Jaringan Syaraf Tiruan untuk Model Prediktif Kontrol  

Oleh:

Biyanto, Totok Ruki

Jenis: Article from Journal - ilmiah nasional
Dalam koleksi: Jurnal Ilmu-Ilmu Teknik (Engineering) vol. 18 no. 1 (Apr. 2006), page 51-60.
Topik: Artificial Neural Network; Model Predictive Control (mpc); Distillation Column

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: JJ106 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Distillation column has complex and nonlinear characteristics, and the controller could be cover its characteristics. Beside that, distillation colums has slow response perfomance and need observer to predict it. Model Predictive Control (MPC) is the new alternative to overcome it. Distillation column modeling has built up by Artificial Neural Network (ANN) with multi layer perceptron (MLP) structure. Model structure is Nonlinear Auto Regressive with eXternal input (NARX). Data set for training and validation was gernerated by Amplitude Pseudo Random Binary Signal (APRBS). ANN learning algorithm using Levenberg-Marquardt algorithm that could be obtain good RMSE, the RMSE value is 3.8295 x l0’~ for distillate product and 1.4594 x l0’~ for bottom product. Simulation result shown that composition control of distillation column based on ANN obtain good performance, with Integral Absolute Error (IAE) 3,9*5 x 1G3 for distillate product aid 5,409105 x 103 for bottom product when set point increased. This control system also has IAE 7.673289719 for distillate product and 3.59*51 x 10~ fbr bottom product when disturbance occured.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali