Cut tobacco dryer temperature control method, device, equipment, medium and product

Abstract

The invention discloses a cut tobacco dryer temperature control method, device and equipment, a medium and a product. The method comprises the steps that if a cut-tobacco dryer temperature control request is detected, a first weight corresponding to a first temperature strategy is determined based on a preset coefficient determination model according to cut-tobacco drying data of a preset historical time period; determining a second weight corresponding to a second temperature strategy according to the first weight and a preset total weight value, and predicting the temperature of the cut tobacco drying cylinder wall according to the first temperature strategy and the second temperature strategy to obtain a first temperature set value and a second temperature set value; according to the first weight, the second weight, the first temperature set value and the second temperature set value, a target temperature set value is determined, so that the cut tobacco dryer is indicated to conduct cut tobacco drying operation based on the target temperature set value, and outlet moisture control over the cut tobacco dryer is achieved. According to the method, multiple temperature determination strategies can be considered, and the accurate and effective temperature set value is determined, so that the cut-tobacco dryer is indicated to perform accurate and effective outlet moisture control.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of cigarette silk making technology, and particularly relates to a cut tobacco drying machine temperature control method, device, equipment, medium and product. BACKGROUND

[0002] Due to the strong nonlinearity, uncertainty and large hysteresis of the cut tobacco drying process, and the particularity of tobacco leaves, the moisture control of the cut tobacco drying process is very complex. In essence, the moisture control of the cut tobacco drying machine belongs to a nonlinear time-varying large hysteresis system.

[0003] Currently, mainstream equipment manufacturers use a cascade PID (Proportional Integral Derivative) control method to control the outlet moisture of the cut tobacco drying machine. However, the cascade multi-stage PID control has the following disadvantages: a large number of controllers, complex parameter adjustment, mutual influence between controllers, slow response speed, and difficulty in parameter adjustment, etc. This results in problems such as hysteresis, large fluctuation and instability of the outlet moisture control of the cut tobacco drying machine, and difficulty in finding optimal parameters.

[0004] Therefore, how to consider multiple temperature determination strategies to determine accurate and effective temperature set values to instruct the cut tobacco drying machine to perform precise and effective outlet moisture control is a problem to be solved at present. SUMMARY

[0005] The present application provides a cut tobacco drying machine temperature control method, device, equipment, medium and product to consider multiple temperature determination strategies to determine accurate and effective temperature set values to instruct the cut tobacco drying machine to perform precise and effective outlet moisture control.

[0006] According to an aspect of the present application, a cut tobacco drying machine temperature control method is provided, comprising:

[0007] If a cut tobacco drying machine temperature control request is detected, a first weight corresponding to a first temperature strategy is determined based on a preset historical period of cut tobacco drying data and a preset coefficient determination model;

[0008] A second weight corresponding to a second temperature strategy is determined according to the first weight and a preset total weight value, and temperature prediction of the cut tobacco drying cylinder wall is performed according to the first temperature strategy and the second temperature strategy respectively to obtain a first temperature set value and a second temperature set value;

[0009] A target temperature set value is determined according to the first weight, the second weight, the first temperature set value and the second temperature set value to instruct the cut tobacco drying machine to perform cut tobacco drying operation based on the target temperature set value to realize outlet moisture control of the cut tobacco drying machine.

[0010] According to another aspect of the present application, there is provided a temperature control device for a cut tobacco machine, comprising:

[0011] a determination module configured to determine a first weight corresponding to a first temperature strategy based on a preset coefficient determination model if a cut tobacco machine temperature control request is detected according to cut tobacco data of a preset historical period;

[0012] a determination module configured to determine a first weight corresponding to a first temperature strategy based on a preset coefficient determination model if a cut tobacco machine temperature control request is detected according to cut tobacco data of a preset historical period;

[0013] a control module configured to determine a target temperature setting value according to the first weight, the second weight, the first temperature setting value and the second temperature setting value, and instruct the cut tobacco machine to perform a cut tobacco operation based on the target temperature setting value to achieve outlet moisture control of the cut tobacco machine.

[0014] According to another aspect of the present application, there is provided an electronic device, comprising:

[0015] at least one processor; and

[0016] a memory connected to the at least one processor in communication; wherein,

[0017] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the cut tobacco machine temperature control method according to any one of the embodiments of the present application.

[0018] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to perform the cut tobacco machine temperature control method according to any one of the embodiments of the present application when executed by the processor.

[0019] According to another aspect of the present application, there is also provided a computer program product comprising a computer program, the computer program being configured to perform the cut tobacco machine temperature control method according to any one of the embodiments of the present application when executed by a processor.

[0020] The technical solution of this invention, if a temperature control request for the yarn drying machine is detected, determines a first weight corresponding to a first temperature strategy based on yarn drying data from a preset historical period and a preset coefficient determination model; determines a second weight corresponding to a second temperature strategy based on the first weight and the total preset weight; and predicts the temperature of the yarn drying cylinder wall based on the first and second temperature strategies respectively to obtain a first temperature setpoint and a second temperature setpoint; and determines a target temperature setpoint based on the first weight, the second weight, the first temperature setpoint, and the second temperature setpoint to instruct the yarn drying machine to perform yarn drying operations based on the target temperature setpoint, thereby achieving outlet moisture control of the yarn drying machine. By considering multiple temperature determination strategies, an accurate and effective temperature setpoint can be determined, thereby instructing the yarn drying machine to perform precise and effective outlet moisture control.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a temperature control method for a wire drying machine provided in an embodiment of the present invention;

[0024] Figure 2 This is a flowchart of a temperature control method for a wire drying machine provided in an embodiment of the present invention;

[0025] Figure 3 This is a structural block diagram of a temperature control device for a wire drying machine provided in an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," "target," "candidate," and "alternative," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the invention described herein can be practiced in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The acquisition, storage, use, and processing of data in the technical solutions of this application comply with relevant laws and regulations.

[0029] It should be noted that in related technologies, there are commonly schemes based on artificial intelligence methods such as machine learning, using data-driven optimization control. These schemes involve predicting the optimal temperature of the drying machine's cylinder wall. Additionally, there are schemes based on advanced control strategies to predict and control the drying machine's cylinder wall temperature. However, for the former, data-driven machine learning control of the drying machine's outlet moisture content relies excessively on historical data and equipment status, easily leading to overfitting, lacking adaptability to dynamic changes in the equipment, and lacking mechanistic understanding, thus failing to analyze the stability of the control system. For the latter, advanced control strategies for drying moisture content rely excessively on the mechanisms of automatic control principles, ignoring the disturbances of non-strongly correlated factors to the system, and lacking correlation with potential data patterns, thus often resulting in limited improvement in control performance. To address these issues, this invention combines machine learning with advanced control strategies. This allows the scheme to possess both the advantages of model-free control driven by data patterns from machine learning and the advantages of mechanistic correlation from advanced control. It can automatically weight and allocate the control values ​​of machine learning and advanced control, and continuously train and optimize, ultimately improving the stability, convergence, and robustness of the material moisture control model for the filament drying machine. Specific implementation methods will be described in detail in subsequent embodiments.

[0030] Example 1

[0031] Figure 1 This is a flowchart of a temperature control method for a yarn drying machine provided in an embodiment of the present invention. This embodiment is applicable to situations where an accurate and effective cylinder wall temperature setpoint is determined based on multiple temperature determination strategies and corresponding weights to instruct the yarn drying machine to control outlet moisture content. This method can be executed by a yarn drying machine temperature control device, which can be implemented in hardware and / or software. This yarn drying machine temperature control device can be configured in an electronic device, such as... Figure 1 As shown, the temperature control method of the wire drying machine includes:

[0032] S101. If a temperature control request for the wire drying machine is detected, the first weight corresponding to the first temperature strategy is determined based on the wire drying data of the preset historical period and the preset coefficient determination model.

[0033] Here, "drying machine" refers to the tobacco drying machine used in the cigarette making process. "Temperature control request" refers to a request to control the temperature of the drying machine's cylinder wall. "Preset historical time period" refers to the time period corresponding to a preset duration prior to the current moment; different drying data may correspond to different preset historical time periods. The preset coefficient determination model is a backpropagation neural network; this model is used to determine the optimal weights corresponding to the input drying data; the first weight represents the reliability of the temperature predicted by the first temperature strategy. The drying data may include at least one of the following: the average actual moisture content of the outlet material, the standard deviation of the outlet material moisture content, the deviation of the outlet material moisture content, the average actual hot air temperature, the standard deviation of the actual hot air temperature, the average actual moisture content of the incoming material, the average actual temperature of the incoming material, the average actual flow rate of the incoming material, and the average negative pressure value of the exhaust fan.

[0034] The first temperature strategy is based on machine learning algorithms to predict the cylinder wall temperature. It should be noted that this strategy involves using historical data from the yarn production line to train commonly used machine learning algorithms such as linear regression, random forest, decision tree, and neural networks, or improved versions thereof. An algorithm with high prediction accuracy is selected to fit a preliminary artificial intelligence prediction model. The training process using machine learning algorithms involves common model training techniques, which will not be elaborated upon in this invention. The goal is to ensure that the prediction accuracy of the machine learning algorithm reaches a generally usable level for prediction based on relevant data from the yarn drying process in the yarn drying machine.

[0035] Optionally, during the operation of the drying machine, the actual values ​​of outlet material moisture, hot air temperature, incoming material moisture, incoming material temperature, incoming material flow rate, and exhaust fan negative pressure can be acquired and stored in real time every second. When a temperature control request for the drying machine is detected, the drying data corresponding to the preset historical time period can be determined from the stored drying data.

[0036] Optionally, the drying data can be input into a preset coefficient to determine the model, and the weights output by the preset coefficient to determine the model can be used as the first weights corresponding to the first temperature strategy.

[0037] Optionally, the model training process for the preset coefficient determination model is as follows: Based on the preset random weight generation strategy, at least two random weights are generated, and the temperature setpoint is determined based on the random weights, the first temperature strategy, and the second temperature strategy to perform the wire drying operation, resulting in at least two sets of training wire drying data; the Pearson coefficient of each set of training wire drying data at different delay times is determined to obtain the optimal delay time of the training wire drying data, and the training wire drying data is time-aligned according to the optimal delay time; the time-aligned training wire drying data and the corresponding random weights are used to fit and train the initial backpropagation neural network to obtain the preset coefficient determination model.

[0038] For example, an automatic k-value generator can be designed to update the k-value every 120 seconds. The k-value is generated by the generator and continuously intervenes in the production to produce the actual value of the corresponding wire drying data, which is used to train the predetermined model of the preset system.

[0039] For example, a k-value generator can be defined as a random value generated between 0 and 1, and its definition formula is: ;in, This represents a random function used to generate random weights k, ranging from 0 to 1.

[0040] Optionally, for each random weight, a first temperature strategy and a second temperature strategy can be used to determine the temperature setpoint, and then the wire drying operation can be performed based on the temperature setpoint, and the obtained wire drying data can be collected. That is, the temperature setpoint is determined based on the random weight, the first temperature strategy and the second temperature strategy to perform the wire drying operation, and at least two sets of training wire drying data are obtained.

[0041] For example, multiple batches of continuously changing k values ​​and all training wire drying data can be recorded. Each set of training wire drying data can include: the average actual value of the outlet material moisture content X1 in the most recent N1 seconds, the standard deviation of the outlet material moisture content X2 in the most recent N2 seconds, the deviation of the outlet material moisture content X3 in the most recent N3 seconds, the average actual value of the hot air temperature X4 in the most recent N4 seconds, the standard deviation of the hot air temperature X5 in the most recent N5 seconds, the average actual value of the incoming material moisture content X6 in the most recent N6 seconds, the average actual value of the incoming material temperature X7 in the most recent N7 seconds, the average actual value of the incoming material flow rate X8 in the most recent N8 seconds, and the average negative pressure value of the exhaust fan X9 in the most recent N9 seconds. Where N1~N9 are the moving time windows for calculating the independent variables, which are time units of 10 seconds in increments of 10 seconds. Furthermore, the values ​​of X1 can be calculated for N1=10s, N1=20s, N1=30s…N1=120s respectively; similarly, the values ​​of X2 can be calculated for N2=10s, N2=20s, N2=30s…N2=120s respectively; and so on, calculating the values ​​of X1 when N…N9…N1=120s ... p =10s, when N p =20s, when Np =30s…N p =120s X p The value of is given, where 1 ≤ p ≤ 9, and p is an integer. Using Pearson's formula and correlation principle, the correlation coefficient between Np and k is calculated when Np = 10s, Np = 20s, Np = 30s, ..., Np = 120s. Finally, the Pearson coefficient is maximized when Np is in time unit t, which is the optimal choice for Np, i.e., the optimal delay time. After calculating the specific values ​​of N1 to N9 based on t, the corresponding X1 to X9 can be obtained for each random weight and the specific values ​​of N1 to N9. Each group of X1 to X9 and the corresponding random weight are normalized to form a historical data record. At least 5000 data records are collected to fit and train the initial backpropagation neural network to obtain the model with preset coefficients.

[0042] For example, the model training process for a model with preset coefficients can be as follows: First, initialize the network. Assign random numbers within the interval (-1, 1) to each connection weight of the backpropagation neural network, set the error function e, and specify the maximum number of learning iterations M. Input the collected training data into the backpropagation neural network. For each training data sample input, calculate the estimated k value in the forward direction. Then, use the square of the difference between the estimated k value and the actual k value as the error for backpropagation to calculate the error between the output layer and the expected value, thereby adjusting the network parameters to reduce the error. During this process, calculate the number of derivations of the error function for each neuron in the output layer. First, use the errors of each neuron in the output layer and the outputs of each neuron in the hidden layer to correct the connection weights. Then, use the errors of the hidden layer and the inputs of each neuron in the input layer to correct the connection weights. Finally, calculate the global error. Determine if the network error meets the requirements. When the error reaches the expected value, or when the number of learning iterations exceeds the set maximum number of iterations M, stop training to prevent the training algorithm from "freezing". Continue to input new historical data samples until all sample data has been trained. Finally, after training on all sample data, if the backpropagation neural network evaluation metric is greater than 0.9, the model training is complete. Otherwise, the historical data is further filtered to delve into the details of feature engineering.

[0043] Optionally, based on the drying data of a preset historical period, a model is determined using preset coefficients to determine the first weight corresponding to the first temperature strategy. This includes: determining at least two collection time periods based on a preset moving time window, and matching the corresponding collection time period for each drying data; determining the target drying data from the drying data of the preset historical period based on the collection time period, and inputting the target drying data into the model using preset coefficients to obtain the first weight corresponding to the first temperature strategy.

[0044] For example, the preset moving time window can be a time length unit of rounded ten seconds with 10-second intervals. The time when the temperature control request of the wire drying machine is detected can be determined as the current time. Correspondingly, at least two collection time periods are the most recent 10 seconds before the current time, the most recent 20 seconds before the current time, the most recent 30 seconds before the current time, and so on.

[0045] Optionally, a corresponding collection time period is matched for each drying data, including: the average actual value of the moisture content of the outlet material, the standard deviation of the moisture content of the outlet material, the deviation of the moisture content of the outlet material, the average actual value of the hot air temperature, the standard deviation of the actual value of the hot air temperature, the average actual value of the moisture content of the incoming material, the average actual value of the temperature of the incoming material, the average actual value of the flow rate of the incoming material, and the average negative pressure value of the exhaust fan. The matching time period is based on the collection time period that increases in a preset time window.

[0046] Here, standard deviation refers to statistical standard deviation (SD). Deviation refers to the indicator that characterizes the deviation between the moisture value of the exported material and the preset target value.

[0047] For example, the deviation HD of the moisture content of the exported material can be determined based on the following formula:

[0048] ;

[0049] Where x represents the moisture content of the exported material, sp represents the control center value of the tobacco process control indicator, i.e., the preset indicator value, and n represents the quantity of moisture content of the exported material collected within the preset historical period.

[0050] For example, the data collected could be, in sequence, the average actual value of the moisture content of the outlet material, the standard deviation of the moisture content of the outlet material, the deviation of the moisture content of the outlet material, the average actual value of the hot air temperature, the standard deviation of the hot air temperature, the average actual value of the incoming material moisture content, the average actual value of the incoming material temperature, the average actual value of the incoming material flow rate, and the average negative pressure value of the exhaust fan. The time period for matching the data collection could be N1 to N9, where N1 to N9 are the most recent 10 seconds, 20 seconds, 30 seconds, 40 seconds, 50 seconds, 60 seconds, 70 seconds, 80 seconds, and 90 seconds before the current time.

[0051] S102. Based on the first weight and the total preset weight, determine the second weight corresponding to the second temperature strategy, and predict the temperature of the drying cylinder wall according to the first temperature strategy and the second temperature strategy respectively, so as to obtain the first temperature setpoint and the second temperature setpoint.

[0052] The preset total weight refers to the sum of the first and second weights, which can be, for example, 1. The second weight refers to the weight of the reliability of the temperature setpoint predicted by the second temperature strategy. The first temperature setpoint is the temperature setpoint obtained by predicting the temperature of the wire drying cylinder wall using the first temperature strategy. The second temperature setpoint is the temperature setpoint obtained by predicting the temperature of the wire drying cylinder wall using the second temperature strategy.

[0053] The second temperature strategy is based on an advanced control strategy to determine the cylinder wall temperature. It should be noted that the process of determining the cylinder wall temperature based on the advanced control strategy can be as follows: The transfer function of the controlled object model of the drying machine is obtained using methods such as system identification, typically fitted with a first-order or second-order lag transfer function. Then, advanced control methods such as Model Predictive Control (MPC), neural network control, and sliding film control are used to control the moisture content at the drying machine outlet. The advanced control strategy methods involve common technologies, which will not be elaborated upon in this invention. Ultimately, the advanced control strategy ensures that the moisture content at the drying machine outlet has strong robustness. The mechanism for updating based on the advanced control strategy involves periodically using methods such as step response and data analysis to correct the transfer function of the controlled object model of the drying machine, and using historical data to correct the advanced process control parameters, thereby achieving the effect of updating the model.

[0054] Optionally, the second weight corresponding to the second temperature strategy is determined based on the first weight and the total preset weight, including: determining the difference between the total preset weight and the first weight as the second weight corresponding to the second temperature strategy. For example, if the first weight is k, the corresponding second weight can be expressed as (1-k).

[0055] S103. Based on the first weight, the second weight, the first temperature setpoint, and the second temperature setpoint, determine the target temperature setpoint to instruct the drying machine to perform drying operation based on the target temperature setpoint, thereby achieving outlet moisture control of the drying machine.

[0056] The target temperature setpoint refers to the final setpoint for controlling the temperature of the drum wall of the wire dryer.

[0057] Optionally, a target temperature setpoint is determined based on a first weight, a second weight, a first temperature setpoint, and a second temperature setpoint to instruct the drying machine to perform drying operations based on the target temperature setpoint, thereby achieving outlet moisture control of the drying machine. This includes: determining a first product of the first weight and the first temperature setpoint, and determining a second product of the second weight and the second temperature setpoint; determining the sum of the first product and the second product as the target temperature setpoint, and controlling the programmable logic controller of the drying machine to determine the control value of the steam film valve based on the target temperature setpoint using a proportional-integral-derivative method, so as to adjust the cylinder wall temperature according to the control value.

[0058] Optionally, after determining the target temperature setpoint, the target temperature setpoint can be compared with the actual measured value of the current cylinder wall temperature. The control value can then be calculated based on the PID (Proportional-Integral-Derivative) algorithm within the PLC (Programmable Logic Controller) of the wire drying machine, thereby controlling the steam diaphragm valve and adjusting the cylinder wall temperature.

[0059] The technical solution of this invention, if a temperature control request for the yarn drying machine is detected, determines a first weight corresponding to a first temperature strategy based on yarn drying data from a preset historical period and a preset coefficient determination model; determines a second weight corresponding to a second temperature strategy based on the first weight and the total preset weight; and predicts the temperature of the yarn drying cylinder wall based on the first and second temperature strategies respectively to obtain a first temperature setpoint and a second temperature setpoint; and determines a target temperature setpoint based on the first weight, the second weight, the first temperature setpoint, and the second temperature setpoint to instruct the yarn drying machine to perform yarn drying operations based on the target temperature setpoint, thereby achieving outlet moisture control of the yarn drying machine. By considering multiple temperature determination strategies, an accurate and effective temperature setpoint can be determined, thereby instructing the yarn drying machine to perform precise and effective outlet moisture control.

[0060] Example 2

[0061] Figure 2 This is a flowchart of a temperature control method for a yarn drying machine provided in an embodiment of the present invention. Based on the above embodiments, this embodiment provides a preferred example of determining an accurate and effective cylinder wall temperature setpoint according to multiple temperature determination strategies and corresponding weights to instruct the yarn drying machine to perform outlet moisture control. Figure 2 As shown, the method includes:

[0062] S201. If a temperature control request for the wire drying machine is detected, at least two data collection time periods are determined based on a preset moving time window, and a corresponding data collection time period is matched for each wire drying data.

[0063] S202. Determine the target drying data from the drying data of the preset historical time period according to the collection time period, and input the target drying data into the preset coefficient determination model to obtain the first weight corresponding to the first temperature strategy.

[0064] S203. Based on the first weight and the total preset weight, the difference between the total preset weight and the first weight is determined as the second weight corresponding to the second temperature strategy.

[0065] S204. Predict the temperature of the drying cylinder wall according to the first temperature strategy and the second temperature strategy respectively, so as to obtain the first temperature setpoint and the second temperature setpoint.

[0066] S205. Determine the first product of the first weight and the first temperature setpoint, and determine the second product of the second weight and the second temperature setpoint.

[0067] S206. The sum of the first product and the second product is determined as the target temperature setpoint, and the programmable logic controller of the wire dryer is controlled to determine the control value of the steam diaphragm valve according to the target temperature setpoint by proportional-integral-derivative method.

[0068] S207. The control unit adjusts the cylinder wall temperature according to the control value to perform the drying operation, thereby controlling the outlet moisture content of the drying unit.

[0069] Example 3

[0070] Figure 3 This is a structural block diagram of a temperature control device for a yarn drying machine provided in an embodiment of the present invention. This embodiment is applicable to situations where an accurate and effective cylinder wall temperature setpoint is determined based on multiple temperature determination strategies and corresponding weights to instruct the yarn drying machine to control outlet moisture. The temperature control device for a yarn drying machine provided by the present invention can execute the temperature control method for a yarn drying machine provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method. This temperature control device for a yarn drying machine can be implemented in hardware and / or software and configured in an electronic device with a yarn drying machine temperature control function, such as... Figure 3 As shown, the temperature control device for the wire drying machine may specifically include:

[0071] The determination module 301 is used to determine the first weight corresponding to the first temperature strategy based on the drying data of the preset historical period and the determination model based on the preset coefficients if a temperature control request for the drying machine is detected.

[0072] The module 302 is used to determine the second weight corresponding to the second temperature strategy based on the first weight and the total value of the preset weight, and to predict the temperature of the drying cylinder wall according to the first temperature strategy and the second temperature strategy respectively, so as to obtain the first temperature set value and the second temperature set value.

[0073] The control module 303 is used to determine the target temperature setting value based on the first weight, the second weight, the first temperature setting value and the second temperature setting value, so as to instruct the drying machine to perform drying operation based on the target temperature setting value, thereby realizing the outlet moisture control of the drying machine.

[0074] The technical solution of this invention, if a temperature control request for the yarn drying machine is detected, determines a first weight corresponding to a first temperature strategy based on yarn drying data from a preset historical period and a preset coefficient determination model; determines a second weight corresponding to a second temperature strategy based on the first weight and the total preset weight; and predicts the temperature of the yarn drying cylinder wall based on the first and second temperature strategies respectively to obtain a first temperature setpoint and a second temperature setpoint; and determines a target temperature setpoint based on the first weight, the second weight, the first temperature setpoint, and the second temperature setpoint to instruct the yarn drying machine to perform yarn drying operations based on the target temperature setpoint, thereby achieving outlet moisture control of the yarn drying machine. By considering multiple temperature determination strategies, an accurate and effective temperature setpoint can be determined, thereby instructing the yarn drying machine to perform precise and effective outlet moisture control.

[0075] Furthermore, the determination module 301 is specifically used for:

[0076] At least two data collection periods are determined based on a preset moving time window, and a corresponding data collection period is matched for each wire drying data.

[0077] The target drying data is determined from the drying data of the preset historical period based on the collection time period, and the target drying data is input into the preset coefficient to determine the model, so as to obtain the first weight corresponding to the first temperature strategy.

[0078] Furthermore, the determination module 301 is specifically used for:

[0079] The data are, in order, the average actual value of the moisture content of the outlet material, the standard deviation of the moisture content of the outlet material, the deviation of the moisture content of the outlet material, the average actual value of the hot air temperature, the standard deviation of the actual hot air temperature, the average actual value of the incoming material moisture content, the average actual value of the incoming material temperature, the average actual value of the incoming material flow rate, and the average negative pressure value of the exhaust fan. The matching time is based on the data collection period that increases incrementally according to the preset time window.

[0080] Furthermore, the first temperature strategy is a strategy for predicting the cylinder wall temperature based on a machine learning algorithm; the second temperature strategy is a strategy for determining the cylinder wall temperature based on an advanced control strategy.

[0081] Module 302 is specifically used for:

[0082] The difference between the preset total weight and the first weight is determined as the second weight corresponding to the second temperature strategy.

[0083] Furthermore, the preset coefficient determination model is a backpropagation neural network; the preset coefficient determination model is used to determine the optimal weights corresponding to the input drying data.

[0084] The model training process, which determines the model by setting pre-defined coefficients, includes:

[0085] Based on a preset random weight generation strategy, at least two random weights are generated, and a temperature setpoint is determined based on the random weights, a first temperature strategy, and a second temperature strategy to perform the wire drying operation, thereby obtaining at least two sets of training wire drying data.

[0086] Determine the Pearson coefficient for each group of training wire drying data at different delay times to obtain the optimal delay time for the training wire drying data, and perform time-series alignment of the training wire drying data based on the optimal delay time;

[0087] Using time-aligned training data for the drying wire and corresponding random weights, an initial backpropagation neural network is fitted to obtain a model with preset coefficients.

[0088] Furthermore, the control module 303 is specifically used for:

[0089] Determine the first product of the first weight and the first temperature setpoint, and determine the second product of the second weight and the second temperature setpoint;

[0090] The sum of the first and second products is determined as the target temperature setpoint. The programmable logic controller of the wire dryer determines the control value of the steam diaphragm valve based on the target temperature setpoint using a proportional-integral-derivative method, so as to adjust the cylinder wall temperature according to the control value.

[0091] Example 4

[0092] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0093] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory 12 or a random access memory 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 12 or loaded from storage unit 18 into the random access memory 13. The random access memory 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, read-only memory 12, and random access memory 13 are interconnected via a bus 14. An input / output interface 15 is also connected to the bus 14.

[0094] Multiple components in electronic device 10 are connected to input / output 15, including: input unit 16, such as a keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as a disk, optical disk, etc.; and communication unit 19, such as a network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0095] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the temperature control method for a wire drying machine.

[0096] In some embodiments, the yarn drying machine temperature control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory 12 and / or communication unit 19. When the computer program is loaded into random access memory 13 and executed by processor 11, one or more steps of the yarn drying machine temperature control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the yarn drying machine temperature control method by any other suitable means (e.g., by means of firmware).

[0097] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), system-on-a-chip (SoCs), complex programmable logic devices (PLCs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0098] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0099] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0100] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube or liquid crystal display) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (e.g., voice input, speech input, or tactile input).

[0101] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0102] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system to address the shortcomings of traditional physical hosts and virtual reality services, such as high management difficulty and weak business scalability.

[0103] In one embodiment, the present invention further includes a computer program product, which includes a computer program that, when executed by a processor, implements the wire drying machine temperature control method of any embodiment of the present invention.

[0104] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0106] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for temperature control of a wire drying machine, characterized in that, include: If a temperature control request for the wire drying machine is detected, the first weight corresponding to the first temperature strategy is determined based on the wire drying data of a preset historical period and the model determined by preset coefficients. Based on the total value of the first weight and the preset weight, the second weight corresponding to the second temperature strategy is determined, and the temperature of the drying cylinder wall is predicted according to the first temperature strategy and the second temperature strategy respectively, so as to obtain the first temperature setpoint and the second temperature setpoint. Based on the first weight, the second weight, the first temperature setpoint, and the second temperature setpoint, a target temperature setpoint is determined to instruct the yarn drying machine to perform yarn drying operations based on the target temperature setpoint, thereby achieving outlet moisture control of the yarn drying machine.

2. The method according to claim 1, characterized in that, Based on the drying data of a preset historical period, a model is determined using preset coefficients to determine the first weight corresponding to the first temperature strategy, including: At least two data collection periods are determined based on a preset moving time window, and a corresponding data collection period is matched for each wire drying data. The target drying data is determined from the drying data of the preset historical period based on the collection time period, and the target drying data is input into the preset coefficient to determine the model, so as to obtain the first weight corresponding to the first temperature strategy.

3. The method according to claim 2, characterized in that, Each wire drying data point is matched with a corresponding data collection time period, including: The data are, in order, the average actual value of the moisture content of the outlet material, the standard deviation of the moisture content of the outlet material, the deviation of the moisture content of the outlet material, the average actual value of the hot air temperature, the standard deviation of the actual hot air temperature, the average actual value of the incoming material moisture content, the average actual value of the incoming material temperature, the average actual value of the incoming material flow rate, and the average negative pressure value of the exhaust fan. The matching time is based on the data collection period that increases incrementally according to the preset time window.

4. The method according to claim 1, characterized in that, in, The first temperature strategy is a strategy based on machine learning algorithms to predict the cylinder wall temperature; the second temperature strategy is a strategy based on advanced control strategies to determine the cylinder wall temperature. Accordingly, based on the first weight and the total preset weight, the second weight corresponding to the second temperature strategy is determined, including: The difference between the preset total weight and the first weight is determined as the second weight corresponding to the second temperature strategy.

5. The method according to claim 1, characterized in that, in, The preset coefficients determine that the model is a backpropagation neural network; The preset coefficient determination model is used to determine the optimal weights corresponding to the input wire drying data; Accordingly, the model training process, which determines the model by presetting coefficients, includes: Based on a preset random weight generation strategy, at least two random weights are generated, and a temperature setpoint is determined based on the random weights, a first temperature strategy, and a second temperature strategy to perform the wire drying operation, thereby obtaining at least two sets of training wire drying data. Determine the Pearson coefficient for each group of training wire drying data at different delay times to obtain the optimal delay time for the training wire drying data, and perform time-series alignment of the training wire drying data based on the optimal delay time; Using time-aligned training data for the drying wire and corresponding random weights, an initial backpropagation neural network is fitted to obtain a model with preset coefficients.

6. The method according to claim 1, characterized in that, Based on the first weight, the second weight, the first temperature setpoint, and the second temperature setpoint, a target temperature setpoint is determined to instruct the yarn drying machine to perform yarn drying operations based on the target temperature setpoint, thereby achieving outlet moisture control of the yarn drying machine, including: Determine the first product of the first weight and the first temperature setpoint, and determine the second product of the second weight and the second temperature setpoint; The sum of the first and second products is determined as the target temperature setpoint. The programmable logic controller of the wire dryer determines the control value of the steam diaphragm valve based on the target temperature setpoint using a proportional-integral-derivative method, so as to adjust the cylinder wall temperature according to the control value.

7. A temperature control device for a wire drying machine, characterized in that, include: The determination module is used to determine the first weight corresponding to the first temperature strategy based on the drying data of a preset historical period and the determination model based on preset coefficients if a temperature control request for the drying machine is detected. The module is used to determine the second weight corresponding to the second temperature strategy based on the first weight and the total value of the preset weight, and to predict the temperature of the drying cylinder wall according to the first temperature strategy and the second temperature strategy respectively, so as to obtain the first temperature setpoint and the second temperature setpoint. The control module is used to determine the target temperature setting value based on the first weight, the second weight, the first temperature setting value, and the second temperature setting value, so as to instruct the drying machine to perform drying operation based on the target temperature setting value, thereby realizing the outlet moisture control of the drying machine.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that is executed by the at least one processor to enable the at least one processor to perform the temperature control method for the wire drying machine according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the temperature control method for the wire drying machine as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the temperature control method for the wire drying machine as described in any one of claims 1-6.

Images