Pressure prediction on a variable-speed pump controlled hydraulic system using structured recurrent neural networks


KILIÇ E., DÖLEN M., ÇALIŞKAN H., KOKU A. B., Balkan T.

CONTROL ENGINEERING PRACTICE, vol.26, pp.51-71, 2014 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 26
  • Publication Date: 2014
  • Doi Number: 10.1016/j.conengprac.2014.01.008
  • Journal Name: CONTROL ENGINEERING PRACTICE
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.51-71
  • Keywords: Pump controlled hydraulic system, Pressure dynamics, Long-term pressure prediction, Structured recurrent neural networks, Nonlinear system identification, Kalman filtering, IDENTIFICATION, BLACK
  • Middle East Technical University Affiliated: Yes

Abstract

This paper presents a study to predict the pressures in the cylinder chambers of a variable-speed pump controlled hydraulic system using structured recurrent neural network topologies where the rotational speed of the pumps, the position and the average velocity of the hydraulic actuator are used as their inputs. The paper elaborates the properties of such networks in extended time periods through detailed simulation- and experimental studies where black-box modeling approaches generally fail to yield acceptable performance. As alternative estimation techniques, both linear- and extended Kalman filters are considered in this paper. The estimation properties of the devised network models are comparatively evaluated and their potential application areas are discussed in detail. (C) 2014 Elsevier Ltd. All rights reserved.