#TITLE_ALTERNATIVE#

• Main Author: FAUZI HADAD (NIM : 32212001), AHMAD
• Format: Dissertations
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/25176
• Institution: Institut Teknologi Bandung

The production of CBM wells are controlled by several important reservoir <br /> <br /> parameters. In this research, the influencing parameters are limited to the three <br /> <br /> important ones, which are: gas content, Langmuir parameters, and permeability; <br /> <br /> at which the existing methods for predicting these three important parameters are <br /> <br /> still very few. This research utilizes the data from CBM fields in East Kalimantan, <br /> <br /> with quite extensive coverage, from coal maturity of lignite to bituminous. <br /> <br /> The objective of this research is to produce the more accurate and consistent <br /> <br /> models to predict three important parameters of CBM reservoir, through Artificial <br /> <br /> Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) <br /> <br /> techniques, furthermore, they can be used as the inputs to predict CBM wells <br /> <br /> production. The prediction of CBM well’s production is a combination between <br /> <br /> fluid flow rate calculations and material balance technique. To compute the work, <br /> <br /> this research produces a software employing Matlab Graphical User Interface <br /> <br /> (GUI) for the prediction of three key parameters and production performance of <br /> <br /> CBM wells. <br /> <br /> This research concludes that AI technique; ANN and ANFIS are able to recognize <br /> <br /> the pattern of well log data (as the input) and three important parameters (as the <br /> <br /> output) very well. The best training techniques for the prediction are: ANFIS for <br /> <br /> gas content and VL CH4, TrainLM for PL CH4, VL CO2 and PL CO2, and TrainBR <br /> <br /> for permeability. It is found that the worthy method to predict all three parameters <br /> <br /> is TrainLM technique (ANN with the Levenberg-Marquardt training algorithm). <br /> <br /> Furthermore, a calculation technique of material balance approach (King-SLFR) <br /> <br /> predicting the production of water and gas of CBM wells quite satisfactorily. It also <br /> <br /> be concluded that a new resulted empirical equation which can act similar as <br /> <br /> diffusion process in CBM reservoir, and be applied in the King-SLFR technique <br /> <br /> stays keeping in balance condition. <br />