Simulation of the Behavior of Disc-Spring Valve Systems with the Fuzzy Inference Systems and Artificial Neural Networks
This paper proposes an analytical tool that supports the design process of a hydraulic damper valve system. The analytical tool combines Artificial Neural Networks (ANNs) and Fuzzy Inference Systems (FIS) into one tool called, in the paper, the Approximation Tool. The proposed Approximation Tool obtains a key design characteristic of a valve, which is the flow rate, and the corresponding maximum stress level in the valve components, as a function of a pressure load. The cases required to prepare the Approximation Tool were produced by a first-principle model using a finite element approach. The model was calibrated based on experimental results to provide accurate results in the entire range of input parameters. The paper describes the proposal, implementation, validation and an example of applying the Approximation Tool that allows the replacement of complex high- fidelity Finite Element analyses. As an approximator the Feed Forward Neural Network and FIS were taken.
KeywordsFuzzy Inference System Shock Absorber Valve System Approximation Tool Maximum Stress Level
Unable to display preview. Download preview PDF.
- 1.Burczynski, T., Orantek, P., Skrobol, A.: Fuzzy-neural and evolutionary computation in identification of defect. Journal of Theoretical and Applied Mechanics 42(3), 445–460 (2004)Google Scholar
- 2.Burczynski, T., Skrobol, A.: Coupled evolutionary algorithm and artificial neural network in defects identification. In: Bathe, K.J. (ed.) Third MIT Conf. on Computational Fluid and Solid Mechanics, pp. 122–1226 (2005)Google Scholar
- 3.Czop, P., Slawik, D., Sliwa, P., Wszolek, G.: Circular plater theory applied to modeling of intake valves used in shock absorbers. Journal of Achievements in Materials and Manufacturing Engineering 33(2), 173–180 (2009)Google Scholar
- 5.Dassault Systemes: Isight 3.5. Getting started guide (2009), http://www.simulia.com
- 7.Kosinski, W., Weigl, M.: Fuzzy-neural systems for multivariate approximation problems. In: Proceeding of 6rd Zittau Fuzzy Colloquium, Zittau, pp. 141–146 (1998)Google Scholar
- 8.Math-Works Inc.: Matlab-Simulink documentation (2011), http://www.mathworks.com/help
- 9.Piatkowski, G., Ziemianski, L.: Neural network identification of a circular hole in the rectangular plate. In: Rutkowski, L., Kacprzyk, J. (eds.) Neural Networks and Soft Computing, pp. 778–783. Physica-Verlag Springer, Heidelberg (2003)Google Scholar
- 10.Rutkowska, D.: Computational intelligent systems. Akademicka Oficyna Wydawnicza PLJ, Warszawa (1997)Google Scholar
- 12.Van der Velden, A., Koch, P.: Isight design optimisation methodologies (2009), http://www.simulia.com
- 13.Van Kasteel, R., et al.: A new shock absorber model with an application in vehicle dynamics studies. In: 2003 SAE International Truck and Bus Meeting and Exhibition, Fort Worth, Texas (2003)Google Scholar
- 14.Young, W.C.: Roark’s formulas for stress and strain. McGraw-Hill, New York (2003)Google Scholar