Online Parameter Estimation of Hydraulic System Based on Stochastic Gradient Descent

Takashi Yamada, Matthew Howard

Research output: Contribution to journalConference paperpeer-review

43 Downloads (Pure)

Abstract

In this paper, offline and online parameter estimation
methods for hydraulic systems based on stochastic gradient
descent are presented. In contrast to conventional approaches,
the proposed methods can estimate any parameter in
mathematical models based on multi-step prediction error.
These advantages are achieved by calculating the gradient of
the multi-step error against the estimated parameters using
Lagrange multipliers and the calculus of variations, and
by forming differentiable models of hydraulic systems. In
experiments on a physical hydraulic system, the proposed
methods with three different gradient decent methods (normal
gradient descent, Nesterov’s Accelerated Gradient (NAG), and
Adam) are compared with conventional least squares. In the
offline experiment, the proposed method with NAG achieves
estimation error about 95% lower than that of least squares.
In online estimation, the proposed method with NAG produces
predictive models with about 20% lower error than that of the
offline method. These results suggest the proposed method is a
practical alternative to more conventional parameter estimation
methods.
Original languageEnglish
JournalBath/ASME symposium on fluid power and motion control
Publication statusAccepted/In press - 11 Jun 2020

Fingerprint

Dive into the research topics of 'Online Parameter Estimation of Hydraulic System Based on Stochastic Gradient Descent'. Together they form a unique fingerprint.

Cite this