A framework for brain learning-based control of smart structures

Abstract A novel framework for intelligent structural control is proposed using reinforcement learning. In this approach, a deep neural network learns how to improve structural responses using feedback control. The effectiveness of the framework is demonstrated in a case study for a moment frame subjected to earthquake excitations. The performance of the learning method was improved by proposing a state-selector function that prevented the neural network from forgetting key states. Results show that the controller significantly improves structural responses not only to earthquake records on which it was trained but also to earthquake records new to the controller. The controller also has stable performance under environmental uncertainties. This capability distinguishes the proposed approach and makes it more appropriate for the situations in which it is likely that the controller will be exposed to unpredictable external excitations and high degrees of uncertainties.

[1]  Naresh K. Sinha,et al.  Modern Control Systems , 1981, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[3]  Alexander S. Poznyak,et al.  Differential Neural Networks for Robust Nonlinear Control: Identification, State Estimation and Trajectory Tracking , 2001 .

[4]  Botond Kádár,et al.  Reinforcement learning in a distributed market-based production control system , 2006, Adv. Eng. Informatics.

[5]  Clarence W. de Silva,et al.  Intelligent Control: Fuzzy Logic Applications , 1995 .

[6]  J. N. Yang,et al.  EFFECT OF SYSTEM UNCERTAINTY ON CONTROL OF SEISMIC-EXCITED BUILDINGS , 1990 .

[7]  Ali Zilouchian,et al.  Intelligent Control Systems Using Soft Computing Methodologies , 2000 .

[8]  Khaldoon A. Bani-Hani,et al.  NONLINEAR STRUCTURAL CONTROL USING NEURAL NETWORKS , 1998 .

[9]  M. Balas.  Direct Velocity Feedback Control of Large Space Structures , 1979 .

[10]  Zhijun Li,et al.  New discrete-time robust H2/H∞ algorithm for vibration control of smart structures using linear matrix inequalities , 2016, Eng. Appl. Artif. Intell..

[11]  Marcello Farina,et al.  Plug-and-Play Decentralized Model Predictive Control for Linear Systems , 2013, IEEE Transactions on Automatic Control.

[12]  Anna Helena Reali Costa,et al.  Optimal control of ship unloaders using reinforcement learning , 2002, Adv. Eng. Informatics.

[13]  J. Geoffrey Chase,et al.  Resettable smart dampers for multi‐level seismic hazard mitigation of steel moment frames , 2003 .

[14]  Dingli Yu,et al.  Neural network model adaptation and its application to process control , 2004, Adv. Eng. Informatics.

[15]  William S. Levine,et al.  Control System Fundamentals , 1999 .

[16]  Ben Tse,et al.  Autonomous Inverted Helicopter Flight via Reinforcement Learning , 2004, ISER.

[17]  Jim Duggan,et al.  Parallel Reinforcement Learning for Traffic Signal Control , 2015, ANT/SEIT.

[18]  Hojjat Adeli,et al.  Recent advances in control algorithms for smart structures and machines , 2017, Expert Syst. J. Knowl. Eng..

[19]  Fereidoun Amini,et al.  Neural Network for Structure Control , 1995 .

[20]  J. Geoffrey Chase,et al.  The impact of total acceleration control for semi-active earthquake hazard mitigation , 2004 .

[21]  Marco Wiering,et al.  Traffic signal optimization through discrete and continuous reinforcement learning with robustness analysis in downtown Tehran , 2018, Adv. Eng. Informatics.

[22]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[23]  S. Joe Qin,et al.  A survey of industrial model predictive control technology , 2003 .

[24]  Marco Wiering,et al.  Reinforcement Learning , 2014, Adaptation, Learning, and Optimization.

[25]  John N. Tsitsiklis,et al.  Analysis of temporal-difference learning with function approximation , 1996, NIPS 1996.

[26]  Albert J. Shih,et al.  Intelligent machine agent architecture for adaptive control optimization of manufacturing processes , 2011, Adv. Eng. Informatics.

[27]  S. O. Reza Moheimani,et al.  Vibration Control With MEMS Electrostatic Drives: A Self-Sensing Approach , 2015, IEEE Transactions on Control Systems Technology.

[28]  N. K. Chandiramani,et al.  LQR Control of Wind Excited Benchmark Building Using Variable Stiffness Tuned Mass Damper , 2014 .

[29]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[30]  Alok Madan,et al.  Vibration control of building structures using self-organizing and self-learning neural networks , 2005 .

[31]  J. Geoffrey Chase,et al.  Robust H∞ Control Considering Actuator Saturation. II: Applications , 1996 .

[32]  Ahsan Kareem,et al.  Model Predictive Control of Wind-Excited Building: Benchmark Study , 2004 .

[33]  Rudibert King,et al.  Combined Feedback–Feedforward Control of Wind Turbines Using State-Constrained Model Predictive Control , 2013, IEEE Transactions on Control Systems Technology.

[34]  Takuji Kobori,et al.  Active mass driver system as the first application of active structural control , 2001 .

[35]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[36]  J. Geoffrey Chase,et al.  Robust H∞ Control Considering Actuator Saturation. I: Theory , 1996 .

[37]  J. Geoffrey Chase,et al.  Quadratic jerk regulation and the seismic control of civil structures , 2003 .

[38]  Sundarapandian Vaidyanathan,et al.  Computational Intelligence Applications in Modeling and Control , 2015, Computational Intelligence Applications in Modeling and Control.

[39]  Jamshid Ghaboussi,et al.  Active Control of Structures Using Neural Networks , 1995 .