Robust and cost-efficient experimental design for technical tests of information and communication technology-based solutions in the automotive sector

Konstantinos Demestichas; Evgenia Adamopoulou; Vasilis Asthenopoulos; Pavlos Kosmides

Robust and cost-efficient experimental design for technical tests of information and communication technology-based solutions in the automotive sector

View Fulltext

Author(s): Konstantinos Demestichas¹ ; Evgenia Adamopoulou¹ ; Vasilis Asthenopoulos¹ ; Pavlos Kosmides¹
- Affiliations: 1: Institute of Communication and Computer Systems , Iroon Polytechneiou 9, Zografou, Athens , Greece
Source: Volume 11, Issue 7, September 2017, p. 368 – 378
DOI: 10.1049/iet-its.2016.0264 , Print ISSN 1751-956X, Online ISSN 1751-9578

Received 17/10/2016, Accepted 27/05/2017, Revised 22/04/2017, Published 30/05/2017

Nowadays, an ever-increasing number of information and communication technology solutions (hardware or software based) are finding their way to the automotive sector. Vehicles are being transformed into electronic hubs of information, communication, entertainment and other applications. Prior to commercial deployment, every single of these solutions must undergo a scrutiny of technical tests, often in the field (i.e. on-road as opposed to simulation), in order to ensure safe operation and robust performance. ‘Robustness’ is here perceived as operating as close to the target specifications as possible and with minimum variance, under varying conditions (factors). Meeting this requirement given a limited amount of resources (human, financial, equipment etc.) available for on-road technical tests is often a serious challenge for both researchers and product developers. This study proposes an experimental design process, based on suitable statistical means, for minimising the number of technical tests required to optimise the performance robustness of an automotive service or product under development. The process is substantiated and exemplified for the case study of an electric vehicle consumption estimation product, but could also be used in a variety of other applications (such as navigation, infotainment, safety solutions and others).

References

1. 1)
  - 6. Roy, R.K.: ‘A primer on the Taguchi method’ (Society of Manufacturing Engineers, 2010, 2nd edn).
2. 2)
  - 10. Hershman, L.L.: ‘The US new car assessment program (NCAP): Past, present and future’. Int. Technical Conf. on the Enhanced Safety of Vehicles, 2001.
3. 3)
  - 4. Taguchi, G.: ‘Introduction to quality engineering: designing quality into products and processes’ (Quality Resources, 1986).
4. 4)
  - 5. Zhu, J., Chew, D.A., Lv, S., et al: ‘Optimization method for building envelope design to minimize carbon emissions of building operational energy consumption using orthogonal experimental design’, Habitat Int., 2013, 37, pp. 148–154.
5. 5)
  - 20. Shewchuk, J.R.: ‘An introduction to the conjugate gradient method without the agonizing pain’ (Carnegie Mellon University, 1994).
6. 6)
  - 2. ‘FP7 Project EMERALD’, http://www.fp7-emerald.eu/, accessed 1 February2017.
7. 7)
  - 25. Yeo, I., Johnson, R.A.: ‘A new family of power transformations to improve normality or symmetry’, Biometrika, 2000, 87, pp. 954–959.
8. 8)
  - 24. Berger, C., Rumpe, B.: ‘Engineering autonomous driving software’, in Rouff, C., Hinchey, M. (Eds.): ‘Experience from the DARPA urban challenge’, 2012, pp. 243–271.
9. 9)
  - 9. ‘euroFOT Project’, http://www.eurofot-ip.eu/, accessed 1 February2017.
10. 10)
  - 3. ‘FP7 Project EcoGem’, http://www.ecogem.eu/, accessed 1 February2017.
11. 11)
  - 11. ‘EURO NCAP Protocols’, http://www.euroncap.com/en/for-engineers/protocols/, accessed 1 February2017.
12. 12)
  - 8. Ji, L., Si, Y., Liu, H., et al: ‘Application of orthogonal experimental design in synthesis of mesoporous bioactive glass’, Micropor. Mesopor. Mat., 2014, 184, pp. 122–126.
13. 13)
  - 17. Geisser, S.: ‘The predictive sample reuse method with applications’, J. Am. Stat. Assoc., 1995, 70, 350, pp. 320–328.
14. 14)
  - 22. Logothetis, N.: ‘Process and techniques of continuous quality improvement’ (Hellenic Open University, 2001).
15. 15)
  - 7. Evans, J.R., Lindsay, W.M.: ‘The management and control of quality’ (West Publishing, New York, 1995, 3rd edn).
16. 16)
  - 23. Hunter, W.G., Hunter, J.S.: ‘Statistics for experimenters: an introduction to design, data analysis, and model building’ (Wiley, 1978).
17. 17)
  - 18. Kohavi, R.: ‘A study of cross-validation and bootstrap for accuracy estimation and model selection’, Int. Joint Conf. Artificial Intelligence, 1996, 14, (2), pp. 1137–1145.
18. 18)
  - 1. Predić, B., Madić, M., Roganović, M., et al: ‘Prediction of passenger car fuel consumption using artificial neural network: a case study in the City Of Niš’, FU Aut. Cont., 2016, 1, (2), pp. 105–111.
19. 19)
  - 21. Barker, T. B., Milivojevich, A.: ‘Quality by experimental design’ (CRC Press, 2016).
20. 20)
  - 12. ‘dieselnet - Emission Test Cycles’, https://www.dieselnet.com/standards/cycles/, accessed 1 February2017.
21. 21)
  - 16. Dehnad, K.: ‘Quality control, robust design, and the Taguchi method’ (Springer Science & Business Media, 2012).
22. 22)
  - 19. Fischetti, M.: ‘Fast training of support vector machines with Gaussian kernel’, Discrete Optim., 2016, 22, (A), pp. 183–194.
23. 23)
  - 14. Specht, D.F.: ‘A general regression neural network’, IEEE Trans. Neural Netw., 1991, 2, (6), pp. 568–576.
24. 24)
  - 15. Masikos, M., Demestichas, K., Adamopoulou, E., et al: ‘Energy-efficient routing based on vehicular consumption predictions of a mesoscopic learning model’, Appl. Soft Comput., 2015, 28, pp. 114–124.
25. 25)
  - 13. Haykin, S.: ‘Neural networks: a comprehensive foundation’ (Prentice Hall, 1998, 2nd edn).

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Robust and cost-efficient experimental design for technical tests of information and communication technology-based solutions in the automotive sector

References

Related content