PERAMALAN PRODUKSI CRUDE PALM OIL DENGAN ALGORITMA BACKPROPAGATION NEURAL NETWORK
نویسندگان
چکیده
Jumlah produksi Crude Palm Oil di PT X pada Januari 2019 mencapai 3.413.353 Kg. Pada bulan berikutnya minyak CPO mengalami penurunan. bahan baku masuk yang berfluktuasi, menyebabkan munculnya ketidakpastian jumlah CPO. Februari turun sebesar 52%. Untuk menghindari keadaan tidak pastinya masa akan datang, maka dilakukan peramalan. Backpropagation merupakan algoritma dapat diterapkan untuk menyelesaikan beberapa permasalahan, terutama masalah berkaitan dengan prediksi atau Berdasarkan hasil pengolahan data Neural Network variasi model arsitektur hidden neuron 4, fungsi pembelajaran trainlm, aktivasi sigmoid, learning rate 0.7, mampu menghasilkan tingkat kesalahan terbaik nilai MSE 0.00054 pelatihan, dan 0,00372 pengujian. Model tersebut digunakan sebagai meramalkan Mei-Desember 2021.
منابع مشابه
Backpropagation Neural Network Tutorial
The Architecture of BPNN’s A population P of objects that are similar but not identical allows P to be partitioned into a set of K groups, or classes, whereby the objects within the same class are more similar and the objects between classes are more dissimilar. The objects have N attributes (called properties or features) that can be measured (observed) so that each object can be represented b...
متن کاملNeural Network Controller for a Crude Oil Distillation Column
The development of neural network that could be used for the control of an industrial process is discussed. Field data from a working distillation column or fractionator of crude oil refinery in Nigeria was used for the development and testing the effectiveness of the controller. The developed controller performed optimally when compared with the installed distributed control system based on pr...
متن کاملHedging Effectiveness of Crude Palm Oil Futures Market in Malaysia
This paper investigated the hedging effectiveness of crude palm oil futures market in Malaysia from January 2009 to June 2011 which traded under Bursa Malaysia Derivatives Berhad. Ordinary Least Squared (OLS) method was used to compute Minimum-Variance hedging ratio (MVHR), R-squared and hedging effectiveness by using daily data from settlement price of crude palm oil futures contracts and spot...
متن کاملPrice Discovery through Crude Palm Oil Futures: An Economic Evaluation
This paper examines the forward pricing efficiency of the local crude palm oil (CPO) futures market. In an efficient market, the relevant signal to be used by -the producers, traders and processors is simply the futures price. The forward pricing efficiency is measured in terms of the forecasting ability of Malaysian crude palm oil futures price on physical price. The relative predictive power ...
متن کاملNeural Modeling for Crude Oil Blending
Crude oil blending is an important unit operation in petroleum re ning industry. A good model for the blending system is bene cial for supervision operation, prediction of the export petroleum quality and realizing model-based optimal control. Since the blending cannot follow the ideal mixing rule in practice, we propose a static neural network to approximate the blending properties. By input-t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Industri Inovatif: Jurnal Teknik Industri
سال: 2023
ISSN: ['2615-3866', '2087-8869']
DOI: https://doi.org/10.36040/industri.v13i1.4887