论文信息 - A fuzzy neural network approach to model component behavior for virtual prototyping of hydraulic system

A fuzzy neural network approach to model component behavior for virtual prototyping of hydraulic system

This paper proposes a fuzzy neural network (FNN) approach to model the behavior of a hydraulic component from input-output data. The approach uses an "effect" variable, which can be used to identify the significant inputs from the input-output data. The variations of the "effects" of the significant inputs are used to determine the number of fuzzy rules and the structure of the network. The proposed approach can be used to effectively map the input to output behavior of a hydraulic pressure control system. This is useful for virtual prototyping of fluid power systems.

Fook Fah Yap | Wei Xiang | Sai Cheong Fok

[1] Greg Schoenau,et al. Neural networks and hydraulic control—from simple to complex applications , 1999 .

[2] Yinghua Lin,et al. Using fuzzy partitions to create fuzzy systems from input-output data and set the initial weights in a fuzzy neural network , 1997, IEEE Trans. Fuzzy Syst..

[3] J Watton,et al. A Self-Organizing Neural Network Approach to Data-Based Modelling of Fluid Power Systems Dynamics Using the GMDH Algorithm , 1995 .