Neural network based nonlinear observers

Nonlinear observers based on the well-known concept of minimum energy estimation are discussed. The approach relies on an output injection operator determined by a Hamilton-Jacobi-Bellman equation whose solution is subsequently approximated by a neural network. A suitable optimization problem allowing to learn the network parameters is proposed and numerically investigated for linear and nonlinear oscillators. (C) 2020 Elsevier B.V. All rights reserved.

Automated summary

Nonlinear observers based on the minimum energy estimation concept are discussed, with an output injection operator approximated by a neural network. An optimization problem is proposed to learn the network parameters and numerically investigate linear and nonlinear oscillators.