For a semi-active suspension design it is important to determine the control law which can achieve good performance both in ride and handling quality. Because of its superiority in non-linear control systems and capability of learning on-line, the fuzzy neural network (FNN) control scheme is proposed for a semi-active suspension system with dynamic absorber. It is employed for a quarter vehicle model which is described by a non-linear system with three degrees of freedom and being subjected to irregular excitations from a road surface. The on-line learning of FNN optimising a fuzzy inference system is presented. Four kinds of methods, passive suspension with and without dynamic absorber, respectively, and semi-active suspension using fuzzy control and FNN control, respectively, are investigated and compared by computer simulation. It is indicated that the semi-active suspension system employing the proposed FNN control strategy is more effective in improving the performance of the vehicle compared to the other methods and it is also shown how the addition of a dynamic absorber reduces the excessive vibration of the wheel mass by a great amount.
Fuzzy neural networks control of a semi-active suspension system with dynamic absorber
Neuronales Netzwerk mit Fuzzy-Regelung für eine halbaktive Fahrwerksaufhängung mit dynamischer Stoßdämpfung
2000
8 Seiten, 10 Bilder, 1 Tabelle, 13 Quellen
Conference paper
English
Fuzzy neural networks control of a semi-active suspension system with dynamic absorber
Automotive engineering | 2000
|Fuzzy Neural Networks Control of A Semi-active Suspension System with Dynamic Absorber
SAE Technical Papers | 2000
|2000-01-3077 Fuzzy Neural Networks Control of a Semi-Active Suspension System with Dynamic Absorber
British Library Conference Proceedings | 2000
|Semi-Active Control of ISD In-Wheel Motors Suspension with Dynamic Vibration Absorber
SAE Technical Papers | 2022
|Semi-Active Control of ISD In-Wheel Motors Suspension with Dynamic Vibration Absorber
British Library Conference Proceedings | 2022
|