CN-121979067-A - Moisture control method, device, equipment and medium for silk making process

CN121979067ACN 121979067 ACN121979067 ACN 121979067ACN-121979067-A

Abstract

The invention discloses a moisture control method, a device, equipment and a medium for a silk making process. The method comprises the steps of obtaining a current state vector corresponding to a target production material in a target wire making process, carrying out state index on the current state vector based on a target state and an action mapping table, determining basic adjustment action information corresponding to the current state vector, and matching corresponding historical adjustment action information in a historical action set based on the current acquisition time, wherein the target state and the action mapping table are determined based on a target nonlinear regression model corresponding to the target production material, carrying out weighted fusion on the historical adjustment action information and the basic adjustment action information to obtain target adjustment action information corresponding to the current state vector, and executing the target adjustment action information to realize moisture control of the target wire making process. By the technical scheme, the accurate, robust and autonomous control of the water content at the outlet of the silk making process can be realized, and the production efficiency of the silk making process is improved.

Inventors

WANG PENG
ZHUO MING
Shi Biran
LIU ZHI
LI FEILONG

Assignees

湖北中烟工业有限责任公司

Dates

Publication Date: 20260505
Application Date: 20260204

Claims (10)

1. A method for controlling moisture in a yarn manufacturing process, comprising: acquiring a current state vector corresponding to a target production material in a target silk making process, wherein the current state vector comprises a current inlet temperature, a current inlet moisture, a current actually measured outlet moisture, a current steam pressure, a current drum rotating speed, a current drum wall temperature, a current hot air speed, a current moisture removal cover negative pressure, a current material flow and a current hot air temperature at a current acquisition time; Performing state index on the current state vector based on a target state and an action mapping table, determining basic adjustment action information corresponding to the current state vector, and matching corresponding historical adjustment action information in a historical action set based on the current acquisition time; and carrying out weighted fusion on the historical adjustment action information and the basic adjustment action information to obtain target adjustment action information corresponding to the current state vector, and executing the target adjustment action information to realize the moisture control of a target wire manufacturing process.
2. The method according to claim 1, wherein the method further comprises: acquiring a target nonlinear regression model corresponding to a target production material and a first state vector corresponding to a first acquisition time, wherein the first acquisition time is the previous acquisition time of the current acquisition time; Carrying out moisture value prediction on the first state vector based on a target nonlinear regression model to obtain a first moisture value prediction result, and determining a first prediction deviation corresponding to the first acquisition time based on the first moisture value prediction result and the current state vector; and updating data of the basic state and the action mapping table based on the first prediction deviation to obtain a target state and the action mapping table.
3. The method of claim 2, further comprising, prior to the obtaining the target nonlinear regression model for the target production material: Acquiring a historical state vector set and a basic nonlinear regression model corresponding to a target production material; carrying out moisture value prediction on a first historical state vector in a historical state vector set based on the basic nonlinear regression model to obtain a historical moisture value prediction result; Determining a historical prediction deviation corresponding to the basic nonlinear regression model based on the historical moisture value prediction result and a second historical state vector, wherein the acquisition time corresponding to the second historical state vector is the later acquisition time of the acquisition time corresponding to the first historical state vector; And carrying out model optimization on the basic nonlinear regression model based on the historical prediction deviation to obtain an optimized target nonlinear regression model.
4. The method according to claim 2, wherein the updating the data of the base state and the action mapping table based on the first prediction bias to obtain the target state and the action mapping table includes: weighting the first prediction deviation, the current actually measured outlet moisture and the target outlet moisture value to obtain a control effect score corresponding to the first acquisition moment; performing error calculation on the current state vector and the control effect score based on a preset time difference calculation rule, and determining a time difference error corresponding to the first acquisition moment; And updating data of the basic state and the action mapping table based on the time difference error to obtain a target state and the action mapping table.
5. The method of claim 1, wherein the historical adjustment action information comprises first adjustment action information and second adjustment action information, wherein the first adjustment action information is adjustment action information corresponding to an acquisition time point which is consistent with the current acquisition time in a first time period in a historical action set, the second adjustment action information is adjustment action information corresponding to an acquisition time point which is consistent with the current acquisition time in a second time period in the historical action set, the second time period is a production time period which is the previous production time period of the current acquisition time, and the first time period is the previous production time period of the second time period; The step of carrying out weighted fusion on the historical adjustment action information and the basic adjustment action information to obtain target adjustment action information corresponding to the current state vector, comprises the following steps: Acquiring a historical forgetting factor and a learning factor corresponding to a target production material; And carrying out weighted fusion on the first adjustment action information, the second adjustment action information and the basic adjustment action information based on the historical forgetting factor and the learning factor to obtain target adjustment action information corresponding to the current state vector.
6. The method of claim 3, further comprising, after said model optimizing said underlying nonlinear regression model based on said historical prediction bias to obtain an optimized target nonlinear regression model: Adding the current state vector to a historical state vector set to obtain an updated historical state vector set; and performing online optimization on the target nonlinear regression model based on the updated historical state vector set to obtain an online optimized target nonlinear regression model.
7. A moisture control device for a thread making process is characterized by comprising: The data acquisition module is used for acquiring a current state vector corresponding to a target production material in a target wire making process, wherein the current state vector comprises a current inlet temperature, a current inlet moisture, a current actually measured outlet moisture, a current steam pressure, a current drum rotating speed, a current drum wall temperature, a current hot air speed, a current moisture removal cover negative pressure, a current material flow and a current hot air temperature at a current acquisition time; The data matching module is used for carrying out state index on the current state vector based on a target state and an action mapping table, determining basic adjustment action information corresponding to the current state vector, and matching corresponding historical adjustment action information in a historical action set based on the current acquisition time; And the action determining module is used for carrying out weighted fusion on the historical adjustment action information and the basic adjustment action information to obtain target adjustment action information corresponding to the current state vector, and executing the target adjustment action information to realize the moisture control of a target wire making process.
8. An electronic device, the electronic device comprising: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the moisture control method of the wire making process of any one of claims 1-6.
9. A computer readable storage medium storing computer instructions for causing a processor to execute the moisture control method of the wire making process according to any one of claims 1 to 6.
10. A computer program product comprising a computer program which, when executed by a processor, implements the moisture control method of a wire making process according to any one of claims 1-6.

Description

Moisture control method, device, equipment and medium for silk making process Technical Field The invention relates to the technical field of tobacco shredding process control, in particular to a moisture control method, a device, equipment and a medium for a shredding process. Background In the cigarette cut tobacco making process, the outlet moisture is a core index for determining the physical characteristics, processing performance and final finished product sensory quality of cut tobacco. The water control precision is directly related to the product homogenization level, raw material consumption and production line operation efficiency, so that the realization of accurate and stable control of outlet water is a key target of automation of the wire making process. At present, the moisture control method in the prior art mainly relies on the following technical paths, namely a feedback control method based on traditional Proportional-Integral-Derivative (PID), and the method generates a control signal through Proportional, integral and Derivative operations by comparing the deviation of an actual measured value of the outlet moisture with a target set value. A feedforward and feedback composite control method based on a fixed process model is characterized in that feedforward compensation is carried out on main interference through an off-line established process model, and then correction is carried out by combining feedback control. The other is a predictive compensation algorithm based on a static data-driven model, which uses historical data to train a regression model to predict outlet moisture and give compensation advice accordingly. However, the silk-making drying process has significant large hysteresis, strong nonlinearity and time-varying characteristics, the traditional linear PID controller is difficult to dynamically adapt to the complex working conditions, the control parameters of the traditional linear PID controller are often manually set highly depending on the experience of operators, and an ideal and stable control effect is difficult to obtain. In actual production, raw material characteristic fluctuation, environmental temperature and humidity change and equipment state drift all can cause serious mismatch between a pre-established fixed process model and an actual process, so that control accuracy is reduced and even instability is caused. In addition, the static data driving model usually adopts an offline training mode and an online application mode, has a long updating period, cannot respond to continuous changes of production conditions in real time, and can continuously accumulate prediction deviation possibly generated due to model aging or working condition migration under long-term operation, so that control quality is finally affected. Therefore, how to realize accurate, robust and autonomous control of the outlet moisture of the silk making process, and improve the accuracy and efficiency of the moisture control of the silk making process so as to improve the production efficiency of the silk making process is a problem to be solved urgently at present. Disclosure of Invention The invention provides a method, a device, equipment and a medium for controlling moisture in a silk manufacturing process, which can solve the problems of low accuracy and low efficiency of moisture control in the silk manufacturing process. According to an aspect of the present invention, there is provided a moisture control method of a wire-making process, including: acquiring a current state vector corresponding to a target production material in a target silk making process, wherein the current state vector comprises a current inlet temperature, a current inlet moisture, a current actually measured outlet moisture, a current steam pressure, a current drum rotating speed, a current drum wall temperature, a current hot air speed, a current moisture removal cover negative pressure, a current material flow and a current hot air temperature at a current acquisition time; Performing state index on the current state vector based on a target state and an action mapping table, determining basic adjustment action information corresponding to the current state vector, and matching corresponding historical adjustment action information in a historical action set based on the current acquisition time; and carrying out weighted fusion on the historical adjustment action information and the basic adjustment action information to obtain target adjustment action information corresponding to the current state vector, and executing the target adjustment action information to realize the moisture control of a target wire manufacturing process. According to another aspect of the present invention, there is provided a moisture control apparatus for a wire-making process, comprising: The data acquisition module is used for acquiring a current state vector corresponding to a target production material in a target wi