Prediction method of performance index of drawing link in the production process of carbon fiber precursor

Abstract

The invention relates to a method for predicting performance indexes of a drafting link in a carbon fiber precursor production process, in particular to a method for predicting performance indexes of a drafting link in a carbon fiber precursor production process based on a least square support vector machine (LS-SVM) optimized by a particle swarm optimization (PSO) algorithm improved by a power law. The method comprises the following steps of selecting a six-stage draft ratio of the drafting link in the carbon fiber precursor production process as feature information, performing linear function normalization, and establishing an input sample dataset; determining main performance indexes, including linear density, precursor strength and breaking elongation rate, influencing carbon fiber quality, performing logarithmic function normalization, and establishing an output sample dataset; and building an LS-SVM model according to the input and output sample datasets, adopting a Gauss radial basis function (RBF) as a kernel function of the LS-SVM, and selecting an optimal penalty factor C and a kernel function parameter sigma by using PSO. The PSO process is improved according to the power law, so that the optimization speed can be greatly increased and accurate prediction is realized.

Description

technical field [0001] The invention belongs to the technical field of carbon fiber intelligent production forecasting, and relates to a method for predicting the performance index of the drafting link in the production process of carbon fiber precursors, in particular to the carbon fiber precursor production process based on the improved PSO optimization LS-SVM based on the power law Prediction method of drafting link. Background technique [0002] Carbon fiber is a new type of fiber material with high strength and high modulus fiber containing more than 95% carbon. Because of its low density, high specific performance, no creep, high temperature resistance in non-oxidizing environment, good fatigue resistance, small thermal expansion coefficient, good corrosion resistance, good electrical and thermal conductivity, and good electromagnetic shielding, it is widely used in national defense and military industries and civilian use. [0003] The production process of carbon f...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is that in the current production process of carbon fiber precursors, the corresponding relationship between the draft ratio of each level and the product performance index often relies on production experience and lacks relevant theoretical guidance. On-line debugging requires the production line to stop production and carry out multiple Secondary production simulation will bring large economic losses, etc., and propose a prediction method for the performance index of the drafting link in the production process of carbon fiber precursors, specifically, based on the power law improved PSO optimized LS-SVM carbon fiber Prediction method of drawing link in raw silk production process

Images