VIBRATION CONTROL OF STRUCTURE USING CMAC ICSSD 2000 VIBRATION CONTROL OF STRUCTURE USING CMAC * Dong-Hyawn Kim: Postdoctoral Researcher, KAIST Kyu-Hong Shim: Postdoctoral Researcher, KAIST In-Won Lee: Professor, KAIST Jong-Heon Lee: Professor, Kyungil University
CONTENTS 1 INTRODUCTION 2 CMAC* FOR VIBRATION CONTROL 3 NUMERICAL EXAMPLES 4 CONCLUSIONS *Cerebellar Model Articulation Controller Structural Dynamics & Vibration Control Lab., KAIST, Korea
1 INTRODUCTION Background Features of neural network control mathematical model is not required in designing controller Application areas - control of structures with uncertainty or nonlinearity Structural Dynamics & Vibration Control Lab., KAIST, Korea
Structural control using neural network external load neural network structure response sensor Structural Dynamics & Vibration Control Lab., KAIST, Korea
Multilayer Neural Network (MLNN) Wij control force state of structure (displacement) (velocity) Wij : weights Structural Dynamics & Vibration Control Lab., KAIST, Korea
Previous studies 1) H. M. Chen et al. (1995). ASCE J. Comp. in Civil Eng. 2) J. Ghaboussi et al. (1995). ASCE J. Eng. Mech. 3) K. Nikzad et al. (1996). ASCE J. Eng. Mech. 4) K. Bani-Hani et al. (1998). ASCE J. Eng. Mech. 5) J. T. Kim et al. (2000). ASCE J. Eng. Mech. - All methods are based on multilayer neural network, whose learning speed is too slow Structural Dynamics & Vibration Control Lab., KAIST, Korea
Objective and Scope To reduce learning time, we apply CMAC* neural network for structural control *Cerebellar Model Articulation Controller Structural Dynamics & Vibration Control Lab., KAIST, Korea
2 CMAC FOR VIBRATION CONTROL CMAC - proposed by J. S. Albus(1975) - a neural network with fast learning speed - mainly used for manipulator control Structural Dynamics & Vibration Control Lab., KAIST, Korea
Procedure of CMAC memory space input space output space x u W1 W2 u displacement velocity Wn-1 control signal Wn weights Structural Dynamics & Vibration Control Lab., KAIST, Korea
Output calculation (1) x1 input x layer 1 layer 2 layer 3 layer 4 W11 W12 W13 W14 W21 W22 W23 W24 W31 W32 W33 W34 W41 W42 W43 W44 output W12+W22+W32+W42 Structural Dynamics & Vibration Control Lab., KAIST, Korea
Output calculation (2) x1 x2 input x layer 1 layer 2 layer 3 layer 4 W11 W12 W13 W14 W21 W22 W23 W24 W31 W32 W33 W34 W41 W42 W43 W44 output W13+W23+W32+W42 Structural Dynamics & Vibration Control Lab., KAIST, Korea
CMAC vs. MLNN items CMAC MLNN memory size Large Small computing mode Local Global learning speed Fast Slow real-time application Feasible Impossible Structural Dynamics & Vibration Control Lab., KAIST, Korea
Vibration Control using CMAC learning rule external load structure response CMAC sensor Structural Dynamics & Vibration Control Lab., KAIST, Korea
Control criterion: cost function (1) : state vector : control vector : relative weighting matrix : time step : final time step Structural Dynamics & Vibration Control Lab., KAIST, Korea
Learning rule proposed method (2) (3) (4) : learning rate (5) Structural Dynamics & Vibration Control Lab., KAIST, Korea
3. NUMERICAL EXAMPLES Model structure Structural Dynamics & Vibration Control Lab., KAIST, Korea
Equation of motion (6) : displacement vector : ground acceleration : control force : Mass matrix : Damping matrix : Restoring force : Location vector Structural Dynamics & Vibration Control Lab., KAIST, Korea
Nonlinear restoring force (Bouc-Wen, 1981) (7) (8) : linear stiffness : contribution of k0 : constants Structural Dynamics & Vibration Control Lab., KAIST, Korea
Effect of parameters Structural Dynamics & Vibration Control Lab., KAIST, Korea
Active Mass Driver (AMD) pump mass piston Structural Dynamics & Vibration Control Lab., KAIST, Korea
Parameters Structure AMD mass : 200 kg (story) stiffness : 2.25105 N/m (inter-story) damping ratios : 0.6, 0.7, 0.3% (modal) AMD mass : 18 kg (3% of building total mass) stiffness : 3.71103 N/m damping ratio : 8.65% Structural Dynamics & Vibration Control Lab., KAIST, Korea
CMAC structure input: 2 (disp., vel. of 3rd floor) output: 1 (control signal) no. of divisions: 3 per variable no. of layers: 200 no. of weights: 1800 Structural Dynamics & Vibration Control Lab., KAIST, Korea
Simulation integration time: 0.25 ms sampling time: 5.0 ms delay time: 0.5 ms Structural Dynamics & Vibration Control Lab., KAIST, Korea
Case studies model linear nonlinear earthquake simulation El Centro train El Centro control Northridge control Kern County control El Centro train El Centro control Northridge control Kern County control Structural Dynamics & Vibration Control Lab., KAIST, Korea
Linear cases (=1.0) training under El Centro earthquake CMAC MLNN ※1 Epoch = 0.005 s × 2000 steps Structural Dynamics & Vibration Control Lab., KAIST, Korea
Training results Jmin epoch neural network MLNN 1.77 10-2 412 CMAC 1.77 10-2 412 (1.00) (1.00) 1.94 10-2 65 (1.09) (0.15) Structural Dynamics & Vibration Control Lab., KAIST, Korea
El Centro earthquake (3rd floor) w/o control w/ control Displacement (m) Velocity(m/sec) Time (sec) Structural Dynamics & Vibration Control Lab., KAIST, Korea
El Centro earthquake (3rd floor) - continued w/o control w/ control Acceleration (m/sec2) Time (sec) Structural Dynamics & Vibration Control Lab., KAIST, Korea
Northridge earthquake (3rd floor) w/o control w/ control Displacement (m) Velocity(m/sec) Time (sec) Structural Dynamics & Vibration Control Lab., KAIST, Korea
Northridge earthquake (3rd floor) - continued w/o control w/ control Acceleration (m/sec2) Time (sec) Structural Dynamics & Vibration Control Lab., KAIST, Korea
Kern County earthquake (3rd floor) w/o control w/ control Displacement (m) Velocity(m/sec) Time (sec) Structural Dynamics & Vibration Control Lab., KAIST, Korea
Kern County earthquake (3rd floor) - continued w/o control w/ control Acceleration (m/sec2) Time (sec) Structural Dynamics & Vibration Control Lab., KAIST, Korea
Nonlinear cases (=0.5) Learning under El Centro earthquake CMAC MLNN Structural Dynamics & Vibration Control Lab., KAIST, Korea
Training results Jmin epoch neural network MLNN 1.91 10-2 427 CMAC 1.91 10-2 427 (1.00) (1.00) 2.02 10-2 34 (1.06) (0.08) Structural Dynamics & Vibration Control Lab., KAIST, Korea
El Centro earthquake (1st floor) w/o control w/ control Structural Dynamics & Vibration Control Lab., KAIST, Korea
Northridge earthquake (1st floor) w/o control w/ control Structural Dynamics & Vibration Control Lab., KAIST, Korea
Kern County earthquake (1st floor) w/o control w/ control Structural Dynamics & Vibration Control Lab., KAIST, Korea
Comparison of control results (linear, 3rd floor) El Centro MLNN CMAC Northridge Displacement (m) Kern County Time (sec) Structural Dynamics & Vibration Control Lab., KAIST, Korea
Comparison of control results (nonlinear, 3rd floor) El Centro MLNN CMAC Northridge Displacement (m) Kern County Time (sec) Structural Dynamics & Vibration Control Lab., KAIST, Korea
Maximum responses of 3rd floor (cm) w/ control CMAC MLNN Earthquake w/o control El Centro Northridge Kern County El Centro Northridge Kern County 5.01 2.06 1.65 (3.04) (1.24) (1.00) 6.15 2.14 1.38 (4.46) (1.55) (1.00) 3.42 0.97 0.72 (4.75) (1.35) (1.00) 3.48 2.54 2.34 (1.49) (1.09) (1.00) 3.94 2.20 1.63 (2.42) (1.35) (1.00) 2.68 0.97 0.80 (3.35) (1.21) (1.00) linear nonlinear Structural Dynamics & Vibration Control Lab., KAIST, Korea
4. CONCLUSIONS Learning speed of CMAC is much faster than that of MLNN. Response controlled by CMAC is slightly larger than that by MLNN. Structural Dynamics & Vibration Control Lab., KAIST, Korea
Future work Further reduction of response controlled by CMAC with fast learning speed. Structural Dynamics & Vibration Control Lab., KAIST, Korea
Thank you for your attention. Structural Dynamics & Vibration Control Lab., KAIST, Korea
Pump dynamics (9) : oil flow rate : control signal : time constant : valve gains Structural Dynamics & Vibration Control Lab., KAIST, Korea
Piston dynamics (10) : displacement of ram : area of ram : compression coefficient : volume of cylinder : leakage coefficient Structural Dynamics & Vibration Control Lab., KAIST, Korea
Sensitivity Evaluation State equation (s-1) : state vector : control force vector : system matrix : control matrix Structural Dynamics & Vibration Control Lab., KAIST, Korea
Discretized equation using ZOH : sampling time Sensitivity matrix (s-5) Structural Dynamics & Vibration Control Lab., KAIST, Korea
Computation of H (s-6) initial condition: (s-7) loading condition: measurement: Structural Dynamics & Vibration Control Lab., KAIST, Korea
Emulator minutes ~ hours Evaluation time Method Time Emulator minutes ~ hours Proposed m sampling time Structural Dynamics & Vibration Control Lab., KAIST, Korea
Convergence of learning rule Structural Dynamics & Vibration Control Lab., KAIST, Korea
Inserting (3), (4) into (2) (c-6) (c-7) (c-8) (c-9) Structural Dynamics & Vibration Control Lab., KAIST, Korea