Restricted accessResearch articleFirst published online 2014-3
Predicting the ride comfort of passenger cars for single-obstacle crossings through an innovative feature extraction method consisting of non-linear geometric approximations of wavelet-transformed acceleration data and airborne sound
In this paper a method is presented to predict the ride comfort of passenger cars for single-obstacle crossings based on measured acceleration data and airborne sound. The method takes advantage of applying the continuous complex wavelet transform to the signals using specially adapted Gabor wavelets. Through an innovative approach, the comfort-relevant features are extracted to describe the geometric properties of the transformed data and to predict the ride comfort using artificial neural networks with a feedforward structure. In order to avoid overfitting, basic data division is applied to the available training data and the networks are trained using Bayesian regulation.
AlbrechtM. Modellierung der Komfortbeurteilung aus Kundensicht am Beispiel des automatisierten Anfahrens. Forschungsberichte, Institut für Produktentwicklung, Universität Karlsruhe, Karlsruhe, Germany, 2005.
2.
SchoegglPRamschakE. Vehicle driveability assessment using neural networks for development, calibration and quality tests. SAE paper 2000-01-0702, 2000.
3.
RiedelABeckerK. Subjektive und objektive Beurteilung des Handling von PKW. Willingen: Expert-Verlag, 2000.
4.
JürgensohnTMüllerWSchefferT. Verbesserte Methoden zur Objektivierung von subjektiven Bewertungen des Fahrverhaltens. Forschungsbericht, Zentrum Mensch-Maschine-Systeme, Technische Universität Berlin, Berlin, Germany, 1996.
5.
HazelaarM. Fahrwerkschwingungen und Komfortbeurteilung bei kurzwelliger Anregung (Achsrauhigkeit). Fortschrittberichte VDI, Reihe12: Verkehrstechnik, Fahrzeugtechnik. Düsseldorf: VDI Verlag, 1994.
6.
RerichaI. Methoden zur objektiven Bewertung des Fahrkomforts. Automobil-Industrie 2/86. Würzburg: Vogel-Verlag, 1986.
7.
StammenK. Bewertung des Schwingungskomforts in PKW mit Hilfe von Regressionsmodellen und künstlichen neuronalen Netzen. Fortschrittberichte VDI. Düsseldorf: VDI-Verlag, 2009.
8.
CucuzS. Schwingempfindung von Pkw-Insassen: Auswirkung von stochastischen Unebenheiten und Einzelhindernissen der realen Fahrbahn. Braunschweig: Technische Universität Braunschweig; 1993.
9.
KosfelderMPériardF. Ein modalanalytischer Ansatz zur Bestimmung der globalen Bewegungsformen von Kraftfahrzeugen, Teil II: Verifikation und Anwendungen. Berlin: Deutsche Gesellschaft für Akustik, 2002.
10.
LeeSKWhitePR. Application of wavelet analysis to the impact harshness of a vehicle. Proc IMechE Part C: J Mechanical Engineering Science2000; 214(11): 1331–1338.
11.
MishraSKMishraSR. Wavelet based identification of dominant scales for self-affine road roughness in context of riding comfort in vehicles. Geotech Geol Engng2009; 27: 473–484.
12.
FalknerAReinalterW. Einfluss fahrbahnerregter Schwingungen auf Lastkollektiv, Bauraum und Fahrkomfort. ATZ – Automobiltechnische Z2005; 107(6): 514–520.
13.
LouisAKMaassPRiederA. Wavelets – theory and applications. New York: John Wiley, 1997.
14.
DahlkeSMaassP. The affine uncertainty principle in one and two dimensions. Comput Math Applic1995; 30(3–6): 293–305.
15.
GaborD. Theory of communication. J Instn Electl Engrs1946; 93: 429–457.
16.
GoupillaudPGrossmannAMorletJ. Cycle-octave and related transforms in seismic signal analysis. Geoexploration1984; 23(1): 85–102.
17.
ArivazhaganSGanesanLPriyalSP. Texture classification using Gabor wavelets based rotation invariant features. Pattern Recognition Lett2006; 27(16): 1976–1982.
18.
ManjunathBS. Gabor wavelet transform and application to problems in early vision. In: 26th Asilomar conference on signals, systems and computers, Pacific Grove, California, USA, 26–28 October 1992, Vol 2, pp. 796–800. New York: IEEE.
19.
ZhangDSuiW. The optimal Morlet wavelet and its application on mechanical fault detection. In: 5th international conference on wireless communications, networking and mobile computing, Beijing, People's Republic of China, 24–26 September 2009, pp. 1–4. New York: IEEE.
20.
GuyonIGunnSNikraveshMZadehLA. Feature extraction: foundations and applications (studies in fuzziness and soft computing). New York: Springer, 2006.
21.
FuhrB. Methode zur Klassifizierung von Unfallszenarien mithilfe von FE-Gesamtfahrzeugsimulationen, Wavelettransformierten und künstlichen neuronalen Netzen. Hamburg: disserta Verlag, 2012.
22.
NixonMSAguadoAS. Feature extraction and image processing. Oxford: Academic Press, 2008.
Dan ForeseeFHaganMT. Gauss–Newton approximation to Bayesian learning. In: 1997 IEEE international conference on neural networks, Houston, Texas, USA, 9–12 June 1997, Vol 3, pp. 1930–1935. New York: IEEE.
