Modeling method of temperature control model for litchi preservation and thawing based on thermodynamic model in electromagnetic field

Abstract

The application provides a modeling method of a litchi preservation and thawing temperature control model based on a thermodynamic model in an electromagnetic field, and specifically comprises the following steps: S1, establishing a thermodynamic model of a litchi preservation and thawing system; S2, obtaining the specific heat capacity of litchi according to the thermodynamic model; S3, calculating the internal temperature of litchi; S4, constructing a GRU model, and using the internal temperature data of litchi obtained in step S3 and the collected thawing environment temperature and thawing water bath temperature as a training set to train the GRU model; S5, optimizing the GRU model by using a whale optimization algorithm, and the optimized GRU model outputs a litchi thawing temperature T pred (t), wherein t is time: S6, constructing a litchi thawing temperature control strategy based on a fuzzy PID controller, using T pred (t) as the input of the litchi thawing temperature control strategy, comparing T pred (t) with a preset value, and performing output control according to the comparison result.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of litchi preservation and thawing, and particularly relates to a modeling method of a litchi preservation and thawing temperature control model based on a thermodynamic model in an electromagnetic field. BACKGROUND

[0002] In the field of food science, tropical fruits such as litchi are popular due to their unique flavor and nutritional value. However, their market season is concentrated, preservation is difficult, and shelf life is extremely short, which severely limits market expansion and industrial economic benefits. Liquid nitrogen quick-freezing is an efficient food freezing technology that can rapidly reduce the temperature of food below freezing point in a very short time, forming fine and uniform ice crystals to maintain the texture, color, and nutritional value of food. However, during freezing and thawing, it is easily affected by temperature fluctuations, leading to poor texture, flavor loss, and degradation of nutritional components. Traditional thawing methods, such as natural room temperature thawing, water bath thawing, or steam thawing, often have problems such as uneven thawing, long time, and adverse effects on fruit quality. To solve these problems, researchers have begun to explore methods of using electromagnetic fields to improve litchi quality during thawing.

[0003] Electromagnetic fields resonate with water molecules in litchi, interfering with the formation and stability of hydrogen bonds between water molecules, thereby inhibiting the freezing of water in litchi. Based on this principle, electromagnetic fields are applied to litchi ice temperature preservation, and auxiliary thawing equipment is used to avoid the freezing of water in litchi under conditions of large temperature fluctuations, thereby improving thawing quality.

[0004] With the in-depth study of heat conduction theory, it is possible to establish thermodynamic models to simulate the heat conduction process. These models can effectively predict the temperature changes of litchi under different environmental conditions, helping to optimize the thawing strategy. At the same time, the rapid development of deep learning and artificial intelligence technology makes data-driven methods a reality. By using historical data and real-time monitoring information, combined with the output of thermodynamic models, an intelligent prediction system can be designed to dynamically adjust the temperature control during thawing.

[0005] The combination of thermodynamic models and deep learning provides a new solution for the thawing process of fruits such as litchi. By accurately simulating the temperature changes of litchi under different environmental conditions through heat conduction models, combined with the nonlinear modeling capabilities of deep learning, the internal temperature changes of fruits during thawing can be more accurately predicted. Deep learning algorithms can process and analyze data in real time, allowing the control system to dynamically adjust heating or cooling strategies and electromagnetic field parameters based on real-time temperature data, ensuring that fruits are in the best thawing state. SUMMARY

[0006] The main purpose of the present application is to provide a lychee preservation and thawing temperature control model modeling method based on a thermodynamic model in an electromagnetic field, which combines the thermodynamic model with deep learning to establish a more accurate control model.

[0007] To achieve the above purpose, the technical scheme adopted by the present application is as follows: a lychee preservation and thawing temperature control model modeling method based on a thermodynamic model in an electromagnetic field, specifically comprising the following steps:

[0008] S1, establishing a thermodynamic model of a lychee preservation and thawing system;

[0009] S2, obtaining the specific heat capacity of lychee according to the thermodynamic model;

[0010] S3, calculating the internal temperature of lychee by the following formula:

[0011]

[0012] T lychee (t) is the calculated internal temperature of lychee at time t, q is the heat absorbed by lychee per unit time, which is calculated from the thermodynamic model, T' lychee is the initial temperature of lychee before thawing, which is obtained by detection, m is the mass of lychee, c lychee is the specific heat capacity of lychee, which is obtained from step S2;

[0013] S4, constructing a GRU model, using the internal temperature data of lychee obtained from step S3 and the collected thawing environment temperature and thawing water bath temperature as a training set to train the GRU model;

[0014] S5, optimizing the GRU model using a whale optimization algorithm, and the optimized GRU model outputs the lychee thawing temperature T pred (t), t is time:

[0015] S6, constructing a lychee thawing temperature control strategy based on a fuzzy PID controller, T pred (t) as the input of the lychee thawing temperature control strategy, comparing T pred (t) with a preset value, and performing output control according to the comparison result.

[0016] Preferably, the step S1 specifically comprises the following steps:

[0017] S11: the heater transfers heat to the heat pipe through heat conduction, the heat pipe is a high-efficiency heat conducting material, quickly transferring heat to water, and the heat output by the heat pipe is obtained by the following formula:

[0018] Q1=Pt(2),

[0019] Wherein, Q1 is the heat transferred from the heat pipe to the water per unit time, P is the heating power of the heat pipe, and t is the working time of the heater or the heat pipe;

[0020] S12, the water heated by the heat pipe transfers heat to the air through heat convection, and the heat transferred from the water to the air is calculated by the following formula:

[0021] Q2=U2A water (T water -T air ) (3),

[0022] Wherein, Q2 is the heat transferred from the water to the air per unit time, U2 is the heat transfer coefficient of the water, A water is the surface area of the water in contact with the air, T water is the current temperature of the water, T airr is the current temperature of the air, and T water is the current temperature of the water;

[0023] S13: the air transfers part of the heat to the litchi, and the heat transferred from the air to the litchi is as follows:

[0024] Q3=U3A air (T air -T lychee ) (4),

[0025] Wherein, Q3 is the heat transferred from the air to the litchi per unit time, U3 is the heat transfer coefficient of the air, A air is the surface area of the air in contact with the litchi, T airr is the current temperature of the air, and T lychee is the current temperature of the litchi;

[0026] Step 14, since the heat pipe is completely inserted into the water, based on the heat balance relationship, we have:

[0027] Q1=Q2+Q3, and further we have:

[0028] Q3=Q1-Q2 (5);

[0029] S15, substituting Q3 into the formula in step 13, we get U3;

[0030] S16, obtain the heat formula of the litchi:

[0031] Q4=m lychee c lychee (T lychee -T l ‘ ychee ) (6),

[0032] Wherein, Q4 is the heat absorbed by the litchi per unit time, mlychee c is the specific heat capacity of the litchi, lychee c is the specific heat capacity of the litchi, lychee T is the current temperature of the litchi, l T is the current temperature of the litchi, ychee T is the initial temperature of the litchi before thawing;

[0033] Step 17, since the heat change of the litchi is equal to the heat transferred to the litchi by the air, Q3 = Q4, c is calculated by the formula in step S16. lychee .

[0034] Preferably, in the step S4, the GRU model comprises an input layer, a GRU layer, and an output layer, and the GRU model is controlled by 2 gate structures, specifically including the following steps:

[0035] Step S41, determining the training set of the GRU model, the training set is represented as [x i (t)train,y i (t)train,z i (t)train], wherein,

[0036]

[0037] x i (t)train is a temperature history data sequence collected by the thawing environment temperature sensor, y i (t)train is a water bath temperature history data sequence, z i (t)train is a litchi internal temperature data sequence, m is the sequence length, a is the number of thawing environment temperature data sequences, b is the number of water bath temperature data sequences, and n is the number of litchi temperature data sequences.

[0038] Step S42, updating the 2 control gates and unit information of the GRU model using the following formula and the training set:

[0039] r t = σ(W r · [h t-1 , x t ] + B r ) (10),

[0040] z t = σ(W z · [h t-1 , x t ] + B z ) (11),

[0041]

[0042] wherein, W r, W z are the weight matrices of the reset gate and update gate respectively, B r , B z , B h are the bias matrices of the reset gate, update gate and candidate hidden state respectively t is the output of the reset gate at time t, z t is the output of the update gate at time t, x t , h t , represent the input, output and hidden layer update candidate value of the hidden layer node at the current moment respectively, h t-1 represents the output of the hidden layer node at the previous moment, and represents Hadamard product, represents the product of matrix elements, σ is a sigmoid activation function, the output is 0 to 1, tanh is a hyperbolic tangent activation function, the output is -1 to 1, x t , y t and z t are the data at time t in the training set

[0043] [x i (t)train,y i (t)train,,z i (t)train];

[0044] Step S43, the prediction value of the output layer of the GRU model is obtained as T t :

[0045] T t = (W y h t +b y ) (14),

[0046] wherein, W y is the output weight, and b y is the output bias;

[0047] Preferably, step S6 specifically comprises the following steps:

[0048] S61: defining the input variable and output variable of the fuzzy PID controller, the input variable is the temperature deviation e t and the temperature change rate de / dt at time t:

[0049] e t = T set - T pred (t) (17),

[0050]

[0051] wherein T setFor the set target temperature,

[0052] The output variable u is represented as follows:

[0053]

[0054] S62: Introduce fuzzy rules: Fuzzify the input quantity, and convert the actual measured temperature deviation e... t The temperature deviation and the rate of change of temperature, de / dt, are used as inputs to the fuzzy PID controller. Fuzzy inference is performed on the temperature deviation and the rate of change of temperature using an empirically based fuzzy control rule table to obtain a fuzzy representation of the fuzzy PID controller's adjustment parameters. Inverse fuzziness is achieved by applying the fuzzy PID controller adjustment parameters ΔK obtained through fuzzy inference to the temperature deviation and the rate of change of temperature. p ΔK i and ΔK d The centroid method is used to convert the values ​​into explicit numerical values.

[0055] Step S73: Based on the obtained adjustment parameter ΔK p ΔK i and ΔK d For K p K i K d Update:

[0056] K p (n)=K p (n-1)+ΔK p (n),

[0057] K i (n)=K i (n-1)+ΔK i (n),

[0058] K d (n)=K d (n-1)+ΔK d (n),

[0059] In the formula, K p (n-1), K i (n-1), K d (n-1) represents the initial scaling factor, integral factor, and differential factor, ΔK p (n), ΔK i (n), ΔK d (n) represents the adjustment parameters for the scaling factor, integral factor, and differential factor after fuzzy calculation, K p (n), K i (n), K d (n) represents the proportional factor, integral factor, and differential factor after fuzzy calculation adjustment.

[0060] Compared with the prior art, the present application has the following beneficial effects:

[0061] The modeling method of the litchi preservation and thawing temperature control model based on the thermodynamic model in the electromagnetic field of the present application comprises the following steps: BRIEF DESCRIPTION OF DRAWINGS

[0062] Figure 1 is the modeling flowchart of the present application;

[0063] Figure 2 is the structure diagram of the GRU model;

[0064] Figure 3 is the flowchart of the whale optimization algorithm;

[0065] Figure 4 is the membership function curve of the fuzzy PID controller;

[0066] Figure 5 is the fuzzy rule table of the fuzzy PID controller. DETAILED DESCRIPTION

[0067] The following description is used to disclose the present application so that those skilled in the art can implement the present application. The preferred embodiments in the following description are only as examples, and other obvious modifications can be conceived by those skilled in the art.

[0068] The modeling method of the litchi preservation and thawing temperature control model based on the thermodynamic model in the electromagnetic field, specifically comprises the following steps:

[0069] S1, a thermodynamic model is established to obtain the specific heat capacity of litchi: during thawing, the heater heats the heat pipe, the heat is inserted into the water to heat the water, and the litchi to be thawed is placed directly above the water. The thawing process of litchi from the heat pipe through water, air to litchi involves multiple heat transfer mechanisms, including heat conduction and heat convection. By obtaining the data of each stage in the heat transfer process, the specific heat capacity of litchi is calculated:

[0070] S11: the heater transmits heat to the heat pipe by heat conduction, the heat pipe is a high-efficiency heat-conducting material, quickly transmits heat to the water, and the heat output by the heat pipe is obtained by the following formula:

[0071] Q1 = Pt (1),

[0072] wherein Q1 is the heat transferred by the heat pipe to the water per unit time (W), P is the heating power of the heat pipe (W), and t is the time during which the heater or the heat pipe is in operation;

[0073] S12, the water heated by the heat pipe transfers heat to the air by heat convection, and the heat transferred by the water to the air is calculated by the following formula:

[0074] Q2 = U2A water (T water -T air ) (3),

[0075] wherein Q2 is the heat transferred by the water to the air per unit time (W), U2 is the heat transfer coefficient of the water (W / (m 2 ·K), A water is the surface area of the water in contact with the air (m 2 ), T water is the current temperature of the water (℃), and T airr is the current temperature of the air (℃);

[0076] S13, the air transfers a portion of the heat to the litchi, and the heat transferred by the air to the litchi is as follows:

[0077] Q3 = U3A air (T air -T lychee ) (4),

[0078] wherein Q3 is the heat transferred by the air to the litchi per unit time (W), U3 is the heat transfer coefficient of the air (W / (m 2 ·K), A air is the surface area of the air in contact with the litchi (m 2 ), T air is the current temperature of the air (℃), and T lychee is the current temperature of the litchi (℃);

[0079] Step 14, since the heat pipe is completely inserted into the water, based on the heat balance relationship, the following can be obtained:

[0080] Q1 = Q2 + Q3, and further, the following can be obtained:

[0081] Q3 = Q1 - Q2;

[0082] S15, substituting Q3 into formula (4) to obtain U3;

[0083] S16, obtaining the heat formula of the litchi:

[0084] Q4 = m lychee c lychee (T lychee -T l ‘ ychee ) (5),

[0085] wherein Q4 is the heat absorbed by litchi per unit time (W), m lychee is the mass of litchi (Kg), c lychee is the specific heat capacity of litchi (J / (Kg·K), T lychee is the current temperature of litchi (℃), T' lychee is the initial temperature of litchi before thawing (℃);

[0086] Step 17, since the heat change of litchi is equal to the heat transferred to litchi by air, Q3 = Q4, c lychee is calculated by formula (5).

[0087] S2: Establish a temperature prediction model based on the thermodynamic model, and calculate the internal temperature T lychee (t) of litchi:

[0088]

[0089] wherein t is the thawing time (s), q is the heat absorbed by litchi per unit time (W), which is calculated by the above thermodynamic model, i.e. q = Q4, T' lychee is the initial temperature of litchi before thawing, m is the mass of litchi (Kg), c lychee is the specific heat capacity of litchi (J / (Kg·K), the input of this temperature prediction model is based on the thermodynamic model, and the main purpose is to generate training data for GRU model;

[0090] S3: Collect data such as thawing environment temperature T air , water bath temperature T water during thawing, and internal temperature T lychee (t) of litchi calculated by formula (6):

[0091] The collected water bath temperature, thawing environment temperature and internal temperature of litchi during thawing and other data are denoised and normalized, and the normalization formula is as follows:

[0092]

[0093] wherein X is the value of the collected water bath temperature, thawing environment temperature and internal temperature of litchi during thawing and other data, X' is the data value after normalization, μ is the data mean, and σ is the data standard deviation;

[0094] S4: Constructing the GRU model. The GRU model itself uses existing technology, but is trained using data related to the preservation and thawing of lychees. The GRU model consists of an input layer, a GRU layer, and an output layer. Its input is multi-dimensional, and its output is one-dimensional, making it a multi-input, single-output model. The GRU unit is controlled by two activation gate structures (update gate and reset gate):

[0095] Step S41: Determine the training set for the GRU model, wherein the training set is represented as...

[0096] [x i (t)train,y i (t)train,z i [t)train], where

[0097]

[0098] x i (t)train is a sequence of historical temperature data collected by a temperature sensor in the thawing environment, y i (t)train represents the historical data sequence of water bath temperature, i.e., all of which are input values ​​for the model training set, z i (t)train represents the internal temperature data sequence of lychee, i.e., the output value of the model training set, m is the sequence length, where the internal temperature data of lychee includes the output temperature data of the thermodynamic model and the historical temperature data collected by the sensor, a is the number of thawing environment temperature data sequences, b is the number of water bath temperature data sequences, and n is the number of lychee internal temperature data sequences.

[0099] Step S42: Update the two control gates and unit information of the GRU model using the following formula and the training set:

[0100] r t =σ(W r ·[h t-1 ,x t ]+B r (11),

[0101] z t =σ(W z ·[h t-1 ,x t ]+B z (12),

[0102]

[0103] Among them, W r W z B are the weight matrices for the reset gate and the update gate, respectively. r B z Bh reset gate, update gate, bias matrix of candidate hidden state, r t is the reset gate in the GRU model to control the amplitude of the hidden state of the previous time step flowing into the hidden state of the current time step, z t is the update gate to control the amount of state information of the previous moment entering the current state, x t , h t , , h t-1 , and h represent the input, output and hidden layer update candidate value of the hidden layer node at the current moment respectively, represents the output of the hidden layer node at the previous moment, and represents the Hadamard product, t , y t , and z t are the data at the t-th moment in the training set [x i (t)train, y i (t)train, z i (t)train];

[0104] Step S43, obtaining the predicted value of the output layer of the GRU model is T t :

[0105] T t = (W y h t +b y ) (15),

[0106] wherein, W y is the output weight, determined by W r and W z after training, b y is the output bias, determined by B r , B z and B h after training; h t is obtained from formula (14), and formula (11), formula (12), formula (13), formula (14), formula (15) constitute the final prediction model, x t is the input, which is actually the detected water temperature and thawing environment temperature.

[0107] Step S5, training the GRU model by using the whale optimization algorithm, and the whale optimization algorithm adopts the prior art;

[0108] Step S6, obtaining the final predicted litchi thawing temperature T pred (t) of the k-th moment of the GRU output:

[0109] The GRU output final prediction of the t time moment of litchi thawing temperature value T pred (t) feedback to the fuzzy PID controller, and as the input value of the fuzzy PID controller;

[0110] Step S7, design litchi thawing temperature control strategy based on fuzzy PID controller, specifically including the following steps:

[0111] S71: define the input variable and output variable of the fuzzy PID controller, the input variable is the temperature deviation e t And the temperature change rate de / dt:

[0112] e t = T set -T pred (16),

[0113] Where T set is the set target temperature,

[0114]

[0115] The output variable u is as follows:

[0116]

[0117] Where K p is the proportional factor, K i is the integral factor, and K d is the differential factor;

[0118] S72: introduce fuzzy rules: input fuzzy, the actual measured temperature deviation e t And the temperature change rate de / dt, as the input of the fuzzy PID controller; fuzzy reasoning, through the fuzzy reasoning of the temperature deviation and the temperature change rate based on the experience-based fuzzy control rule table to obtain the fuzzy PID controller adjustment parameter fuzzy expression; inverse fuzzy, the fuzzy PID controller adjustment parameters ΔK p , ΔK i And ΔK d are converted into explicit numerical values by the barycenter method;

[0119] Step S73: update K p , K i , K d According to the obtained adjustment parameters ΔK p , ΔK i , ΔK d :

[0120] K p (n) = K p(n-1) + AK p (n),

[0121] K i (n) = K i (n-1) + AK i (n),

[0122] K d (n) = K d (n-1) + AK d (n),

[0123] In the formula, K p (n-1), K i (n-1), K d (n-1) are initial proportional factor, integral factor and differential factor, AK p (n), AK i (n), AK d (n) are fuzzy calculated proportional factor, integral factor and differential factor adjustment parameters, K p (n), K i (n), K d (n) are fuzzy calculated proportional factor, integral factor and differential factor;

[0124] S8: the fuzzy PID controller corresponding output u as a control parameter to the actuator (heating pipe) and electromagnetic generator control, and continue to monitor the litchi thaw temperature.

[0125] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above examples, the above examples and the description described in the specification is only the principle of the present application, without departing from the spirit and scope of the present application will have various changes and improvements, these changes and improvements all fall within the scope of the claimed present application. The scope of protection claimed by the appended claims and their equivalents.

Claims

1. A method for modeling a litchi preservation and thawing temperature control model based on a thermodynamic model in an electromagnetic field, specifically comprising the following steps: S1, establishing a thermodynamic model of a litchi preservation and thawing system; S2, obtaining the specific heat capacity of litchi according to the thermodynamic model; S3, calculating the internal temperature of litchi by the following formula: T lychee (t) is the internal temperature of litchi at time t, q is the heat absorbed by litchi per unit time, which is calculated by the thermodynamic model, T′ lychee is the initial temperature of litchi before thawing, which is obtained by detection, m is the mass of litchi, c lychee is the specific heat capacity of litchi, which is obtained by step S2; S4, constructing a GRU model, and using the internal temperature data of litchi obtained in step S3 and the collected thawing environment temperature and thawing water bath temperature as a training set to train the GRU model; S5, the GRU model is optimized by using the whale optimization algorithm, and the optimized GRU model outputs the thawing temperature T of litchi pred (t), t is time: S6, construct a fuzzy PID controller-based litchi thawing temperature control strategy, T pred (t) as the input of the litchi thawing temperature control strategy, T pred (t) is compared with the preset value, and output control is performed according to the comparison result.

2. The modeling method of claim 1, wherein, The step S1 specifically comprises the following steps: S11: The heater transmits heat to the heat pipe through heat conduction, the heat pipe is a high-efficiency heat conduction material, quickly transmits heat to water, and the heat output by the heat pipe is obtained by the following formula: Q1=Pt(2), Wherein, Q1 is the heat transmitted by the heat pipe to the water per unit time, P is the heating power of the heat pipe, and t is the working time of the heater or the heat pipe; S12, the water heated by the heat pipe transmits heat to the air through heat conduction, and the heat transmitted by the water to the air is calculated by the following formula: Q2 = U2A water (T water -T air ) (3), where Q2 is the heat transferred from the water to the air per unit time, U2 is the heat transfer coefficient of the water, A water is the surface area of the water in contact with the air, T water is the current temperature of the water, T airr is the current temperature of the air, T water is the current temperature of the water; S13: The air transmits part of the heat to the litchi, and the heat transmitted by the air to the litchi is as follows: Q3 = U3A air (T air -T lychee ) (4), where Q3 is the heat transferred from the air to the lychee per unit time, U3 is the heat transfer coefficient of the air, A air is the surface area of the air in contact with the lychee, T airr is the current temperature of the air, T lychee is the current temperature of the lychee; Step 14, since the heat pipe is completely inserted into the water, based on the heat balance relationship, we have: Q1=Q2+Q3, and further: Q3=Q1-Q2 (5); S15, substituting Q3 into the formula in step 13 to obtain U3; S16, obtaining the heat formula of litchi: Q4 = m lychee c lychee (T lychee -T‘ lychee ) (6), wherein Q4 is the heat absorbed by the litchi per unit time, m lychee is the mass of the litchi, c lychee is the specific heat capacity of the litchi, T lychee is the current temperature of the litchi, T' lychee is the initial temperature of the litchi before thawing; Step 17, since the heat change of the lychee is equal to the heat transferred to the lychee by the air, therefore, Q3 = Q4, calculate c through the formula in step S16 lychee .

3. The modeling method of claim 1, wherein, In the step S4, the GRU model comprises an input layer, a GRU layer and an output layer, and the GRU model is controlled by two gate structures, specifically comprising the following steps: Step S41, determining the training set of the GRU model, the training set is represented as [x i (t)train, y i (t)train, z i (t)train], wherein, x i (t)train is a temperature history data sequence collected by the thawing environment temperature sensor, y i (y)train is a water bath temperature history data sequence, z i (t)trian is a litchi internal temperature data sequence, m is the sequence length, a is the number of thawing environment temperature data sequences, b is the number of water bath temperature data sequences, and n is the number of litchi temperature data sequences; Step S42, update the two control gates and unit information of the GRU model by the following formula and the training set: r t = σ(W r · [h t-1 x t ]+ B r ) (10), z t = σ(W z · [h t-1 , x t ] + B z ) (11), wherein W r , W z are the weight matrices of the reset gate and update gate respectively, B r , B z , B h are the bias matrices of the reset gate, update gate and candidate hidden state respectively, r t is the output of the reset gate at time t, z t is the output of the update gate at time t, x t , h t , represent the input, output and hidden layer update candidate value of the current time respectively, h t-1 represents the output of the hidden layer node at the previous time, ⊙ represents Hadamard product, represents the product of matrix elements, σ is the sigmoid activation function, the output is 0 to 1, tanh is the hyperbolic tangent activation function, the output is -1 to 1, x t , y t and z t are the data at time t in the training set [x i (t)train, y i (t)train, z i (t)train] Step S43, the prediction value of the output layer of the GRU model is obtained as T t : T t = (W y h t + b y ) (14), where W y are output weights, and b y is an output bias.

4. The modeling method of claim 1, wherein, Step S6, specifically comprising the following steps: S61: define the input variable and the output variable of the fuzzy PID controller, the input variable is the temperature deviation e at time t t and the temperature change rate de / dt: e t = T set - T pred (t) (17), where T set is a set target temperature, The output variable u is represented as follows: S62: Introducing fuzzy rule: input quantity is fuzzified, the temperature deviation e actually measured t and the temperature change rate de / dt are taken as the inputs of the fuzzy PID controller; fuzzy inference is made on the temperature deviation and the temperature change rate by the fuzzy control rule table based on experience to obtain the fuzzy PID controller's regulating parameter fuzzy expression; de-fuzzing, converting the fuzzy PID controller adjustment parameters ΔK p , ΔK i and ΔK d into definite numerical values using the barycentric method; Step S73: Update K p , K i , and K d according to the obtained adjustment parameter ΔK p , K i , K d ​ K p (n) = K p (n-1) + ΔK p (n), K i (n) = K i (n - 1) + ΔK i (n), K d (n) = K d (n-1) + ΔK d (n), where K p (n-1), K i (n-1), K d (n-1) are initial proportional, integral, and derivative factors, ΔK p (n), ΔK i (n), ΔK d (n) are fuzzy-computed proportional, integral, and derivative factor adjustment parameters, K p (n), K i (n), K d (n) are fuzzy-computed adjusted proportional, integral, and derivative factors.

Images