Real-time neural network based semiactive model predictive control of structural vibrations. (15th January 2023)

• Record Type: Journal Article
• Authors: Yu, Tianhao; Mu, Zeyu; Johnson, Erik A.
• Is Part Of: Computers & structures. Volume 275(2023)
• Publication Date: 2023-01-15
• Subjects: Model predictive control -- Neural network -- Real-time control -- Semiactive control; Structural engineering -- Data processing -- Periodicals; Electronic data processing -- Structures, Theory of -- Periodicals; 624.171
• DOI: 10.1016/j.compstruc.2022.106899
• Languages: English
• ISSNs: 0045-7949

Abstract

Highlights: Proposes a computationally efficient semiactive model predictive control algorithm. Uses neural networks to predict online the integer variables at optimality. Adapts fast model algorithm to solve the resulting quadratic programming optimization. Proposes novel sampling approaches and codewords for tractably small neural networks. Demonstrates performance comparable to conventional approach but 10 times faster. Abstract: Semiactive model predictive control (sMPC) can be very effective, but its computational cost due to the inherent mixed-integer quadratic programming (MIQP) optimization precludes its use in real-time vibration control. This study proposes training neural networks (NNs) to predict in real-time only the MIQP's integer variables' values, called a strategy, for a given structure state. Because the number of strategies is exponential in the number of sMPC horizon steps, the resulting NN can be massive. This study proposes to reduce the NN dimension by exploiting the homogeneity-of-order-one nature of this control problem and, using state vector statistics, to efficiently choose training samples. The single large NN is proposed to be split into several much smaller NNs, each predicting a strategy grouping, that together uniquely and efficiently predict the strategy. Given the strategy's integer values, the MIQP optimization reduces to a quadratic programming (QP) problem, solved using a fast QP solver with proposed adaptations: exploiting optimization efficiencies and bounding sub-optimality; using several NN predictions; and reverting to a simpler (suboptimal) semiactive control algorithm upon occasional incorrect NN predictions or QP solver nonconvergence. Shear building examples demonstrate significant online computational cost reductions with control performance comparable to the conventional MIQP-based control.