Structure-and Parameter Identification for a Two-Mass-System With Backlash and Friction Using a Self-Organizing Map

A self-commissioning system for high performance speed and position control of electrical drives requires a structure and parameter identification of a nonlinear mechanic as basic building block. This self-commisioning system in combination with a new identification scheme is presented here. The identification is based on extraction of characteristic features from the system response and evaluation of these features by self-organizing neural network, especially the self-organizing feature map (SOM).

[1]  Ulrich Rückert,et al.  System identification using selforganizing feature maps , 1997 .

[2]  F. Schutte,et al.  Online identification of mechanical parameters using extended Kalman filters , 1997, IAS '97. Conference Record of the 1997 IEEE Industry Applications Conference Thirty-Second IAS Annual Meeting.

[3]  H. Wertz,et al.  Comparison of parameter identification schemes for self-commissioning drive control of nonlinear two-mass systems , 1997, IAS '97. Conference Record of the 1997 IEEE Industry Applications Conference Thirty-Second IAS Annual Meeting.

[4]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[5]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .