Comparison of Deep Learning and Deterministic Algorithms for Control Modeling

TL;DR

This paper compares physics-informed neural networks (PINN) with traditional control methods for nonlinear system control, highlighting their performance, limitations, and computational costs in modeling the van der Pol oscillator.

Contribution

It provides a comprehensive comparison between PINN and classical control algorithms for nonlinear dynamics, emphasizing their effectiveness, failure modes, and computational requirements.

Findings

PINN achieves lower relative errors for certain trajectories.

Feedforward control successfully converges to desired trajectories.

PINN requires significantly more computational time than traditional methods.

Abstract

Controlling nonlinear dynamics arise in various engineering fields. We present efforts to model the forced van der Pol system control using physics-informed neural networks (PINN) compared to benchmark methods, including idealized nonlinear feedforward (FF) control, linearized feedback control (FB), and feedforward-plus-feedback combined (C). The aim is to implement circular trajectories in the state space of the van der Pol system. A designed benchmark problem is used for testing the behavioral differences of the disparate controllers and then investigating controlled schemes and systems of various extents of nonlinearities. All methods exhibit a short initialization accompanying arbitrary initialization points. FF control successfully converges to the desired trajectory, and PINN executes good controls with higher stochasticity observed for higher-order terms based on the phase portraits. In contrast, combined control failed. Varying trajectory amplitudes revealed that FF, FB, and combined control all fail for unity nonlinear damping gain. Traditional control methods display a robust fluctuation for higher-order terms. For some various nonlinearities, PINN failed to implement the desired trajectory instead of becoming "trapped" in the phase of a small radius, yet FB successfully implemented controls. PINN generally exhibits lower relative errors for varying targeted trajectories. However, PINN also shows evidently higher computational burden compared with traditional control theory methods, with at least more than 30 times longer control time compared with benchmark idealized nonlinear feed-forward control. This manuscript proposes a comprehensive comparative study for future controller employment considering deterministic and machine learning approaches.