Abstract
This paper develops a bi-directional prediction approach to predict the production parameters and performance of differential fibers based on neural networks and a multi-objective evolutionary algorithm. The proposed method does not require accurate description and calculation for the multiple processes, different modes and complex conditions of fiber production. The bi-directional prediction approach includes the forward prediction and backward reasoning. Particle swam optimization algorithms with K-means algorithm are used to minimize the prediction error of the forward prediction results. Based on the forward prediction, backward reasoning uses the multi-objective evolutionary algorithm to find the reasoning results. Experiments with polyester filament parameters of differential production conditions indicate that the proposed approach obtains good prediction results. The results can be used to optimize fiber production and to design differential fibers. This study also has important value and widespread application prospects regarding the spinning of differential fiber optimization.
Highlights
It is well known that before the fiber production line starts, the production parameters must be determined
The forward prediction is based on the clustering results, and backward reasoning is based on the forward prediction; the modified clustering algorithm is the foundation of the bi-directional prediction approach
The fiber performance, including EYS1.5, EYSCV, DT and DE, can be predicted by forward prediction with the production parameters consisting of spinning velocity (SV), spinning temperature (ST), quenching velocity (QV) and quenching temperature (QT)
Summary
It is well known that before the fiber production line starts, the production parameters must be determined. If the fiber performance needed is changed, the corresponding production parameters must be changed, too. If there is an approach to find the relationship between fiber performance and production parameters, the fiber production can be optimized. The fiber production line is a large-scale production system that has multiple processes, different modes and complex conditions, so it is difficult to complete the above task. Since the 1960s, a large amount of basic theory research has been applied on fiber production. The traditional optimization methods of this system involve controlling the production equipment, improving the production processes and optimizing the fiber performance. There has been some research in building mathematic models of the production process, which uses simulation technologies to find the accurate description and calculation for every step or a part of the fiber production, but not the whole process. If the production mode or the equipment condition is changed, this research must be re-modified in order to adapt to the new production process
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
