Accurate Shock Absorber Load Modeling in an All Terrain Vehicle using Black Box Neural Network Techniques
暂无分享,去创建一个
This paper presents the results of a study of using a neural network black box model of a shock absorber of an ATV (All Terrain Vehicle, four wheel drive, off road, single person vehicle) for accurate load modeling. This study is part of a larger investigation into the dynamic behavior and associated fatigue of an ATV vehicle, which is conducted under the auspices of the Fatigue Design and Evaluation Committee of SAE of North America (www.fatigue.org). The general objectives are to develop new correlated methodologies that will allow engineers to predict the durability of components of proposed vehicles by means of a "digital prototype" simulation. Current state of the art multi body dynamics predictions use linear frequency response functions or non-linear polynomial approximations to describe the behavior of non-linear suspension components such as shock absorbers or bushings. The proposed method yields more accurate predictions due to the fact that both the non-linear and hysteretic behavior of the shock absorber are modeled. This paper demonstrates how neural network black box technologies, particularly in the form of the Empirical Dynamics Models, can be used for accurate prediction of shock absorber loads encountered by a vehicle and the potential improvement in fatigue life predictions under this approach. INTRODUCTION A number of technologies exist today to predict analytically the durability of automotive structures (components, systems and full vehicles) prior to building actual physical specimen. To improve the predictive capabilities the Fatigue Design and Evaluation (FD&E) Committee of the Society of Automotive Engineers (SAE) of North America has elected to investigate what technologies are available today and aid the engineering community in developing improved methods for predicting fatigue life of complex structures [1]. To support this project, the authors of this paper present the study of neural network black box modeling for accurate load description of components under complex loading. The technique employed can be used to predict the behavior of a variety of dynamically loaded components with inherent complex behavior. In particular, the response behavior of a shock absorber under random loading is predicted and compared to a measured response and predictions achieved via currently commonly used methods. FATIGUE DESIGN AND EVALUATION COMMITTEE (FD&E) OF THE SAE – The FD&E committee is dedicated to improve the understanding of fatigue processes in materials and engineering structures. The committee meets twice per year in different locations and also hosts a special session during the annual SAE World Congress in Detroit. The committee consists of members from academia, research institutes and industry and is open to the public. Contributions to projects are made through monetary and labor donations. All results are placed in the public domain. Past contributions in the field of fatigue prediction have been published by the committee through a series of handbooks and conference proceedings, e.g. [2], [3] and [4]. Under it’s latest effort the committee has elected to advance the state of the art in predicting the fatigue life of structural components and systems through an
[1] E. W. C. Wilkins,et al. Cumulative damage in fatigue , 1956 .
[2] K. Bowman. Mechanical Behavior of Materials , 2003 .
[3] K. Chawla,et al. Mechanical Behavior of Materials , 1998 .
[4] Russell A. Chernenkoff,et al. Recent developments in fatigue technology , 1997 .
[5] Andrew J. Barber. Accurate models for complex vehicle components using empirical methods , 2000 .
[6] Richard C. Rice,et al. Fatigue design handbook , 1988 .