A RBFNN-Based Adaptive Disturbance Compensation Approach Applied to Magnetic Suspension Inertially Stabilized Platform

Abstract

Compared with traditional mechanical inertially stabilized platform (ISP), magnetic suspension ISP (MSISP) can absorb high frequency vibrations via a magnetic suspension bearing system with five degrees of freedom between azimuth and pitch gimbals. However, force acting between rotor and stator will introduce coupling torque to roll and pitch gimbals. Since the disturbance of magnetic bearings has strong nonlinearity, classic state feedback control algorithm cannot bring higher precision control for MSISP. In order to enhance the control accuracy for MSISP, a disturbance compensator based on radial basis function neural network (RBFNN) is developed to compensate for the disturbance. Using the Lyapunov theorem, the weighting matrix of RBFNN can be updated online. Therefore, the RBFNN can be constructed without priori training. At last, simulations and experiment results validate that the compensation method proposed in this paper can improve ISP accuracy significantly.

Coupling Analysis and Cross-Feedback Control of Three-Axis Inertially Stabilized Platform with an Active Magnetic Bearing System

“…e angular displacement of each gimbal is the feedback signal to realize closed-loop control about attitude of three-axis ISP, and then the attitude stabilization precision of three gimbals would be kept at balanced state. Moreover, the function of compensation module of base coupling in the red dotted-line diagram of Figure 10 is to compensate the base coupling torques T b p in (15), T b r in (17), and T b y in (19). e angular rates of three gimbals and the base plate are used as the feedback signal to compute the compensation terms for minimizing the base coupling torques.…”

“…In addition, the disturbances could be transferred from the pitch and roll gimbals to the yaw gimbal such that the attitude stabilization precision of yaw gimbal is reduced [12][13][14]. erefore, in order to suppress the vibration acting on yaw gimbal, an active magnetic bearing (AMB) [15][16][17] system was designed for suspending the yaw gimbal in three-axis ISP. Since the AMB system provides a contactless suspension to yaw gimbal, the vibration disturbances from other gimbals could be effectively isolated, and the friction between levitated gimbal and suspension elements would be minimized [18].…”

A Novel Separated Position and Orientation System Integrated with Inertially Stabilized Platform

“…In the centralized POS, extra angular rate gyros are mounted on roll, pitch, and azimuth gimbals of the ISP system, respectively, to achieve feed forward control [9][10][11], such as Swiss Leica PAV80 and PVA100, in which the centralized POS is assembled inside the camera and additional piezoelectric gyros are located at three gimbals [12]. However, BUAA fixes the centralized POS on the shell of camera; meanwhile, the open-loop fiber optic gyros (or MEMS gyros) and quartz accelerometers are installed on each gimbal for rate feedback and initial leveling [13,14].…”

An Adaptive B-Spline Neural Network and Its Application in Terminal Sliding Mode Control for a Mobile Satcom Antenna Inertially Stabilized Platform

“…Therefore, this method offers low control accuracy and robustness. A feedforward scheme for a two axis inertial stabilized platform (ISP) was adopted to reject the periodic disturbing torque acting on the payload due to the static mass unbalance [9,10], but the accelerometer signal may be easily distorted by the centripetal acceleration [11]. The H ∞ control method presents strong robustness, but it is highly conservative and the control accuracy is usually sacrificed [12].…”