Bilinear realization from input-output data with neural networks

2022/08/22 by Karachalios, Dimitrios S., Gosea, Ion Victor, Kour, Kirandeep +1
#34H05 #37N35 #49J15 #Dynamical Systems (math.DS) #FOS: Mathematics

paper · doi:10.48550/arxiv.2208.10124

Abstract

We present a method that connects a well-established nonlinear (bilinear) identification method from time-domain data with neural network (NNs) advantages. The main challenge for fitting bilinear systems is the accurate recovery of the corresponding Markov parameters from the input and output measurements. Afterward, a realization algorithm similar to that proposed by Isidori can be employed. The novel step is that NNs are used here as a surrogate data simulator to construct input-output (i/o) data sequences. Then, classical realization theory is used to build a bilinear interpretable model that can further optimize engineering processes via robust simulations and control design.

Related

• Bilinear residual Neural Network for the identification and forecasting of dynamical systems
• Identification of Continuous-Time Dynamical Systems: Neural Network\n Based Algorithms and Parallel Implementation
• Finite Sample Identification of Partially Observed Bilinear Dynamical Systems
• Identification For Control Based on Neural Networks: Approximately Linearizable Models
• Input Classes for Identification of Bilinear Systems