Premium
Prediction of YoungModulus of coal using artificial neural networks in Qinshui Basin, China
Author(s) -
GUO Xiaoqian,
LIU Dameng,
YAO Yanbin
Publication year - 2015
Publication title -
acta geologica sinica ‐ english edition
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.444
H-Index - 61
eISSN - 1755-6724
pISSN - 1000-9515
DOI - 10.1111/1755-6724.12305_15
Subject(s) - artificial neural network , coal , structural basin , china , environmental science , artificial intelligence , computer science , geology , engineering , geography , paleontology , archaeology , waste management
Mechanical properties of coal are most important parameters in controlling fluid storage and flow before and after coal extraction [1-2].Reservoir simulation design and wellbore stability analysis are influenced by elastic and strength character of coal rocks[3].Young’s modulus, and shear modulus are usedwhen deformations in underground mines need to be computed. Thus accurate assessment of elastic properties of coal rocks is extremely important for ground mining. Traditional methods such asuniaxial compressive strength, triaxial compressive strength,point load, schmidt hammer, scratch and indentation tests,were conducted to obtain the compressive strength and elastic modulus.Theprocedure for measuring these parameters has beenstandardized by both the American Society for Testingand Materials (ASTM) and the International Societyfor Rock Mechanics (ISRM).However, these experiments are complicated and time consuming[45].Another disadvantage of test samples is that it will not be in the in situ conditions anymore. It’s very difficult and nearly impossible to simulate the ground stress and fluid condition in lab. And due to variations in rock composition, lab results may not be fully representative of the entire reservoirs. Geophysical well logs can be used to deliver a continuousdataof in situ properties of rocks. Amongthese logs, full wave sonic logs can be used to calculate dynamic Young Modulus (Edyn). However, due to the complicated and expensive operation procedures, full wave sonic logs are seldom used. In order to overcome these difficulties, lots of relationships have been developed to estimate the Edyn, but majority of them are based on a special rock type [2,6]. In this study, neural network technique was introduced for prediction of Edynin Zhengzhuang District of Qinshui Basin in China. Density logs (DL), gamma ray(GR) and shear wave logs (AC) are the frequently used well logs for the target zone. Network between Edyn and the three logs will be established.