A soy sauce koji-making whole-process temperature and humidity intelligent control method, device, equipment and readable storage medium

Abstract

The present application relates to the brewing technical field, specifically to a kind of soy sauce koji-making whole process temperature and humidity intelligent control method, device, equipment and readable storage medium, soy sauce koji-making whole process temperature and humidity intelligent control method includes collecting real-time operating parameter, calculates temperature and humidity real-time control deviation;Real-time control deviation is decoupled based on feedforward decoupling compensation structure and is handled, obtains mutually independent temperature decoupling deviation and humidity decoupling deviation;Call fuzzy gain scheduling rule base, according to temperature decoupling deviation, humidity decoupling deviation and respective deviation change rate, output proportional-integral controller parameter real-time correction quantity;Based on the reference parameter and real-time correction quantity of predetermination, obtain the real-time proportional-integral controller control parameter adapted to current working condition;Using the real-time proportional-integral controller control parameter calculation final control instruction, drive corresponding actuator to run, and adjust koji-making environment temperature and humidity to set value.

Description

Technical Field

[0001] This invention relates to a method, device, equipment, and readable storage medium for intelligent temperature and humidity control throughout the entire process of soy sauce koji making, belonging to the field of brewing technology. Background Technology

[0002] During the soy sauce brewing process, the growth and reproduction of microorganisms and the synthesis of enzymes are extremely sensitive to environmental temperature and humidity: in the early stage of koji making, temperature and humidity need to be increased to promote spore germination; in the middle stage, temperature and humidity need to be controlled and stabilized to maintain efficient enzyme synthesis; and in the later stage, temperature and humidity need to be decreased to inhibit the growth of miscellaneous bacteria. Small fluctuations in temperature and humidity can not only directly affect the growth rate and enzyme activity level of microorganisms, but also lead to batch differences in the quality of koji, and even cause contamination by miscellaneous bacteria, resulting in production losses.

[0003] Traditional koji-making processes often rely on manual, experience-based adjustments of equipment such as fans, heaters, and humidifiers. This approach suffers from drawbacks such as control lag, large errors, and dependence on operator experience, making it difficult to achieve precise temperature and humidity control. Consequently, the consistency of enzyme activity in the koji is poor, raw material utilization is low, and the needs of large-scale, standardized soy sauce production cannot be met. With the development of automation technology, some koji-making equipment has introduced single-variable PID control to independently regulate temperature or humidity. However, temperature and humidity in the koji-making environment exhibit strong coupling characteristics: adjusting fans and heaters simultaneously affects the humidity in the koji room, and adjusting humidifiers causes temperature fluctuations. Single-variable control cannot effectively counteract the coupling interference between temperature and humidity loops, easily leading to control oscillations, large overshoot, and high steady-state errors, making it difficult to achieve coordinated and stable temperature and humidity control.

[0004] In existing technologies, some solutions employ feedforward decoupling or fuzzy PID control methods to control the temperature and humidity during koji making. However, these methods still have several limitations: First, existing decoupling controls are mostly based on simplified model designs and do not fully consider the changes in operating conditions throughout the entire koji making cycle, as well as the strong disturbances caused by microbial metabolism and koji turning operations. Therefore, the decoupling effect is limited and cannot completely eliminate the control interference caused by temperature and humidity coupling. Second, traditional PID control parameters often rely on manual trial-and-error tuning, which is highly subjective and makes it difficult to obtain optimal parameters suitable for all stages of koji making. Some solutions that use particle swarm optimization algorithms to optimize PID parameters do not introduce actuator saturation constraints, which can easily lead to fans, valves, and other equipment operating at saturation levels for extended periods. First, existing control schemes often suffer from high energy consumption and severe equipment wear and tear. Second, they mostly employ fixed-parameter PID control, which cannot adjust control parameters online according to changes in operating conditions and disturbances during the early, middle, and late stages of koji making. This results in weak anti-disturbance capabilities, and when faced with sudden conditions such as microbial metabolic heat and humidity release and koji turning, the temperature and humidity recovery time is long, making it difficult to guarantee control accuracy. Third, existing technologies lack an integrated control scheme that combines model identification, feedforward decoupling, offline parameter optimization, and online adaptive correction. This makes it impossible to achieve adaptive control without human intervention throughout the entire koji making process. Operators still need to frequently adjust parameters according to changes in operating conditions, resulting in high reliance on manual intervention and low production efficiency. Summary of the Invention

[0005] This invention addresses the shortcomings of existing technologies by providing a method, apparatus, equipment, and readable storage medium for intelligent temperature and humidity control throughout the entire process of soy sauce koji making, aiming to solve the aforementioned problems.

[0006] The technical solution of this invention to solve the above-mentioned technical problems is as follows: A method for intelligent temperature and humidity control throughout the entire process of soy sauce koji making, comprising the following steps: Collect the measured values ​​of temperature and humidity in the current koji-making environment and the real-time operating parameters of each actuator. Calculate the real-time temperature and humidity control deviation based on the set and measured values ​​of temperature and humidity corresponding to the current koji-making stage. Based on the feedforward decoupling compensation structure, the real-time control deviation is decoupled to obtain independent temperature decoupling deviation and humidity decoupling deviation. The fuzzy gain scheduling rule library is invoked to output the real-time correction amount of the proportional-integral controller parameters based on the temperature decoupling deviation, humidity decoupling deviation and their respective deviation change rates. Based on the predetermined baseline parameters and real-time correction values, the real-time proportional-integral controller control parameters adapted to the current operating conditions are obtained. The final control command is calculated using the control parameters of the real-time proportional-integral controller, which drives the corresponding actuator to operate and adjusts the temperature and humidity of the koji-making environment to the set value.

[0007] In a preferred embodiment provided by the present invention, the feedforward decoupling compensation structure is pre-constructed through the following steps: Collect temperature and humidity data and actuator operating parameters throughout the entire historical koji-making cycle; identify and establish a multi-input multi-output coupled mathematical model of temperature and humidity, wherein the coupled mathematical model takes the control quantity of the actuator as input and the temperature and humidity of the koji-making environment as output; Based on the coupled mathematical model, the coupling interference between the temperature control loop and the humidity control loop is calculated, and a feedforward decoupling compensation matrix is ​​constructed to form the feedforward decoupling compensation structure.

[0008] In a preferred embodiment of the present invention, when establishing the coupled mathematical model, the effects of the heater on humidity and the humidifier on temperature are considered as weakly coupled terms and ignored.

[0009] In a preferred embodiment provided by the present invention, the reference parameters of the proportional-integral controller are predetermined through the following steps: based on the stretching coupling mathematical model, a simulation environment for the entire koji-making process is built; In the simulation environment, the particle swarm optimization algorithm is used to perform offline optimization of the proportional-integral controller parameters to obtain the optimal fixed parameters that are suitable for the entire music production process, which are then used as the reference parameters for the proportional-integral controller.

[0010] In a preferred embodiment of the present invention, the fuzzy gain scheduling rule library is pre-established through the following steps: based on the simulation environment, temperature and humidity control data under different working conditions are obtained; combined with the experience of koji-making process control, fuzzy control rules are established with temperature and humidity decoupling deviation and deviation change rate as inputs and proportional-integral controller parameter correction amount as outputs, thus forming the fuzzy gain scheduling rule library.

[0011] In a preferred embodiment provided by the present invention, the coupled mathematical model includes: ; in: T(s) represents the temperature output; H(s) represents the humidity output; Uf(s) is the fan control input; Ud(s) is the control input for the air valve; Uh(s) is the heater control input; Um(s) is the humidifier control input; GTf(s) represents the model of the fan's effect on temperature; GTd(s) represents the model of the effect of the damper on temperature; GTh(s) represents the heater's effect on temperature model; GHf(s) represents the model of the effect of the fan on humidity; GHd(s) represents the model of the effect of the damper on humidity; GHh(s) represents the humidifier's effect on humidity.

[0012] In a preferred embodiment provided by the present invention, the method employs a temperature main control loop, a humidity main control loop, and a temperature and humidity auxiliary control loop; The fan is used to regulate the airflow speed and serves as the main temperature control loop to achieve temperature regulation through negative feedback; the air valve is used to regulate the ratio of fresh air to circulating air and serves as the main humidity control loop to achieve humidity regulation through negative feedback; the heater is used for auxiliary heating under low temperature conditions; and the humidifier is used for auxiliary humidification under low humidity conditions. By comparing the setpoints for temperature and humidity with the real-time monitored values, the proportional-integral controller outputs control commands to achieve closed-loop control of the temperature and humidity in the koji-making environment.

[0013] This invention also provides an intelligent temperature and humidity control device for the entire process of soy sauce koji making, comprising: The data acquisition module is used to collect the measured values ​​of temperature and humidity in the current koji-making environment and the real-time operating parameters of each actuator. Based on the set and measured values ​​of temperature and humidity corresponding to the current koji-making stage, the module calculates the real-time control deviation of temperature and humidity. The feedforward decoupling module is used to decouple the real-time control deviation based on the feedforward decoupling compensation structure, so as to obtain independent temperature decoupling deviation and humidity decoupling deviation. The fuzzy gain scheduling module is used to call the fuzzy gain scheduling rule library and output the real-time correction amount of the proportional-integral controller parameters based on the temperature decoupling deviation, humidity decoupling deviation and their respective deviation change rates. The control module is used to obtain real-time proportional-integral controller control parameters adapted to the current operating conditions based on predetermined reference parameters and real-time correction values. The actuator control module is used to calculate the final control command using the control parameters of the real-time proportional-integral controller, drive the corresponding actuator to run, and adjust the temperature and humidity of the fermentation environment to the set value.

[0014] Furthermore, to achieve the above objectives, the present invention also provides an intelligent temperature and humidity control device for the entire process of soy sauce koji making. The intelligent temperature and humidity control device for the entire process of soy sauce koji making includes a processor, a memory, and an intelligent temperature and humidity control program for the entire process of soy sauce koji making stored in the memory and executable by the processor. When the intelligent temperature and humidity control program for the entire process of soy sauce koji making is executed by the processor, the steps of the intelligent temperature and humidity control method for the entire process of soy sauce koji making described above are implemented.

[0015] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a temperature and humidity intelligent control program for the entire process of soy sauce koji making, wherein when the temperature and humidity intelligent control program for the entire process of soy sauce koji making is executed by a processor, the steps of the temperature and humidity intelligent control method for the entire process of soy sauce koji making as described above are implemented.

[0016] The beneficial effects of this invention are as follows: By collecting real-time temperature and humidity data of the koji-making environment and actuator operating parameters to form control deviations, and combining this with a feedforward decoupling compensation structure to decouple the temperature and humidity deviations, the coupling relationship between the temperature and humidity control loops is effectively weakened, avoiding the mutual disturbance problem of temperature adjustment interfering with humidity and humidity adjustment affecting temperature. Relying on the fuzzy gain scheduling rule library, the proportional-integral controller parameter correction is dynamically output according to the decoupling deviation and the deviation change rate. Combined with preset benchmark parameters, the controller control parameters are updated in real time, which can adapt to the changes in different working conditions in the early, middle, and late stages of soy sauce koji-making, while effectively resisting process disturbances such as microbial heat and humidity generation and koji turning. By generating control commands by matching the proportional-integral control parameters of the working conditions in real time and driving the actuator to accurately regulate, the overshoot and steady-state error of temperature and humidity control are significantly reduced, the disturbance recovery adjustment time is shortened, and the control stability and anti-interference ability are significantly improved. The entire process realizes closed-loop adaptive intelligent regulation of temperature and humidity, eliminating the need for frequent manual adjustment of controller parameters, ensuring a stable and consistent temperature and humidity environment throughout the koji-making process, which is conducive to improving the uniformity of koji quality and the utilization rate of raw materials. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the hardware structure of the intelligent temperature and humidity control device for the entire process of soy sauce koji making involved in this invention; Figure 2 This is a flowchart illustrating the intelligent temperature and humidity control method for the entire process of soy sauce koji making involved in this invention. Figure 3 This is a structural diagram of the temperature and humidity closed-loop control system of the present invention; Figure 4 This is a diagram of the temperature and humidity feedforward decoupling control structure of the present invention; Figure 5 This is a diagram of the PSO-PI offline optimization module of the present invention; Figure 6 This is a flowchart of the PSO optimization method of the present invention; Figure 7 This is a structural diagram of the fuzzy gain PI control system of the present invention.

[0018] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0020] The intelligent temperature and humidity control method for the entire process of soy sauce koji making involved in this invention is mainly applied to the intelligent temperature and humidity control equipment for the entire process of soy sauce koji making. This intelligent temperature and humidity control equipment for the entire process of soy sauce koji making can be a PC, a portable computer, a mobile terminal, or other devices with display and processing functions.

[0021] Reference Figure 1 , Figure 1 This is a schematic diagram of the hardware structure of the intelligent temperature and humidity control device for the entire soy sauce koji-making process involved in the embodiments of the present invention. In this embodiment, the intelligent temperature and humidity control device for the entire soy sauce koji-making process may include a processor 1001 (e.g., CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize communication between these components; the user interface 1003 may include a display screen or an input unit such as a keyboard; the network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface); the memory 1005 may be a high-speed RAM memory or a stable non-volatile memory, such as a disk storage device, and the memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0022] Those skilled in the art will understand that Figure 1 The hardware structure shown does not constitute a limitation on the intelligent temperature and humidity control device for the entire process of soy sauce koji making. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0023] Continue to refer to Figure 1 , Figure 1 The memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, and an intelligent temperature and humidity control program for the entire process of soy sauce koji making.

[0024] exist Figure 1 In this embodiment, the network communication module is mainly used to connect to the server and communicate with the server for data; while the processor 1001 can call the intelligent temperature and humidity control program for the entire process of soy sauce koji making stored in the memory 1005 and execute the intelligent temperature and humidity control method for the entire process of soy sauce koji making provided in this embodiment.

[0025] This invention provides a method for intelligent temperature and humidity control throughout the entire process of soy sauce koji making, with reference to... Figures 2-3 The steps include: S10. Collect the measured values ​​of temperature and humidity in the current koji-making environment and the real-time operating parameters of each actuator. Calculate the real-time temperature and humidity control deviation based on the set and measured values ​​of temperature and humidity corresponding to the current koji-making stage. S20. Based on the feedforward decoupling compensation structure, the real-time control deviation is decoupled to obtain independent temperature decoupling deviation and humidity decoupling deviation. S30. Call the fuzzy gain scheduling rule library and output the real-time correction amount of the proportional-integral controller parameters based on the temperature decoupling deviation, humidity decoupling deviation and their respective deviation change rates. S40. Based on the predetermined reference parameters and real-time correction values, obtain the real-time proportional-integral controller control parameters adapted to the current operating conditions. S50. The final control command is calculated using the control parameters of the real-time proportional-integral controller, and the corresponding actuator is driven to run, so as to adjust the temperature and humidity of the koji-making environment to the set value.

[0026] This invention first collects real-time measured data of temperature and humidity in the koji-making environment and the operating parameters of each actuator. Combined with the setpoints for temperature and humidity at different stages of the koji-making process, the real-time control deviations of temperature and humidity are calculated. Then, using a feedforward decoupling compensation structure, the coupled temperature and humidity control deviations are decoupled and descrambled, resulting in independent temperature and humidity decoupling deviations, eliminating the drawbacks of mutual influence between temperature and humidity loops. Subsequently, using the decoupling deviation and its rate of change as the criterion, a fuzzy gain scheduling rule library is invoked for intelligent matching and inference, outputting real-time correction values ​​for the proportional-integral controller parameters. The pre-determined proportional-integral baseline parameters are coupled and corrected with the real-time correction values ​​to generate real-time control parameters adapted to the actual working conditions of the koji-making process. Finally, the updated real-time proportional-integral control parameters are used to generate precise control commands, driving the corresponding actuators to adjust the koji-making environment. Through continuous closed-loop regulation, the temperature and humidity are automatically and stably maintained at the process setpoints throughout the entire koji-making process, adaptively matching changes in working conditions and the impact of on-site disturbances at each stage of koji-making.

[0027] In this embodiment, compared with the prior art, the present invention has the following beneficial effects: The feedforward decoupling control method effectively weakens the coupling effect between temperature and humidity, improving system stability. The PSO algorithm is used for offline optimization of PI parameters, obtaining the optimal control parameters across the entire process range and improving control accuracy. Online dynamic correction of PI parameters is achieved through fuzzy gain scheduling, enhancing the system's adaptability to different operating conditions and complex disturbances. This effectively reduces system overshoot, system error, and disturbance rejection performance, improving temperature and humidity control accuracy. It also reduces the probability of long-term saturation operation of actuators, extending equipment lifespan. Furthermore, it can adapt to the multi-stage process requirements of soy sauce koji making, improving the stability of koji quality.

[0028] The feedforward decoupling compensation structure is pre-built through the following steps: Collect temperature and humidity data and actuator operating parameters throughout the entire historical koji-making cycle; identify and establish a multi-input multi-output coupled mathematical model of temperature and humidity, wherein the coupled mathematical model takes the control quantity of the actuator as input and the temperature and humidity of the koji-making environment as output; Based on the coupled mathematical model, the coupling interference between the temperature control loop and the humidity control loop is calculated, and a feedforward decoupling compensation matrix is ​​constructed to form the feedforward decoupling compensation structure.

[0029] When establishing the coupled mathematical model, the effects of the heater on humidity and the humidifier on temperature are considered as weakly coupled terms and ignored.

[0030] The reference parameters of the proportional-integral controller are predetermined through the following steps: Based on the scaling coupling mathematical model, a simulation environment for the entire koji-making process is built; In the simulation environment, the particle swarm optimization algorithm is used to perform offline optimization of the proportional-integral controller parameters to obtain the optimal fixed parameters that are suitable for the entire music production process, which are then used as the reference parameters for the proportional-integral controller.

[0031] The fuzzy gain scheduling rule base is pre-established through the following steps: based on the simulation environment, acquire temperature and humidity control data under different working conditions; combine the experience of koji-making process control, take the temperature and humidity decoupling deviation and deviation change rate as input, and the proportional-integral controller parameter correction amount as output, establish fuzzy control rules, and form the fuzzy gain scheduling rule base.

[0032] In this embodiment, the method employs a temperature main control loop, a humidity main control loop, and a temperature and humidity auxiliary control loop. The fan is used to regulate the airflow speed and serves as the main temperature control loop to achieve temperature regulation through negative feedback; the air valve is used to regulate the ratio of fresh air to circulating air and serves as the main humidity control loop to achieve humidity regulation through negative feedback; the heater is used for auxiliary heating under low temperature conditions; and the humidifier is used for auxiliary humidification under low humidity conditions. By comparing the setpoints for temperature and humidity with the real-time monitored values, the proportional-integral controller outputs control commands to achieve closed-loop control of the temperature and humidity in the koji-making environment.

[0033] This invention provides another embodiment of a method for intelligent temperature and humidity control throughout the entire process of soy sauce koji making, comprising the following steps: Step 1: Collect temperature and humidity data and actuator operating parameters during the koji-making process, and identify the coupled mathematical model of temperature and humidity with multiple inputs and multiple outputs; Step 2: Based on the coupled mathematical model, construct a temperature and humidity multi-input multi-output control system, establish a temperature and humidity closed-loop control structure based on PI control, and set up a simulation environment for the entire koji-making process. Step 3: Use the feedforward decoupling method to decouple the temperature and humidity coupled control loop, and establish and obtain PI control parameters; Step 4: Use the Particle Swarm Optimization (PSO) algorithm to perform offline optimization on the conventional PI control parameters to obtain the optimal fixed parameters throughout the entire koji-making process; Step 5: Based on the optimal fixed parameters, a fuzzy control method is introduced to dynamically correct the PI control parameters online, and a fuzzy gain scheduling PI control structure is constructed to achieve adaptive control of temperature and humidity under different working conditions throughout the koji-making process.

[0034] In step 1, a coupled mathematical model of temperature and humidity with multiple inputs and multiple outputs is established: ; in: T(s) represents the temperature output; H(s) represents the humidity output; Uf(s) is the fan control input; Ud(s) is the control input for the air valve; Uh(s) is the heater control input; Um(s) is the humidifier control input; GTf(s) represents the model of the fan's effect on temperature; GTd(s) represents the model of the effect of the damper on temperature; GTh(s) represents the heater's effect on temperature model; GHf(s) represents the model of the effect of the fan on humidity; GHd(s) represents the model of the effect of the damper on humidity; GHh(s) represents the humidifier's effect on humidity.

[0035] Since the effects of the heater on humidity and the humidifier on temperature are weaker than the coupling effect between the fan and the valve, they are treated as weak coupling terms and ignored in this embodiment, and the corresponding transfer function is simplified to 0.

[0036] In step 2, the temperature and humidity multi-input multi-output control system includes a temperature main control loop, a humidity main control loop, and a temperature and humidity auxiliary control loop. in: The fan is used to regulate the airflow speed and serves as the main temperature control loop to achieve temperature regulation through negative feedback. The air valve is used to adjust the ratio of fresh air to circulating air, and as the main humidity control loop, it achieves humidity regulation through negative feedback. The heater is used for auxiliary heating under low-temperature conditions; Humidifiers are used for auxiliary humidification in low humidity conditions; The control system compares the setpoints for temperature and humidity with the real-time monitored values, and outputs control commands via a PI controller to achieve closed-loop control of the temperature and humidity in the koji-making environment.

[0037] In step 3, a feedforward decoupling method is used to weaken the coupling effect between the temperature loop and the humidity loop. The feedforward decoupling compensation matrix is ​​as follows: ; In step 4, based on the actual koji-making process requirements, the koji-making process is divided into an early stage, a middle stage, and a late stage, and the following are introduced into the simulation environment: microbial exothermic disturbance; microbial moisture release disturbance; koji-turning disturbance; and initial environmental value setting.

[0038] In step 4, the Particle Swarm Optimization (PSO) algorithm is used to optimize the PI control parameters offline. The integral time absolute error (ITAE) index is used as the optimization objective function, and an actuator saturation constraint penalty term is introduced. The optimization objective function is as follows: ; in: e(t) represents the systematic error; ω and λ are penalty coefficients.

[0039] U represents the saturation penalty term for the executor.

[0040] Optimization parameters include: Temperature proportionality coefficient Kp_T; Temperature integral coefficient Ki_T; Humidity proportionality coefficient Kp_H; Humidity integral coefficient Ki_H.

[0041] In step 5, the system error and the rate of change of error are used as inputs to the fuzzy controller, and the PI parameter correction values ​​ΔKp and ΔKi are output after fuzzy inference. Based on the aforementioned correction amount, the PI controller parameters are dynamically corrected online to obtain: Kp = Kp0 + ΔKp; Ki = Ki0 + ΔKi; Wherein, Kp0 and Ki0 are the optimal parameters obtained by the PSO algorithm offline optimization; The fuzzy controller uses fuzzy linguistic variables: NB,NS,ZO,PS,PB; it establishes temperature and humidity control rules based on system error and error change rate, and adjusts PI parameters online to achieve adaptive temperature and humidity control under different working conditions throughout the entire koji-making process.

[0042] Specifically, the present invention provides a method for controlling temperature and humidity throughout the entire process of soy sauce koji making, comprising the following steps: 1. Collect temperature and humidity data and actuator operating parameters during the koji-making process, and identify the dynamic mathematical model of the temperature and humidity control system; 2. Based on the dynamic mathematical model, a temperature and humidity multi-input multi-output control system is constructed, and a temperature and humidity closed-loop control structure based on PI control is established. 3. The temperature and humidity coupled control loop is decoupled using a feedforward decoupling method to establish a simulation environment for temperature and humidity control throughout the entire koji-making process and obtain PI control parameters; 4. The Particle Swarm Optimization (PSO) algorithm is used to perform offline optimization of the conventional PI control parameters to obtain the optimal fixed parameters throughout the entire koji-making process; 5. Based on the optimal fixed parameters, a fuzzy control method is introduced to dynamically correct the PI control parameters online, and a fuzzy gain scheduling PI control structure is constructed to achieve adaptive control of temperature and humidity under different working conditions throughout the entire koji-making process.

[0043] In this embodiment, PI stands for Proportional-Integral Controller.

[0044] Furthermore, the specific implementation process of each step will be explained in detail with reference to specific embodiments. This embodiment takes the koji-making process of brewing original soy sauce using a disc koji-making machine as an example: Step S1: System data acquisition and modeling; Temperature and humidity sensors are installed at the air return vent and in the center of the disc-shaped koji-making machine on site to collect real-time temperature and humidity data of the koji-making environment.

[0045] The control actuator includes: Fans, fresh air valves, heaters, and humidifiers.

[0046] in: The fan frequency adjustment range is set to 5% to 100%; The opening range of the fresh air valve is set to 5% to 100%; The heater power range is set to 0–100%; The humidifier power range is set from 0 to 100%.

[0047] Establish a multi-input, multi-output coupled model of temperature and humidity in the koji-making environment.

[0048] ; in: T(s) represents the temperature output; H(s) represents the humidity output; Uf(s) is the fan control input; Ud(s) is the control input for the air valve; Uh(s) is the heater control input; Um(s) is the humidifier control input; GTf(s) represents the model of the fan's effect on temperature; GTd(s) represents the model of the effect of the damper on temperature; GTh(s) represents the heater's effect on temperature model; GHf(s) represents the model of the effect of the fan on humidity; GHd(s) represents the model of the effect of the damper on humidity; GHh(s) represents the humidifier's effect on humidity.

[0049] Since the effects of the heater on humidity and the humidifier on temperature are weaker than the coupling effect between the fan and the valve, they are treated as weak coupling terms and ignored in this embodiment, and the corresponding transfer function is simplified to 0.

[0050] Step excitation signals were applied to each actuator, and the temperature and humidity response curves were recorded. The collected data were then filtered, normalized, and outlier removed.

[0051] The transfer functions of each actuator are obtained using a system identification method: ; ; ; ; ; ; Step S2: Establish the PI control structure; Establish a temperature and humidity multi-input multi-output control system.

[0052] in: The fan acts as the main temperature control actuator; The fresh air valve acts as the main humidity control actuator. The heater serves as an auxiliary heating actuator; The humidifier serves as an auxiliary humidification actuator.

[0053] In the simulation software environment, a working condition model of the entire koji-making process is set up, and a PI control system structure is established. The control system acquires temperature and humidity feedback values ​​in real time, compares them with the set values, and outputs control commands through the PI controller to achieve closed-loop control.

[0054] The music production process includes: The initial stage of koji making, involving raising the temperature and humidity; The mid-stage of koji making involves stable cultivation under controlled temperature and humidity. The cooling and dehumidification stage in the later stage of koji making; in: The initial temperature setting is 32℃, and the humidity setting is 80%RH. The mid-term temperature setting is 34℃, and the humidity setting is 90%RH. The temperature gradually decreased to 25℃ and the humidity gradually decreased to 60%RH. At the same time, the following is introduced into the simulation environment: Initial ambient temperature and humidity; Microbial exothermic disturbances and moisture-releasing disturbances; Flip-over perturbation; in: The initial temperature was 25℃ and the humidity was 60%RH; The microbial disturbance time was 1500 minutes in total; The folding perturbation occurs in the middle of the process, between 700 and 900 minutes.

[0055] Step 3: Feedforward decoupling control; A feedforward decoupling method is used to establish a decoupling compensator to weaken the coupling effect between temperature and humidity. The feedforward decoupling compensator is represented as follows: ; In the decoupled control structure of the simulation software system, a better control effect is obtained by adjusting the PI parameters. At this time, the control parameters are: Kp_T=18, Ki_T=0.5, Kp_H=5, Ki_H=0.01; Step 4: PSO Offline Optimization The Particle Swarm Optimization (PSO) algorithm is adopted, with the integral time absolute error (ITAE) index as the optimization objective function, and an actuator saturation constraint penalty term is introduced. The objective function is: ; in: e(t) represents the systematic error; ω and λ are penalty coefficients.

[0056] U is the actuator saturation penalty term, represented by the sum of the saturation times of the fan and the damper: ; The saturation operating time of the fan and the damper are expressed as follows: ; ; in: ; ; The PSO algorithm is used to optimize the following parameters: Temperature proportionality coefficient Kp_T; Temperature integral coefficient Ki_T; Humidity proportionality coefficient Kp_H; Humidity integral coefficient Ki_H.

[0057] Obtain the optimal fixed parameters throughout the entire process: Kp_T=25.23,Ki_T=0.51,Kp_H=7.96,Ki_H=0.0068.

[0058] Step 5: Online adjustment of fuzzy gain PI; Using error e and error change rate de as input variables, fuzzy rules for temperature and humidity are compiled respectively, and a fuzzy controller is established to realize adaptive control under different working conditions at different stages of the entire koji-making process.

[0059] Input variables: Error e and rate of change of error de; Output variables: Parameter corrections ΔKp and ΔKi; Based on the aforementioned correction amount, the PI controller parameters are dynamically corrected online to obtain: Kp = Kp0 + ΔKp; Ki = Ki0 + ΔKi; Wherein, Kp0 and Ki0 are the optimal parameters obtained by the PSO algorithm offline optimization; The fuzzy universes of discourse for e and de, as well as the fuzzy universes of discourse for the adjustment variables ΔKp and ΔKi, are all determined to be [-1,1]. The fuzzy word set corresponding to the fuzzy domain is {NB.NS,ZO,PS,PB}, which are negative large, negative small, zero, positive small, and positive large, respectively. The membership function uses a triangular membership function.

[0060] Establish 25 fuzzy rules each for temperature proportionality coefficient, integral coefficient, and humidity proportionality coefficient, totaling 100 rules.

[0061] Examples of some fuzzy rules: When constructing the remaining fuzzy rules, consider the following principles: The temperature and humidity main loop has a negative feedback transmission relationship, and the Kp design is biased towards the negative error region to enhance the main control effect; The temperature and humidity rules are designed differently. The temperature rule avoids integral saturation, while the humidity rule focuses on time delay characteristics.

[0062] The results show that, in terms of temperature control, the fuzzy gain PI control system is significantly superior in terms of overshoot and steady-state error parameters. Particularly during the turbulence disturbance stage, the temperature overshoot was 1.74℃, 0.8℃, and 0.48℃, respectively, and the disturbance recovery times were 197 min, 64 min, and 0 min, respectively. IAE and ITAE also decreased by 36.7% and 53%, respectively, demonstrating a significant improvement in overall error control and residual elimination capabilities. In terms of humidity control, the fuzzy gain PI control system performs better in terms of global error indicators, with IAE reduced by 37% and ITAE by 57.7%. The initial overshoot decreased from 3.43% RH to 1.06% RH, and the disturbance overshoot decreased from 6.13% RH to 3.35% RH.

[0063] The designed intelligent temperature and humidity control system exhibits excellent control performance, with advantages such as high stability, small overshoot, and strong anti-interference capability. It can provide a stable temperature and humidity environment for the entire koji-making process. This invention also provides an intelligent temperature and humidity control device for the entire process of soy sauce koji making, comprising: The data acquisition module is used to collect the measured values ​​of temperature and humidity in the current koji-making environment and the real-time operating parameters of each actuator. Based on the set and measured values ​​of temperature and humidity corresponding to the current koji-making stage, the module calculates the real-time control deviation of temperature and humidity. The feedforward decoupling module is used to decouple the real-time control deviation based on the feedforward decoupling compensation structure, so as to obtain independent temperature decoupling deviation and humidity decoupling deviation. The fuzzy gain scheduling module is used to call the fuzzy gain scheduling rule library and output the real-time correction amount of the proportional-integral controller parameters based on the temperature decoupling deviation, humidity decoupling deviation and their respective deviation change rates. The control module is used to obtain real-time proportional-integral controller control parameters adapted to the current operating conditions based on predetermined reference parameters and real-time correction values. The actuator control module is used to calculate the final control command using the control parameters of the real-time proportional-integral controller, drive the corresponding actuator to run, and adjust the temperature and humidity of the fermentation environment to the set value.

[0064] Furthermore, embodiments of the present invention also provide a computer-readable storage medium.

[0065] The present invention stores a temperature and humidity intelligent control program for the entire process of soy sauce koji making on a computer-readable storage medium. When the temperature and humidity intelligent control program for the entire process of soy sauce koji making is executed by a processor, it implements the steps of the temperature and humidity intelligent control method for the entire process of soy sauce koji making as described above.

[0066] The method implemented when the intelligent temperature and humidity control program for the entire process of soy sauce koji making is executed can be referred to in various embodiments of the intelligent temperature and humidity control method for the entire process of soy sauce koji making of this invention, and will not be repeated here.

[0067] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0068] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0069] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0070] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0071] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are exhaustively listed. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0072] For those skilled in the art, various modifications and improvements can be made without departing from the concept of the present invention, and these modifications and improvements are all within the scope of protection of the present invention. The scope of protection of the present invention is defined by the appended claims.

Claims

1. A method for intelligent temperature and humidity control throughout the entire process of soy sauce koji making, comprising the following steps: Collect the measured values ​​of temperature and humidity in the current koji-making environment and the real-time operating parameters of each actuator. Calculate the real-time temperature and humidity control deviation based on the set and measured values ​​of temperature and humidity corresponding to the current koji-making stage. Based on the feedforward decoupling compensation structure, the real-time control deviation is decoupled to obtain independent temperature decoupling deviation and humidity decoupling deviation. The fuzzy gain scheduling rule library is invoked to output the real-time correction amount of the proportional-integral controller parameters based on the temperature decoupling deviation, humidity decoupling deviation and their respective deviation change rates. Based on the predetermined baseline parameters and real-time correction values, the real-time proportional-integral controller control parameters adapted to the current operating conditions are obtained. The final control command is calculated using the control parameters of the real-time proportional-integral controller, which drives the corresponding actuator to operate and adjusts the temperature and humidity of the koji-making environment to the set value.

2. The intelligent temperature and humidity control method for the entire process of soy sauce koji making according to claim 1, characterized in that, The feedforward decoupling compensation structure is pre-built through the following steps: Collect temperature and humidity data and actuator operating parameters throughout the entire historical music production cycle; A coupled mathematical model of temperature and humidity with multiple inputs and multiple outputs is identified and established. The coupled mathematical model takes the control quantity of the actuator as input and the temperature and humidity of the fermentation environment as output. Based on the coupled mathematical model, the coupling interference between the temperature control loop and the humidity control loop is calculated, and a feedforward decoupling compensation matrix is ​​constructed to form the feedforward decoupling compensation structure.

3. The intelligent temperature and humidity control method for the entire process of soy sauce koji making according to claim 2, characterized in that, When establishing the coupled mathematical model, the effects of the heater on humidity and the humidifier on temperature are considered as weakly coupled terms and ignored.

4. The intelligent temperature and humidity control method for the entire process of soy sauce koji making according to claim 2, characterized in that, The reference parameters of the proportional-integral controller are determined in advance through the following steps: Based on the scaling coupling mathematical model, a simulation environment for the entire koji-making process is built; In the simulation environment, the particle swarm optimization algorithm is used to perform offline optimization of the proportional-integral controller parameters to obtain the optimal fixed parameters that are suitable for the entire music production process, which are then used as the reference parameters for the proportional-integral controller.

5. The intelligent temperature and humidity control method for the entire process of soy sauce koji making according to claim 4, characterized in that, The fuzzy gain scheduling rule base is pre-established through the following steps: based on the simulation environment, acquire temperature and humidity control data under different working conditions; combine the experience of koji-making process control, take the temperature and humidity decoupling deviation and deviation change rate as input, and the proportional-integral controller parameter correction amount as output, establish fuzzy control rules, and form the fuzzy gain scheduling rule base.

6. The intelligent temperature and humidity control method for the entire process of soy sauce koji making according to claim 2, characterized in that, The coupled mathematical model includes: ; in: T(s) represents the temperature output; H(s) represents the humidity output; Uf(s) is the fan control input; Ud(s) is the control input for the air valve; Uh(s) is the heater control input; Um(s) is the humidifier control input; GTf(s) represents the model of the fan's effect on temperature; GTd(s) represents the model of the effect of the damper on temperature; GTh(s) represents the heater's effect on temperature model; GHf(s) represents the model of the effect of the fan on humidity; GHd(s) represents the model of the effect of the damper on humidity; GHh(s) represents the humidifier's effect on humidity.

7. The intelligent temperature and humidity control method for the entire process of soy sauce koji making according to claim 1, characterized in that, The method employs a main temperature control loop, a main humidity control loop, and auxiliary temperature and humidity control loops. The fan is used to regulate the airflow speed and serves as the main temperature control loop to achieve temperature regulation through negative feedback; the air valve is used to regulate the ratio of fresh air to circulating air and serves as the main humidity control loop to achieve humidity regulation through negative feedback; the heater is used for auxiliary heating under low temperature conditions; and the humidifier is used for auxiliary humidification under low humidity conditions. By comparing the setpoints for temperature and humidity with the real-time monitored values, the proportional-integral controller outputs control commands to achieve closed-loop control of the temperature and humidity in the koji-making environment.

8. A smart temperature and humidity control device for the entire process of soy sauce koji making, characterized in that, include: The data acquisition module is used to collect the measured values ​​of temperature and humidity in the current koji-making environment and the real-time operating parameters of each actuator. Based on the set and measured values ​​of temperature and humidity corresponding to the current koji-making stage, the module calculates the real-time control deviation of temperature and humidity. The feedforward decoupling module is used to decouple the real-time control deviation based on the feedforward decoupling compensation structure, so as to obtain independent temperature decoupling deviation and humidity decoupling deviation. The fuzzy gain scheduling module is used to call the fuzzy gain scheduling rule library and output the real-time correction amount of the proportional-integral controller parameters based on the temperature decoupling deviation, humidity decoupling deviation and their respective deviation change rates. The control module is used to obtain real-time proportional-integral controller control parameters adapted to the current operating conditions based on predetermined reference parameters and real-time correction values. The actuator control module is used to calculate the final control command using the control parameters of the real-time proportional-integral controller, drive the corresponding actuator to run, and adjust the temperature and humidity of the fermentation environment to the set value.

9. A temperature and humidity intelligent control device for the entire process of soy sauce koji making, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, it implements the steps of the intelligent temperature and humidity control method for the entire process of soy sauce koji making as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the intelligent temperature and humidity control method for the entire process of soy sauce koji making as described in any one of claims 1 to 7.

Images