A constrained optimization approach to nonlinear system identification through simulation error minimization

This paper proposes a novel approach to system identification for nonlinear input-output models by minimizing the simulation error and formulating it as a constrained optimization problem. This method addresses vanishing gradient issues, enabling faster convergence than traditional gradient-based methods. We present an algorithm that utilizes feedback-linearization controlled multipliers optimization and provide a theoretical analysis of its performance. We prove that the algorithm converges to a local minimum, and we optimize the computational efficiency by leveraging the problem structure. Numerical experiments illustrate that our approach outperforms gradient-based methods in computational effort and accuracy.