A method and system for controlling moisture content at the inlet of dried silk
A technology of moisture content and entrance, applied in the direction of tobacco preparation, application, tobacco, etc., can solve the problems of unstable tobacco quality and different setting values, and achieve the effects of improving efficiency, reducing memory space, and improving training efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0045] Embodiment 1: A method of controlling the moisture content at the entrance of dried silk, please refer to figure 1 , to collect basic working condition information of historical operations, and to establish different working models for different basic working conditions;
[0046] Establishing a machine learning model, the machine learning model including a coding unit, an optimization target and a variable coding; controlling the moisture content at the entrance of the dried shredded silk to the optimization target, and the working model is in one-to-one correspondence with the coding unit through the variable coding;
[0047] Provide the basic working condition information of the current processing stage obtained by each measuring point on the production line when the order is placed, the zero point value of the loose outlet moisture meter, the zero point value of the feeding inlet moisture meter, the zero point value of the feeding outlet moisture meter, and the zero p...
Embodiment 2
[0064] Example 2, in the actual production of silk production, the initial stage is often a gradual process, which is the dynamic data of inverted "U", which cannot stably reflect the relationship between actual variables and related factors. In order to further improve the reliability of the optimization scheme, the preceding N Minute data is coded as variables without processing, that is, during the learning process of the machine learning model, the unsteady data in the production line is eliminated, and they are coded as variables without processing. The unstable data includes data at the initial stage of production line work , data during the time period of production interruption, and abnormal data far beyond the set normal range, the screening of data greatly improves the accuracy of the final optimization plan.
Embodiment 3
[0065] Embodiment three, the machine learning model establishes different models according to different processing stages to form a multi-stage series model, and conducts Pearson correlation analysis for each processing stage, and screens out variables with strong correlations, and then analyzes all The filtered variables are variable coded. That is, in each processing stage, variables with less correlation are not considered in the model, and the model only considers how to optimize the variables with greater correlation to control the moisture content at the inlet of dried silk, which greatly improves the prediction efficiency and accuracy.
[0066] When obtaining the optimization plan, the variables that can be obtained before the production line work are used to predict the amount of moisture change in each processing stage, and then through the amount of moisture change in each stage, the moisture content of the drying silk inlet is reversed from the set value of the moist...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


