Abstract

There are different weft insertion methods used in the weaving machines. Electromagnetic launcher can be used as accelerator to yarn which is attached to ferromagnetic projectile. A validated finite element model can predict the system behavior accurately and faster than experiments. For optimization of the new weft insertion, the system outputs should be predicted by numerous states of inputs. Thus, prediction of the system outputs in less computation time is very important. The present study is an attempt to examine the use of an adaptive neuro fuzzy interface system (ANFIS) to simulate this new weft insertion system. The results show that simulation of this weft insertion system by ANFIS can function more efficiently and about 26 times faster than the finite element model.

摘要

织机中使用了不同的引纬方法。电磁发射器可用作附着在铁磁弹丸上的纱线的加速器。经过验证的有限元模型可以比实验更准确、更快地预测系统行为。为了优化新的引纬，系统输出应通过输入的多种状态进行预测。因此，在较少的计算时间内预测系统输出是非常重要的。本研究试图检验使用自适应神经模糊接口系统 (ANFIS) 来模拟这种新的引纬系统。结果表明，通过 ANFIS 对该引纬系统的模拟可以更有效地运行，并且比有限元模型快约 26 倍。