PEMODELAN STATISTICAL CONTROL DETECTION ADAPTIVE (SCDA) UNTUK MONITORING DAN PREDIKSI VOLUME PRODUKSI CRUDE PALM OIL (CPO) NASIONAL

Wahyu Widji Pamungkas, M. Syamsul Ma'arif, Tun Teja Irawadi, Yandra Arkeman

Abstract


Achievement of national palm oil industry as a producer and exporter of crude palm oil (CPO) in the world, it is now giving birth insecurity issues. This is because the growth of upstream and downstream industries of national palm oil that has not been balanced, which in turn encourages the national palm oil industry players to be oriented to the export of CPO which eliminates the added value in the country. On the other hand, though bring in foreign exchange for the country, but is prone commodity export orientation encountered a barriers problem in the international market. It is therefore important to provide a means of monitoring, prediction and assessment to facilitate the formulation of policies more about the marketing of national CPO industry. This research proposed the development of a model framework called adaptive threshold statistical control detection adaptive (SCDA) as a means of monitoring, prediction, and assessment of the movement of national CPO production volume. SCDA idea is to determine the dynamic threshold based mapping pattern historical data and predictions from the aspect of the frequency and trends. SCDA model adapted the techniques of statistical process control (SPC), while the values of the predictions generated from the simulation prediction model developed using the techniques of artificial neural network back propagation (ANN-BP) based on historical data of the national CPO production volume. The data used was the average volume of annual national CPO production period 1967 to 2015. The simulation results showed that the prediction model of national CPO production volume in 2016 until 2018 predicted were31.025 million, 32.214 million, and 34.504 million tons, respectively, while the values of maximum and minimum threshold that was formed in the model predictions SCDA for the period 2016-2018 each sequence were 33,322,065 and 29,246,547, respectively. As far as the literature search results, modeling SCDA has never been done in the research included for monitoring and prediction of national production volume of CPO. Therefore, research on the modeling of SCDA was contributing both to the development of knowledge about modeling as well as in the management of the national supply of CPO.

Keywords: adaptive threshold, modelling, artificial neural network, palm oil


Full Text:

PDF


DOI: http://dx.doi.org/10.24961/j.tek.ind.pert.2017.27.1.1

Editorial Office

Jurnal Teknologi Industri Pertanian (Journal of Agroindustrial Technology)

Department of Agroindustrial Technology, Faculty of Agricutural Technology Building, Bogor Agricultural University
Jln. Kamper, Kampus IPB Darmaga, Bogor 16680, Indonesia
Phone/Fax.: +62-251-8621974
e-mail: jurnal_tip@yahoo.co.id; tipjurnal@gmail.com; jurnal_tip@ipb.ac.id
 

Copyright Notice: 

All publications by Journal of Agroindustrial Technology [p-ISSN: 0216-3160, e-ISSN: 2252-3901] is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.