Forecasting of Refined Palm Oil Quality using Principal Component Regression

Citations of this article
Mendeley users who have this article in their library.


Over the past few decades, Malaysia has led the world in terms of production and export of palm oil. Driven by the prolific growth of palm oil industry, the quality of refined palm oil has become one of the predominant parts in related palm oil based industries. However, if the quality does not meet the standard, the out-specification refined palm oil needs to recycle back to the deodorization tank. The equipment cost, worker salary, processing time, and energy are all the expenses needed to recycle the out-spec palm oil which potentially being a great loss in time and cost for the plant. Therefore, the goal of this study is to develop a principal component regression (PCR)-based model to predict the quality of refined palm oil. The variables; Free Fatty Acid content (FFA), Iodine Value (IV) and Moisture Content (MOIST) are used to build the prediction model. Comparison of PCR predicted result with industrial data was made. It was proven in this study that PCR can be used to estimate the quality of refined palm oil. By having this predictor, the quality of the refined palm oil can be guaranteed thus all expenses related to recycling out of specification refined palm oil such as energy, salary, can be saved.




Rashid, N. A., Mohd Rosely, N. A., Mohd Noor, M. A., Shamsuddin, A., Abd Hamid, M. K., & Asri Ibrahim, K. (2017). Forecasting of Refined Palm Oil Quality using Principal Component Regression. In Energy Procedia (Vol. 142, pp. 2977–2982). Elsevier Ltd.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free