System identification for Quad-rotor parameters using neural network

Tarek N. Dief, Shigeo Yoshida

    Research output: Contribution to journalArticlepeer-review

    36 Citations (Scopus)

    Abstract

    This paper presents a new technique to identify the system parameters without using the system governing equations. This technique is the time series prediction using neural network. The theoretical model was applied using simulations, after that the experiments were done to get the suitable construction for the neural model. A comparison between neural network and placket’s model is discussed. The advantages and disadvantages of both models were explained. The main idea of neural network is based on back-propagation algorithm. The equations and steps for iteration are presented and the relation between changing the number of iteration with the system frequency. The controller used is pole placement controller based on the neural network results as a system model.

    Original languageEnglish
    Pages (from-to)6-11
    Number of pages6
    JournalEvergreen
    Volume3
    Issue number1
    DOIs
    Publication statusPublished - 2016

    All Science Journal Classification (ASJC) codes

    • Electronic, Optical and Magnetic Materials
    • Ceramics and Composites
    • Surfaces, Coatings and Films
    • Management, Monitoring, Policy and Law

    Fingerprint

    Dive into the research topics of 'System identification for Quad-rotor parameters using neural network'. Together they form a unique fingerprint.

    Cite this