A flue-cured tobacco house temperature and humidity regulation system and method based on deep learning optimization

Abstract

The application discloses a kind of based on deep learning optimization's flue-cured tobacco room temperature and humidity regulation system and method, wherein the system includes: data acquisition module, to collect the environmental data and tobacco image data in flue-cured tobacco room;Data processing module, to carry out data preprocessing to tobacco image data and environmental data, and color analysis is carried out to tobacco image data, to obtain the color feature data of tobacco image;Data prediction module, to predict the color change trend of tobacco and the temperature change trend in flue-cured tobacco room according to the environmental data and color feature data after preprocessing;Equipment control module, to dynamically regulate the heating equipment in flue-cured tobacco room according to temperature change trend and color change trend;The output of the present application through data prediction module, dynamically adjusts PID parameter, to accurately control flue-cured tobacco room heating equipment, realize accurate control of temperature and humidity in flue-cured tobacco room, reduce temperature fluctuation, ensure the quality consistency and color uniformity in tobacco curing process.

Description

TECHNICAL FIELD

[0001] The present application relates to the tobacco leaf roasting technical field, especially to a tobacco leaf roasting room temperature and humidity control system and method based on deep learning optimization. BACKGROUND

[0002] Tobacco leaf roasting is a key link in tobacco production, and its purpose is to remove moisture from tobacco leaves so that the tobacco leaves reach a state suitable for storage, alcoholization and cigarette processing. The control of temperature and humidity during the roasting process directly affects the color, aroma and chemical composition of the tobacco leaves and determines the final quality of the tobacco leaves.

[0003] The traditional tobacco leaf roasting method mainly relies on manual experience and preset temperature and humidity values. The temperature and humidity in the tobacco leaf roasting room are monitored by sensors, and the environment of the tobacco leaf roasting room is adjusted manually. However, this method is complex to operate and highly dependent on manual experience, with many uncertain factors, making it difficult to accurately control the roasting process and easily leading to damage to the quality of the tobacco leaves. At the same time, the influence of the state change of the tobacco leaves themselves on the quality of the tobacco leaves is not fully considered.

[0004] Chinese Patent No. CN206292605U discloses an online image recognition control system for tobacco leaf roasting room. The system monitors the video signal of the tobacco leaves online, masters the roasting state of the tobacco leaves according to the appearance and color state of the tobacco leaves, adjusts the tobacco leaf roasting process, and realizes intelligent roasting of the tobacco leaves. However, this method only adjusts the process parameters in the tobacco leaf roasting room after identifying the state of the tobacco leaves by image recognition, and cannot predict the future change trend of the temperature and humidity in the tobacco leaf roasting room, nor can it adjust the roasting equipment in advance. It is difficult to accurately control the temperature and humidity during the roasting process, resulting in large fluctuations in temperature and humidity, affecting the uniformity and quality consistency of the tobacco leaf roasting, and thus reducing the overall quality of the tobacco leaves. SUMMARY

[0005] In view of the above shortcomings of the prior art, the present application provides a tobacco leaf roasting room temperature and humidity control system and method based on deep learning optimization to solve the problems of inaccurate temperature and humidity control and insufficient prediction ability in the prior art, thereby improving the uniformity and overall quality of the tobacco leaf roasting.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical solutions,

[0007] In a first aspect, the present application provides a tobacco leaf roasting room temperature and humidity control system based on deep learning optimization, comprising:

[0008] a data acquisition module for acquiring environmental data and tobacco leaf image data in the tobacco leaf roasting room;

[0009] a data processing module connected to the data acquisition module, for performing data preprocessing on the tobacco leaf image data and environmental data, and performing color analysis on the tobacco leaf image data to obtain color feature data of the tobacco leaf image;

[0010] A data prediction module, connected to the data processing module, for predicting the color change trend of tobacco leaves and the temperature change trend in the tobacco flue-curing room based on the pre-processed environmental data and the color characteristic data;

[0011] The equipment control module is connected to the data processing module and the data prediction module respectively, and is used to dynamically adjust the parameters of the PID control algorithm according to the temperature change trend and the color change trend to regulate the heating equipment in the tobacco flue-curing room.

[0012] Optionally, the data processing module includes an image preprocessing unit, a storage unit, a color clustering unit and a color uniformity unit;

[0013] The input end of the image preprocessing unit is connected to the output end of the data acquisition module, and is used to preprocess the environmental data in the tobacco flue-curing room and the tobacco leaf image data, and send the preprocessed tobacco leaf image data to the color clustering unit;

[0014] The input end of the color clustering unit is connected to the output end of the image preprocessing unit, and is used to perform color division on the tobacco leaf images in the preprocessed tobacco leaf image data to obtain color clusters of the tobacco leaf images;

[0015] The input end of the color uniformity unit is connected to the output end of the color clustering unit, so as to evaluate the color uniformity of the tobacco leaf image according to the color clustering to obtain the color uniformity of the tobacco leaf image;

[0016] The input end of the storage unit is connected to the output ends of the image pre-processing unit, the color clustering unit and the color uniformity unit respectively for storing data.

[0017] Optionally, the data prediction module includes a temperature prediction unit, a temperature optimization unit, and a color prediction unit;

[0018] The input end of the temperature prediction unit is connected to the output end of the storage unit, and is used to predict the preprocessed environmental data and the color feature data based on a pre-trained temperature prediction model to obtain a predicted temperature value;

[0019] The input end of the temperature optimization unit is connected to the output end of the temperature prediction unit, and is used to optimize the predicted temperature value by constructing a temperature objective function and constraint conditions to obtain an optimal predicted temperature value, so as to predict the temperature change trend in the tobacco flue-curing room;

[0020] An input end of the color prediction unit is connected with an output end of the storage unit, so as to predict the preprocessed environmental data and the color feature data based on the pre-trained tobacco color prediction model, to obtain a tobacco color prediction value, and to predict a color change trend of the tobacco.

[0021] Optionally, the system further comprises a warning module and a data management module.

[0022] An input end of the warning module is connected with an output end of the data acquisition module, so as to evaluate a dangerous condition in the tobacco curing barn through the environmental data in the tobacco curing barn, to trigger a corresponding warning.

[0023] Input ends of the data management module are respectively connected with output ends of the data processing module and the data prediction module, so as to provide an interface for data display, and to provide a query and management interface.

[0024] In a second aspect, an embodiment of the present application provides a tobacco curing barn temperature and humidity regulation method based on deep learning optimization, which is applied to the tobacco curing barn temperature and humidity regulation system as described above, and comprises the following steps:

[0025] S1: collecting environmental data and tobacco image data in the tobacco curing barn;

[0026] S2: performing data preprocessing on the tobacco image data and the environmental data, and performing color analysis on the tobacco image data to obtain color feature data of the tobacco image;

[0027] S3: predicting a color change trend of the tobacco and a temperature change trend in the tobacco curing barn according to the preprocessed environmental data and the color feature data;

[0028] S4: dynamically adjusting parameters of a PID control algorithm according to the temperature change trend and the color change trend, to regulate a heating device in the tobacco curing barn.

[0029] Optionally, S2 specifically comprises the following steps:

[0030] S21: performing data preprocessing on the tobacco image data and the environmental data to obtain preprocessed tobacco image data and environmental data;

[0031] S22: performing color division on the preprocessed tobacco image data to obtain color clustering of the tobacco image;

[0032] S23: performing color uniformity evaluation on the tobacco image according to the color clustering to obtain color uniformity of the tobacco image.

[0033] Optionally, S22 specifically comprises the following steps:

[0034] S221: transferring the preprocessed tobacco leaf image to the HSV color space to obtain the HSV value corresponding to each pixel in the tobacco leaf image;

[0035] S222: Initialize the cluster center of the K-means algorithm;

[0036] S223: assigning each pixel in the tobacco leaf image to the nearest cluster center according to its HSV value;

[0037] S224: Calculate the average HSV values ​​of all pixels in each cluster, and update the cluster center according to each average value;

[0038] S225: Determine whether the cluster centers before and after the update are exactly the same; if so, output the updated cluster center as the color cluster of the tobacco leaf image; if not, use the updated cluster center as the current cluster center and return to step S223;

[0039] The S23 specifically includes the following steps:

[0040] S231: Calculate the color difference between the color of each pixel in the tobacco leaf image and the color of its corresponding cluster center:

[0041] S232: Calculate the standard deviation of the color difference to evaluate the uniformity of the tobacco leaf color.

[0042] Optionally, S3 specifically includes the following steps:

[0043] S31: Predicting the preprocessed environmental data and the color feature data based on a pre-trained temperature prediction model to obtain a predicted temperature value;

[0044] Among them, environmental data includes temperature data and humidity data;

[0045] The functional expression of the temperature prediction model is:

[0046]

[0047] Where, Y is the predicted temperature value; is the current temperature data; is the current humidity data; is the color characteristic data of the current tobacco leaf; is the intercept; is the coefficient corresponding to the current temperature data; is the coefficient corresponding to the current humidity data; is the corresponding coefficient of the color characteristic data of the current tobacco leaf; is the deviation between the actual value and the predicted value;

[0048] S32: Optimizing the predicted temperature value by constructing a temperature objective function and constraint conditions to obtain an optimal predicted temperature value, so as to predict the temperature change trend in the tobacco flue-curing room;

[0049] The expression of the temperature objective function is:

[0050]

[0051] Where Z is the temperature objective function; For in time t Control input; is the cumulative error between the predicted temperature value and the target temperature value from time t to time t+N-1; N is a fixed period; For the time point k The weight factor of is the target temperature value; is the predicted temperature value;

[0052] Function expression of the constraint condition:

[0053]

[0054]

[0055] Where, and are the minimum and maximum predicted temperature values ​​respectively; and are the minimum and maximum values ​​of the control input respectively;

[0056] S33: Based on the pre-trained tobacco leaf color prediction model, the pre-processed environmental data and color feature data are predicted to obtain a tobacco leaf color prediction value to predict the color change trend of the tobacco leaf.

[0057] Optionally, in S33, the specific steps of training the pre-trained tobacco leaf color prediction model include:

[0058] Get historical baking data;

[0059] The historical baking data includes historical environmental data, historical color characteristic data, actual tobacco leaf color change data and tobacco leaf final quality data;

[0060] Fusing the historical environmental data and the historical color feature data to generate multi-channel input data;

[0061] Based on the actual color change data of tobacco leaves and the final quality data of tobacco leaves, corresponding true labels are generated for each set of input data.

[0062] Constructing a tobacco leaf color prediction model based on a convolutional neural network model and initializing the tobacco leaf color prediction model;

[0063] The tobacco leaf color prediction model includes a convolutional layer, a maximum pooling layer and a fully connected layer;

[0064] After performing feature extraction on the input data through the convolution layer, the most significant features are extracted from the output of the convolution layer using the maximum pooling layer, and the features are transferred to the fully connected layer for regression analysis of the color change trend to obtain the color prediction value;

[0065] A loss function is used to calculate a loss value to evaluate the difference between the predicted value of the tobacco leaf color prediction model and the true label, and the weights and biases of the tobacco leaf color prediction model are updated by backpropagating the loss value, and iterative training is continued until the prediction accuracy reaches a predetermined accuracy threshold or the number of iterations reaches a predetermined iteration value.

[0066] Optionally, the specific steps of S4 include:

[0067] Dynamically adjust the PID parameters of the PID control algorithm according to the optimal predicted temperature value and the predicted tobacco leaf color value, and regulate the heating equipment in the tobacco flue-curing room through the PID control algorithm after parameter adjustment;

[0068] The PID parameters include proportional gain, integral gain and differential gain;

[0069] The functional expression of the PID control algorithm is:

[0070]

[0071] Where, is the proportional gain; is the error of the current time; is the integral gain; It is the cumulative value of all error times from the start time to the current time; ; is the rate of change of error.

[0072] The beneficial effects brought about by the embodiments provided by the present invention include:

[0073] The embodiment of the present invention utilizes a data acquisition module to acquire environmental data and tobacco leaf image data in a flue-curing room in real time, sends the environmental data and tobacco leaf image data to a data processing module for data preprocessing and color feature extraction, and then sends the processed data to a data prediction module. The temperature and tobacco leaf color change trends are predicted based on a temperature prediction model and a tobacco leaf color prediction model in the data prediction module. The equipment control module dynamically adjusts PID parameters based on the temperature and tobacco leaf color change trends to accurately control the heating equipment in the flue-curing room, thereby achieving precise control of the temperature and humidity in the flue-curing room, reducing temperature fluctuations, and ensuring quality consistency and color uniformity during the tobacco leaf curing process.

[0074] The embodiment of the present invention constructs a temperature prediction model through a multivariate linear regression algorithm, which can accurately predict the temperature change trend in the tobacco flue-curing room based on historical environmental data and tobacco leaf image data; and constructs a tobacco leaf color prediction model through a convolutional neural network model, which can deeply analyze the color characteristics of tobacco leaf images and predict the color change trend of tobacco leaves during the curing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0076] Figure 1 It shows a structural block diagram of the temperature and humidity control system of the flue-cured tobacco room in the embodiment of this specification;

[0077] Figure 2 shows a structural block diagram of a data processing module in an embodiment of this specification;

[0078] Figure 3 Shows a structural block diagram of the data prediction module in an embodiment of this specification;

[0079] Figure 4 The figure shows a flow chart of the method for controlling the temperature and humidity in a tobacco flue-curing room according to an embodiment of the present invention. DETAILED DESCRIPTION

[0080] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. In the detailed description below, many specific details are proposed in order to provide a comprehensive understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention can be implemented without the need for some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.

[0081] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "connected" and "connection" should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integral connection; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0082] Example 1

[0083] like Figure 1 As shown, this embodiment provides a temperature and humidity control system for a tobacco flue-curing room based on deep learning optimization, including a data acquisition module, a data processing module, a data prediction module, an equipment control module, a data management module and an early warning model;

[0084] Exemplarily, the data acquisition module is used to collect environmental data and tobacco leaf image data in the tobacco flue-curing room; wherein the environmental data includes temperature data and humidity data;

[0085] The input end of the data processing module is communicatively connected to the output end of the data acquisition module, and is used to perform data preprocessing on the tobacco leaf image data and the environmental data, and perform color analysis on the tobacco leaf image data to obtain color feature data of the tobacco leaf image;

[0086] The input end of the data prediction module is communicatively connected to the output end of the data processing module, and is used to predict the color change trend of the tobacco leaves and the temperature change trend in the tobacco flue-curing room based on the preprocessed environmental data and the color feature data;

[0087] The input end of the equipment control module is communicatively connected to the output end of the data processing module and the output end of the data prediction module, respectively, for dynamically adjusting the parameters of the PID control algorithm according to the temperature change trend and the color change trend to regulate the heating equipment in the tobacco flue-curing room;

[0088] The input end of the data management module is respectively connected to the output end of the data processing module and the data prediction module to provide an interface for data display; it is also used to provide a query and management interface;

[0089] The input end of the early warning module is communicatively connected to the output end of the data acquisition module, so as to evaluate the dangerous conditions in the tobacco flue-curing room through the environmental data in the tobacco flue-curing room to trigger corresponding alarms.

[0090] like Figure 2 As shown, in some embodiments, the data processing module includes an image pre-processing unit, a storage unit, a color clustering unit, and a color uniformity unit;

[0091] The input end of the image preprocessing unit is communicatively connected to the output end of the data acquisition module, and is used to preprocess the environmental data in the tobacco flue-curing room and the tobacco leaf image data, and send the preprocessed tobacco leaf image data to the color clustering unit;

[0092] Among them, data preprocessing includes image denoising, grayscale conversion, white balance adjustment, image enhancement and normalization;

[0093] The input end of the color clustering unit is communicatively connected to the output end of the image preprocessing unit, and is used to perform color classification on the tobacco leaf images in the preprocessed tobacco leaf image data to obtain color clusters of the tobacco leaf images;

[0094] An input end of the color uniformity unit is communicatively connected to an output end of the color clustering unit, for evaluating the color uniformity of the tobacco leaf image according to the color clustering to obtain the color uniformity of the tobacco leaf image;

[0095] The input end of the storage unit is communicatively connected to the output ends of the image pre-processing unit, the color clustering unit and the color uniformity unit respectively, for storing the above data;

[0096] like Figure 3 As shown, in some embodiments, the data prediction module includes a temperature prediction unit, a temperature optimization unit, and a color prediction unit;

[0097] The input end of the temperature prediction unit is communicatively connected to the output end of the storage unit, and is used to predict the preprocessed environmental data and the color feature data based on a pre-trained temperature prediction model to obtain a predicted temperature value;

[0098] The input end of the temperature optimization unit is communicatively connected to the output end of the temperature prediction unit, and is used to optimize the predicted temperature value by constructing a temperature objective function and constraint conditions, thereby obtaining an optimal predicted temperature value and predicting the temperature change trend in the tobacco flue-curing room;

[0099] The input end of the color prediction unit is communicatively connected to the output end of the storage unit, and is used to predict the preprocessed environmental data and color feature data based on a pre-trained tobacco leaf color prediction model, obtain a tobacco leaf color prediction value, and predict the color change trend of the tobacco leaf.

[0100] In some embodiments, the data acquisition module includes an image acquisition component, a plurality of temperature sensors, and a plurality of humidity sensors disposed in a tobacco flue-curing room;

[0101] Specifically, the image acquisition component includes a plurality of cameras that are communicatively connected to each other, wherein the plurality of cameras are evenly distributed in the tobacco flue-curing room to realize image acquisition of tobacco leaves in the tobacco flue-curing room.

[0102] In some embodiments, a smoke concentration sensor and a carbon monoxide sensor are also included;

[0103] Specifically, the output terminals of the smoke concentration sensor and the carbon monoxide sensor are respectively connected to the input terminal of the early warning module. The early warning module evaluates the dangerous conditions in the tobacco flue-curing room through the temperature and humidity data, smoke concentration data and carbon monoxide data in the tobacco flue-curing room to trigger the corresponding alarm.

[0104] Among them, when one or more of the temperature and humidity data, smoke concentration data and carbon monoxide data in the tobacco flue-curing room exceeds the preset safety threshold, the early warning module determines that the environment in the tobacco flue-curing room is in a dangerous state, triggers the sound and light alarm in the tobacco flue-curing room to sound an alarm, and notifies the relevant personnel to take emergency measures.

[0105] In some embodiments, the heating equipment in the tobacco flue-curing room includes an electric heater and an infrared heater.

[0106] Example 2

[0107] like Figure 4 As shown, the present invention provides a method for controlling temperature and humidity in a tobacco flue-curing room based on deep learning optimization, comprising:

[0108] S1: Collecting environmental data and tobacco leaf image data in a tobacco flue-curing room; the environmental data includes temperature data and humidity data;

[0109] S2: performing data preprocessing on the tobacco leaf image data and the environmental data, and performing color analysis on the tobacco leaf image data to obtain color feature data of the tobacco leaf image;

[0110] In some embodiments, S2 specifically includes the following steps:

[0111] S21: performing data preprocessing on the tobacco leaf image data and the environmental data to obtain the preprocessed tobacco leaf image data and the environmental data;

[0112] Among them, data preprocessing includes image denoising, grayscale conversion, white balance adjustment, image enhancement and normalization;

[0113] S22: performing color segmentation on the tobacco leaf image in the preprocessed tobacco leaf image data to obtain color clusters of the tobacco leaf image;

[0114] S23: performing color uniformity evaluation of the tobacco leaf image according to the color clustering to obtain the color uniformity of the tobacco leaf image.

[0115] Specifically, S22 includes the following steps:

[0116] S221: converting the preprocessed tobacco leaf image into an HSV color space through a color space conversion algorithm to obtain an HSV value corresponding to each pixel in the tobacco leaf image;

[0117] Among them, the function expression of the color space conversion algorithm is:

[0118]

[0119]

[0120]

[0121] Where, R is the red component value; G is the green component value; B is the blue component value; V is the brightness value; S is saturation; H For color tone.

[0122] S222: Initialize the cluster center of the K-means algorithm;

[0123] S223: assigning each pixel in the tobacco leaf image to the nearest cluster center according to its HSV value;

[0124] S224: Calculate the average HSV values ​​of all pixels in each cluster, and update the cluster center according to each average value;

[0125] S225: Determine whether the cluster centers before and after the update are exactly the same; if so, output the updated cluster center as the color cluster of the tobacco leaf image; if not, use the updated cluster center as the current cluster center and return to step S223;

[0126] Specifically, S23 includes the following steps:

[0127] S231: Calculate the color difference between the color of each pixel in the tobacco leaf image and the color of its corresponding cluster center:

[0128] S232: Calculate the standard deviation of the color difference to evaluate the uniformity of the tobacco leaf color.

[0129] S3: predicting the color change trend of the tobacco leaves and the temperature change trend in the tobacco flue-curing room based on the preprocessed environmental data and the color characteristic data;

[0130] In some embodiments, S3 specifically includes the following steps:

[0131] S31: Predicting the preprocessed environmental data and the color feature data based on a pre-trained temperature prediction model to obtain a predicted temperature value;

[0132] The functional expression of the temperature prediction model is:

[0133]

[0134] Where, Y is the predicted temperature value; is the current temperature data; is the current humidity data; is the color characteristic data of the current tobacco leaf; is the intercept, which is the predicted value of the model when all input features are zero; is the coefficient corresponding to the current temperature data; is the coefficient corresponding to the current humidity data; is the corresponding coefficient of the color characteristic data of the current tobacco leaf; is the deviation between the actual value and the predicted value;

[0135] S32: Optimizing the predicted temperature value by constructing a temperature objective function and constraint conditions to obtain an optimal predicted temperature value, so as to predict the temperature change trend in the tobacco flue-curing room;

[0136] The expression of the temperature objective function is:

[0137]

[0138] Where Z is the temperature objective function; For in time t Control input; is the cumulative error between the predicted temperature value and the target temperature value from time t to time t+N-1; N is a fixed period; For the time point k The weight factor is used to reflect the importance of the deviation between the predicted temperature and the target temperature at different time points; is the target temperature value; is the predicted temperature value; represents the cost function at each time point k.

[0139] Function expression of the constraint condition:

[0140]

[0141]

[0142] Where, and are the minimum and maximum predicted temperature values ​​respectively; and are the minimum and maximum values ​​of the control input, respectively.

[0143] In this embodiment, by minimizing the temperature objective function Z and the constraints, the temperature and humidity in the tobacco flue-curing room are always within the range suitable for tobacco leaf curing, while the energy consumption in the tobacco flue-curing room is maintained at a low level.

[0144] S33: Based on the pre-trained tobacco leaf color prediction model, the pre-processed environmental data and color feature data are predicted to obtain a tobacco leaf color prediction value to predict the color change trend of the tobacco leaf.

[0145] In some embodiments, in S31, the specific steps of training the pre-trained temperature prediction model include:

[0146] Based on the multiple linear regression algorithm, a temperature prediction model is constructed;

[0147] Obtain historical environmental data and historical color feature data;

[0148] Inputting the historical environmental data and the historical color feature data into a temperature prediction model for training to obtain a trained temperature prediction model;

[0149] The temperature prediction model in this embodiment predicts the temperature change trend based on the current environmental data by learning the influence relationship between environmental factors and color characteristics on temperature changes.

[0150] In some embodiments, in S33, the specific steps of training the pre-trained tobacco leaf color prediction model include:

[0151] S331: Obtain historical baking data;

[0152] Among them, historical baking data includes historical environmental data, historical color characteristic data, actual tobacco leaf color change data and tobacco leaf final quality data;

[0153] S332: Fusing the historical environment data and the historical color feature data to generate multi-channel input data;

[0154] S333: Based on the actual tobacco leaf color change data and the tobacco leaf final quality data, generate a corresponding true label for each set of input data.

[0155] In this embodiment, the real label data is used to guide the model to learn the trend of tobacco leaf color change and its relationship with environmental factors. The real label is the actual situation of color change under specific environmental conditions and the final quality of the tobacco leaves.

[0156] S334: constructing a tobacco leaf color prediction model based on the convolutional neural network model, and initializing the tobacco leaf color prediction model;

[0157] The tobacco leaf color prediction model includes a convolutional layer, a maximum pooling layer and a fully connected layer;

[0158] S335: After performing feature extraction on the input data through the convolution layer, the most significant features are extracted from the output of the convolution layer using the maximum pooling layer, and the features are transmitted to the fully connected layer to perform regression analysis on the color change trend to obtain a color prediction value;

[0159] Specifically, the convolution layer performs a convolution operation on the input data to extract feature maps:

[0160]

[0161] Where, S After the convolution operation i Row, No. j Column, No. k Output value on each channel; For input data in i+m-1 Row, No. j+n-1 The value at the column position; For the k The convolution kernel is m Row, No. n The weight value at the column position. bk For the k The bias term of the convolution kernel.

[0162] Specifically, the maximum pooling layer is used to reduce the dimension of the convolution layer output, and its function expression is:

[0163]

[0164] Where, After the pooling operation i Row, No. j Column, No. k Output value on each channel; The convolutional layer output is i+m-1 Row, No. j+n-1 Column, No. k The value at the position of each channel; To find the maximum value of the elements in the local area (pooling window). In this embodiment, the maximum pooling layer pools the features output by the convolution layer through a 2x2 pooling window;

[0165] In this embodiment, the regression analysis algorithm selects one of the recursive neural network structures such as LSTM (long short-term memory network) and GRU (gated recurrent unit) as the core of the regression analysis algorithm, which can effectively capture the long-term dependencies in the input data and can more accurately predict the color change trend of tobacco leaves during the baking process, thereby significantly improving the prediction accuracy of tobacco leaf baking quality.

[0166] S336: Use the loss function to calculate the loss value to evaluate the difference between the predicted value of the tobacco leaf color prediction model and the true label, and update the weight and bias of the tobacco leaf color prediction model by backpropagating the loss value, and continue iterative training until the prediction accuracy reaches a predetermined accuracy threshold or the number of iterations reaches a predetermined iteration value.

[0167] Among them, the loss function is the mean square error loss, and its function expression is:

[0168]

[0169] Where, L is the mean square error loss; N is the total number of samples, , For the j The true value of the samples; For the j The predicted value of the sample.

[0170] S4: adjusting the parameters of the PID control algorithm according to the temperature change trend and the color change trend to regulate the heating equipment in the tobacco flue-curing room.

[0171] In some embodiments, the specific steps of S4 include:

[0172] Dynamically adjust the PID parameters of the PID control algorithm according to the optimal predicted temperature value and the predicted tobacco leaf color value, and regulate the heating equipment in the tobacco flue-curing room through the PID control algorithm after parameter adjustment;

[0173] The PID parameters include proportional gain, integral gain and differential gain;

[0174] The functional expression of the PID control algorithm is:

[0175]

[0176] Where, is the proportional gain; is the error of the current time; is the integral gain; It is the cumulative value of all error times from the start time to the current time; ; is the rate of change of error.

[0177] Among them, in this embodiment, the parameters (Kp, Ki, Kd) of the PID controller are dynamically adjusted according to the optimal predicted temperature value and the predicted tobacco leaf color value to adapt to the control requirements under different baking stages or conditions and the temperature and humidity adjustment requirements in the smoke room.

[0178] In addition, in some embodiments, a feedforward control mechanism can be introduced on the basis of PID control. Through feedforward control, the control quantity is pre-adjusted using prediction information to reduce the delay and error of the system response. For example, a rough adjustment is first made using the prediction model to set the target temperature, and then the PID controller is used for fine adjustment to ensure the stability and response speed of the system. Through this combination of multiple control strategies, the temperature and humidity control system of the tobacco flue-curing room can more effectively respond to temperature and humidity changes during the baking process, thereby improving the consistency and prediction accuracy of the tobacco leaf baking quality.

[0179] In summary, this embodiment uses the data acquisition module to obtain the environmental data and tobacco leaf image data in the tobacco flue-curing room in real time, sends the environmental data and tobacco leaf image data to the data processing module for data preprocessing and color feature extraction, and then sends the processed data to the data prediction module. According to the temperature prediction model and color prediction model in the data prediction module, the changing trends of temperature and tobacco leaf color are predicted; the data prediction module sends the changing trends of temperature and tobacco leaf color to the equipment control module, and the equipment control module dynamically adjusts the PID parameters according to the changing trends of temperature and tobacco leaf color to accurately control the heating equipment in the tobacco flue-curing room, so as to achieve precise control of temperature and humidity in the flue-curing room, reduce temperature fluctuations, and ensure quality consistency and color uniformity during tobacco leaf curing;

[0180] This embodiment automatically collects environmental and image data from within the flue-curing room, analyzes and predicts it, and then adjusts the temperature based on the predicted results, reducing the need for manual monitoring and adjustment, and lowering labor intensity. Furthermore, the tobacco leaf color prediction model in this embodiment is constructed using a convolutional neural network, which has good generalization capabilities. This improves the stability and reliability of the humidity control system in the flue-curing room under different curing conditions and can adapt to different curing environments and tobacco leaf characteristics.

[0181] This embodiment dynamically adjusts the PID parameters of the PID control algorithm through the output of the temperature prediction model and the color prediction model to accurately adjust the heating equipment in the tobacco flue-curing room. This not only improves the automation level of the baking process in the tobacco flue-curing room, but also enables timely adjustment of the heating equipment, improves baking efficiency, shortens the baking cycle, and reduces energy waste through precise control, achieving energy conservation and emission reduction, while also improving the efficiency and quality of tobacco leaf baking.

[0182] The above description is merely that of the preferred embodiments of the present application, and thus is not intended to limit the present application. It will be apparent to those skilled in the art that the present application can be embodied in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the scope of the present application should be determined not by the above description but by the appended claims and their equivalents in meaning and scope.

Claims

1. A temperature and humidity control system for a flue-cured tobacco house based on deep learning optimization, characterized in that: include: Data acquisition module, used to collect environmental data and tobacco leaf image data in the tobacco flue-curing room; a data processing module connected to the data acquisition module, for performing data preprocessing on the tobacco leaf image data and environmental data, and performing color analysis on the tobacco leaf image data to obtain color feature data of the tobacco leaf image; A data prediction module, connected to the data processing module, for predicting the color change trend of tobacco leaves and the temperature change trend in the tobacco flue-curing room based on the pre-processed environmental data and the color characteristic data; An equipment control module is connected to the data processing module and the data prediction module respectively, and is used to dynamically adjust the parameters of the PID control algorithm according to the temperature change trend and the color change trend to regulate the heating equipment in the tobacco flue-curing room; The data prediction module is configured to perform the following steps: Based on a pre-trained temperature prediction model, the pre-processed environmental data and the color feature data are predicted to obtain a predicted temperature value; Among them, environmental data includes temperature data and humidity data; The functional expression of the temperature prediction model is: ； Where, is the predicted temperature value; is the current temperature data; is the current humidity data; is the color characteristic data of the current tobacco leaf; is the intercept; is the coefficient corresponding to the current temperature data; is the coefficient corresponding to the current humidity data; is the corresponding coefficient of the color characteristic data of the current tobacco leaf; is the deviation between the actual value and the predicted value; By constructing a temperature objective function and constraint conditions, the predicted temperature value is optimized to obtain the optimal predicted temperature value to predict the temperature change trend in the tobacco flue-curing room; The expression of the temperature objective function is: ； Where Z is the temperature objective function; is the control input at time t; is the cumulative error between the predicted temperature value and the target temperature value from time t to time t+N-1; N is a fixed period; is the weight factor at time point k; is the target temperature value; is the predicted temperature value; Function expression of the constraint condition: ； ； Where, and are the minimum and maximum predicted temperature values ​​respectively; and are the minimum and maximum values ​​of the control input respectively; Based on the pre-trained tobacco leaf color prediction model, the pre-processed environmental data and color feature data are predicted to obtain the tobacco leaf color prediction value to predict the color change trend of the tobacco leaves.

2. The system according to claim 1, wherein: The data processing module includes an image preprocessing unit, a storage unit, a color clustering unit and a color uniformity unit; The input end of the image preprocessing unit is connected to the output end of the data acquisition module, and is used to preprocess the environmental data in the tobacco flue-curing room and the tobacco leaf image data, and send the preprocessed tobacco leaf image data to the color clustering unit; The input end of the color clustering unit is connected to the output end of the image preprocessing unit, and is used to perform color classification on the tobacco leaf images in the preprocessed tobacco leaf image data to obtain color clusters of the tobacco leaf images; The input end of the color uniformity unit is connected to the output end of the color clustering unit, and is used to evaluate the color uniformity of the tobacco leaf image according to the color clustering to obtain the color uniformity of the tobacco leaf image; The input end of the storage unit is connected to the output ends of the image pre-processing unit, the color clustering unit and the color uniformity unit respectively for storing data.

3. The system according to claim 1, wherein: The data prediction module includes a temperature prediction unit, a temperature optimization unit, and a color prediction unit; The input end of the temperature prediction unit is connected to the output end of the storage unit, and is used to predict the preprocessed environmental data and the color feature data based on a pre-trained temperature prediction model to obtain a predicted temperature value; The input end of the temperature optimization unit is connected to the output end of the temperature prediction unit, and is used to optimize the predicted temperature value by constructing a temperature objective function and constraint conditions to obtain an optimal predicted temperature value, so as to predict the temperature change trend in the tobacco flue-curing room; The input end of the color prediction unit is connected to the output end of the storage unit, and is used to predict the preprocessed environmental data and color feature data based on a pre-trained tobacco leaf color prediction model, obtain a tobacco leaf color prediction value, and predict the color change trend of the tobacco leaf.

4. The system according to claim 1, wherein: It also includes early warning module and data management module; The input end of the early warning module is connected to the output end of the data acquisition module, and is used to evaluate the dangerous conditions in the tobacco flue-curing room through the environmental data in the tobacco flue-curing room to trigger a corresponding alarm; The input end of the data management module is connected to the output end of the data processing module and the data prediction module respectively, so as to provide an interface for data display; and also to provide an interface for query and management.

5. A method for controlling temperature and humidity in a flue-cured tobacco house based on deep learning optimization, characterized in that: The temperature and humidity control system for a flue-cured tobacco house as claimed in any one of claims 1 to 4 comprises the following steps: S1: Collect environmental data and tobacco leaf image data in the tobacco flue-curing room; S2: performing data preprocessing on the tobacco leaf image data and the environmental data, and performing color analysis on the tobacco leaf image data to obtain color feature data of the tobacco leaf image; S3: predicting the color change trend of tobacco leaves and the temperature change trend in the tobacco flue-curing room based on the preprocessed environmental data and the color characteristic data; S4: dynamically adjusting the parameters of the PID control algorithm according to the temperature change trend and the color change trend to regulate the heating equipment in the tobacco flue-curing room; The S3 specifically includes the following steps: S31: Predicting the preprocessed environmental data and the color feature data based on a pre-trained temperature prediction model to obtain a predicted temperature value; Among them, environmental data includes temperature data and humidity data; The functional expression of the temperature prediction model is: ； Where, is the predicted temperature value; is the current temperature data; is the current humidity data; is the color characteristic data of the current tobacco leaf; is the intercept; is the coefficient corresponding to the current temperature data; is the coefficient corresponding to the current humidity data; is the corresponding coefficient of the color characteristic data of the current tobacco leaf; is the deviation between the actual value and the predicted value; S32: Optimizing the predicted temperature value by constructing a temperature objective function and constraint conditions to obtain an optimal predicted temperature value, so as to predict the temperature change trend in the tobacco flue-curing room; The expression of the temperature objective function is: ； Where Z is the temperature objective function; is the control input at time t; is the cumulative error between the predicted temperature value and the target temperature value from time t to time t+N-1; N is a fixed period; is the weight factor at time point k; is the target temperature value; is the predicted temperature value; Function expression of the constraint condition: ； ； Where, and are the minimum and maximum predicted temperature values ​​respectively; and are the minimum and maximum values ​​of the control input respectively; S33: Based on the pre-trained tobacco leaf color prediction model, the pre-processed environmental data and color feature data are predicted to obtain a tobacco leaf color prediction value to predict the color change trend of the tobacco leaf.

6. The method according to claim 5, characterized in that S2 specifically includes the following steps: S21: performing data preprocessing on the tobacco leaf image data and the environmental data to obtain the preprocessed tobacco leaf image data and the environmental data; S22: performing color segmentation on the tobacco leaf image in the preprocessed tobacco leaf image data to obtain color clusters of the tobacco leaf image; S23: performing color uniformity evaluation of the tobacco leaf image according to the color clustering to obtain the color uniformity of the tobacco leaf image.

7. The method according to claim 6, characterized in that S22 specifically includes the following steps: S221: transferring the preprocessed tobacco leaf image to the HSV color space to obtain the HSV value corresponding to each pixel in the tobacco leaf image; S222: Initialize the cluster center of the K-means algorithm; S223: assigning each pixel in the tobacco leaf image to the nearest cluster center according to its HSV value; S224: Calculate the average HSV values ​​of all pixels in each cluster, and update the cluster center according to each average value; S225: Determine whether the cluster centers before and after the update are exactly the same; if so, output the updated cluster center as the color cluster of the tobacco leaf image; if not, use the updated cluster center as the current cluster center and return to step S223; The S23 specifically includes the following steps: S231: Calculate the color difference between the color of each pixel in the tobacco leaf image and the color of its corresponding cluster center: S232: Calculate the standard deviation of the color difference to evaluate the uniformity of the tobacco leaf color.

8. The method according to claim 5, characterized in that In S33, the specific steps of training the pre-trained tobacco leaf color prediction model include: Get historical baking data; The historical baking data includes historical environmental data, historical color characteristic data, actual tobacco leaf color change data and tobacco leaf final quality data; Fusing the historical environmental data and the historical color feature data to generate multi-channel input data; Generate corresponding true labels for each set of input data based on the actual color change data of tobacco leaves and the final quality data of tobacco leaves; Constructing a tobacco leaf color prediction model based on a convolutional neural network model and initializing the tobacco leaf color prediction model; The tobacco leaf color prediction model includes a convolutional layer, a maximum pooling layer and a fully connected layer; After extracting features from the input data through the convolution layer, the most significant features are extracted from the output of the convolution layer using the maximum pooling layer, and the features are transferred to the fully connected layer for regression analysis of color change trends to obtain color prediction values; A loss function is used to calculate a loss value to evaluate the difference between the predicted value of the tobacco leaf color prediction model and the true label, and the weights and biases of the tobacco leaf color prediction model are updated by backpropagating the loss value, and iterative training is continued until the prediction accuracy reaches a predetermined accuracy threshold or the number of iterations reaches a predetermined iteration value.

9. The method according to claim 5, characterized in that The specific steps of S4 include: Dynamically adjust the PID parameters of the PID control algorithm according to the optimal predicted temperature value and the predicted tobacco leaf color value, and regulate the heating equipment in the tobacco flue-curing room through the PID control algorithm after parameter adjustment; The PID parameters include proportional gain, integral gain and differential gain; The functional expression of the PID control algorithm is: ； Where, is the proportional gain; is the error of the current time; is the integral gain; It is the cumulative value of all error times from the start time to the current time; is the differential gain; is the rate of change of error.

Images