An artificial-intelligence based decision-making protocol is developed for tight gas sands to identify re-fracturing wells and used in case studies. The methodology is based on fuzzy logic to deal with imprecision and subjectivity through mathematical representations of linguistic vagueness, and is a computing system based on the concepts of fuzzy set theory, fuzzy if-then rules, and fuzzy reasoning. Five indexes are used to characterize hydraulic fracture quality, reservoir characteristics, operational parameters, initial conditions, and production related to the selection of re-fracturing well, and each index includes 3 related parameters. The value of each index/parameter is grouped into three categories that are low, medium, and high. For each category, a trapezoidal membership function all related rules are defined. The related parameters of an index are input into the rule-based fuzzy-inference system to output value of the index. Another fuzzy-inference system is built with the reservoir index, operational index, initial condition index and production index as input parameters and re-fracturing potential index as output parameter to screen out re-fracturing wells. This approach was successfully validated using published data.

针对人工气砂开发了基于人工智能的决策方案，以识别重压井并用于案例研究。该方法基于模糊逻辑，通过语言模糊性的数学表示来处理不精确性和主观性，是基于模糊集理论，模糊假设规则和模糊推理的概念的计算系统。五个指标用于表征水力压裂质量，储层特征，运行参数，初始条件和与再压裂井的选择有关的产量，每个指标包括三个相关参数。每个索引/参数的值分为三类：低，中和高。对于每个类别，梯形隶属函数定义了所有相关规则。索引的相关参数被输入到基于规则的模糊推理系统中以输出索引的值。建立了以储层指标，运行指标，初始条件指标和生产指标为输入参数，再压裂潜力指标为输出参数的模糊推理系统，以筛选出再压裂井。使用已发布的数据已成功验证了此方法。