Adjustment Method of Polymerization Process Parameters Based on Viscosity Change

A technology of aggregation process and parameter adjustment, which is applied in data processing applications, predictions, instruments, etc., can solve problems such as hindering applications, hidden layer node redundancy, and small fluctuations in prediction results, achieving short time consumption and data reduction The effect of improving the processing capacity and stability

CN109472397BActive Publication Date: 2021-12-14DONGHUA UNIV
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2021-12-14

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The present invention relates to a kind of polymerization process parameter adjustment method based on viscosity change, the past continuous time period T a The melt viscosity data in the system is converted into time series I, and then fuzzy information granulation is performed on it to obtain three eigenvectors Low, R and Up, and then the three eigenvectors are input into the improved ELM, and its output and future continuous time Section T b The value related to the fluctuation range of the melt viscosity data in the melt viscosity data, compare the fluctuation range with the reference range, and then adjust the polymerization process parameters according to the comparison result. The improved ELM is obtained after optimizing the input layer weight and hidden layer threshold by using the particle swarm algorithm. ELM, the fitness function of the particle swarm algorithm is the mean square error of the training samples. The invention organically combines fuzzy information granulation, extreme learning machine and particle swarm algorithm, has few sample dimensions, good real-time performance, and high prediction accuracy; meanwhile, the prediction result can adjust process parameters.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of process optimization and relates to a method for adjusting polymerization process parameters based on viscosity changes, in particular to a method for predicting melt intrinsic viscosity based on fuzzy information granulation and improved ELM and then adjusting polymerization process parameters. Background technique

[0002] Polyester fiber not only has high elasticity and high strength, but also has good chemical stability, abrasion resistance, stretchability and wrinkle resistance, so it is widely used in the fields of civil textiles and industrial fibers. The polymerization process is the main body and leader of polyester fiber production, and the level of the polymerization process will directly affect the quantity and quality of the product. Among them, the intrinsic viscosity of the melt is an index that directly reflects the polymerization level. Therefore, the prediction of intrinsic viscosity can provide ...

Examples

Embodiment Construction

[0080] The present invention will be further described below in combination with specific embodiments. It should be understood that these examples are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the teachings of the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the appended claims of the present application.

[0081] A method for adjusting polymerization process parameters based on viscosity change, the steps are as follows:

[0082] (1) Obtain the past continuous time period T a Inner and past continuous time periods T c Melt viscosity data within the past continuous time period T a and the past continuous time period T c The length is M, M is 5000min, the melt viscosity is the intrinsic viscosity, and the unit is dl / g; ...