Analysis of the torque characteristic of a magnetorheological clutch using neural networks. (April 2015)

• Record Type: Journal Article
• Authors: Bucchi, F; Forte, P; Frendo, F
• Other Names: Dragoni Eugenio guest-editor.; Kiefer Bjoern guest-editor.; Koo Jeong-Hoi guest-editor.
• Is Part Of: Journal of intelligent material systems and structures. Volume 26:Number 6(2015:Apr.)
• Page Start: 680
• Page End: 689
• Publication Date: 2015-04
• Subjects: Magnetorheological clutch -- neural networks -- experimental characteristics -- automotives; Smart materials -- Periodicals; Intelligent control systems -- Periodicals; Artificial intelligence -- Periodicals; Matériaux intelligents -- Périodiques; Commande intelligente -- Périodiques; Intelligence artificielle -- Périodiques; 620.11
• DOI: 10.1177/1045389X14546654
• Languages: English
• ISSNs: 1045-389X

Abstract

In this paper the dependence of the torque characteristic of a magnetorheological clutch on several working parameters is analyzed by means of a feedforward neural network. The clutch was envisaged to have the possibility to disengage the vacuum pump in diesel engine vehicles, in order to increase the overall vehicle efficiency. A large set of test was carried out following different protocols in order to obtain a detailed characterization of the clutch. Results showed that, due to the characteristics of MR fluids and to the complex mechanism of torque transmission, the torque characteristics (both the yield torque and the torque-slip behavior) are a function of the relative speed between the input and output shafts, of the energy dissipated during the clutch slip and of the rest time between consecutive slippages. The data acquired during all tests were used to train a neural network with five input elements and one output element. The developed neural network proved to satisfactorily reproduce the actual clutch properties and could be used in the future in an engine-vehicle simulator in order to model the torque characteristic of the clutch subjected to different operating cycles.