However, these values confirm a very good fitof the NN 5 model. Conclusion The artificial work model was developed and works were trained at the Institute of Textile and Clothing Technology, Technische Universitat Dresden. The use of Bayesian regularization to reduce the testing error for the practical applications has shown quite promising results. From the testing performance of NN 5 as shown in Table 3,a maximum deviation of about 2 mm is observable, which falls well within the 3 mm negligible range for determination of the LAP. This concludes that works can be applied in the future for putation of the LAP, with the advantages of fast adjustment and saving of material and time. The accuracy putation can lead to better sliver CV% and better yarn quality. Table 3 Test performance of NN 5.
全文预览