Backstepping Control for Flexible Joint with Friction Using Wavelet Neural Networks and L₂‐Gain Approach

Abstract

In this study, a new backstepping control scheme is proposed to deal with the high accuracy flexible joint servo system's position control. Based on the introduction of non‐consecutive friction, the cascade dynamics equations of flexible joint are established. The macroscopic controller is designed using a backstepping design technique to suppress the flexibility and external disturbance based on the L2 property. To identify the non‐consecutive function, the wavelet neural networks (WNN) are utilized in the microscopic controller to compensate for nonlinear friction and uncertainties. The combined strategy of macro and micro controller can overcome the derivation explosion problem and avoid the joint acceleration measurement and upper bound forecast. Finally, stability analysis and mathematical simulations are presented to verify the effectiveness of this new controller.

A sliding mode control and artificial neural network based MPPT for a direct grid‐connected photovoltaic source

“…Nowadays, artificial neural networks are attracting growing interest. They are applied in various fields without requiring detailed information on the system operation and they establish the relationship between input and output variables by analyzing the training database . They provide a soft computing algorithm for complex nonlinear problems and can avoid the fail of the conventional techniques to track variations under fast varying conditions .…”

Adaptive Chattering Free Neural Network Based Sliding Mode Control for Trajectory Tracking of Redundant Parallel Manipulators

“…Recently, computational intelligence related approaches have been widely employed for control, such as fuzzy systems [16][17][18][19][20][21], neural networks [22][23][24][25], neurofuzzy systems [26,27], or radial basis function neural networks (in short, RBFN or RBFNN) [28][29][30]. Some researchers have tried to employ these adaptive networks in sliding mode controllers.…”

Sliding Mode Differentiator Based Tracking Control of Uncertain Nonlinear Systems with Application to Hypersonic Flight

“…Back-stepping is a powerful tool to design controllers for nonlinear systems with certain specific structures [1][2][3][4][5]. For example, back-stepping design has been widely applied in actuator and manipulator control [5][6][7], and in the field of hypersonic flight control [8][9][10].…”