Determination of Harness Production Time and Defective Product Formation Risk Factors with Artificial Neural Network

Abstract

The aim of this research is to estimate the projected production times of the cable harnesses produced for the tender in a company operating in the aviation and defense industry in our country by artificial neural network. For this, artificial neural network model has been formed for the number of work order, the number of cable harness module, the number of cable harness pin, the number of cable harness label, the number of cable harness back shell, the number of cable harness heat shrink tube, and the number of cable harness terminal variables which may have an effect on the projected production times of cable harnesses for the tender. Multiple linear regression analysis method is used to compare the predictive power of this model and the most appropriate method for estimating the projected production time of cable harnesses for the tender is provided. The aim of the research is to determine the effect of cable harness connector type, cable harness label type and personnel competence level risk factors on the formation of faulty cable harnesses determined during the quality control and electrical testing steps in the production process using logistic regression analysis.

Keywords

• Machine learning
• Artificial neural networks
• Logistic regression analysis
• Determination of risk factors

References

1. Alpaydın E. 2010. Introduction to machine learning (Second edition). MIT Press, London, UK, pp: 537.
2. Bayır F. 2006. An application on artificial neural networks and predictive modeling. Master Thesis, Istanbul University Institute of Social Sciences, Department of Business Administration, İstanbul, Türkiye, pp: 122.
3. Beale MH, HaganMT, Demuth HB. 2010. Neural network toolbox 7 user’s guide. The MathWorks Inc., Natick, Massachusetts, US, pp: 424.
4. Burduk A. 2013. Artificial neural networks as tools for controlling production systems and ensuring their stability. 12th International Conference on Information Systems and Industrial Management (CISIM), Computer Information Systems and Industrial Management, 25-27 October, 2013, Krakow, Poland, pp: 487-498.
5. Chiang YM, Chang LC, Chang FJ. 2004. Comparison of static-feedforward and dynamic-feedback neural networks for rainfall–runoff modeling. J Hydrol, 209: 297-311.
6. Elmas Ç. 2003. Artificial neural networks theory, architecture, education, practice (first edition). Seçkin Publishing, Ankara, Türkiye, pp: 192.
7. Gürsoy A. 2012. Estimation of tire mold cost with artificial neural networks approach. Master Thesis, Kocaeli University Institute of Science and Technology, Department of Industrial Engineering, Kocaeli, Türkiye, pp: 102.
8. Haykin S. 1994. Neural netwroks: A comprehensive foundation (First edition). Macmillan College Publishing, New York, Us, pp: 696.

9. Jackson J. 2002. Data mining: A conceptual overview. Communication of the Association for Information System Magazine, 8(1): 267-296.
10. Kalogirou SA. 2000. Applications of artifical neural-networks for energy systems. Appl Energy, 67(1): 17-35.
11. Karabulut E, Alpar R. 2011. Logistic regression, applied multivariate statistical methods. Detay Publishing, Ankara, Türkiye, pp: 876.
12. Kotsiantis SB. 2007. Supervised machine learning: A review of classification techniques. Informatica, 31(3): 249-268.
13. Küçüksille E. 2009. Evaluation of portfolio performance using data mining process and an application in the ISE stock market. PhD Thesis, Süleyman Demirel University, Institute of Social Sciences, Department of Business Administration, Isparta, Türkiye, pp: 128.
14. Kurt R, Karayılmazlar S, İmren E, Çabuk Y. 2017. Predictive modeling with artificial neural networks: The case of Turkish paper-cardboard industry. J Bartın Fac Forestry, 19(2): 99-106.
15. Leech HL, Barrett KC, Morgan GA. 2004. Spss for intermediate statistics: use and interpretation (Second edition). Lawrance Erlbaum Associates Publishers, 240, Manwah New Jersey.
16. Öğücü MO. 2006. System recognition with artificial neural networks. Master Thesis, Istanbul Technical University, Institute of Science and Technology, Department of Control and Automation Engineering, İstanbul, Türkiye, pp: 85.
17. Öztemel E. 2003. Artificial neural network (first edition). Papatya Publishing, İstanbul, Türkiye, pp: 232.
18. Pacci S, Safli ME, Odabas MS, Dengiz O. 2023. Variation of USLE-K soil erodibility factor and its estimation with artificial neural network approach in semi-humid environmental condition. Brazilian Arch Biol Technol, 66: e23220481.
19. Tiryaki S, Bardak S, Bardak T. 2015. Experimental investigation and prediction of bonding strength of oriental beech (Fagus orientalis Lipsky) bonded with polyvinyl acetate adhesive. J Adhesion Sci Technol, 29(23): 2521-2536.