Using neural networks to model an electromagnetic-actuated microactuator

Abstract

We present the use of artificial neural networks ͑ANNs͒ to model an electromagnetic microelectromechanical system ͑MEMS͒ microactuator. It is inherently complex and time consuming to model/ predict the response of an electromagnetic microactuator numerically by finite element analysis, particularly when it is actuated by a pulse of current in media with different properties ͑e.g., air, water, and diluted methanol͒. ANNs are used to model the maximum displacement ͑d max ͒ of the microactuator for a range of burst frequencies ͑f b ͒ and input currents ͑I coil ͒, as well as different mechanical designs and actuation media. The prediction errors of the ANN model in normal and pressurized air are Ͻ13 and Ͻ2%, respectively. The prediction error for the same response in water or 50% diluted methanol in water is Ͻ10%.

Analytical evaluation of magnetic field by planar micro-electromagnet spirals for MEMS applications

“…These values are identical to the computed values of B z (and close to the measured magnetic field) at the points z = 10 mm, 14 mm, 18 mm and 22 mm on the z axis with the electromagnetic spiral of figure 2(a) (i.e., the macro-scale spiral). This corroborates to the scaling argument drawn from equation (11). Along the z axis the x and y components of the field are zero, and hence | B| = B z .…”

“…To eliminate power consumption and to improve the magnetic force, micro inductor integrated with magnetic permalloy, namely a microelectromagnet [7,8], has been proposed to successfully separate magnetic beads [9], and also for microfluidics application to build microvalve [10] and microactuators [11].…”