Hot air temperature self-adaptive control method based on expanded tobacco shred moisture prediction before moisture regaining

Abstract

The invention provides a hot air temperature parameter adaptive control method based on expanded tobacco shred moisture prediction, which comprises the following steps of: reconstructing related data such as tobacco shred height of a metering zone, hot air temperature, hot air speed, steam flow, quantitative zone frequency and the like, and performing data correlation analysis on main factors and influence degrees of tobacco shred moisture before moisture regaining; the hot air temperature and the metering zone tobacco shred height with high correlation are obtained and serve as an input radial basis function neural network model for expanded tobacco shred moisture prediction, and moisture prediction is conducted; the moisture prediction result of the expanded tobacco shreds is fed back to a hot air temperature control link, and the hot air temperature control quantity of a PID controller is adaptively adjusted through a moisture prediction error, so that the problem that the traditional PID control performance is influenced by system time lag is solved; the hot air temperature parameter self-adaptive control decision method is provided for improving the moisture tracking control effect of the expanded tobacco shreds before moisture regaining and narrowing the moisture fluctuation range of the expanded tobacco shreds before moisture regaining.

Description

Technical Field

[0001] The invention relates to a hot air temperature adaptive control method based on the moisture prediction of expanded cut tobacco before rehumidification, and belongs to the technical field of automated control of expanded cut tobacco production. Background Art

[0002] Controlling the moisture content of expanded tobacco is a key factor in ensuring the quality of tobacco. Since the conventional method of feedback of tobacco weight through sensors has lag, it is necessary to estimate the weight of expanded tobacco before rehumidification in advance. At present, the moisture control of expanded tobacco before rehumidification mainly adopts traditional PID moisture feedback control, which cannot eliminate the influence of large system delay on the moisture control accuracy, nor can it achieve adaptive control. It is reported that in the existing technology of moisture content control of expanded tobacco, neural networks are rarely used for estimation modeling; and if unprocessed data is directly input into the neural network for training, or data with weak correlation is used as the input of the estimation model, due to problems such as data correlation and data misalignment, it is easy to cause the estimation model neural network training time to be long and the training results to be unsatisfactory, which in turn affects the estimation accuracy. Summary of the invention

[0003] The purpose of the present invention is to provide a hot air temperature adaptive control method based on the prediction of the moisture content of expanded tobacco before rehumidification, and to achieve the effect of reducing the moisture fluctuation range of the expanded tobacco before rehumidification by improving the PID adaptive control method of the hot air temperature based on the prediction of the moisture content of the expanded tobacco based on a basic neural network.

[0004] In order to achieve the above objectives / solve the above technical problems, the present invention is implemented by adopting the following technical solutions.

[0005] In a first aspect, the present invention provides a hot air temperature adaptive control method based on the prediction of moisture content of expanded cut tobacco before rehumidification, characterized in that it comprises:

[0006] Obtain data on factors affecting moisture content of expanded tobacco during the expansion process;

[0007] Input the data of factors affecting the moisture content of expanded cut tobacco into a pre-trained radial basis neural network model to obtain the predicted value of the moisture content of expanded cut tobacco before rehumidification;

[0008] According to the error between the predicted value of the moisture content of expanded tobacco before rehumidification and the target value of the moisture content of expanded tobacco before rehumidification, PID adjustment is performed on the data of factors affecting the moisture content of expanded tobacco during the expansion process to keep the moisture content of expanded tobacco at the target value before rehumidification.

[0009] Furthermore, the acquisition of data on factors affecting moisture content of expanded cut tobacco during the expansion process specifically includes the following steps:

[0010] The Pearson correlation coefficient method is used to perform correlation analysis on several sample data in the expansion process of a set batch of tobacco. The sample data and the actual value of the moisture content of the expanded tobacco are set as two variables, and the Pearson coefficient of the two variables is defined. The sample data between -1 and 1 are the factors affecting the moisture content of expanded tobacco;

[0011] ,

[0012] ,

[0013] ,

[0014] in: To set the actual moisture value of the expanded tobacco before the i-th moisture reconditioning in the batch, is the i-th data sample in the same batch, is the total number of samples in the same batch, is the sample mean of the weight of expanded tobacco, is the sample mean of the sample data;

[0015] The sample data is one of the metering belt tobacco height, hot air temperature, hot air speed, steam flow, and metering belt frequency during the expansion process.

[0016] Furthermore, the first 70% of the data on factors affecting the moisture content of expanded tobacco in the process of batch expansion are set as a training set, and the last 30% of the data are set as a test set.

[0017] Furthermore, the training method of the radial basis neural network model includes:

[0018] The K-means clustering algorithm is used to perform cluster analysis on the sample data in the training set, and the sample data in the training set is divided into several clusters. The centroid of each cluster is used as the central vector of the corresponding hidden layer unit;

[0019] Calculate the width parameter of each hidden unit based on the Euclidean distance between the centroids;

[0020] For each sample data in the training set, calculate its activation value on all hidden units based on the Gaussian radial basis function, and combine these activation values ​​into the hidden layer output matrix;

[0021] The weight matrix of the output layer is optimized and solved by the least square method or gradient descent method. The optimization goal is to minimize the nominal error between the predicted value of the moisture content of the expanded tobacco and the actual value of the moisture content of the expanded tobacco to less than 5%;

[0022] The performance of the radial basis neural network model is optimized by continuously iteratively adjusting the center vector, width parameter and output layer weight until the value of the loss function converges or reaches a predetermined maximum number of iterations, thereby obtaining the final trained radial basis neural network model;

[0023] Where: Gaussian radial basis function:

[0024] ,

[0025] in, is the jth sample data in the training set, For the The center of the kernel function of the hidden unit,

[0026] For the The width of the kernel function of hidden units, For the The radial basis functions of the hidden units of .

[0027] Further, the PID adjustment of the data of factors affecting the moisture content of expanded tobacco during the expansion process is performed according to the error between the predicted value of the moisture content of expanded tobacco before rehumidification and the target value of the moisture content of expanded tobacco before rehumidification, so that the moisture content of the expanded tobacco before rehumidification is maintained at the target value specifically includes the following steps:

[0028] ,

[0029] in, represents the scale parameter, represents the integral parameter, represents the differential parameter, is the adaptive adjustment coefficient; The target moisture value of expanded tobacco before rehumidification. (t) is the predicted moisture value of expanded tobacco before rehumidification at time t, is the deviation between the target value and the predicted value of the moisture content of the expanded tobacco before rehumidification at time t; is the integration variable, is the PID adjustment output value at time t, It is the actual output value of the corrected hot air temperature at time t.

[0030] Furthermore, before using the Pearson correlation coefficient method to perform correlation analysis on a number of sample data after the expansion process of a set batch of wire, the sample data needs to be preprocessed and reconstructed, specifically including:

[0031] The sample data and the actual value of the moisture content of the expanded tobacco before rehumidification are shifted backward or forward by a set time step so that the time lag between the two variables is eliminated or reduced, the data of different units are standardized, and the noise and clutter of the data are eliminated through data smoothing.

[0032] In a second aspect, the present invention provides a hot air temperature adaptive control device based on the prediction of moisture content of expanded cut tobacco before rehumidification, comprising:

[0033] Acquisition module: used to obtain data on factors affecting moisture content of expanded tobacco during the expansion process;

[0034] An input module is used to input the data of factors affecting the moisture content of expanded cut tobacco into a pre-trained radial basis neural network model to obtain a predicted value of the moisture content of the expanded cut tobacco before rehumidification;

[0035] The adjustment module is used to perform PID adjustment on the data of factors affecting the moisture content of expanded tobacco during the expansion process according to the error between the predicted value of the moisture content of expanded tobacco before rehumidification and the target value of the moisture content of expanded tobacco before rehumidification, so as to keep the moisture content of the expanded tobacco at the target value before rehumidification.

[0036] In a third aspect, the present invention provides a hot air temperature adaptive control system based on the prediction of moisture content of expanded cut tobacco before rehumidification, and a memory for storing computer programs / instructions;

[0037] A processor is used to execute the computer program / instructions to implement the steps of the above-mentioned method for adaptively controlling the moisture content of expanded tobacco before rehumidification.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for adaptively controlling the moisture content of expanded tobacco before rehumidification.

[0039] In a fifth aspect, a computer program product includes a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the steps of the above-mentioned method for adaptively controlling the moisture content of expanded tobacco before rehumidification.

[0040] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention adopts a radial basis function neural network to perform prediction modeling of the moisture content of expanded tobacco, inputs the processed data into the radial basis function neural network model for training, removes data with weak correlation, solves the influence of data correlation and data misalignment problems on the prediction accuracy of moisture content before rehumidification, utilizes the prediction ability of the radial basis function neural network model, weakens the influence of the moisture sensor time lag in the traditional PID control, and improves the prediction accuracy of the moisture content of expanded tobacco before rehumidification.

[0041] The present invention combines radial basis function neural network with PID control, and proposes an online adaptive control method for hot air temperature based on the prediction of moisture content of expanded tobacco before rehumidification. The controller coefficient is dynamically and adaptively adjusted according to the prediction error, thereby improving the adaptive regulation ability of hot air temperature control to moisture content before rehumidification, and providing an adaptive control decision model to meet the ever-changing processing environment and production needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a block diagram of hot air temperature adaptive control based on the prediction of moisture content of expanded cut tobacco in this application;

[0043] Figure 2 This is an example diagram of moisture prediction of expanded tobacco before rehumidification for this application. DETAILED DESCRIPTION

[0044] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0045] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.

[0046] Example 1

[0047] like Figure 1 An embodiment shown in the figure provides a hot air temperature adaptive control method based on the prediction of moisture content of expanded cut tobacco before rehumidification, comprising:

[0048] Step 1: Obtain data on factors affecting moisture content of expanded tobacco during the expansion process

[0049] In order to reduce the moisture fluctuation, the main factors affecting the moisture fluctuation are extracted through correlation analysis. The present invention uses the Pearson simple correlation coefficient to measure the linear correlation between the moisture content of the expanded tobacco before rehydration and other physical variables;

[0050] According to the type of feedforward signal, the selected fixed-distance data include: height of tobacco cut in metering belt, hot air temperature, hot air velocity, steam flow, frequency of metering belt and actual value of moisture content of expanded tobacco cut before rehumidification;

[0051] Step 2: Data Reconstruction

[0052] Taking the quantitative band frequency and the actual value of the moisture content of expanded tobacco before rehumidification as examples, the above data are translated backward or forward for a certain time step, so that the time lag between the two physical variables is eliminated or reduced, and the data of different units are standardized, and the noise and clutter of the data are eliminated through data smoothing, so as to complete the preprocessing and reconstruction of the fixed-distance data;

[0053] Step 3: Correlation Analysis

[0054] The Pearson correlation coefficient method is used to perform correlation analysis on multiple batches of data in the expanded tobacco production process, and the Pearson coefficient between two variables is defined. It is a value between -1 and 1, and its absolute value reflects the correlation between the two variables; Definition: The actual value variable of the moisture content of expanded tobacco before rehumidification is , the variables such as the height of the tobacco cut in the metering belt, the hot air temperature, the hot air speed, the steam flow rate, and the frequency of the metering belt are , its Pearson coefficient As shown below:

[0055] ,

[0056] ,

[0057] ,

[0058] in: To set the actual moisture value of the expanded tobacco before the i-th moisture reconditioning in the batch, is the i-th data sample in the same batch, is the total number of samples in the same batch, is the sample mean of tobacco weight, is the sample mean of the sample data;

[0059] The i-th data sample of tobacco height, hot air temperature, hot air velocity, steam flow rate, and quantitative band frequency of any metering band in the same batch;

[0060] It is the sample mean of variables such as tobacco height, hot air temperature, hot air speed, steam flow, and quantitative belt frequency.

[0061] It can be seen that: according to the correlation analysis of actual data, the correlation between the three factors of hot air speed, steam flow rate and quantitative belt frequency and the actual value of moisture content of expanded tobacco before rehumidification is relatively low. It is difficult to accurately estimate the actual value of moisture content of expanded tobacco before rehumidification using the data of any one factor alone; since the height of tobacco in the metering belt and the hot air temperature are highly correlated with the actual value of moisture content of expanded tobacco before rehumidification, the combination of these two influencing factors is selected.

[0062] Step 4: Moisture prediction modeling of expanded tobacco before rehydration based on radial basis function neural network

[0063] The height of tobacco cut in the metering belt and the temperature of hot air are used as the input vectors of the radial basis neural network, and the output vector is the predicted value of the moisture content of the expanded tobacco cut;

[0064] The first 70% of the data of the metering belt tobacco height and hot air temperature are used as the training set, and the relationship between the metering belt tobacco height, hot air temperature and the predicted value of the expanded tobacco moisture is trained through the training set;

[0065] The training method of the radial basis neural network model includes:

[0066] Firstly, the K-means clustering algorithm is used to perform cluster analysis on the sample data of the training set, and the data in the training set is divided into several clusters. The centroid of each cluster is used as the central vector of the corresponding hidden layer unit.

[0067] Subsequently, the width parameter of each hidden unit is calculated based on the Euclidean distance between the centroids;

[0068] Next, for each sample data in the training set, its activation value on all hidden units is calculated based on the Gaussian radial basis function, and these activation values ​​are combined into a hidden layer output matrix;

[0069] Afterwards, the weight matrix of the output layer is solved by the least square method or gradient descent method, with the goal of minimizing the nominal error between the predicted value of the moisture content of the expanded tobacco and the actual value of the moisture content of the expanded tobacco to less than 5%, and the prediction result is directly used in the control process;

[0070] The model performance is optimized by continuously iteratively adjusting the center vector, width parameter and output layer weight until the value of the loss function converges or reaches the predetermined maximum number of iterations, and the final trained radial basis neural network model is obtained;

[0071] Where: Gaussian radial basis function:

[0072] ,

[0073] in, is the jth sample data in the training set, For the The center of the kernel function of the hidden unit,

[0074] For the The width of the kernel function of hidden units, For the The number of radial basis functions of hidden units.

[0075] Step 5: Model Testing

[0076] The last 30% of the data of tobacco height and hot air temperature in the metering belt is used as the test set.

[0077] ,

[0078] in, is the nominal error of the sth sample data in the test set, is the moisture prediction value of expanded tobacco before rehydration for the sth sample data in the test set, is the actual value of moisture content of expanded tobacco before rehumidification in the sth sample data of the test set.

[0079] like Figure 2 As shown, the nominal error between the predicted value and the actual value of the moisture content of expanded cut tobacco before rehydration in the two selected time periods is within ±3.38%, which shows the high prediction accuracy of the radial basis function neural network model of this embodiment.

[0080] Step 6: Adaptive hot air temperature control method based on moisture prediction before rehumidification

[0081] The radial basis function neural network is combined with PID control to realize the adaptive control of the moisture content of expanded tobacco before rehydration. According to the error between the predicted value of the moisture content of expanded tobacco before rehydration and the target value of the moisture content of expanded tobacco before rehydration, the PID is adjusted for the data of factors affecting the moisture content of expanded tobacco during the expansion process, so that the moisture content of expanded tobacco before rehydration is maintained at the target value:

[0082] ,

[0083] in, represents the scale parameter, represents the integral parameter, represents the differential parameter, is the adaptive adjustment coefficient; The target moisture value of expanded tobacco before rehumidification. (t) is the predicted moisture value of expanded tobacco before rehumidification at time t, is the deviation between the target value and the predicted value of the moisture content of the expanded tobacco before rehumidification at time t; is the integration variable, is the PID adjustment output value at time t, It is the actual output value of the corrected hot air temperature at time t.

[0084] Example 2

[0085] This embodiment provides a hot air temperature adaptive control device based on the prediction of moisture content of expanded cut tobacco before rehumidification, comprising:

[0086] Acquisition module: used to obtain data on factors affecting moisture content of expanded tobacco during the expansion process;

[0087] An input module is used to input the data of factors affecting the moisture content of expanded cut tobacco into a pre-trained radial basis neural network model to obtain a predicted value of the moisture content of the expanded cut tobacco before rehumidification;

[0088] The adjustment module is used to perform PID adjustment on the data of factors affecting the moisture content of expanded tobacco during the expansion process according to the error between the predicted value of the moisture content of expanded tobacco before rehumidification and the target value of the moisture content of expanded tobacco before rehumidification, so as to keep the moisture content of the expanded tobacco at the target value before rehumidification.

[0089] Example 3

[0090] This embodiment provides a hot air temperature adaptive control system based on the prediction of moisture content of expanded cut tobacco before rehumidification, and a memory for storing computer programs / instructions;

[0091] A processor is used to execute the computer program / instructions to implement the steps of the above-mentioned method for adaptively controlling the moisture content of expanded tobacco before rehumidification.

[0092] Example 4

[0093] This embodiment provides a computer-readable storage medium on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, the steps of the above-mentioned method for adaptively controlling the moisture content of expanded tobacco before rehumidification are implemented.

[0094] Example 5

[0095] A computer program product includes a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned method for adaptively controlling the moisture content of expanded tobacco before rehumidification.

[0096] The time-varying lag of the moisture sensor in the processing of expanded tobacco before rehumidification makes it difficult for traditional PID control to meet the moisture fluctuation control range under the varying lag. The radial basis function neural network model for predicting moisture before rehumidification obtained by training with hot air temperature and moisture data before rehumidification can accurately predict the moisture of expanded tobacco before rehumidification based on the hot air temperature data, thereby reducing the influence of time lag on the traditional PID control effect.

[0097] Based on the predicted value of the moisture content of the expanded tobacco before rehydration, the PID controller adjusts the hot air temperature in real time to keep the moisture content of the expanded tobacco before rehydration within the ideal range. The prediction ability of the neural network model is used to reduce the influence of the time-varying and time-delayed moisture content of the expanded tobacco before rehydration.

[0098] In addition, based on the prediction of moisture content before rehumidification, an adaptive adjustment method for PID controller parameters was proposed. By using the error between the predicted moisture content and the actual moisture content, an adaptive algorithm was used to dynamically adjust the proportional, integral and differential parameters of the PID controller to obtain the adaptive control result of the hot air temperature. The parameters of the prediction model were corrected online through the actual moisture content of expanded tobacco before rehumidification, and adaptive PID control of the moisture content of expanded tobacco before rehumidification based on a radial basis function neural network was realized, so that the moisture content of the expanded tobacco before rehumidification was kept within an ideal range.

[0099] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0103] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A hot air temperature adaptive control method based on the prediction of moisture content of expanded cut tobacco before rehumidification, characterized in that: include: Obtain data on factors affecting moisture content of expanded tobacco during the expansion process; Input the data of factors affecting the moisture content of expanded cut tobacco into a pre-trained radial basis neural network model to obtain the predicted value of the moisture content of expanded cut tobacco before rehumidification; According to the error between the predicted value of the moisture content of expanded tobacco before rehumidification and the target value of the moisture content of expanded tobacco before rehumidification, PID adjustment is performed on the data of factors affecting the moisture content of expanded tobacco during the expansion process to keep the moisture content of expanded tobacco at the target value before rehumidification.

2. The hot air temperature adaptive control method based on the prediction of moisture content of expanded cut tobacco before rehydration according to claim 1 is characterized in that: The method of obtaining data on factors affecting moisture content of expanded cut tobacco during the expansion process specifically includes the following steps: The Pearson correlation coefficient method is used to perform correlation analysis on several sample data in the expansion process of a set batch of tobacco. The sample data and the actual value of the moisture content of the expanded tobacco are set as two variables, and the Pearson coefficient of the two variables is defined. The sample data between -1 and 1 are the factors affecting the moisture content of expanded tobacco; ， ， ， in: To set the actual moisture value of the expanded tobacco before the i-th moisture reconditioning in the batch, is the i-th data sample in the same batch, is the total number of samples in the same batch, is the sample mean of the weight of expanded tobacco, is the sample mean of the sample data; The sample data is one of the height of tobacco shreds in the metering belt, the hot air temperature, the hot air velocity, the steam flow rate, and the frequency of the metering belt.

3. The hot air temperature adaptive control method based on the prediction of moisture content of expanded cut tobacco before rehydration according to claim 2 is characterized in that: The first 70% of the data on factors affecting the moisture content of expanded tobacco in the expansion process of a given batch of tobacco is used as the training set, and the last 30% of the data is used as the test set.

4. The hot air temperature adaptive control method based on the prediction of moisture content of expanded cut tobacco before rehydration according to claim 3 is characterized in that: The training method of the radial basis neural network model includes: The K-means clustering algorithm is used to perform cluster analysis on the sample data in the training set, and the sample data in the training set is divided into several clusters. The centroid of each cluster is used as the central vector of the corresponding hidden layer unit; Calculate the width parameter of each hidden unit based on the Euclidean distance between the centroids; For each sample data in the training set, calculate its activation value on all hidden units based on the Gaussian radial basis function, and combine these activation values ​​into the hidden layer output matrix; The weight matrix of the output layer is optimized and solved by the least square method or gradient descent method. The optimization goal is to minimize the nominal error between the predicted value of the moisture content of the expanded tobacco and the actual value of the moisture content of the expanded tobacco to less than 5%; The performance of the radial basis neural network model is optimized by continuously iteratively adjusting the center vector, width parameter and output layer weight until the value of the loss function converges or reaches a predetermined maximum number of iterations, thereby obtaining the final trained radial basis neural network model; Where: Gaussian radial basis function: ， in, is the jth sample data in the training set, For the The center of the kernel function of the hidden unit, For the The width of the kernel function of hidden units, For the The radial basis functions of the hidden units of .

5. The hot air temperature adaptive control method based on the prediction of moisture content of expanded cut tobacco before rehydration according to claim 3 is characterized in that: The method of performing PID adjustment on the data of factors affecting the moisture content of expanded tobacco during the expansion process according to the error between the predicted value of the moisture content of expanded tobacco before rehydration and the target value of the moisture content of expanded tobacco before rehydration so as to keep the moisture content of expanded tobacco at the target value before rehydration specifically comprises the following steps: ， in, represents the scale parameter, represents the integral parameter, represents the differential parameter, is the adaptive adjustment coefficient; The target moisture value of expanded tobacco before rehumidification. (t) is the predicted moisture value of expanded tobacco before rehumidification at time t, is the deviation between the target value and the predicted value of the moisture content of the expanded tobacco before rehumidification at time t; is the integration variable, is the PID adjustment output value at time t, It is the actual output value of the corrected hot air temperature at time t.

6. The hot air temperature adaptive control method based on the prediction of moisture content of expanded cut tobacco before rehydration according to claim 2, characterized in that: Before using the Pearson correlation coefficient method to perform correlation analysis on several sample data of a set batch of expanded wire process, the sample data needs to be preprocessed and reconstructed, including: The sample data and the actual value of the moisture content of the expanded tobacco before rehumidification are shifted backward or forward by the set time step.

7. A hot air temperature adaptive control device based on the prediction of moisture content of expanded tobacco before rehumidification, characterized in that: Acquisition module: used to obtain data on factors affecting moisture content of expanded tobacco during the expansion process; An input module is used to input the data of factors affecting the moisture content of expanded cut tobacco into a pre-trained radial basis neural network model to obtain a predicted value of the moisture content of the expanded cut tobacco before rehumidification; The adjustment module is used to perform PID adjustment on the data of factors affecting the moisture content of expanded tobacco during the expansion process according to the error between the predicted value of the moisture content of expanded tobacco before rehumidification and the target value of the moisture content of expanded tobacco before rehumidification, so as to keep the moisture content of the expanded tobacco at the target value before rehumidification.

8. A hot air temperature adaptive control system based on the prediction of moisture content of expanded tobacco before rehydration, characterized in that: include: Memory, for storing computer programs / instructions; A processor is used to execute the computer program / instructions to implement the steps of the method for adaptively controlling the moisture content of expanded tobacco before rehumidification according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the steps of the method for adaptively controlling the moisture content of expanded tobacco before rehumidification as described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by the processor, the steps of the method for adaptively controlling the moisture content of expanded tobacco before rehumidification as described in any one of claims 1 to 6 are implemented.

Images