning components are not damaged, preserving their original aroma and color through temperature and humidity control. Traditional drying methods usually rely on manual temperature and humidity control, which introduces many uncertainties and instabilities, easily leading to uneven product quality, excessive energy consumption, and low production efficiency.

[0003] Currently, Chinese invention patent application number CN202411990556.X discloses a material drying control method, device, equipment, and storage medium, which solves the technical problem of poor material drying effect caused by the mismatch between the control and adjustment of the drying process and the material moisture evaporation in related technologies. This solution can more accurately judge the environmental parameters of the drying process, thereby adjusting the operating parameters of the equipment to match the material moisture evaporation, thus improving the drying effect of the equipment on the material. However, existing technologies have problems such as overheating or underheating when drying compound seasonings, excessive risk of temperature or flavor loss, inability to balance energy consumption and product quality, uneven air velocity and temperature inside the dryer, uneven distribution of solution sets in traditional multi-objective optimization, and uncontrollable internal state of the dryer. Summary of the Invention

[0004] The technical problem solved by this invention is that existing technologies may cause overheating or underheating, excessive risk of temperature or flavor loss, incompatibility between energy consumption and product quality, uneven air velocity and temperature inside the dryer, uneven distribution of solution set in traditional multi-objective optimization, and uncontrollable internal state of the dryer when drying compound seasonings.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an intelligent drying control system for compound seasoning production, comprising a data acquisition module, a control module, an optimization module, and an execution module: The acquisition module is used to acquire two-dimensional heat maps, temperature field distribution maps, and wind speed distribution maps, and to perform characteristic detection on compound seasonings; The control module is used to dynamically adjust the opening and closing angle of the gradually expanding guide pipe and optimize the position of the conical distributor through Kalman filtering. It also adjusts the heating power and fan speed according to the PID formula and protects the compound seasonings from excessive temperature and flavor risks during the drying process. The optimization module is used to construct an energy consumption-quality multi-objective optimization model, and to optimize the energy consumption-quality multi-objective optimization model using an improved genetic algorithm; The execution module is used to perform linkage control on the execution layer devices.

[0006] Preferably, the acquisition module includes: The internal temperature of the dryer is monitored by using an infrared thermal imager and an array of Pt100 temperature sensors. The infrared thermal imager is used to acquire temperature data at different locations inside the dryer in real time, forming a two-dimensional thermal map arranged according to time points. The data collected by each sensor are combined, and a complete temperature field distribution map is generated through spatial interpolation algorithm; The distribution of airflow in various areas of the dryer is monitored by a miniature anemometer array. The real-time collected wind speed data is compared and corrected with the wind speed field data predicted by the CFD model. The anemometer data is adjusted using the model correction algorithm, and the wind speed distribution map is updated once every unit time. The two-dimensional heat map, temperature field distribution map and wind speed distribution map are fed back to the control module in real time.

[0007] Preferably, the characteristic testing of the compound seasoning includes: The moisture content of compound seasonings was determined using an online near-infrared spectrometer. The determination process included: The spectral data of the compound seasoning were collected in real time using a near-infrared spectrometer, and the spectral data were analyzed using a partial least squares regression model. Based on the absorbance and wavelength changes of the sample, the moisture content of the compound seasoning was predicted in real time. The moisture content data is acquired and processed at intervals, and then fed back to the control module. An integrated electronic nose sensor array collects real-time data of volatile flavor compounds, extracts characteristic information of volatile components using principal component analysis, measures concentration using a calibration method, updates volatile compound concentration once every unit time, and outputs volatile compound concentration value to the control module. The particle distribution is monitored by the change in current of the vibrating screen. The current signal is combined with the discrete element model, and the particle size distribution is obtained by reverse calculation. The particle size distribution data is updated at unit time intervals.

[0008] Preferably, the control module includes a temperature-wind speed coordinated control unit, a PID parameter tuning unit, and an inert gas protection unit. The temperature-wind speed co-control unit is used to dynamically adjust the opening and closing angle of the gradually expanding guide pipe and optimize the position of the cone splitter through Kalman filtering; Dynamic adjustment of the opening and closing angle of the gradually expanding guide pipe includes: The temperature field is monitored in real time, and the temperature difference between the pre-divided central and edge regions is calculated. When the temperature difference exceeds a set threshold, an adjustment process is initiated. The adjustment process includes automatically calculating the opening and closing angle of the guide pipe based on the temperature difference. The mathematical expression for the opening and closing angle of the guide pipe is: ; in, The opening and closing angle of the diversion pipe. From a basic perspective, For temperature difference; The opening and closing angle of the flow guide pipe is controlled by a servo motor to precisely adjust the flow guide angle and monitor the temperature difference after adjustment in real time. If the temperature difference does not decrease to the preset temperature threshold, the angle of the flow guide pipe is adjusted until the temperature difference is higher than the preset temperature threshold. Optimizing the position of the tapered splitter using Kalman filtering includes: The temperature field distribution map and wind speed distribution map are extracted to obtain the distribution of airflow inside the dryer. The Kalman filter algorithm is used to process the wind speed and temperature data included in the temperature field distribution map and wind speed distribution map to optimize and predict the position of the conical splitter. The position of the conical splitter is controlled by a stepper motor to ensure the balance of the wind speed field and temperature field. Based on the temperature field distribution map and wind speed distribution map updated at unit time intervals obtained by the acquisition module, the position of the splitter is recursively updated and corrected.

[0009] Preferably, the PID parameter tuning unit includes: Calculate the temperature deviation, which is the difference between the actual temperature and the set temperature, and adjust the heating power according to the PID formula, which is: Heating power = proportional coefficient × temperature deviation + differential coefficient × temperature change rate + compound seasoning flow feedforward compensation; Calculate the wind speed deviation, which is the difference between the actual wind speed and the set wind speed. Then, adjust the fan speed according to a PID formula, which is: Fan speed = proportional coefficient × wind speed deviation + integral coefficient × cumulative wind speed deviation; Adjust the power output of the heater and the speed of the fan.

[0010] Preferably, the inert gas protection unit includes protection against excessively high temperature and flavor risks during the drying process of the compound seasoning, and the protection logic includes: When the risk of temperature or flavor loss is too high, it can be quantitatively expressed by increasing the inert gas flow rate and adjusting the fan speed. When the temperature inside the dryer exceeds a set threshold, or when the concentration of volatile substances decreases beyond a set threshold, inert gas protection is triggered, and the nitrogen flow rate is adjusted. The mathematical expression for adjusting the nitrogen flow rate is: ; in, Nitrogen flow rate, The flavor loss rate is the percentage decrease in the concentration of volatile substances, and the nitrogen supply is adjusted based on the calculated nitrogen flow rate.

[0011] Preferably, constructing an energy consumption-quality multi-objective optimization model includes: Define a dual objective function, which includes an integrated original objective and a new objective. The original objective is the dehumidification capacity per unit of energy consumption, which is obtained by the ratio of input electrical energy to dehydration capacity. The new objective is the flavor retention index, which is the retention rate of volatile component concentration relative to the initial value. The numerical values ​​of the original and newly added objectives are dimensionless, and the original and newly added objectives are combined using a linear weighting method to obtain a comprehensive objective function. The mathematical expression of the comprehensive objective function is as follows: ; in, For the comprehensive objective function, The original target after dimensionless processing. This is the newly added target after dimensionless processing. and The coefficients are constants, and + =1, the weight is adjusted according to user needs, such as energy saving priority. > .

[0012] Preferably, the key parameters of the energy consumption-quality multi-objective optimization model are subject to range constraints and conditional constraints: The key parameters include controllable variables and disturbance variables. Controllable variables include temperature, humidity, wind speed and heat pump compressor frequency. Disturbance variables include fluctuations in the initial moisture content of the compound seasoning and changes in ambient temperature and humidity. The range of controllable variables includes: Temperature is 60-150℃, humidity is 8-20g / kg dry air, wind speed is 0.5-2m / s, and heat pump compressor frequency is 30-60Hz; The range of interference variables includes: The initial moisture content of the compound seasoning fluctuated by ±2%, and the change in ambient temperature and humidity was ±5%. The constraints of a condition constraint include: Flavor substance degradation exceeds the preset degradation threshold; The safe temperature limits are ≤120℃ for salt-based compound seasonings and ≤80℃ for sugar-based compound seasonings; The dryer operates within the following limits: heat pump evaporation temperature ≥ 5℃ and condensation pressure ≤ 1.8MPa.

[0013] Preferably, the energy consumption-quality multi-objective optimization model is optimized using an improved genetic algorithm, and the optimization process includes: The temperature, moisture content, and wind speed data collected by the acquisition module in various areas of the dryer are discretized into binary strings. By combining the comprehensive objective function with a penalty function to handle out-of-bounds solutions, an optimized fitness function is obtained, which includes: ; in, To optimize the fitness function, For the i-th variable, Let i be the allowed value boundary of the i-th variable. Let be the width of the value range for the i-th variable. For variables The absolute distance from the constraint boundary; Based on the output of the optimized energy consumption-quality multi-objective optimization model, the Pareto optimal solution set is selected by non-dominated sorting method to obtain the multi-objective trade-off scheme; The energy consumption-quality multi-objective optimization model is iteratively optimized, and the multi-objective trade-off scheme is updated in real time until the preset iteration threshold is reached and the iteration operation is stopped.

[0014] Preferably, the linkage control includes: Precisely adjust the positions of the guide vanes and distributors, adjust the fan speed, nitrogen supply and airflow circulation, process particles by adjusting the mesh belt turning frequency and vibrating screen, and adaptively handle abnormal situations in the dryer.

[0015] The beneficial effects of this invention are as follows: This invention uses multiple sensors to collect real-time two-dimensional thermal images, temperature fields, wind speed fields, and material characteristic data. Combined with dynamic adjustment of the opening and closing angle of the guide pipe and the position of the conical distributor, it significantly improves temperature uniformity and reduces drying time and energy consumption. A feedforward compensation mechanism is introduced, dynamically adjusting heating power and fan speed based on temperature deviation and flow rate, resulting in faster response and avoiding overheating or underheating. When the risk of temperature or flavor loss is too high, nitrogen flow is automatically increased to inhibit the degradation of volatile substances, preserving the flavor of compound seasonings (such as the aroma of chili powder and cumin seeds) and increasing product added value. An energy consumption-quality dual-objective optimization model is constructed, with dehumidification capacity per unit of energy consumption and flavor retention index as the core objectives. A linear weighted method is used to balance energy saving and quality requirements, achieving efficient resource utilization. Kalman filtering is applied to optimize the position of the physical structure, and the conical distributor is dynamically adjusted through a prediction-correction mechanism to reduce wind speed and temperature non-uniformity, which is superior to traditional PID static control. The formula for adjusting the opening and closing angle of the guide pipe is based on real-time dynamic adjustment of temperature difference, achieving precise closed-loop control. In the heating power regulation, feedforward compensation of compound seasoning flow rate is introduced, combined with temperature deviation and rate of change, to improve the system's anti-interference capability. Energy consumption and flavor retention index are combined into a comprehensive objective function, and multi-objective trade-offs are achieved through dimensionless and linear weighting processing, supporting user-defined optimization directions (such as energy saving or quality preservation priority). The improved genetic algorithm introduces adaptive mutation rate and penalty function constraints to avoid premature convergence and solve the problem of uneven solution set distribution in traditional multi-objective optimization. In the seasoning drying process, dynamic adjustment of nitrogen flow rate and temperature / flavor threshold triggering logic are combined to quantify the protection response, reduce flavor loss, and avoid excessive use of inert gas. The integration of multiple devices such as guide vanes, flow dividers, fans, and vibrating screens, combined with adaptive anomaly handling (such as triggering high-frequency flipping + wind speed pulse when particles agglomerate), forms a closed-loop feedback system to improve the overall process stability. Attached Figure Description

[0016] Figure 1 This is a basic flowchart of an intelligent drying control system for compound seasoning production, provided as an embodiment of the present invention. Detailed Implementation

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0018] Reference Figure 1 As one embodiment of the present invention, an intelligent drying control system for compound seasoning production is provided, including a data acquisition module, a control module, an optimization module, and an execution module: The data acquisition module is used to acquire two-dimensional heat maps, temperature field distribution maps, and wind speed distribution maps, and to perform characteristic detection on compound seasonings; The control module is used to dynamically adjust the opening and closing angle of the gradually expanding guide pipe and optimize the position of the conical distributor through Kalman filtering. It also adjusts the heating power and fan speed according to the PID formula and protects the compound seasoning from excessive temperature and flavor risks during the drying process. The optimization module is used to construct an energy consumption-quality multi-objective optimization model, and to optimize the energy consumption-quality multi-objective optimization model using an improved genetic algorithm; The execution module is used to perform linkage control on the execution layer devices.

[0019] The data acquisition module includes: The internal temperature of the dryer is monitored by using an infrared thermal imager and an array of Pt100 temperature sensors. The infrared thermal imager is used to acquire temperature data at different locations inside the dryer in real time, with a temperature range of 0-150℃, forming a two-dimensional thermal map arranged according to time points. The data collected by each sensor are combined, and a complete temperature field distribution map is generated through spatial interpolation algorithm; The distribution of airflow in various areas of the dryer is monitored by a miniature anemometer array. The real-time collected wind speed data is compared and corrected with the wind speed field data predicted by the CFD model. The model correction algorithm is used to adjust the anemometer data to ensure the consistency between the actual measurement results and the prediction results. The wind speed distribution map is updated once every unit of time, and the two-dimensional heat map, temperature field distribution map and wind speed distribution map are fed back to the control module in real time.

[0020] The characteristics of compound seasonings are tested, including: The moisture content of compound seasonings was determined using an online near-infrared spectrometer. The determination process included: The spectral data of the compound seasoning were collected in real time using a near-infrared spectrometer, and the spectral data were analyzed using a partial least squares regression model. Based on the absorbance and wavelength changes of the sample, the moisture content of the compound seasoning was predicted in real time. The moisture content data is acquired and processed at intervals, and then fed back to the control module for dynamic adjustment of the drying process. An integrated electronic nose sensor array collects real-time data of volatile flavor compounds, extracts characteristic information of volatile components using principal component analysis, measures concentration using a calibration method, updates volatile compound concentration once every unit time, and outputs volatile compound concentration value to the control module. The particle distribution is monitored by the change in current of the vibrating screen. The change in current of the vibrating screen reflects the particle size distribution. The motion information of the particles is captured by the change in vibration signal. The current signal is combined with the discrete element model, and the particle size distribution is obtained by reverse calculation. The particle size distribution data is updated at unit time intervals to ensure the consistency of compound seasoning during the drying process.

[0021] Through the above steps, various key data can be collected in real time to ensure accurate monitoring and feedback of temperature, wind speed, moisture content of compound seasonings, concentration of flavor substances and particle size distribution, thereby providing reliable data support for intelligent drying control.

[0022] The control module includes a temperature-wind speed coordinated control unit, a PID parameter tuning unit, and an inert gas protection unit. The temperature-wind speed co-control unit is used to dynamically adjust the opening and closing angle of the gradually expanding guide pipe and optimize the position of the cone splitter through Kalman filtering; The dynamically adjustable opening and closing angle of the gradually expanding guide pipe is used to reduce the temperature difference within the dryer and ensure uniform temperature distribution by adjusting the opening and closing angle of the guide pipe, including: The temperature field is monitored in real time, and the temperature difference between the pre-divided central and edge regions is calculated. When the temperature difference exceeds a set threshold, an adjustment process is initiated. This process includes automatically calculating the opening and closing angle of the guide pipe based on the temperature difference. The mathematical expression for the opening and closing angle of the guide pipe is: ; in, The opening and closing angle of the diversion pipe. From a basic perspective, For temperature difference; The opening and closing angle of the guide pipe is controlled by a servo motor, and the guide angle is precisely adjusted to achieve uniformity of the temperature field. The temperature difference after adjustment is monitored in real time. If the temperature difference does not decrease to the preset temperature threshold, the angle of the guide pipe is adjusted until the temperature difference is higher than the preset temperature threshold. Kalman filtering is used to optimize the position of the conical splitter to ensure uniform airflow distribution, thereby improving temperature uniformity. This includes: The temperature field distribution map and wind speed distribution map are extracted to obtain the distribution of airflow inside the dryer. The Kalman filter algorithm is used to process the wind speed and temperature data included in the temperature field distribution map and wind speed distribution map to optimize and predict the position of the conical splitter to reduce the non-uniformity of wind speed and temperature. The position of the conical splitter is controlled by a stepper motor to ensure the balance of the wind speed field and temperature field. Based on the temperature field distribution map and wind speed distribution map updated at unit time intervals obtained by the acquisition module, the position of the splitter is recursively updated and corrected.

[0023] The PID parameter tuning unit includes: Calculate the temperature deviation, which is the difference between the actual temperature and the set temperature. Adjust the heating power according to the PID formula, which is: Heating power = proportional coefficient × temperature deviation + differential coefficient × temperature change rate + compound seasoning flow feedforward compensation; The feedforward compensation for compound seasoning flow is obtained through a compensation mechanism; Calculate the wind speed deviation, which is the difference between the actual wind speed and the set wind speed. Then, adjust the fan speed according to a PID formula, which is: Fan speed = proportional coefficient × wind speed deviation + integral coefficient × cumulative wind speed deviation; Adjust the heater's power output and the fan speed to ensure that the temperature and airflow remain within the set range.

[0024] The inert gas protection unit includes protection against excessive temperature and flavor risks during the drying process of compound seasonings. The protection logic includes: When the risk of temperature or flavor loss is too high, flavor loss can be prevented by increasing the inert gas flow rate and adjusting the fan speed. A quantitative representation of an excessively high risk of temperature or flavor loss is as follows: When the temperature inside the dryer exceeds a set threshold, or when the concentration of volatile substances decreases beyond a set threshold, inert gas protection is triggered, and the nitrogen flow rate is adjusted. The mathematical expression for adjusting the nitrogen flow rate is: ; in, Nitrogen flow rate, The flavor loss rate is the percentage decrease in the concentration of volatile substances. The nitrogen supply is adjusted based on the calculated nitrogen flow rate to achieve a protective effect.

[0025] Through real-time PID regulation, temperature-wind speed coordinated control, and inert gas protection strategy, this control layer can effectively adjust temperature, wind speed, and gas flow to ensure temperature uniformity and wind speed stability during the drying process. It also reduces flavor loss through nitrogen protection, achieving efficient and safe intelligent drying control.

[0026] Constructing an energy consumption-quality multi-objective optimization model includes: Define a dual objective function, which includes an integrated original objective and a new objective. The original objective is the dehumidification capacity per unit energy consumption (kg / kWh), which reflects the drying efficiency. The dehumidification capacity per unit energy consumption is obtained by the ratio of the input electrical energy to the amount of water removed. The new objective is the flavor retention index, which is the retention rate (%) of the volatile component concentration relative to the initial value. The numerical values ​​of the original and newly added objectives are dimensionless, and then the original and newly added objectives are combined using a linear weighting method to obtain the comprehensive objective function. The mathematical expression of the comprehensive objective function is as follows: ; in, For the comprehensive objective function, The original target after dimensionless processing. This is the newly added target after dimensionless processing. and The coefficients are constants, and + =1, the weight is adjusted according to user needs, such as energy saving priority. > .

[0027] Range and condition constraints are imposed on the key parameters of the energy consumption-quality multi-objective optimization model: Key parameters include controllable variables and disturbance variables. Controllable variables include temperature, humidity, wind speed and heat pump compressor frequency. Disturbance variables include fluctuations in the initial moisture content of the compound seasoning and changes in ambient temperature and humidity. The range of controllable variables includes: Temperature is 60-150℃, humidity is 8-20g / kg dry air, wind speed is 0.5-2m / s, and heat pump compressor frequency is 30-60Hz; The range of interference variables includes: The initial moisture content of the compound seasoning fluctuated by ±2%, and the change in ambient temperature and humidity was ±5%. The constraints of a condition constraint include: The degradation of flavor compounds exceeds the preset degradation threshold, as determined by sensory evaluation. The safe temperature limits are ≤120℃ for salt-based compound seasonings and ≤80℃ for sugar-based compound seasonings; The dryer operates within the following limits: heat pump evaporation temperature ≥ 5℃ and condensation pressure ≤ 1.8MPa.

[0028] The energy consumption-quality multi-objective optimization model was optimized using an improved genetic algorithm. The optimization process included: The temperature, moisture content, and wind speed data collected by the acquisition module in various areas of the dryer are discretized into binary strings. By combining the comprehensive objective function with a penalty function to handle out-of-bounds solutions, the optimal fitness function is obtained. The optimal fitness function includes: ; in, To optimize the fitness function, For the i-th variable, Let i be the allowed value boundary of the i-th variable. Let be the width of the value range for the i-th variable. For variables The absolute distance from the constraint boundary, for example: if the allowed range of a variable is [50℃, 100℃], and the current value is 110℃, then |110-100|=10; The overall logic of the fitness function includes: F prioritizes ensuring the overall performance of the solution by balancing energy consumption and quality; the penalty term ∏ penalizes out-of-bounds variables, reducing the fitness of illegal solutions; if all variables are within the legal range, the penalty term is 1, and the fitness equals F; if a variable goes out of bounds, the penalty term is less than 1, and the fitness value is weakened. Eliminate dimensional differences to ensure that different variables have a fair impact on fitness; Individual selection is performed using a roulette wheel, where individuals with higher fitness have a higher probability of entering the next generation. The single-point crossover probability is set to 0.8 to preserve superior genes from the parents, and the adaptive mutation rate is used to avoid premature convergence.

[0029] Based on the output of the optimized energy consumption-quality multi-objective optimization model, the Pareto optimal solution set is selected by non-dominated sorting method to obtain the multi-objective trade-off scheme; The energy consumption-quality multi-objective optimization model is iteratively optimized, and the multi-objective trade-off scheme is updated in real time until the preset iteration threshold is reached and the iteration operation is stopped.

[0030] Linkage control includes: Precisely adjust the positions of the guide vanes and distributors to control temperature and airflow, adjust fan speed, nitrogen supply and airflow circulation to ensure uniform drying, optimize the drying process by adjusting the mesh belt turning frequency and vibrating screen, and perform adaptive abnormal handling of the dryer.

[0031] Adaptive exception handling includes: Addressing uneven temperature distribution includes adding guide vanes and adjusting pipe angles.

[0032] Particle agglomeration treatment includes: increasing the flipping frequency and enabling wind speed pulses.

[0033] Flavor loss treatment includes increasing nitrogen flow and appropriately cooling the air.

[0034] Handling excessive energy consumption includes adjusting energy consumption weights and enabling waste heat recovery.

[0035] Algorithm execution example (chili powder + cumin seeds) Initial setup: chili powder in the high-temperature zone, cumin seeds in the low-temperature zone, and nitrogen replacement to ensure low oxygen content.

[0036] Dynamic adjustment: If the temperature in the high-temperature zone is too high, adjust the angle between the distributor and the pipe.

[0037] When the wind speed is too low, activate the wind speed pulse.

[0038] Increase nitrogen flow and lower temperature when flavor is lost.

[0039] Waste heat recovery will be activated when energy consumption exceeds the standard.

[0040] This invention utilizes multiple sensors to collect real-time data on two-dimensional thermal maps, temperature fields, wind speed fields, and material characteristics. Combined with dynamic adjustment of the opening and closing angle of the guide pipes and the position of the conical distributor, it significantly improves temperature uniformity and reduces drying time and energy consumption. A feedforward compensation mechanism is introduced, dynamically adjusting heating power and fan speed based on temperature deviation and flow rate, resulting in faster response and preventing overheating or underheating. When the risk of temperature or flavor loss is too high, nitrogen flow is automatically increased to inhibit the degradation of volatile substances, preserving the flavor of compound seasonings (such as the aroma of chili powder and cumin seeds) and increasing product added value. An energy consumption-quality dual-objective optimization model is constructed, with dehumidification capacity per unit of energy consumption and flavor retention index as core objectives. A linear weighted method is used to balance energy saving and quality requirements, achieving efficient resource utilization. Kalman filtering is applied to optimize the physical structure's position, and a predictive-correction mechanism dynamically adjusts the conical distributor, reducing wind speed and temperature non-uniformity, which is superior to traditional PID static control. The formula for adjusting the opening and closing angle of the guide pipes is based on real-time dynamic adjustment of temperature difference, achieving precise closed-loop control. In the heating power regulation, feedforward compensation of compound seasoning flow rate is introduced, combined with temperature deviation and rate of change, to improve the system's anti-interference capability. Energy consumption and flavor retention index are combined into a comprehensive objective function, and multi-objective trade-offs are achieved through dimensionless and linear weighting processing, supporting user-defined optimization directions (such as energy saving or quality preservation priority). The improved genetic algorithm introduces adaptive mutation rate and penalty function constraints to avoid premature convergence and solve the problem of uneven solution set distribution in traditional multi-objective optimization. In the seasoning drying process, dynamic adjustment of nitrogen flow rate and temperature / flavor threshold triggering logic are combined to quantify the protection response, reduce flavor loss, and avoid excessive use of inert gas. The integration of multiple devices such as guide vanes, flow dividers, fans, and vibrating screens, combined with adaptive anomaly handling (such as triggering high-frequency flipping + wind speed pulse when particles agglomerate), forms a closed-loop feedback system to improve the overall process stability.

[0041] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can be implemented in the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can be implemented in the form of computer program products embodied on one or more computer-usable storage media containing computer-usable program code. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0042] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent drying control system for compound seasoning production, characterized in that, It includes a data acquisition module, a control module, an optimization module, and an execution module: The acquisition module is used to acquire two-dimensional heat maps, temperature field distribution maps, and wind speed distribution maps, and to perform characteristic detection on compound seasonings; The control module is used to dynamically adjust the opening and closing angle of the gradually expanding guide pipe and optimize the position of the conical distributor through Kalman filtering. It also adjusts the heating power and fan speed according to the PID formula and protects the compound seasonings from excessive temperature and flavor risks during the drying process. The optimization module is used to construct an energy consumption-quality multi-objective optimization model, and to optimize the energy consumption-quality multi-objective optimization model using an improved genetic algorithm; The execution module is used to perform linkage control on the execution layer devices.

2. The intelligent drying control system for compound seasoning production as described in claim 1, characterized in that, The acquisition module includes: The internal temperature of the dryer is monitored by using an infrared thermal imager and an array of Pt100 temperature sensors. The infrared thermal imager is used to acquire temperature data at different locations inside the dryer in real time, forming a two-dimensional thermal map arranged according to time points. The data collected by each sensor are combined, and a complete temperature field distribution map is generated through spatial interpolation algorithm; The distribution of airflow in various areas of the dryer is monitored by a miniature anemometer array. The real-time collected wind speed data is compared and corrected with the wind speed field data predicted by the CFD model. The anemometer data is adjusted using the model correction algorithm, and the wind speed distribution map is updated once every unit time. The two-dimensional heat map, temperature field distribution map and wind speed distribution map are fed back to the control module in real time.

3. The intelligent drying control system for compound seasoning production as described in claim 2, characterized in that, The characteristics of compound seasonings are tested, including: The moisture content of compound seasonings was determined using an online near-infrared spectrometer. The determination process included: The spectral data of the compound seasoning were collected in real time using a near-infrared spectrometer, and the spectral data were analyzed using a partial least squares regression model. Based on the absorbance and wavelength changes of the sample, the moisture content of the compound seasoning was predicted in real time. The moisture content data is acquired and processed at intervals, and then fed back to the control module. An integrated electronic nose sensor array collects real-time data of volatile flavor compounds, extracts characteristic information of volatile components using principal component analysis, measures concentration using a calibration method, updates volatile compound concentration once every unit time, and outputs volatile compound concentration value to the control module. The particle distribution is monitored by the change in current of the vibrating screen. The current signal is combined with the discrete element model, and the particle size distribution is obtained by reverse calculation. The particle size distribution data is updated at unit time intervals.

4. The intelligent drying control system for compound seasoning production as described in claim 3, characterized in that, The control module includes a temperature-wind speed coordinated control unit, a PID parameter tuning unit, and an inert gas protection unit. The temperature-wind speed co-control unit is used to dynamically adjust the opening and closing angle of the gradually expanding guide pipe and optimize the position of the cone splitter through Kalman filtering; Dynamic adjustment of the opening and closing angle of the gradually expanding guide pipe includes: The temperature field is monitored in real time, and the temperature difference between the pre-divided central and edge regions is calculated. When the temperature difference exceeds a set threshold, an adjustment process is initiated. The adjustment process includes automatically calculating the opening and closing angle of the guide pipe based on the temperature difference. The mathematical expression for the opening and closing angle of the guide pipe is: ； in, The opening and closing angle of the diversion pipe. From a basic perspective, For temperature difference; The opening and closing angle of the flow guide pipe is controlled by a servo motor to precisely adjust the flow guide angle and monitor the temperature difference after adjustment in real time. If the temperature difference does not decrease to the preset temperature threshold, the angle of the flow guide pipe is adjusted until the temperature difference is higher than the preset temperature threshold. Optimizing the position of the tapered splitter using Kalman filtering includes: The temperature field distribution map and wind speed distribution map are extracted to obtain the distribution of airflow inside the dryer. The Kalman filter algorithm is used to process the wind speed and temperature data included in the temperature field distribution map and wind speed distribution map to optimize and predict the position of the conical splitter. The position of the conical splitter is controlled by a stepper motor to ensure the balance of the wind speed field and temperature field. Based on the temperature field distribution map and wind speed distribution map updated at unit time intervals obtained by the acquisition module, the position of the splitter is recursively updated and corrected.

5. The intelligent drying control system for compound seasoning production as described in claim 4, characterized in that, The PID parameter tuning unit includes: Calculate the temperature deviation, which is the difference between the actual temperature and the set temperature, and adjust the heating power according to the PID formula, which is: Heating power = proportional coefficient × temperature deviation + differential coefficient × temperature change rate + compound seasoning flow feedforward compensation; Calculate the wind speed deviation, which is the difference between the actual wind speed and the set wind speed. Then, adjust the fan speed according to a PID formula, which is: Fan speed = proportional coefficient × wind speed deviation + integral coefficient × cumulative wind speed deviation; Adjust the power output of the heater and the speed of the fan.

6. The intelligent drying control system for compound seasoning production as described in claim 5, characterized in that, The inert gas protection unit includes protection against excessively high temperature and flavor risks during the drying process of the compound seasoning. The protection logic includes: When the risk of temperature or flavor loss is too high, it can be quantitatively expressed by increasing the inert gas flow rate and adjusting the fan speed. When the temperature inside the dryer exceeds a set threshold, or when the concentration of volatile substances decreases beyond a set threshold, inert gas protection is triggered, and the nitrogen flow rate is adjusted. The mathematical expression for adjusting the nitrogen flow rate is: ； in, Nitrogen flow rate, The flavor loss rate is the percentage decrease in the concentration of volatile substances, and the nitrogen supply is adjusted based on the calculated nitrogen flow rate.

7. The intelligent drying control system for compound seasoning production as described in claim 6, characterized in that, Constructing an energy consumption-quality multi-objective optimization model includes: Define a dual objective function, which includes an integrated original objective and a new objective. The original objective is the dehumidification capacity per unit of energy consumption, which is obtained by the ratio of input electrical energy to dehydration capacity. The new objective is the flavor retention index, which is the retention rate of volatile component concentration relative to the initial value. The numerical values ​​of the original and newly added objectives are dimensionless, and the original and newly added objectives are combined using a linear weighting method to obtain a comprehensive objective function. The mathematical expression of the comprehensive objective function is as follows: ； in, For the comprehensive objective function, The original target after dimensionless processing. This is the newly added target after dimensionless processing. and The coefficients are constants, and + =1, the weight is adjusted according to user needs, such as energy saving priority. > .

8. The intelligent drying control system for compound seasoning production as described in claim 7, characterized in that, The key parameters of the energy consumption-quality multi-objective optimization model are subject to range and condition constraints: The key parameters include controllable variables and disturbance variables. Controllable variables include temperature, humidity, wind speed and heat pump compressor frequency. Disturbance variables include fluctuations in the initial moisture content of the compound seasoning and changes in ambient temperature and humidity. The range of controllable variables includes: Temperature is 60-150℃, humidity is 8-20g / kg dry air, wind speed is 0.5-2m / s, and heat pump compressor frequency is 30-60Hz; The range of interference variables includes: The initial moisture content of the compound seasoning fluctuated by ±2%, and the change in ambient temperature and humidity was ±5%. The constraints of a condition constraint include: Flavor substance degradation exceeds the preset degradation threshold; The safe temperature limits are ≤120℃ for salt-based compound seasonings and ≤80℃ for sugar-based compound seasonings; The dryer operates within the following limits: heat pump evaporation temperature ≥ 5℃ and condensation pressure ≤ 1.8MPa.

9. The intelligent drying control system for compound seasoning production as described in claim 8, characterized in that, The energy consumption-quality multi-objective optimization model is optimized using an improved genetic algorithm. The optimization process includes: The temperature, moisture content, and wind speed data collected by the acquisition module in various areas of the dryer are discretized into binary strings. By combining the comprehensive objective function with a penalty function to handle out-of-bounds solutions, an optimized fitness function is obtained, which includes: ； in, To optimize the fitness function, For the i-th variable, Let i be the allowed value boundary of the i-th variable. Let be the width of the value range for the i-th variable. For variables The absolute distance from the constraint boundary; Based on the output of the optimized energy consumption-quality multi-objective optimization model, the Pareto optimal solution set is selected by non-dominated sorting method to obtain the multi-objective trade-off scheme; The energy consumption-quality multi-objective optimization model is iteratively optimized, and the multi-objective trade-off scheme is updated in real time until the preset iteration threshold is reached and the iteration operation stops.

10. The intelligent drying control system for compound seasoning production as described in claim 9, characterized in that, Linkage control includes: Precisely adjust the positions of the guide vanes and distributors, adjust the fan speed, nitrogen supply and airflow circulation, process particles by adjusting the mesh belt turning frequency and vibrating screen, and adaptively handle abnormal situations in the dryer.

Images