Data-driven fuzzy modelling of rotary dryer

Leena Yliniemi, Jukka Koskinen, K. Leiviskä

    Research output: Contribution to journalArticleScientificpeer-review

    9 Citations (Scopus)

    Abstract

    It was examined how different fuzzy modelling approaches, such as neuro-fuzzy, fuzzy clustering and linguistic equation methods, apply to the modelling of a rotary dryer. Because rotary drying, one of the oldest process in industry, is a highly nonlinear, strongly interactive multivariable process, its modelling is a demanding task. Its mathematical model, consisting of partial differential equations with several experimental parameters, is very complex and cumbersome. Therefore, the data-driven model is attractive, especially because many experimental observations and operating experience exist. The paper describes the fuzzy modelling approaches applied to the modelling of a rotary dryer. The applicability of different approaches has been evaluated by simulations, with the data collected from a pilot plant rotary dryer. The performance was estimated by an error index root means squared method and by comparing the modelling results with the results achieved by a linear regression model and a neural network model. The results show that neuro-fuzzy, fuzzy clustering and linguistic equation methods apply well, and no big differences can be detected between the methods.

    Original languageEnglish
    Pages (from-to)819-836
    Number of pages18
    JournalInternational Journal of Systems Science
    Volume34
    Issue number14-15
    DOIs
    Publication statusPublished - 2003
    MoE publication typeA1 Journal article-refereed

    Fingerprint

    Fuzzy Modeling
    Data-driven
    Fuzzy clustering
    Linguistics
    Neuro-fuzzy
    Fuzzy Clustering
    Modeling
    Pilot plants
    Linear regression
    Partial differential equations
    Drying
    Process Modeling
    Linear Regression Model
    Neural Network Model
    Mathematical models
    Neural networks
    Partial differential equation
    Roots
    Industry
    Mathematical Model

    Cite this

    Yliniemi, Leena ; Koskinen, Jukka ; Leiviskä, K. / Data-driven fuzzy modelling of rotary dryer. In: International Journal of Systems Science. 2003 ; Vol. 34, No. 14-15. pp. 819-836.
    @article{f8e4a1d684db46fb8faf0d05f5b6473c,
    title = "Data-driven fuzzy modelling of rotary dryer",
    abstract = "It was examined how different fuzzy modelling approaches, such as neuro-fuzzy, fuzzy clustering and linguistic equation methods, apply to the modelling of a rotary dryer. Because rotary drying, one of the oldest process in industry, is a highly nonlinear, strongly interactive multivariable process, its modelling is a demanding task. Its mathematical model, consisting of partial differential equations with several experimental parameters, is very complex and cumbersome. Therefore, the data-driven model is attractive, especially because many experimental observations and operating experience exist. The paper describes the fuzzy modelling approaches applied to the modelling of a rotary dryer. The applicability of different approaches has been evaluated by simulations, with the data collected from a pilot plant rotary dryer. The performance was estimated by an error index root means squared method and by comparing the modelling results with the results achieved by a linear regression model and a neural network model. The results show that neuro-fuzzy, fuzzy clustering and linguistic equation methods apply well, and no big differences can be detected between the methods.",
    author = "Leena Yliniemi and Jukka Koskinen and K. Leivisk{\"a}",
    year = "2003",
    doi = "10.1080/00207720310001640304",
    language = "English",
    volume = "34",
    pages = "819--836",
    journal = "International Journal of Systems Science",
    issn = "0020-7721",
    publisher = "Taylor & Francis",
    number = "14-15",

    }

    Yliniemi, L, Koskinen, J & Leiviskä, K 2003, 'Data-driven fuzzy modelling of rotary dryer', International Journal of Systems Science, vol. 34, no. 14-15, pp. 819-836. https://doi.org/10.1080/00207720310001640304

    Data-driven fuzzy modelling of rotary dryer. / Yliniemi, Leena; Koskinen, Jukka; Leiviskä, K.

    In: International Journal of Systems Science, Vol. 34, No. 14-15, 2003, p. 819-836.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Data-driven fuzzy modelling of rotary dryer

    AU - Yliniemi, Leena

    AU - Koskinen, Jukka

    AU - Leiviskä, K.

    PY - 2003

    Y1 - 2003

    N2 - It was examined how different fuzzy modelling approaches, such as neuro-fuzzy, fuzzy clustering and linguistic equation methods, apply to the modelling of a rotary dryer. Because rotary drying, one of the oldest process in industry, is a highly nonlinear, strongly interactive multivariable process, its modelling is a demanding task. Its mathematical model, consisting of partial differential equations with several experimental parameters, is very complex and cumbersome. Therefore, the data-driven model is attractive, especially because many experimental observations and operating experience exist. The paper describes the fuzzy modelling approaches applied to the modelling of a rotary dryer. The applicability of different approaches has been evaluated by simulations, with the data collected from a pilot plant rotary dryer. The performance was estimated by an error index root means squared method and by comparing the modelling results with the results achieved by a linear regression model and a neural network model. The results show that neuro-fuzzy, fuzzy clustering and linguistic equation methods apply well, and no big differences can be detected between the methods.

    AB - It was examined how different fuzzy modelling approaches, such as neuro-fuzzy, fuzzy clustering and linguistic equation methods, apply to the modelling of a rotary dryer. Because rotary drying, one of the oldest process in industry, is a highly nonlinear, strongly interactive multivariable process, its modelling is a demanding task. Its mathematical model, consisting of partial differential equations with several experimental parameters, is very complex and cumbersome. Therefore, the data-driven model is attractive, especially because many experimental observations and operating experience exist. The paper describes the fuzzy modelling approaches applied to the modelling of a rotary dryer. The applicability of different approaches has been evaluated by simulations, with the data collected from a pilot plant rotary dryer. The performance was estimated by an error index root means squared method and by comparing the modelling results with the results achieved by a linear regression model and a neural network model. The results show that neuro-fuzzy, fuzzy clustering and linguistic equation methods apply well, and no big differences can be detected between the methods.

    U2 - 10.1080/00207720310001640304

    DO - 10.1080/00207720310001640304

    M3 - Article

    VL - 34

    SP - 819

    EP - 836

    JO - International Journal of Systems Science

    JF - International Journal of Systems Science

    SN - 0020-7721

    IS - 14-15

    ER -