PEMELAJARAN JARINGAN SYARAF BUATAN ( ARTIFICIAL NEURAL NETWORK ) PADA POMPA BENAM LISTRIK

• Main Author: Puji Santoso, Anas
• Format: Theses
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/4526
• Institution: Institut Teknologi Bandung

<b>Abstract:<p align=\"justify\"> <br /> Artificial Neural Network (ANN) is a computational structure by the study of biological neural processing. There are many different types of ANN, from relatively simple to very complex as discribe in theories on biological neural processing. Neural network model are designed to emulate human information processing capabilities such as knowledge processing, speech, prediction and control. Therefore, there is no exaggerated if neural network apllications are used today to solve the problem of design, optimization and selection the Electrical Submergible Pumps (ESP). <br /> Before the ANN model used to provide the desired output, the model must be trained to recognize the relationship between the input parameters. The first step, the vertical flow model for computing the pump discharge pressure requirement and pressure lost in pump to calculate intake pressure of pump used Duns and Ros correlations. The second step, training proccess to calculate weights as pressure lost constant through tubing and pump with small error tolerance. <br /> The results of this research is a computer program to select electrical submersible pump type with certain at the production rate and pump stages.<p align=\"justify\">