Predicting quality parameters of denim fabrics using developed ANN based Artificial Bee Colony algorithm

Abstract

Denim is a special fabric preferred by all segments of society. Many production factors affect the properties, performance levels and quality of denim products. In today’s textile manufacturing management, quality parameter prediction is very important. In the context of this work, a new prediction model has been introduced for calculating denim fabric quality parameters. The meta-heuristic combination of Artificial Neural Network (ANN) and Artificial Bee Colony (ABC) algorithm is the proposed in this study. The proposed hybrid model was evaluated using data on production parameters acquired from a significant Turkish manufacturer of denim fabric. The denim fabric quality parameters results obtained from the ANN and the proposed ANN based ABC (ABC-ANN) algorithms were compared with the results of all models on test data. The performances of the measured quality values were evaluated and compared in terms of Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and Receiver Operating Characteristic (ROC) curve analysis. According to the comparison results, the proposed ANN-based ABC algorithm is superior in predicting the mechanical properties of denim fabric from the production parameters.

Keywords:

• Denim
• mechanical properties
• prediction
• artificial neural network
• Artificial Bee Colony

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This study was supported by the Scientifc and Technological Research Council of Turkey under Grant TUBITAK: TEYDEB-1505, 520006. Gözde Katırcıoğlu is supported as a YÖK 100/2000 scholar.