@article{scholars16934,
       publisher = {John Wiley and Sons Inc},
         journal = {Chemical Engineering and Technology},
           pages = {667--677},
            year = {2022},
           title = {Intelligent Control of an Industrial Debutanizer Column},
          number = {4},
            note = {cited By 2},
          volume = {45},
             doi = {10.1002/ceat.202100039},
          author = {Fatima, S. A. and Zabiri, H. and Taqvi, S. A. A. and Ramli, N. and Maulud, A. S.},
            issn = {09307516},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125037763&doi=10.1002\%2fceat.202100039&partnerID=40&md5=ecdb61c61a2a103b3f76e5ad3954d026},
        keywords = {Adaptive control systems; Disturbance rejection; Fuzzy inference; Fuzzy neural networks; Intelligent control; Proportional control systems; Two term control systems, Adaptive neuro-fuzzy inference; Adaptive neuro-fuzzy inference system; Control design; Debutanizer columns; Intelligent techniques; Malaysia; Neuro-fuzzy inference systems; Product composition; Proportional integral derivatives; Uncertain dynamics, Fuzzy systems},
        abstract = {A debutanizer column located at a refinery in Malaysia produces LPG as its top product and light naphtha as its bottom product. Control of the product compositions of the column is very important to maintain the desired purities. The current control design of the debutanizer column is based on the classical proportional integral derivative approach, which has been found to be less effective in controlling the variations in the column as the process is characterized by strong nonlinear and uncertain dynamics. Here, intelligent control based on an adaptive neuro-fuzzy inference system (ANFIS) is investigated and compared against an artificial neural network, for the special case of limited training data of the industrial debutanizer column. The ANFIS-based controller outperforms the other control configurations for both set point tracking and disturbance rejection cases and has better generalization performance even when trained with limited data samples. {\^A}{\copyright} 2022 Wiley-VCH GmbH}
}