Pengeluaran minyak sawit dan isirong sawit sering kali menghadapi masalah, antara lain kadar kehilangan minyak sawit dan isirong sawit yang tinggi semasa pemprosesan dan penggunaan sumber-sumber yang tidak optimum. Model pengoptimuman pengeluaran minyak sawit dan isirong sawit perlu direka bentuk untuk menyelesaikan permasalahan tersebut sehingga dapat memaksimumkan hasil, meminimumkan kos pengeluaran serta meminimumkan kehilangan minyak sawit dan isirong sawit. Model yang dibangunkan adalah gabungan antara model sistem pakar kabur dengan model pengaturcaraan pelbagai objektif. Pengoptimuman model dilakukan dengan menggunakan kaedah algoritma genetik. Model disimulasikan menggunakan data daripada sebuah kilang minyak sawit di Indonesia dan hasil kajian membuktikan pencapaian pengeluaran yang lebih baik serta kehilangan minyak sawit dan isirong sawit yang lebih kecil berbanding keadaan pengeluaran sedia ada di kilang minyak sawit tersebut.
Kata kunci: Minyak sawit mentah, pengoptimuman pengeluaran, sistem pakar kabur, model pengaturcaraan pelbagai objektif, algoritma genetik
The production of crude palm oil and palm kernel are frequented by problems, among others the high loss of crude palm oil and palm kernel during processing and the consumption of resources that are not optimised. An optimisation model for crude palm oil and palm kernel production has to be developed to solve these problems so as to maximise revenue, minimise production costs as well as to minimise palm oil and palm kernel losses. The developed model is an integration between fuzzy expert system models and multi objective programming model. Model optimisation is performed using the genetic algorithm method. The model was simulated using data from a palm oil mill in Indonesia and results from the study show that the model produces an optimum quantity of production and capable of reducing palm oil and palm kernel losses compared with the existing production conditions in the palm oil mill.
Key words: Crude palm oil, production optimisation, fuzzy expert system, multi objective programming model, genetic algorithm
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.