@inproceedings{scholars20063,
             doi = {10.1109/GECOST60902.2024.10474717},
            year = {2024},
            note = {cited By 0; Conference of 2024 International Conference on Green Energy, Computing and Sustainable Technology, GECOST 2024 ; Conference Date: 17 January 2024 Through 19 January 2024; Conference Code:198440},
           pages = {458--462},
           title = {Non-linear, non-convex and discontinuous base oil processing optimization using Differential Evolution Method},
         journal = {2024 International Conference on Green Energy, Computing and Sustainable Technology, GECOST 2024},
          author = {Mohd Fadzil, M. A. and Zabiri, H.},
        abstract = {The processing of base oil is a complex procedure involving various units, including the atmospheric distillation unit (ADU), vacuum distillation unit (VDU), intermediate tanks, hydrotreating unit, hydroisomerization unit, hydrodearomatization unit, and product fractionation unit (PFU). These units operate in a combination of batch and continuous processes to generate multiple product grades from the same raw material. Integrating all these units creates a challenging optimization problem characterized by non-linearity, non-convexity, and discontinuity. Solving such a problem is exceedingly difficult without simplifying the model to a linear form or assuming fixed base oil yields for each grade. However, the Differential Evolution optimization method offers a solution to this problem. By employing Differential Evolution optimization, it becomes possible to solve the problem while considering the model's complexity and without making simplifications. This approach has the advantage of accommodating changes in the feedstock, particularly its composition, in order to determine the optimal operating conditions for maximizing yields. The effectiveness of this method has been demonstrated through successful testing using actual plant data. {\^A}{\copyright} 2024 IEEE.},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85190367185&doi=10.1109\%2fGECOST60902.2024.10474717&partnerID=40&md5=42b60d8293f371ad96a61dcf053337c6},
        keywords = {Distillation equipment; Evolutionary algorithms; Machine learning; Optimization, Base oil; Complex procedure; Differential evolution method; Differential evolution optimizations; First principles; Hybrid; Machine-learning; Non linear; Oil processing; Processing optimizations, Distillation}
}