Nine targets which stand both for the static characteristic of produced formations and the dynamic parameter of wells including the average permeability,variation coefficient of permeability,moving capability,remainin...Nine targets which stand both for the static characteristic of produced formations and the dynamic parameter of wells including the average permeability,variation coefficient of permeability,moving capability,remaining recoverable reserves,coefficient of flooding,daily oil production,increasing rate of water cut,cumulative liquid production per unit meter and efficiency index of oil production are selected as the evaluation indexes,a novel model to evaluate the porous formations in long-term waterflooding sand reservoir was established by using the support vector machine and clustering analysis. Data of 57 wells from Shentuo 21 block Shengli oilfield was analyzed by using the model. Four kinds of formation groups were gained. According to the analysis result,different adjustment solutions were put forward to develop the relevant formations. The Monthly oil production increased 7.6 % and the water cut decreased 8.9 % after the adjusted solutions. Good results indicate that the learning from this method gained will be valuable adding to other long-term waterflooding sand reservoirs in Shengli oilfield and other similar reservoirs worldwide.展开更多
目的建立皮尔逊相关系数(Pearson correlation coefficient,PCC)和长短期记忆(long short term memory,LSTM)神经网络的反应液葡萄糖含量预测模型用以实时预测葡萄糖酸锌生产过程中反应液葡萄糖含量。方法通过葡萄糖酸锌制备实验,结合PC...目的建立皮尔逊相关系数(Pearson correlation coefficient,PCC)和长短期记忆(long short term memory,LSTM)神经网络的反应液葡萄糖含量预测模型用以实时预测葡萄糖酸锌生产过程中反应液葡萄糖含量。方法通过葡萄糖酸锌制备实验,结合PCC理论确定对反应液葡萄糖含量有较大影响的因素,对这些因素进行数据采集并将其作为神经网络的输入变量,采集反应液葡萄糖含量数据并进行处理,将其作为神经网络的输出变量,进而建立反向传播神经网络(backpropagation neural network,BP)和LSTM神经网络的反应液葡萄糖含量预测模型。结果通过100次模型迭代训练,对照BP反应液葡萄糖含量预测模型可以看出LSTM反应液葡萄糖含量预测模型在测试集的误差约为0.45%,误差较小,准确度较高。结论基于LSTM反应液葡萄糖含量预测模型显著提高了预测精度,相比现有检测方法更加智能高效,能够有效辅助生产进行。展开更多
The influence of long-term solution treatment for various intervals on the microstructure,mechanical properties,and corrosion resistance of the as-cast Mg–5Zn–1.5Y alloy was investigated.Variation of secondary phase...The influence of long-term solution treatment for various intervals on the microstructure,mechanical properties,and corrosion resistance of the as-cast Mg–5Zn–1.5Y alloy was investigated.Variation of secondary phases was studied during solution treatment through thermal analysis test and thermodynamic calculations.Tensile and hardness tests,as well as polarization and immersion tests,were performed to evaluate the mechanical properties and corrosion behavior of the ascast and heat-treated alloy,respectively.Results show that solution treatment transforms I-phaseinto W-phaseas well as dissolves it into the a-Mg matrix to some extent;therefore,the amount of W-phase increases.Moreover,prolonged solution treatment decreases the volume fraction of the phases.In the first stage of solution treatment for 14 h,the tensile properties significantly increase due to the incomplete phase transformation.Although long-term solution treatment sharply decreases the tensile and hardness properties of the alloy,it improves the corrosion resistance due to the transformation of I-phase into W-phase.In fact,it decreases corrosion potential and simultaneously dissolves intermetallic compounds into the a-Mg matrix,resulting in the reduction in galvanic microcells between the matrix and compounds.It is found that the optimum time for long-term solution treatment is 14 h,which improves both corrosion behavior and mechanical properties.展开更多
基金supported by funds from the Key Pro-ject of Chinese National Programs for Fundamental Research and Development (863 Program) under thenumber 2007AA090701the Young and Mid-dle-aged Researchers Innovation and Technology Foun-dation of CNPC under the number 04E7029
文摘Nine targets which stand both for the static characteristic of produced formations and the dynamic parameter of wells including the average permeability,variation coefficient of permeability,moving capability,remaining recoverable reserves,coefficient of flooding,daily oil production,increasing rate of water cut,cumulative liquid production per unit meter and efficiency index of oil production are selected as the evaluation indexes,a novel model to evaluate the porous formations in long-term waterflooding sand reservoir was established by using the support vector machine and clustering analysis. Data of 57 wells from Shentuo 21 block Shengli oilfield was analyzed by using the model. Four kinds of formation groups were gained. According to the analysis result,different adjustment solutions were put forward to develop the relevant formations. The Monthly oil production increased 7.6 % and the water cut decreased 8.9 % after the adjusted solutions. Good results indicate that the learning from this method gained will be valuable adding to other long-term waterflooding sand reservoirs in Shengli oilfield and other similar reservoirs worldwide.
文摘目的建立皮尔逊相关系数(Pearson correlation coefficient,PCC)和长短期记忆(long short term memory,LSTM)神经网络的反应液葡萄糖含量预测模型用以实时预测葡萄糖酸锌生产过程中反应液葡萄糖含量。方法通过葡萄糖酸锌制备实验,结合PCC理论确定对反应液葡萄糖含量有较大影响的因素,对这些因素进行数据采集并将其作为神经网络的输入变量,采集反应液葡萄糖含量数据并进行处理,将其作为神经网络的输出变量,进而建立反向传播神经网络(backpropagation neural network,BP)和LSTM神经网络的反应液葡萄糖含量预测模型。结果通过100次模型迭代训练,对照BP反应液葡萄糖含量预测模型可以看出LSTM反应液葡萄糖含量预测模型在测试集的误差约为0.45%,误差较小,准确度较高。结论基于LSTM反应液葡萄糖含量预测模型显著提高了预测精度,相比现有检测方法更加智能高效,能够有效辅助生产进行。
文摘The influence of long-term solution treatment for various intervals on the microstructure,mechanical properties,and corrosion resistance of the as-cast Mg–5Zn–1.5Y alloy was investigated.Variation of secondary phases was studied during solution treatment through thermal analysis test and thermodynamic calculations.Tensile and hardness tests,as well as polarization and immersion tests,were performed to evaluate the mechanical properties and corrosion behavior of the ascast and heat-treated alloy,respectively.Results show that solution treatment transforms I-phaseinto W-phaseas well as dissolves it into the a-Mg matrix to some extent;therefore,the amount of W-phase increases.Moreover,prolonged solution treatment decreases the volume fraction of the phases.In the first stage of solution treatment for 14 h,the tensile properties significantly increase due to the incomplete phase transformation.Although long-term solution treatment sharply decreases the tensile and hardness properties of the alloy,it improves the corrosion resistance due to the transformation of I-phase into W-phase.In fact,it decreases corrosion potential and simultaneously dissolves intermetallic compounds into the a-Mg matrix,resulting in the reduction in galvanic microcells between the matrix and compounds.It is found that the optimum time for long-term solution treatment is 14 h,which improves both corrosion behavior and mechanical properties.
