OPEN ACCESS
This research reports a vehicle occupant restraint system design that takes account of uncertainties of crash conditions and situations by using a multi-objective robust design optimization method called MORDO. The vehicle occupant restraint system is composed of restraint equipment, such as an airbag, a seatbelt and a knee bolster. The optimization aims to improve the safety performance of the system and its robustness simultaneously. The safety of the system is evaluated by some indexes based on some safety regulations, which are calculated by response surface model of an occupant at a crash. In addition, its robustness is evaluated by the mean value and the standard deviation of objective functions, which are calculated by using Monte Carlo simulation based on a certain probabilistic distribution in space of design variables around each design candidate. Some helpful information for designing the restraint systems, such as trade-off information of safety performance and its robustness, are provided by visualizing and analysing the Pareto optimal solutions.
evolutionary algorithm, machine learning, multi-objective optimization, occupant safety, robust optimization
[1] Fu, Y. & Abramoski, E., Robust design for occupant restraint system. Proceedings of Reliability and robust design in automotive engineering 2005 (SAE Technical Paper 2005-01-0814), 2005. https://doi.org/10.4271/2005-01-0814
[2] Padvan, L., Pediroda, V. & Poloni, C., Multi objective robust design optimization of airfoils in transonic field. Proceedings of International Congress on Evolutionary Meth- ods for Design, Optimization and Control with Applications to Industrial Problems, EUROGEN2003, 2003.
[3] Parussini, L., Pedirda, V. & Obayashi, S., Design under uncertainties of wings in transonic field. JSME International Journal, Series B, 48(2), pp. 218–223, 2005. https://doi.org/10.1299/jsmeb.48.218
[4] Simoyama, K., Oyama, A. & Fujii, K., A new efficient and useful robust optimization approach -- design for multi-objective six sigma, Proceedings of the 2005 IEEE Con- gress on Evolutionary Computation, 1, pp. 950–957, 2005. https://doi.org/10.1109/cec.2005.1554785
[5] Horii, H., Estimate modelling for assessing the safety performance of occupant restraint systems. WIT Transactions on the Built Environment, 134, pp. 627–635, 2014. http://dx.doi.org/10.2495/SAFE130561
[6] Horii, H., Multi-objective optimization of vehicle occupant restraint system by using evolutionary algorithm with response surface model. International Journal of Compu- tational Methods and Experimental Measurements, 5(2), pp. 163–173, 2017. http://dx.doi.org/ 10.2495/CMEM-V5-N2-163-170
[7] Rasmussen, C.E. & Williams, C.K.I, Gaussian Processes for Machine Learning, MIT Press, Cambridge, 2006.
[8] Sasaki, D. & Obayashi, S., Efficient search for trade-offs by adaptive range multi- objective genetic algorithms. AIAA Journal of Aerospace Computing, Information and Communication, 2, pp. 44–64, 2005. https://doi.org/10.2514/1.12909