A Novel Hybrid Ensemble Classification Approach to Candidate Well Selection for CBM Well Fracturing

2018 4th International Conference on Environment and Renewable Energy

生态环境科学;能源学

Xu, Lei^1,2 ; Liu, Fang^1

Neijiang Normal University, Neijiang, China^1

Data Recovery Key Laboratory of Sichuan Province, China^2

关键词: Commercial development;    Development characteristics;    Ensemble classification;    Extreme learning machine;    Interval type-2 fuzzy logic systems;    Qualitative and quantitative analysis;    Reservoir stimulations;    Stimulation treatments;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/159/1/012007/pdf
DOI  :  10.1088/1755-1315/159/1/012007

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

For coalbed methane commercial development, hydraulic fracturing is the most common stimulation treatment. The selection of wells or layers is the first link. Fracturing with big yield potential and good effect can not only reduce fracturing risk but also offer more technological choices for reservoir stimulation. A method combined with qualitative and quantitative analysis is adopted to construct the index system of candidate wells selection according to coalbed reservoir properties and development characteristics. In order to study the complex uncertainty and unbalanced classification problem in the process of candidate well selection, a fusion of interval type 2 fuzzy logic system (IT2FLS) and extreme learning machine(ELM) based selective ensemble method is proposed in this paper. Illustrative examples are provided to show to the validity of the proposed method.