@inproceedings{scholars930,
            year = {2010},
           title = {Modeling of reformer tube metal temperature},
         journal = {2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010},
         address = {Kuala Lumpur},
             doi = {10.1109/ICIAS.2010.5716248},
            note = {cited By 1; Conference of 2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010 ; Conference Date: 15 June 2010 Through 17 June 2010; Conference Code:84196},
        abstract = {This paper presents the empirical modeling of the primary reformer tube metal temperature (TMT) based on the real-time data of an ammonia plant. The model being developed shall serve to give adequate approximation of future outputs which in this case are temperature of the reformer tubes, given the process variables which act as inputs. The significance of this project are to initiate the creation of a robust predictive control to prevent overheating from occurring as well as to help the plant operator to plan the Preventative Maintenance if any of the unavoidable situation causing overheating occurs such as feedstock/steam failure, restricted process flow or the burners misalignment 1. The tube temperature can also be optimised to yield better production while generating more profits. This paper outlines the heuristic approaches taken in modeling the TMT using Artificial Neural Network (ANN), and other blackbox models developed using system identification and multiple linear regression (MLR) meant to serve as benchmarks.},
          author = {Rahim, M. A. B. A. and Ibrahim, R. B.},
            isbn = {9781424466238},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-79952757702&doi=10.1109\%2fICIAS.2010.5716248&partnerID=40&md5=3bf542f8177a8d18d4344cb54f117827},
        keywords = {Artificial Neural Network; Black-box model; Empirical model; Heuristic approach; Tube metal temperature prediction, Heuristic methods; Linear regression; Metals; Profitability; Tubes (components), Neural networks}
}