Neural network compensation of semi-active control for magneto-rheological suspension with time delay uncertainty

• Published in: Smart materials and structures Vol. 18; no. 1; pp. 015014 - 015014 (14)
• Main Authors: Dong, XiaoMin, Yu, Miao, Li, Zushu, Liao, Changrong, Chen, Weimin
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.01.2009; Institute of Physics
• Subjects: Applied sciences; Exact sciences and technology; Machine components; Mechanical engineering. Machine design; Springs and dampers; Human; Time frequency domain method; Pavement; Highway; Frequency domain method; Shock absorbers; Neural network; Passive system; Experimental study; Modeling; Magnetorheological fluid; Uncertain system; Time domain method; Vehicle suspension; Active system; Delay time; Dynamic model; Intelligent control
• ISSN: 0964-1726; 1361-665X
• DOI: 10.1088/0964-1726/18/1/015014

This study presents a new intelligent control method, human-simulated intelligent control (HSIC) based on the sensory motor intelligent schema (SMIS), for a magneto-rheological (MR) suspension system considering the time delay uncertainty of MR dampers. After formulating the full car dynamic model featuring four MR dampers, the HSIC based on eight SMIS is derived. A neural network model is proposed to compensate for the uncertain time delay of the MR dampers. The HSIC based on SMIS is then experimentally realized for the manufactured full vehicle MR suspension system on the basis of the dSPACE platform. Its performance is evaluated and compared under various road conditions and presented in both time and frequency domains. The results show that significant gains are made in the improvement of vehicle performance. Results include a reduction of over 35% in the acceleration peak-to-peak value of a sprung mass over a bumpy road and a reduction of over 24% in the root-mean-square (RMS) sprung mass acceleration over a random road as compared to passive suspension with typical original equipment (OE) shock absorbers. In addition, the semi-active full vehicle system via HSIC based on SMIS provides better isolation than that via the original HSIC, which can avoid the effect of the time delay uncertainty of the MR dampers.