• DocumentCode
    2048148
  • Title

    Comparison of different model structure selection using R2, MDL and AIC criterion

  • Author

    Marzaki, Mohd Hezri ; Tajjudin, Mazidah ; Adnan, R. ; Rahiman, M.H.F. ; Jalil, M.H.A.

  • Author_Institution
    Fac. of Electr. Eng., Univ. Teknol. MARA, Shah Alam, Malaysia
  • fYear
    2013
  • fDate
    19-20 Aug. 2013
  • Firstpage
    80
  • Lastpage
    85
  • Abstract
    This paper present the comparison of different model structure selection of ARX modelling using R2, MDL and AIC criterion. Input signal for the process is pseudo-random binary sequence (PRBS) and STEP response with a magnitude which vary from 0 to 5 volts. The comparisons have been made by considering the ACF and CCF validation technique. The results have shown that R2 provides superior model performance when model complexity is not considered as the penalty.
  • Keywords
    autoregressive processes; binary sequences; computational complexity; control system synthesis; distillation; essential oils; industrial control; predictive control; random sequences; ACF validation technique; AIC criterion; ARX modelling; Autoregressive with External Input model; CCF validation technique; MDL criterion; MPC design; PRBS; R2 criterion; STEP response; essential oil; input signal; model complexity; model performance; model predictive control; model structure selection; pseudorandom binary sequence; steam distillation plant; Complexity theory; Computational modeling; Data models; Estimation; Mathematical model; Temperature control; Temperature measurement; ARX; MDL and AIC; PRBS; R2; Step response;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Control and System Graduate Research Colloquium (ICSGRC), 2013 IEEE 4th
  • Conference_Location
    Shah Alam
  • Print_ISBN
    978-1-4799-0550-8
  • Type

    conf

  • DOI
    10.1109/ICSGRC.2013.6653280
  • Filename
    6653280
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2048148