ABSTRACT
Creating assemblies of different components is one of the main processes in industry. To optimize these assembly processes, data-driven models are suitable that describe the influence of the components onto the assembled products. This often requires high quality process data, which can be efficiently generated by Design of Experiments (DoE). However, DoE methods which are dealing with assembly experiments are rare. In this paper, a novel methodology to create space-filling designs for assembled products is presented, that optimally allocates given components to the single products. Considering the given data distribution and constraints within the data points, a design that covers the design space as uniformly as possible is constructed. As an extension of this approach, rotation-symmetric components are regarded that can be mounted in multiple positions. The resulting additional constraints are incorporated in the optimization process. The novel methodology is tested on both artificial assembly processes and a real-world assembly process. Compared to a random design, the novel methodology achieves a significantly better uniformity.
- Christine M. Anderson-Cook and Timothy J. Robinson. 2009. A Designed Screening Study with Prespecified Combinations of Factor Settings. Quality Engineering 21, 4 (sep 2009), 392–404. https://doi.org/10.1080/08982110903179069Google ScholarCross Ref
- David K. Anthony and Andy J. Keane. 2004. Genetic algorithms for design of experiments on assembled products. Technical Report. University of Southampton. 27 pages.Google Scholar
- Chih-Cherng Chen, Ko-Ta Chiang, Chih-Chung Chou, and Yan-Ching Liao. 2011. The use of D-optimal design for modeling and analyzing the vibration and surface roughness in the precision turning with a diamond cutting tool. The International Journal of Advanced Manufacturing Technology 54, 5-8 (2011), 465–478.Google ScholarCross Ref
- Shiyong Cui and Mihai Datcu. 2015. Comparison of Kullback-Leibler divergence approximation methods between Gaussian mixture models for satellite image retrieval. In 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). IEEE, Milan, Italy, 3719–3722.Google ScholarCross Ref
- Tobias Ebert, Torsten Fischer, Julian Belz, Tim Oliver Heinz, Geritt Kampmann, and Oliver Nelles. 2015. Extended Deterministic Local Search Algorithm for Maximin Latin Hypercube Designs. In 2015 IEEE Symposium Series on Computational Intelligence. IEEE, Cape Town, South Africa, 375–382. https://doi.org/10.1109/ssci.2015.63Google Scholar
- M. Chris Jones. 1993. Simple boundary correction for kernel density estimation. Statistics and computing 3, 3 (1993), 135–146.Google Scholar
- Astrid Jourdan and Jessica Franco. 2010. Optimal Latin hypercube designs for the Kullback–Leibler criterion. AStA Advances in Statistical Analysis 94, 4 (dec 2010), 341–351. https://doi.org/10.1007/s10182-010-0145-yGoogle ScholarCross Ref
- Alan Jović, Karla Brkić, and Nikola Bogunović. 2015. A review of feature selection methods with applications. In 2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO). IEEE, Opatija, Croatia, 1200–1205. https://doi.org/10.1109/MIPRO.2015.7160458Google ScholarCross Ref
- Ruth K. Meyer and Christopher J. Nachtsheim. 1995. The Coordinate-Exchange Algorithm for Constructing Exact Optimal Experimental Designs. Technometrics 37, 1 (feb 1995), 60–69. https://doi.org/10.1080/00401706.1995.10485889Google ScholarCross Ref
- Douglas C. Montgomery. 2017. Design and analysis of experiments. John wiley & sons, Hoboken, USA.Google Scholar
- Luc Pronzato. 2017. Minimax and maximin space-filling designs: some properties and methods for construction. Journal de la Societe Française de Statistique 158, 1 (mar 2017), 7–36.Google Scholar
- Thomas J. Santner, Brian J. Williams, and William I. Notz. 2018. The Design and Analysis of Computer Experiments. Springer New York, New York, USA. https://doi.org/10.1007/978-1-4939-8847-1Google Scholar
- Christine J. Sexton, David K. Anthony, Susan M. Lewis, Colin P. Please, and Andy J. Keane. 2006. Design of Experiment Algorithms for Assembled Products. Journal of Quality Technology 38, 4 (oct 2006), 298–308. https://doi.org/10.1080/00224065.2006.11918619Google ScholarCross Ref
- Christine J. Sexton, Susan. M. Lewis, and Colin. P. Please. 2001. Experiments for derived factors with application to hydraulic gear pumps. Journal of the Royal Statistical Society: Series C (Applied Statistics) 50, 2 (jan 2001), 155–170. https://doi.org/10.1111/1467-9876.00226Google ScholarCross Ref
- Bernard W. Silverman. 1986. Density estimation for statistics and data analysis. Vol. 26. CRC press, Boca Raton, USA.Google Scholar
- Stefan H. Steiner, R. Jock Mackay, and John S. Ramberg. 2008. An Overview of the Shainin System TM for Quality Improvement. Quality Engineering 20, 6-19 (2008), 37–41.Google ScholarCross Ref
Index Terms
- Space-Filling Designs for Experiments with Assembled Products
Recommendations
Using Design of Experiments to Support the Commissioning of Industrial Assembly Processes
Intelligent Data Engineering and Automated Learning – IDEAL 2022AbstractEnsuring high product quality is an important success factor in modern industry. Data-driven models are increasingly used for this purpose and need to be integrated into industrial processes as early as possible. As these models require high-...
An ontology for numerical design of experiments processes
Numerical design of experiments may require advanced knowledge to be configured and executed efficiently.The ontology, ODE, for numerical design of experiments processes is proposed.ODE is designed according to existing ontologies.ODE provides a ...
Comments