A method and device for controlling the outlet moisture temperature of a silk thread thin plate drying machine

Abstract

The present application belongs to the technical field of silk thread production, and discloses a method and device for controlling the outlet moisture temperature of a thin plate silk thread drying machine for silk thread. The method and device obtain first silk thread drying data and first steam environment data at a specified time, and obtain first moisture temperature data based on the first silk thread drying data, the first steam environment data and a preset machine learning model, so as to use an intelligent algorithm to predict the outlet moisture temperature data at the specified time; then, when the difference between the first moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold, the first moisture temperature data is optimized to obtain second silk thread drying data, and the outlet moisture temperature is automatically controlled according to the second silk thread drying data, so as to ensure the stability of the silk thread drying process by adjusting key variable data, which can not only make the outlet moisture temperature of the silk thread drying machine for silk thread meet normal requirements, but also improve the consistency of product quality and production efficiency.

Description

Technical Field

[0001] The present application belongs to the technical field of silk thread production, and in particular relates to a method and device for controlling the outlet moisture temperature of a silk thread thin plate drying machine. Background Art

[0002] In tobacco shredded tobacco workshops, the sheet dryer is a crucial piece of equipment in the tobacco processing process. Its outlet moisture and temperature are key process indicators that influence tobacco quality. As the tobacco industry's requirements for product quality continue to increase, effectively controlling the outlet moisture and temperature of the dryer has become a long-term research topic in the industry.

[0003] In the traditional tobacco drying machine control method, the one-stage thin-plate tobacco drying machine for tobacco drying has a relatively simple structure and only involves a single steam heating area. The temperature regulation of the tobacco during the drying process is relatively direct, and the operator only needs to adjust a single internal energy to achieve stable control of the outlet temperature. For the two-stage thin-plate tobacco drying machine for tobacco drying, since the thin-plate tobacco drying machine is equipped with two independent steam cylinder wall heating areas, the tobacco needs to go through two heating stages, which significantly increases the complexity of temperature control.

[0004] In the actual production process, the two-stage thin-plate tobacco drying machine has better temperature uniformity than the one-stage thin-plate tobacco drying machine, and can effectively reduce the impact of fluctuations. However, since there are many variables affecting the outlet moisture and temperature, and there is a significant coupling effect between different variables, the traditional moisture and temperature control method of the two-stage thin-plate tobacco drying machine is difficult to cope with complex control requirements, which not only affects the control stability of the moisture and temperature of the tobacco, but also easily reduces the consistency of product quality and production efficiency. Summary of the Invention

[0005] This application aims to address the technical drawbacks of the traditional moisture and temperature control method of the two-stage thin-plate tobacco drying machine mentioned above, which is difficult to cope with complex control requirements. This method not only affects the control stability of the moisture and temperature of tobacco, but also easily reduces the consistency of product quality and production efficiency. A method and device for controlling the outlet moisture and temperature of a thin-plate tobacco drying machine for making tobacco is proposed. The technical solution is as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for controlling the outlet moisture temperature of a silk thread thin plate drying machine, comprising:

[0007] Obtaining first wire drying data and first steam environment data of a wire-making thin plate drying machine at a specified time, and obtaining first moisture temperature data based on the first wire drying data, the first steam environment data, and a preset machine learning model;

[0008] When the difference between the first moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold, the first moisture temperature data is optimized to obtain second tow-baked data;

[0009] The outlet moisture temperature of the silk line thin plate silk drying machine is controlled and processed according to the second silk drying data.

[0010] In an optional solution of the first aspect, obtaining the first moisture temperature data according to the first tow-baked food data, the first steam environment data, and a preset machine learning model includes:

[0011] Determine a historical moment based on a preset sliding period and a designated moment, and obtain historical silk drying data and historical steam environment data of a silk-making wire sheet drying machine from the historical moment to the designated moment;

[0012] Calculating third strand drying data based on the first strand drying data and historical strand drying data;

[0013] Calculating second steam environment data based on the first steam environment data and historical steam environment data;

[0014] The third tow drying data and the second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data.

[0015] In another optional solution of the first aspect, the second steam environment data includes at least one steam data and at least one environment data;

[0016] Before inputting the third tow-baked strands data and the second steam environment data into a preset machine learning model to obtain the first moisture temperature data, the method further includes:

[0017] Dividing the historical steam data corresponding to each type of steam data from the historical steam environment data, and dividing the historical environment data corresponding to each type of environment data;

[0018] Perform correlation analysis on the historical steam data corresponding to any two steam data to obtain the corresponding steam correlation results;

[0019] Perform correlation analysis on the historical environmental data corresponding to any two environmental data to obtain the corresponding environmental correlation results;

[0020] Obtaining a steam environment data set according to all steam correlation results and all environment correlation results, and screening the second steam environment data based on the steam environment data set;

[0021] The third tow-baked data and the second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data, including:

[0022] The third tow-baked data and the processed second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data.

[0023] In another optional solution of the first aspect, obtaining a steam environment data set according to all steam correlation results and all environment correlation results includes:

[0024] When it is detected that at least one steam correlation result among all steam correlation results is in a preset correlation interval, the total number of steam correlation results in the preset correlation interval is counted;

[0025] When the total number of steam correlation results exceeds a preset number threshold, determining the steam data type corresponding to at least one steam correlation result in a preset correlation interval;

[0026] When it is detected that at least one environment correlation result among all the environment correlation results is in a preset correlation interval, the total number of environment correlation results in the preset correlation interval is counted;

[0027] When the total number of environmental correlation results exceeds a preset number threshold, at least one environmental correlation result in a preset correlation interval and the corresponding environmental data type are determined, and all steam data types and all environmental data types are taken as a steam environment data set.

[0028] In another optional solution of the first aspect, optimizing the first moisture temperature data to obtain the second tow-baked data includes:

[0029] Processing the first moisture and temperature data based on a preset multi-objective optimization algorithm to obtain at least two sets of candidate tow-baked data;

[0030] Based on the preset hierarchical analysis algorithm, each group of candidate dried tofu data is weighted and processed to obtain the corresponding weight results;

[0031] All candidate tow-bread drying data and all weight results are processed based on a preset ideal solution sorting algorithm, and the second tow-bread drying data is determined from all candidate tow-bread drying data according to the processing results.

[0032] In yet another alternative of the first aspect, the method further comprises:

[0033] Obtaining second moisture temperature data based on the second tow-baked data, the first steam environment data, and a preset machine learning model;

[0034] When the difference between the second moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold, the second moisture temperature data is optimized to obtain fourth tow-baked data;

[0035] The outlet moisture temperature of the silk line thin plate silk drying machine is controlled according to the fourth silk drying data.

[0036] In another optional solution of the first aspect, the first tobacco drying data includes hot air velocity and dehumidification damper opening, and the first steam environment data includes at least one inlet tobacco data, at least one environment data, at least one steam data and preset water removal flow data.

[0037] In a second aspect, an embodiment of the present application provides an outlet moisture temperature control device for a silk thread thin plate drying machine, comprising:

[0038] a first processing module for acquiring first wire drying data and first steam environment data of the wire-making thin plate drying machine at a specified time, and obtaining first moisture temperature data based on the first wire drying data, the first steam environment data, and a preset machine learning model;

[0039] a second processing module, configured to optimize the first moisture temperature data to obtain second tow-baked data when the difference between the first moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold;

[0040] The third processing module is used to control the outlet moisture temperature of the silk line thin plate silk drying machine according to the second silk drying data.

[0041] In a third aspect, an embodiment of the present application further provides an outlet moisture temperature control device for a silk thread thin plate drying machine, comprising a processor and a memory;

[0042] The processor is connected to the memory;

[0043] a memory for storing executable program code;

[0044] The processor runs the program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the outlet moisture temperature control method of the silk wire thin plate drying machine provided by the first aspect of the embodiment of the present application or any one of the implementation methods of the first aspect.

[0045] In fourth aspect, an embodiment of the present application provides a computer storage medium, which stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, the outlet moisture temperature control method of the silk wire thin plate drying machine provided by the first aspect of the embodiment of the present application or any one of the implementation methods of the first aspect can be implemented.

[0046] Beneficial effects of this application:

[0047] When controlling the outlet moisture temperature of a two-stage thin-plate wire drying machine, the first wire drying data (including key variable data affecting the outlet moisture temperature) and the first steam environment data of the thin-plate wire drying machine of the silk-making line at a specified time are obtained, and the first moisture temperature data is obtained based on the first wire drying data, the first steam environment data and a preset machine learning model, so as to accurately predict the outlet moisture temperature data of the thin-plate wire drying machine of the silk-making line at the specified time using an intelligent learning algorithm; then, when the difference between the first moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold, the first moisture temperature data is optimized to obtain the second wire drying data, and the outlet moisture temperature of the thin-plate wire drying machine of the silk-making line is automatically controlled according to the second wire drying data, so as to ensure the stability of the wire drying process by adjusting the key variable data, so as to not only make the outlet moisture temperature of the thin-plate wire drying machine of the silk-making line meet normal requirements, but also improve the consistency of product quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 This is an overall flow chart of a method for controlling the outlet moisture temperature of a silk thread thin plate drying machine provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of the structure of an outlet moisture temperature control device of a silk thread thin plate drying machine provided in an embodiment of the present application;

[0051] Figure 3 A schematic structural diagram of an outlet moisture temperature control device for another silk thread thin plate drying machine provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0053] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application. Different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments described. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, even though the embodiment may not be clearly described in the following text.

[0054] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the elements described without departing from the scope of the present application. Various examples may appropriately omit, replace, or add various processes or components. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted, or combined. In addition, features described in some examples may be combined in other examples.

[0055] It's important to emphasize that most current single-stage thin-plate dryers struggle to balance the specific temperature and moisture requirements of different drying stages, making precise control of outlet moisture and temperature difficult. This is especially true when initial moisture distribution varies across batches, leading to fluctuating outlet moisture and unstable product quality. Furthermore, due to differences in tobacco morphology (such as thickness and fiber distribution), moisture migration and evaporation rates vary during the drying process. Single-stage thin-plate dryers lack the fine-grained control capabilities to achieve uneven moisture distribution, leaving some tobacco over-dried while others remain damp. Furthermore, single-stage thin-plate dryers typically utilize high hot air temperatures and velocities. This high-intensity drying method can easily lead to "surface hardening," a phenomenon in which surface moisture evaporates rapidly while internal moisture fails to migrate quickly, compromising drying uniformity. This can also damage the fiber structure and cause the loss of aroma components, impacting the flavor and smoking quality of the tobacco. In summary, the current one-stage thin-plate tobacco drying machine is difficult to correct quickly by relying solely on simple hot air adjustments, has poor adjustment flexibility, and is prone to causing large fluctuations in batch tobacco quality.

[0056] To address the shortcomings of the aforementioned one-stage thin-plate tobacco drying machine, a two-stage thin-plate tobacco drying machine currently exists. This method significantly improves drying efficiency and quality by dividing the drying process into an initial drying stage and a stable drying stage. In the initial drying stage, high-temperature hot air is used to rapidly evaporate the surface moisture of the tobacco, shortening the drying time and reducing the load in subsequent stages. In the stable drying stage, the hot air temperature and wind speed are lowered, and the moisture migration rate is carefully adjusted to ensure sufficient internal moisture migration and uniform evaporation, effectively improving the problem of uneven moisture distribution. However, the design of the two-stage thin-plate tobacco drying machine, due to its use of a two-wall structure, increases the complexity and difficulty of the adjustment process to a certain extent. For example, the heat exchange and mutual influence between the two walls mean that adjusting the temperature of one wall may also affect the temperature of the other wall. This mutually coupled relationship complicates temperature control, requiring operators to simultaneously monitor the temperature changes of both walls, which increases the difficulty of control. In addition, operators may cause overshoot due to inaccurate judgment of temperature changes. For example, when the temperature of one barrel wall needs to rise, excessive adjustment may cause the temperature to rise rapidly, exceeding the preset range, thereby affecting the drying effect of the tobacco and even damaging the equipment. Secondly, because the temperature changes of the two barrel walls take a certain amount of time to be detected and fed back to the control system, this feedback delay may cause a lag in real-time control, increasing the difficulty of adjustment. In actual production environments, the traditional moisture and temperature control method of two-stage thin plate drying machines requires the use of complex control strategies and algorithms to comprehensively consider multiple factors, increasing the design and control requirements of the overall control method. Secondly, it must be adjusted by operators with high professional knowledge and experience, which is prone to human judgment errors during peak production periods, thus affecting the stable control of tobacco moisture and temperature, and also easily reducing product quality consistency and production efficiency.

[0057] Based on this, this application will explain the outlet moisture temperature control method of the silk thread thin plate drying machine in combination with one or more embodiments shown below to solve the technical defects of the above-mentioned two-stage thin plate drying machine.

[0058] See next Figure 1 , Figure 1 The overall flow chart of the outlet moisture temperature control method of a silk thread thin plate drying machine provided in an embodiment of the present application is shown.

[0059] like Figure 1 As shown, the outlet moisture temperature control method of the silk thread thin plate drying machine may include at least the following steps:

[0060] Step 102: Obtain first wire drying data and first steam environment data of the wire thin plate drying machine at a specified time, and obtain first moisture temperature data based on the first wire drying data, the first steam environment data and a preset machine learning model.

[0061] In an embodiment of the present application, the outlet moisture temperature control method of the silk line thin plate silk drying machine can be but is not limited to being applied to a control terminal, which can be connected to a two-stage thin plate silk drying machine to obtain data collected by the two-stage thin plate silk drying machine during operation, and automatically control the outlet moisture temperature of the two-stage thin plate silk drying machine based on the data, so as to effectively optimize the drying effect of the two-stage thin plate silk drying machine on tobacco, thereby ensuring that the production quality meets the standards.

[0062] Here, the data collected by the two-stage thin-plate tobacco drying machine during operation may include but is not limited to the inlet tobacco humidity, inlet tobacco flow, workshop ambient temperature, workshop ambient humidity, HT inlet tobacco flow (HT can be understood as a tunnel-type rehumidification machine), HT steam pressure, HT outlet temperature, hot air temperature, hot air speed, dehumidification damper opening, area 1 steam mass flow (i.e., the steam mass flow in the first cylinder wall structure), area 1 cylinder temperature (i.e., the temperature in the first cylinder wall structure), area 2 steam mass flow (i.e., the steam mass flow in the second cylinder wall structure) and area 2 cylinder temperature (i.e., the temperature in the second cylinder wall structure), etc. Each type of data can be collected by sensors or control devices set at corresponding positions and fed back to the control terminal in real time.

[0063] It can be understood that the control terminal can obtain the first wire drying data (including key variable data affecting the outlet moisture temperature) and the first steam environment data of the silk wire thin plate wire drying machine at a specified time, and obtain the first moisture temperature data based on the first wire drying data, the first steam environment data and the preset machine learning model, so as to use the intelligent learning algorithm to accurately predict the outlet moisture temperature data of the silk wire thin plate wire drying machine at the specified time; then, when the difference between the first moisture temperature data and the standard moisture temperature data exceeds the preset difference threshold, the first moisture temperature data is optimized to obtain the second wire drying data, and the outlet moisture temperature of the silk wire thin plate wire drying machine is automatically controlled according to the second wire drying data, so as to ensure the stability of the wire drying process by adjusting the key variable data, so as to not only make the outlet moisture temperature of the silk wire thin plate wire drying machine meet normal requirements, but also improve the consistency of product quality and production efficiency.

[0064] Specifically, when controlling the outlet moisture temperature of a two-stage thin-plate wire drying machine, the control terminal can, but is not limited to, combine the historical data of the two-stage thin-plate wire drying machine and the corresponding outlet moisture temperature data to analyze multiple types of data with the strongest correlation with the outlet moisture temperature, and use these multiple types of data as key variable data affecting the outlet moisture temperature, so that when the outlet moisture temperature is subsequently controlled, the key variable data affecting the outlet moisture temperature is adjusted, and other variable data are kept unchanged (that is, no adjustment is performed), which not only effectively reduces external interference, but also ensures the stability of the wire drying process. Here, the key variable data affecting the outlet moisture temperature may be, but are not limited to, the hot air velocity and dehumidification damper opening collected during the operation of the two-stage thin-plate wire drying machine, that is, by adjusting the hot air velocity and dehumidification damper opening of the two-stage thin-plate wire drying machine, the outlet moisture temperature can be effectively controlled; other variable data can be understood as various types of data associated with the outlet moisture temperature, which may be, but are not limited to, the inlet tobacco humidity, inlet tobacco flow, workshop ambient temperature, workshop ambient humidity, HT inlet tobacco flow, HT steam pressure, HT outlet temperature, hot air temperature, steam mass flow of area 1, drum temperature of area 1, steam mass flow of area 2, and drum temperature of area 2 collected during the operation of the two-stage thin-plate wire drying machine, and are not limited to these.

[0065] It can be understood that when analyzing the multiple types of data with the strongest correlation with the outlet moisture temperature, the control terminal can, but is not limited to, perform a correlation analysis on each type of data in the historical data and the corresponding outlet temperature data, so as to use the type of data with the highest correlation result as the key variable data affecting the outlet temperature; and can also perform a correlation analysis on each type of data in the historical data and the corresponding outlet moisture data, so as to use the type of data with the highest correlation result as the key variable data affecting the outlet moisture, and use the key variable data affecting the outlet temperature and the key variable data affecting the outlet moisture as the multiple types of data with the strongest correlation with the outlet moisture temperature, and is not limited to this.

[0066] It should be noted that other variable data can also be determined through the correlation results mentioned above, for example but not limited to taking all types of data corresponding to all correlation results in a preset interval as other variable data, so as to effectively avoid the other variable data containing one or more types of data that have no correlation with the outlet water temperature, and is not limited to this.

[0067] Furthermore, after determining the key variable data and other variable data that affect the outlet moisture temperature, the control terminal can monitor the working status of the two-stage thin plate wire drying machine in real time, so as to obtain the first wire drying data and the first steam environment data of the two-stage thin plate wire drying machine at a specified time after the two-stage thin plate wire drying machine is in operation. Here, the specified time can be but is not limited to the current time or any next time. The first tobacco drying data can be understood as all types of data at the specified time included in the key variable data affecting the outlet moisture temperature mentioned above, such as the hot air speed and the dehumidification damper opening at the specified time; the first steam environment data can be understood as all types of data at the specified time included in the other variable data mentioned above, which can specifically include at least one inlet tobacco data, at least one environmental data, at least one steam data and preset water removal flow data at the specified time. The at least one inlet tobacco data can be but is not limited to including at least one of the inlet tobacco humidity, the inlet tobacco flow and the HT inlet tobacco flow. The at least one environmental data can be but is not limited to including at least one of the workshop ambient temperature and the workshop ambient humidity. The at least one steam data can be but is not limited to including at least one of the HT steam pressure, HT outlet temperature, hot air temperature, steam mass flow rate in area 1, barrel temperature in area 1, steam mass flow rate in area 2 and barrel temperature in area 2.

[0068] Furthermore, after determining the first wire drying data and the first steam environment data, the control terminal can, but is not limited to, pre-processing the first wire drying data and the first steam environment data respectively, such as performing outlier cleaning processing and normalization processing in sequence, and inputting the processed first wire drying data and the first steam environment data into a preset machine learning model to predict the outlet moisture temperature data of the two-stage thin plate wire drying machine at a specified time through an intelligent learning algorithm, that is, the first moisture temperature data.

[0069] It can be understood that the preset machine learning model can be but is not limited to a neural network structure well known in the art, which is trained by at least two sets of historical data of the two-stage thin plate wire drying machine, the outlet moisture temperature data corresponding to each set of historical data, and the moisture temperature standard data, and the at least two sets of historical data of the two-stage thin plate wire drying machine can also be updated and processed according to preset time intervals, that is, the preset machine learning model can be updated in real time to ensure the accuracy and effectiveness of the output results of the preset machine learning model.

[0070] As an option in the embodiment of the present application, first moisture temperature data is obtained according to the first tow-baked food data, the first steam environment data, and a preset machine learning model, including:

[0071] Determine a historical moment based on a preset sliding period and a designated moment, and obtain historical silk drying data and historical steam environment data of a silk-making wire sheet drying machine from the historical moment to the designated moment;

[0072] Calculating third strand drying data based on the first strand drying data and historical strand drying data;

[0073] Calculating second steam environment data based on the first steam environment data and historical steam environment data;

[0074] The third tow drying data and the second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data.

[0075] Specifically, to ensure temporal consistency of the tow-steel drying data and steam environment data, thereby avoiding lags in real-time control and improving the accuracy of subsequent data processing, the control terminal can also determine a historical moment based on a preset sliding period and a designated moment. For example, but not limited to, taking the designated moment as A hour and B minute and the preset sliding period as C minutes, the difference between the designated moment and the preset sliding period, A hours (BC) minutes, can be used as the historical moment. The control terminal can also obtain historical tow-steel drying data and historical steam environment data collected from the historical moment to the designated moment while the two-stage thin-plate tow-steel drying machine was in operation. Here, historical tow-steel drying data can be understood as all types of data from the historical moment to the designated moment, including the key variable data affecting the outlet water temperature mentioned above. Historical steam environment data can be understood as all types of data from the historical moment to the designated moment, including the other variable data mentioned above. The historical tow-steel drying data can include tow-steel drying data corresponding to at least two moments between the historical moment and the designated moment, and the historical steam environment data can include steam environment data corresponding to at least two moments between the historical moment and the designated moment.

[0076] Next, the control terminal may substitute each type of data in the first tow-roasted data and all data of the corresponding type in the historical tow-roasted data into a preset sliding average formula for calculation, and use the calculation results of all types as the third tow-roasted data. Here, the preset sliding average formula may be, but is not limited to, the following:

[0077]

[0078] In the above formula, It can be the calculation result of any type of data in the first tow-baked data at time t (that is, the specified time), and n can be a preset sliding period. It can be the data of the corresponding type in the historical wire-baking data at time ti (i can be any value from 0 to n, when i=0, it can be understood as the data of the corresponding type in the first wire-baking data, when i=n-1, it can be understood as the data of the corresponding type in the historical wire-baking data corresponding to the historical moment).

[0079] It is understandable that the control terminal can also substitute each type of data in the first steam environment data and all data of the corresponding type in the historical steam environment data into the above-mentioned preset sliding average formula, and use the calculation results of all types as the second steam environment data.

[0080] Then, after determining the third wire drying data and the second steam environment data, the control terminal can, but is not limited to, pre-process the third wire drying data and the second steam environment data respectively, such as performing outlier cleaning and normalization processing in sequence, and inputting the processed third wire drying data and the second steam environment data into a preset machine learning model to predict the outlet moisture temperature data of the two-stage thin plate wire drying machine at a specified time through an intelligent learning algorithm, that is, the first moisture temperature data.

[0081] As another option of the embodiment of the present application, the second steam environment data includes at least one steam data and at least one environment data;

[0082] Before inputting the third tow-baked strands data and the second steam environment data into a preset machine learning model to obtain the first moisture temperature data, the method further includes:

[0083] Dividing the historical steam data corresponding to each type of steam data from the historical steam environment data, and dividing the historical environment data corresponding to each type of environment data;

[0084] Perform correlation analysis on the historical steam data corresponding to any two steam data to obtain the corresponding steam correlation results;

[0085] Perform correlation analysis on the historical environmental data corresponding to any two environmental data to obtain the corresponding environmental correlation results;

[0086] Obtaining a steam environment data set according to all steam correlation results and all environment correlation results, and screening the second steam environment data based on the steam environment data set;

[0087] The third tow-baked data and the second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data, including:

[0088] The third tow-baked data and the processed second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data.

[0089] Specifically, in order to further improve the prediction accuracy and efficiency of the preset machine learning model, the control terminal can also divide all the historical steam data corresponding to each type of steam data from the historical steam environment data mentioned above, and can perform correlation analysis on all the historical steam data corresponding to any two types of steam data, for example but not limited to standardizing all the historical steam data corresponding to any two types of steam data, and substituting all the historical steam data corresponding to the two types of steam data after processing into the preset Pearson correlation coefficient calculation formula to obtain the steam correlation results corresponding to the two types of steam data. Here, the range of the steam correlation result can be, but is not limited to, between -1 and 1. The closer the steam correlation result is to 1 or -1, the stronger the correlation between the two types of steam data; the closer the steam correlation result is to 0, the weaker the correlation between the two types of steam data.

[0090] It can be understood that the control terminal can also divide all historical environmental data corresponding to each type of environmental data from the historical steam environmental data mentioned above, and can perform correlation analysis on all historical environmental data corresponding to any two types of environmental data, for example but not limited to standardizing all historical environmental data corresponding to any two types of environmental data, and substituting all historical environmental data corresponding to the two types of processed environmental data into the preset Pearson correlation coefficient calculation formula to obtain the environmental correlation results corresponding to the two types of environmental data.

[0091] Then, after obtaining all steam correlation results and all environment correlation results, the control terminal can also determine a steam environment data set, which includes at least one steam data type corresponding to a higher steam correlation result and at least one environment data type corresponding to a higher environment correlation result, and can screen and process the second steam environment data based on the steam environment set to eliminate all steam data corresponding to all steam data types in the steam environment set, and eliminate all environment data corresponding to all environment data types in the steam environment set, thereby achieving the purpose of reducing the data volume of the second steam environment data.

[0092] Then, after screening and processing the second steam environment data, the control terminal can also pre-process the third wire drying data and the processed second steam environment data, such as performing outlier cleaning and normalization processing in sequence, and input the processed third wire drying data and the second steam environment data into the preset machine learning model to predict the outlet moisture temperature data of the two-stage thin plate wire drying machine at a specified time through the intelligent learning algorithm, that is, the first moisture temperature data.

[0093] As another option of the embodiment of the present application, a steam environment data set is obtained according to all steam correlation results and all environment correlation results, including:

[0094] When it is detected that at least one steam correlation result among all steam correlation results is in a preset correlation interval, the total number of steam correlation results in the preset correlation interval is counted;

[0095] When the total number of steam correlation results exceeds a preset number threshold, determining the steam data type corresponding to at least one steam correlation result in a preset correlation interval;

[0096] When it is detected that at least one environment correlation result among all the environment correlation results is in a preset correlation interval, the total number of environment correlation results in the preset correlation interval is counted;

[0097] When the total number of environmental correlation results exceeds a preset number threshold, at least one environmental correlation result in a preset correlation interval and the corresponding environmental data type are determined, and all steam data types and all environmental data types are taken as a steam environment data set.

[0098] Specifically, when determining the steam environment data set, the control terminal can also determine whether there is at least one steam correlation result among all steam correlation results that exceeds a preset correlation interval, so as to determine whether there are two types of data with high correlation in the steam environment data, and when it is detected that there is a steam correlation result that exceeds the preset correlation interval, the total number of steam correlation results in the preset correlation interval is counted. It can be understood that when the total number of steam correlation results exceeds the preset number threshold, it indicates that there are at least two types of data with high correlation in the steam environment data, and the two steam data corresponding to each steam correlation result in the preset correlation interval can be screened out, so as to calculate the proportion of the number of screening times of each steam data in all the screened steam data, and the steam data type with the highest proportion of screening times is used as the steam data type corresponding to at least one steam correlation result in the preset correlation interval. Of course, in the embodiment of the present application, multiple steam data types with high proportion of screening times can also be used as the steam data type corresponding to at least one steam correlation result in the preset correlation interval, and are not limited to this.

[0099] In addition, the control terminal can also determine at least one environmental correlation result in a preset correlation interval. The corresponding environmental data type and its processing method can refer to the above description, but will not be elaborated here. All steam data types and all environmental data types can be regarded as steam environment data sets.

[0100] It should be noted that if any steam data type and any environmental data type are not determined, it may indicate that there are no at least two steam data with high correlation and no at least two environmental data with high correlation in the steam environment data, and thus there is no need to screen the second steam environment data.

[0101] Step 104: When the difference between the first moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold, the first moisture temperature data is optimized to obtain second tow-baked data.

[0102] Specifically, after predicting the first moisture temperature data, the control terminal can, but is not limited to, perform a difference calculation between the first moisture temperature data and the standard moisture temperature data. For example, a difference calculation can be performed between the temperature data in the first moisture temperature data and the standard temperature data, and a difference calculation can be performed between the moisture data in the first moisture temperature data and the standard moisture data. When it is detected that any difference result exceeds a preset difference threshold, it indicates that there is an abnormality in the current outlet moisture temperature of the two-stage thin plate wire drying machine. Then, the first moisture temperature data can be processed based on a preset multi-objective optimization algorithm to obtain at least two sets of alternative wire drying data (which can also be understood as the optimal solution Pareto solution set, and each set of alternative wire drying data may include alternative hot air speed and alternative moisture exhaust door opening). Here, the preset multi-objective optimization algorithm may include but is not limited to parameters such as a preset evolutionary algorithm, multiple preset objective functions, constraints, and the number of iterations. Each preset objective function can be understood as a function expression containing a moisture-temperature data type and a torrefied data type (not limited to this), and the constraints can be understood as the data interval corresponding to the moisture-temperature data type and the data interval corresponding to the torrefied data type. The preset multi-objective optimization algorithm can also refer to technical means well known in the art, but will not be elaborated here.

[0103] Furthermore, after obtaining multiple sets of candidate to-beef roasting data, the control terminal can also perform weighting on each set of candidate to-beef roasting data based on a preset hierarchical analysis algorithm to obtain corresponding weighted results. Here, the preset hierarchical analysis algorithm can construct a judgment matrix corresponding to each set of candidate to-beef roasting data, calculate eigenvalues ​​and eigenvectors for each judgment matrix, and obtain corresponding weighted results. The preset hierarchical analysis algorithm can also refer to well-known technical means in the art and will not be described in detail here.

[0104] Furthermore, after obtaining the weighted results for each set of candidate wire-roasted data, the control terminal may further process all candidate wire-roasted data and all weighted results based on a preset ideal solution sorting algorithm to obtain a sorted result for all candidate wire-roasted data, and select the optimal candidate wire-roasted data from the sorted results as the second wire-roasted data. Here, the preset ideal solution sorting algorithm may, but is not limited to, construct a decision matrix based on each set of candidate wire-roasted data, then normalize each decision matrix, and then multiply each processed decision matrix by the corresponding weighted results to determine an ideal solution and a negative ideal solution from each product. The distance between each set of candidate wire-roasted data and the ideal solution and the negative ideal solution may be calculated, respectively, to determine a relative proximity based on the two distances. All candidate wire-roasted data may then be sorted in descending order of relative proximity. The candidate wire-roasted data ranked highest may be selected as the second wire-roasted data. The preset ideal solution sorting algorithm may also refer to well-known technical means in the art and will not be described in detail here.

[0105] It should be noted that the optimized second-stage tofu drying data can effectively balance the unstable factors of the two-stage model, avoid frequent overshoot, and further make the two-stage model suitable for formal production environments. Ultimately, it ensures the stability and efficiency of the tofu drying production process and provides a reliable guarantee for improving production quality and efficiency.

[0106] Step 106: Control the outlet moisture temperature of the silk thread thin plate drying machine according to the second silk drying data.

[0107] Specifically, after obtaining the second wire drying data, the control terminal can, but is not limited to, adjust the two-stage thin-plate wire drying machine according to the second wire drying data. For example, taking the second wire drying data including the target hot air speed and the target dehumidification damper opening as an example, the hot air equipment of the two-stage thin-plate wire drying machine can be adjusted to adjust the current hot air speed to be consistent with the target hot air speed, thereby achieving control of the outlet moisture; at the same time, the dehumidification pipe solenoid valve of the two-stage thin-plate wire drying machine can also be adjusted to adjust the current dehumidification damper opening to be consistent with the target dehumidification damper opening, thereby achieving control of the outlet temperature.

[0108] As another option of the embodiment of the present application, the method further includes:

[0109] Obtaining second moisture temperature data based on the second tow-baked data, the first steam environment data, and a preset machine learning model;

[0110] When the difference between the second moisture temperature data and the standard moisture temperature data exceeds the preset difference threshold, optimizing the second moisture temperature data to obtain fourth tow-baked data;

[0111] The outlet moisture temperature of the silk line thin plate silk drying machine is controlled and processed according to the fourth silk drying data.

[0112] Specifically, in order to ensure the continuous stability of the outlet moisture temperature, after the control terminal controls and processes the outlet moisture temperature of the silk line thin plate silk drying machine according to the second silk drying data, it can also, but is not limited to, pre-process the second silk drying data and the first steam environment data separately, such as performing outlier cleaning and normalization processing in sequence, and inputting the processed second silk drying data and the first steam environment data into the preset machine learning model, so as to predict the outlet moisture temperature data of the two-stage thin plate silk drying machine after control processing, that is, the second moisture temperature data, through the intelligent learning algorithm.

[0113] It can be understood that when the difference between the second moisture temperature data and the standard moisture temperature data does not exceed the preset difference threshold, the real-time wire drying data of the two-stage thin-plate wire drying machine can be kept consistent with the second wire drying data to ensure the continuous stability of the outlet moisture temperature; when the difference exceeds the preset difference threshold, it indicates that the two-stage thin-plate wire drying machine still has abnormal outlet moisture temperature after control processing, and then refer to one or more of the above-mentioned embodiments to optimize the second moisture temperature data to obtain the fourth wire drying data, and control the outlet moisture temperature of the wire thin-plate wire drying machine again according to the fourth wire drying data, but no further details will be given here until the outlet moisture temperature of the two-stage thin-plate wire drying machine is within the normal range after control processing.

[0114] See next Figure 2 , Figure 2 A schematic structural diagram of an outlet moisture temperature control device of a silk thread thin plate drying machine provided in an embodiment of the present application is shown.

[0115] like Figure 2 As shown, the outlet moisture temperature control device of the silk thread thin plate drying machine may include at least a first processing module 201, a second processing module 202 and a third processing module 203, wherein:

[0116] The first processing module 201 is used to obtain first wire drying data and first steam environment data of the wire-making thin plate drying machine at a specified time, and obtain first moisture temperature data based on the first wire drying data, the first steam environment data, and a preset machine learning model;

[0117] The second processing module 202 is configured to optimize the first moisture temperature data to obtain second tow-baked data when the difference between the first moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold;

[0118] The third processing module 203 is used to control the outlet moisture temperature of the silk thread thin plate drying machine according to the second silk drying data.

[0119] In some possible embodiments, obtaining the first moisture temperature data according to the first tow-baked food data, the first steam environment data, and a preset machine learning model includes:

[0120] Determine a historical moment based on a preset sliding period and a designated moment, and obtain historical silk drying data and historical steam environment data of a silk-making wire sheet drying machine from the historical moment to the designated moment;

[0121] Calculating third strand drying data based on the first strand drying data and historical strand drying data;

[0122] Calculating second steam environment data based on the first steam environment data and historical steam environment data;

[0123] The third tow drying data and the second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data.

[0124] In some possible embodiments, the second steam environment data includes at least one steam data and at least one environment data;

[0125] Before inputting the third tow-baked strands data and the second steam environment data into a preset machine learning model to obtain the first moisture temperature data, the method further includes:

[0126] Dividing the historical steam data corresponding to each type of steam data from the historical steam environment data, and dividing the historical environment data corresponding to each type of environment data;

[0127] Perform correlation analysis on the historical steam data corresponding to any two steam data to obtain the corresponding steam correlation results;

[0128] Perform correlation analysis on the historical environmental data corresponding to any two environmental data to obtain the corresponding environmental correlation results;

[0129] Obtaining a steam environment data set according to all steam correlation results and all environment correlation results, and screening the second steam environment data based on the steam environment data set;

[0130] The third tow-baked data and the second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data, including:

[0131] The third tow-baked data and the processed second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data.

[0132] In some possible embodiments, obtaining a steam environment data set according to all steam correlation results and all environment correlation results includes:

[0133] When it is detected that at least one steam correlation result among all steam correlation results is in a preset correlation interval, the total number of steam correlation results in the preset correlation interval is counted;

[0134] When the total number of steam correlation results exceeds a preset number threshold, determining the steam data type corresponding to at least one steam correlation result in a preset correlation interval;

[0135] When it is detected that at least one environment correlation result among all the environment correlation results is in a preset correlation interval, the total number of environment correlation results in the preset correlation interval is counted;

[0136] When the total number of environmental correlation results exceeds a preset number threshold, at least one environmental correlation result in a preset correlation interval and the corresponding environmental data type are determined, and all steam data types and all environmental data types are taken as a steam environment data set.

[0137] In some possible embodiments, optimizing the first moisture temperature data to obtain the second wire drying data includes:

[0138] Processing the first moisture and temperature data based on a preset multi-objective optimization algorithm to obtain at least two sets of candidate tow-baked data;

[0139] Based on the preset hierarchical analysis algorithm, each group of candidate dried tofu data is weighted and processed to obtain the corresponding weight results;

[0140] All candidate tow-bread drying data and all weight results are processed based on a preset ideal solution sorting algorithm, and the second tow-bread drying data is determined from all candidate tow-bread drying data according to the processing results.

[0141] In some possible embodiments, the device further includes:

[0142] Obtaining second moisture temperature data based on the second tow-baked data, the first steam environment data, and a preset machine learning model;

[0143] When the difference between the second moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold, the second moisture temperature data is optimized to obtain fourth tow-baked data;

[0144] The outlet moisture temperature of the silk line thin plate silk drying machine is controlled according to the fourth silk drying data.

[0145] In some possible embodiments, the first tobacco drying data includes hot air velocity and dehumidification damper opening, and the first steam environment data includes at least one inlet tobacco data, at least one environment data, at least one steam data and preset dehydration flow data.

[0146] Those skilled in the art will clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently perform or cooperate with other components to perform specific functions, where the hardware can be, for example, a field-programmable gate array (FPGA) or an integrated circuit (IC).

[0147] See also Figure 3 , Figure 3 A structural schematic diagram of another outlet moisture temperature control device of a silk thread thin plate drying machine provided in an embodiment of the present application is shown.

[0148] like Figure 3 As shown, the outlet moisture temperature control device 300 of the silk thread thin plate drying machine may include at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 and at least one communication bus 302 .

[0149] The communication bus 302 may be used to implement the connection and communication between the above components.

[0150] The user interface 303 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0151] The network interface 304 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, and the like.

[0152] The processor 301 may include one or more processing cores. Using various interfaces and circuits, the processor 301 connects various components within the outlet moisture temperature control device 300 for the silk thread sheet drying machine. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and accessing data stored in the memory 305, the processor 301 executes various functions and processes data within the outlet moisture temperature control device 300 for the silk thread sheet drying machine. Optionally, the processor 301 may be implemented in hardware using at least one of a DSP, FPGA, and PLA. The processor 301 may integrate one or a combination of a CPU, a GPU, and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display; and the modem handles wireless communications. It is understood that the modem may be implemented independently of the processor 301 and implemented as a separate chip.

[0153] Among them, the memory 305 may include RAM and ROM. Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be optionally at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an outlet moisture temperature control application of the silk thread thin plate drying machine.

[0154] Specifically, the processor 301 may be used to call the outlet moisture temperature control application of the silk thread thin plate drying machine stored in the memory 305, and specifically perform the following operations:

[0155] Obtaining first wire drying data and first steam environment data of a wire-making thin plate drying machine at a specified time, and obtaining first moisture temperature data based on the first wire drying data, the first steam environment data, and a preset machine learning model;

[0156] When the difference between the first moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold, the first moisture temperature data is optimized to obtain second tow-baked data;

[0157] The outlet moisture temperature of the silk line thin plate silk drying machine is controlled and processed according to the second silk drying data.

[0158] In some possible embodiments, obtaining the first moisture temperature data according to the first tow-baked food data, the first steam environment data, and a preset machine learning model includes:

[0159] Determine a historical moment based on a preset sliding period and a designated moment, and obtain historical silk drying data and historical steam environment data of a silk-making wire sheet drying machine from the historical moment to the designated moment;

[0160] Calculating third strand drying data based on the first strand drying data and historical strand drying data;

[0161] Calculating second steam environment data based on the first steam environment data and historical steam environment data;

[0162] The third tow drying data and the second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data.

[0163] In some possible embodiments, the second steam environment data includes at least one steam data and at least one environment data;

[0164] Before inputting the third tow-baked strands data and the second steam environment data into a preset machine learning model to obtain the first moisture temperature data, the method further includes:

[0165] Dividing the historical steam data corresponding to each type of steam data from the historical steam environment data, and dividing the historical environment data corresponding to each type of environment data;

[0166] Perform correlation analysis on the historical steam data corresponding to any two steam data to obtain the corresponding steam correlation results;

[0167] Perform correlation analysis on the historical environmental data corresponding to any two environmental data to obtain the corresponding environmental correlation results;

[0168] Obtaining a steam environment data set according to all steam correlation results and all environment correlation results, and screening the second steam environment data based on the steam environment data set;

[0169] The third tow-baked data and the second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data, including:

[0170] The third tow-baked data and the processed second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data.

[0171] In some possible embodiments, obtaining a steam environment data set according to all steam correlation results and all environment correlation results includes:

[0172] When it is detected that at least one steam correlation result among all steam correlation results is in a preset correlation interval, the total number of steam correlation results in the preset correlation interval is counted;

[0173] When the total number of steam correlation results exceeds a preset number threshold, determining the steam data type corresponding to at least one steam correlation result in a preset correlation interval;

[0174] When it is detected that at least one environment correlation result among all the environment correlation results is in a preset correlation interval, the total number of environment correlation results in the preset correlation interval is counted;

[0175] When the total number of environmental correlation results exceeds a preset number threshold, at least one environmental correlation result in a preset correlation interval and the corresponding environmental data type are determined, and all steam data types and all environmental data types are taken as a steam environment data set.

[0176] In some possible embodiments, optimizing the first moisture temperature data to obtain the second wire drying data includes:

[0177] Processing the first moisture and temperature data based on a preset multi-objective optimization algorithm to obtain at least two sets of candidate tow-baked data;

[0178] Based on the preset hierarchical analysis algorithm, each group of candidate dried tofu data is weighted and processed to obtain the corresponding weight results;

[0179] All candidate tow-bread drying data and all weight results are processed based on a preset ideal solution sorting algorithm, and the second tow-bread drying data is determined from all candidate tow-bread drying data according to the processing results.

[0180] In some possible embodiments, the processor 301 is further configured to execute:

[0181] Obtaining second moisture temperature data based on the second tow-baked data, the first steam environment data, and a preset machine learning model;

[0182] When the difference between the second moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold, the second moisture temperature data is optimized to obtain fourth tow-baked data;

[0183] The outlet moisture temperature of the silk line thin plate silk drying machine is controlled according to the fourth silk drying data.

[0184] In some possible embodiments, the first tobacco drying data includes hot air velocity and dehumidification damper opening, and the first steam environment data includes at least one inlet tobacco data, at least one environment data, at least one steam data and preset dehydration flow data.

[0185] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0186] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0187] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0188] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0189] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disk, etc., various media that can store program code.

Claims

1. A method for controlling the outlet moisture temperature of a silk thread thin plate drying machine, characterized in that: include: Obtaining first tobacco drying data and first steam environment data of a tobacco-making line sheet drying machine at a specified time, and obtaining first moisture temperature data based on the first tobacco drying data, the first steam environment data, and a preset machine learning model; wherein the first tobacco drying data includes hot air velocity and dehumidification damper opening, and the first steam environment data includes at least one type of inlet tobacco data, at least one type of environment data, at least one type of steam data, and preset dewatering flow rate data; When the difference between the first moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold, the first moisture temperature data is optimized to obtain second tow-baked data; controlling the outlet moisture temperature of the silk-making line sheet drying machine according to the second silk-making line drying data; The first moisture temperature data is obtained according to the first tow-baked food data, the first steam environment data, and a preset machine learning model, including: Determine a historical moment based on a preset sliding period and the designated moment, and obtain historical wire drying data and historical steam environment data of the wire thin plate wire drying machine from the historical moment to the designated moment; calculating third cut-wire baking data based on the first cut-wire baking data and the historical cut-wire baking data; the third cut-wire baking data is calculated by substituting each type of data in the first cut-wire baking data and all data of the corresponding type in the historical cut-wire baking data into a preset sliding average formula; Calculating second steam environment data based on the first steam environment data and the historical steam environment data; the second steam environment data is calculated based on substituting each type of data in the first steam environment data and all data of the corresponding type in the historical steam environment data into the preset sliding average formula; The third tow-baked data and the second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data.

2. The method according to claim 1, characterized in that The second steam environment data includes at least one steam data and at least one environment data; Before inputting the third wire-baking data and the second steam environment data into a preset machine learning model to obtain the first moisture temperature data, the method further includes: Dividing the historical steam environment data into historical steam data corresponding to each type of the steam data, and dividing the historical environment data corresponding to each type of the environment data; Performing correlation analysis on the historical steam data corresponding to any two of the steam data to obtain corresponding steam correlation results; Performing correlation analysis on the historical environmental data corresponding to any two of the environmental data to obtain corresponding environmental correlation results; Obtaining a steam environment data set according to all of the steam correlation results and all of the environment correlation results, and performing screening processing on the second steam environment data based on the steam environment data set; The step of inputting the third wire drying data and the second steam environment data into a preset machine learning model to obtain the first moisture temperature data includes: The third wire drying data and the processed second steam environment data are input into a preset machine learning model to obtain first moisture temperature data.

3. The method according to claim 2, characterized in that The step of obtaining a steam environment data set according to all of the steam correlation results and all of the environment correlation results includes: When it is detected that at least one of all the steam correlation results is within a preset correlation interval, the total number of the steam correlation results within the preset correlation interval is counted; When the total number of the steam correlation results exceeds a preset number threshold, determining the steam data type corresponding to at least one of the steam correlation results in the preset correlation interval; When it is detected that at least one of all the environment correlation results is within the preset correlation interval, a total number of the environment correlation results within the preset correlation interval is counted; When the total number of the environmental correlation results exceeds the preset number threshold, determine at least one of the environmental correlation results in the preset correlation interval and the corresponding environmental data type, and take all the steam data types and all the environmental data types as a steam environment data set.

4. The method according to claim 1, wherein The optimizing process of the first moisture and temperature data to obtain the second wire drying data includes: Processing the first moisture and temperature data based on a preset multi-objective optimization algorithm to obtain at least two sets of candidate tow-baked data; Performing weight distribution processing on each group of candidate dried tofu data based on a preset hierarchical analysis algorithm to obtain corresponding weight results; All the candidate cut-to-be-baked data and all the weighted results are processed based on a preset ideal solution sorting algorithm, and the second cut-to-be-baked data is determined from all the candidate cut-to-be-baked data according to the processing results.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: Obtaining second moisture temperature data based on the second tow-baked data, the first steam environment data, and a preset machine learning model; When the difference between the second moisture temperature data and the standard moisture temperature data exceeds the preset difference threshold, optimizing the second moisture temperature data to obtain fourth tow-baked data; The outlet moisture temperature of the silk line thin plate silk drying machine is controlled and processed according to the fourth silk drying data.

6. A device for controlling the outlet moisture temperature of a silk thread thin plate drying machine, characterized in that: include: a first processing module configured to obtain first tobacco drying data and first steam environment data of the tobacco-making line sheet drying machine at a specified time, and to obtain first moisture temperature data based on the first tobacco drying data, the first steam environment data, and a preset machine learning model; wherein the first tobacco drying data includes hot air velocity and dehumidification damper opening, and the first steam environment data includes at least one type of inlet tobacco data, at least one type of environmental data, at least one type of steam data, and preset dewatering flow rate data; a second processing module, configured to optimize the first moisture temperature data to obtain second tow-baked data when the difference between the first moisture temperature data and the standard moisture temperature data exceeds a preset difference threshold; a third processing module, configured to control the outlet moisture temperature of the silk-making line sheet drying machine according to the second silk-making line drying data; The first moisture temperature data is obtained according to the first tow-baked food data, the first steam environment data, and a preset machine learning model, including: Determine a historical moment based on a preset sliding period and the designated moment, and obtain historical wire drying data and historical steam environment data of the wire thin plate wire drying machine from the historical moment to the designated moment; calculating third cut-wire baking data based on the first cut-wire baking data and the historical cut-wire baking data; the third cut-wire baking data is calculated by substituting each type of data in the first cut-wire baking data and all data of the corresponding type in the historical cut-wire baking data into a preset sliding average formula; Calculating second steam environment data based on the first steam environment data and the historical steam environment data; the second steam environment data is calculated based on substituting each type of data in the first steam environment data and all data of the corresponding type in the historical steam environment data into the preset sliding average formula; The third tow-baked data and the second steam environment data are input into a preset machine learning model to obtain the first moisture temperature data.

7. An outlet moisture temperature control device for a silk thread thin plate drying machine, characterized in that: including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 5.

Images