Machine-Learning Based Optimal Seismic Control of Structure with Active Mass Damper
In recent years, optimal control which minimizes a cost function formulated by weighted states and control inputs has been applied to the seismic control of structures. Optimal control requires structural states which may not be available in real application; therefore, state estimation is essential...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/15/5342 |
| _version_ | 1797560478954684416 |
|---|---|
| author | Pei-Ching Chen Kai-Yi Chien |
| author_facet | Pei-Ching Chen Kai-Yi Chien |
| author_sort | Pei-Ching Chen |
| collection | DOAJ |
| description | In recent years, optimal control which minimizes a cost function formulated by weighted states and control inputs has been applied to the seismic control of structures. Optimal control requires structural states which may not be available in real application; therefore, state estimation is essential, which inevitably takes additional computation time. However, time delay and state estimate error could affect the control performance. In this study, a multilayer perceptron (MLP) model and an autoregressive with exogenous inputs (ARX) model in machine learning are applied to learn the control force generated from a linear-quadratic regulator (LQR) with weighting matrices optimized by applying symbiotic organisms search algorithm. A 10-story building is adopted as a benchmark model for training and validation of the MLP and ARX models. Numerical simulation results demonstrate that the MLP and ARX models are able to emulate the LQR control force from the acceleration response directly, indicating that state estimation is not essential for optimal control implementation in real application. Finally, the machine-learning based approach is experimentally validated by conducting shake table testing in the laboratory in which the structural model is controlled by an active mass damper. The experimental results and structural control performance of the MLP and ARX models are compared with those of the LQR with a Kalman filter. |
| first_indexed | 2024-03-10T18:01:06Z |
| format | Article |
| id | doaj.art-86f4c664c2fd43f9877dd3cb83958acd |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T18:01:06Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-86f4c664c2fd43f9877dd3cb83958acd2023-11-20T08:52:37ZengMDPI AGApplied Sciences2076-34172020-08-011015534210.3390/app10155342Machine-Learning Based Optimal Seismic Control of Structure with Active Mass DamperPei-Ching Chen0Kai-Yi Chien1Department of Civil and Construction Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanDepartment of Civil and Construction Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanIn recent years, optimal control which minimizes a cost function formulated by weighted states and control inputs has been applied to the seismic control of structures. Optimal control requires structural states which may not be available in real application; therefore, state estimation is essential, which inevitably takes additional computation time. However, time delay and state estimate error could affect the control performance. In this study, a multilayer perceptron (MLP) model and an autoregressive with exogenous inputs (ARX) model in machine learning are applied to learn the control force generated from a linear-quadratic regulator (LQR) with weighting matrices optimized by applying symbiotic organisms search algorithm. A 10-story building is adopted as a benchmark model for training and validation of the MLP and ARX models. Numerical simulation results demonstrate that the MLP and ARX models are able to emulate the LQR control force from the acceleration response directly, indicating that state estimation is not essential for optimal control implementation in real application. Finally, the machine-learning based approach is experimentally validated by conducting shake table testing in the laboratory in which the structural model is controlled by an active mass damper. The experimental results and structural control performance of the MLP and ARX models are compared with those of the LQR with a Kalman filter.https://www.mdpi.com/2076-3417/10/15/5342machine learningmultilayer perceptronautoregressive neural networkoptimal controlactive mass damperseismic performance |
| spellingShingle | Pei-Ching Chen Kai-Yi Chien Machine-Learning Based Optimal Seismic Control of Structure with Active Mass Damper Applied Sciences machine learning multilayer perceptron autoregressive neural network optimal control active mass damper seismic performance |
| title | Machine-Learning Based Optimal Seismic Control of Structure with Active Mass Damper |
| title_full | Machine-Learning Based Optimal Seismic Control of Structure with Active Mass Damper |
| title_fullStr | Machine-Learning Based Optimal Seismic Control of Structure with Active Mass Damper |
| title_full_unstemmed | Machine-Learning Based Optimal Seismic Control of Structure with Active Mass Damper |
| title_short | Machine-Learning Based Optimal Seismic Control of Structure with Active Mass Damper |
| title_sort | machine learning based optimal seismic control of structure with active mass damper |
| topic | machine learning multilayer perceptron autoregressive neural network optimal control active mass damper seismic performance |
| url | https://www.mdpi.com/2076-3417/10/15/5342 |
| work_keys_str_mv | AT peichingchen machinelearningbasedoptimalseismiccontrolofstructurewithactivemassdamper AT kaiyichien machinelearningbasedoptimalseismiccontrolofstructurewithactivemassdamper |