Disturbance observer using machine learning algorithms

Dong Ki Han, Ismi Rosyiana Fitri, Jung Su Kim

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


This paper presents a method of constructing an inverse model-based disturbance observer using two neural network methods: Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). Learning data is prepared for MLP and RNN by selecting input data such that it contains various signal shapes such as constant, step, sinusoidal and random number, and frequency components. This input data is injected into the nominal model of the system and the resulting state values are used as the measurement. The weights of MLP and RNN are optimized using these data, and how unknown disturbances are estimated is explained using the learned MLP and RNN. The simulation results show that the proposed method works well; in other words, the MLP-and RNN-based disturbance observer can reject both external disturbances and model uncertainties.

Original languageEnglish
Pages (from-to)386-392
Number of pages7
JournalJournal of Institute of Control, Robotics and Systems
Issue number5
Publication statusPublished - 2018


  • Disturbance observer
  • Inverse model
  • Machine learning
  • Robust control


Dive into the research topics of 'Disturbance observer using machine learning algorithms'. Together they form a unique fingerprint.

Cite this