Statistical and computational intelligence tools for the analyses of warp tension in different back-rest oscillations

Abstract

In this paper, experimental, computational intelligence based and statistical investigations of warp tensions in different back-rest oscillations are presented. Firstly, in the experimental stage, springs having different stiffnesses are used to obtain different back-rest oscillations. For each spring, fabrics are woven in different weft densities and the warp tensions are measured and saved during weaving process. Secondly, in the statistical investigation, the experimental data are analyzed by using linear multiple and quadratic multiple-regression models. Later, in the computational intelligence based investigation, the data obtained from the experimental study are analyzed by using artificial neural networks that are universal approximators which provide a massively parallel processing and decentralized computing. Specialty, radial basis function neural network structure is chosen. In this structure, cross-validation technique is used in order to determine the number of radial basis functions. Finally, the results of regression analysis, the computational intelligence based analysis and experimental measurements are compared by using the coefficient of determination. From the results, it is shown that the computational intelligence based analysis indicates a better agreement with the experimental measurement than the statistical analysis.