An optimized artificial neural network for estimating design effort of jigs and fixtures used in aviation industry

Abstract

This paper investigates the usefulness of the machine learning methods to predict the design effort of jigs and fixtures used in the aviation industry. Reaching the best possible result by determining the ideal machine learning model to obtain the best estimate and the most appropriate set of inputs and parameters forms the basis of this study. To that end, most popular machine learning models that can be used for regression are combined with various data encoding methods. The best combination is optimized as well. The results showed that an optimized Artificial Neural Network architecture with binary encoding applied to the input data can be applied satisfactorily in the aviation industry for the solution of the given problem.

Keywords

• Tool design effort
• aviation industry
• artificial neural network
• machine learning

References

1. Benedetto, H., Vieira, D., Proposed framework for estimating effort in design projects, Int. J. Manag. Proj. Bus., 11 (2) (2018), 257-274, https://doi.org/10.1108/IJMPB-03-2017-0022.
2. Martin, M. V., Ishii, K., Design for variety: a methodology for understanding the costs of product proliferation, International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, 97607 (1996), https://doi.org/10.1115/96-DETC/DTM-1610.
3. Dentsoras, A. J., Information generation during design: information importance and design effort, AI EDAM, 19 (1) (2005), 19-32, https://doi.org/10.1017/S089006040505002X.
4. Bashir, H. A., Thomson, V., Estimating design complexity, J. Eng. Des., 10 (3) (1999), 247-257, https://doi.org/10.1080/095448299261317.
5. Bashir, H. A., Thomson, V., Estimating design effort for GE hydro projects, Comput. Ind. Eng., 46 (2) (2004), 195-204, https://doi.org/10.1016/j.cie.2003.12.005.
6. Bashir, H. A., Modeling of development time for hydroelectric generators using factor and multiple regression analyses, Int. J. Proj. Manag., 26 (4) (2008), 457-464, https://doi.org/10.1016/j.ijproman.2007.08.006.
7. Bashir, H. A., Thomson, V., An analogy-based model for estimating design effort. Des. Stud., 22 (2) (2001), 157-167, https://doi.org/10.1016/S0142-694X(00)00015-6.
8. Ou-Yang, C., Lin, T., Developing an integrated framework for feature-based early manufacturing cost estimation, Int. J. Adv. Manuf. Technol., 13 (9) (1997), 618-629, https://doi.org/10.1007/BF01350820.

9. Wang, H., Li, H., Wen, X., Luo, G., Unified modeling for digital twin of a knowledge based system design, Robot. Comput. Integr. Manuf., 68 (2021), 102074, https://doi.org/10.1016/j.rcim.2020.102074.
10. Thomson, A., Hird, A., Estimating design effort needs of product design projects using captured expert knowledge–a proposed method, Proceedings of the Design Society, 1 (2021), 1391-1400, https://doi.org/10.1017/pds.2021.139.
11. Sehra, S. K., Brar, Y. S., Kaur, N., Sehra, S. S., Research patterns and trends in software effort estimation, Inf. Softw. Technol., 91 (2017), 1-21, https://doi.org/10.1016/j.infsof.2017.06.002.
12. Aktan, U., Dikmen, M., Estimation of design effort of jigs and fixtures used in aviation industry by machine learning methods, 2nd International Eurasian Conference on Science, Engineering and Technology, (2020), 500-505.
13. Genton, M. G., Classes of kernels for machine learning: a statistics perspective, J. Mach. Learn. Res., 2 (2001), 299-312.
14. Levenberg, K., A method for the solution of certain non-linear problems in least squares, Q. Appl. Math., 2 (2) (1944), 164-168.
15. Soylu, K., Güzel, M. S., Emek Soylu B., Bostanci, G. E., Genetic hyperparameter optimization library development and its application on plant disease detection problem, 28th Signal Processing and Communications Applications Conference (SIU), (2020), 1-4, https://doi.org/10.1109/SIU49456.2020.9302246.