PEMODELAN KERANGKA ADAPTIVE THRESHOLD UNTUK MEMONITOR PRODUKSI MINYAK SAWIT NASIONAL BERBASIS STATISTICAL PROCESS CONTROL DAN ARTIFICIAL NEURAL NETWORK-BACKPROPAGATION

Indonesia is the largest exporter of palm oil in the world, as the largest producer Indonesia still havemany problems. The problem caused by incomparable between the growth of upstream and downstreampalm oil industries. This impact to low added value of palm oil, then Indonesia exports palm oil in crudeform. On the other hand, On the other hand , orientation export of this commodity is also prone of barrier,because Indonesia was not the price setter of this commodity in the international market. Therefore it isimportant to monitor and predict the development of national palm oil production volume in order to takegood anticipation. This research develop a framework model adaptive threshold to monitor the growing ofnational palm oil production volume with techniques of statistical process control (SPC) and back propagationartificial neural network (ANN - BP) methods. Historical data production volume period from 1967 to 2015was used as a base of the behavior as data to determine the threshold and prediction volume for nextperiods. The formation of the threshold value was based on the behavior of the historical data, which areoriented by the epicenter of the average value in the last two periods .Through mapping of data historicalperiod values, existing and forecast values with adaptive threshold can show tolerant level for the threshold.Furthermore, based on the analysis, it is known that the prediction of 2016 to 2018 period, there will behappen the dynamics production volume of national palm oil within tolerance threshold. The values of thesepredictions generated from the simulation model predictions of ANN-BP with the level very good of validationmodel, demonstrated the level of squared errors is very small1 in the MSE = 0.00021136 with a degree ofoutput correlation and the target is very strong2 with R Validation is 99.98 percent.Keywords: adaptive threshold, statistical process control, artificial neural network, national palm oilproduction