摘要：This study combined fault identification with a deep learning algorithm and applied a convolutional neural network(CNN)design based on an improved balanced crossentropy(BCE)loss function to address the low accuracy in the intelligent identification of seismic faults and the slow training speed of convolutional neural networks caused by unbalanced training sample *** network structure and optimal hyperparameters were determined by extracting feature maps layer by layer and by analyzing the results of seismic feature *** BCE loss function was used to add the parameter which is the ratio of nonfaults to the total sample sets,thereby changing the loss function to find the reference of the minimum weight parameter and adjusting the ratio of fault to nonfault *** method overcame the unbalanced number of sample sets and improved the iteration *** a brief training,the accuracy could reach more than 95%,and gradient descent was *** proposed method was applied to fault identification in an oilfield *** trained model can predict faults clearly,and the prediction results are basically consistent with an actual case,verifying the effectiveness and adaptability of the method.

摘要：利用高精度遥感数据(分辨率已达亚米级)提取相关信息评价检波器组合、选择有利检波器埋置位置,既可在观测系统设计阶段用于评估采集设计方案能否实施及辅助选择适当检波器组合图形,也可在外业测量前逐点优选检波器组合中心点,从而达到改善接收条件、提高观测系统的可实施性及保证地震资料采集质量的目的.利用高精度遥感数据提取相关信忠评价影响检波器接收信号质量的因素,所对应的遥感信忠主要用于三个方面的评估:①利用DEM(数字高程模型)与坡度计算检波器组合图形内的平整度与展开能力(组合展开度);②利用检波器组合区域的组内高差、坡度、湿度、地表松散度评价耦合条件的优劣程度(组合优度);③利用综合高精度正射影像与DEM提取的相关信忠划定工区内需要避让的地段及不符合HSE规范的施工禁区(可实施性).实例分析表明,通过遥感影像选择检波器组合与检波器埋置中心,提高了检波器组合内埋置点的平整度与组合展开度,对减轻野外劳动强度,提高劳动生产率,节约成本都起到了重要作用.

摘要：In this study,the gamma-ray spectrum of single elemental capture spectrum log was *** numerical simulation we obtain a single-element neutron capture gamma *** neutron and photon transportable processes were simulated using the Monte Carlo N-Particle Transport Code System(MCNP),where an Am–Be neutron source generated the neutrons and thermal neutron capture reactions with the stratigraphic *** characteristic gamma rays and the standard gamma spectra were recorded,from analyzing of the characteristic spectra analysis we obtain the ten elements in the stratum,such as Si,Ca,Fe,S,Ti,Al,K,Na,Cl,and *** with single elemental capture gamma spectrum of Schlumberger,the simulated characteristic peak and the spectral change results are in good agreement with *** characteristic peak positions observed also consistent with the data obtained from the National Nuclear Data Center of the International Atomic Energy *** neutron gamma spectrum results calculated using this simple method have practical *** also serve as an reference for data processing using other types of element logging tools.

摘要：To deal with the stress interference caused by simultaneous propagation of multiple fractures and the wettability reversal and physical property changes of the reservoir caused by fracturing fluid getting in during large-volume fracturing of tight oil reservoirs through a horizontal well, a non-planar 3D fracture growth model was built, wettability reversal characterizing parameters and change of relative permeability curve were introduced to correct the production prediction model of fractured horizontal well, a fracturing design optimization software(Fr Smart) by integrating geological and engineering data was developed, and a fracturing design optimization approach for tight oil reservoirs based on fracture control was worked out. The adaptability of the method was analyzed and the fracture parameters of horizontal wells in tight oil reservoirs were optimized. The simulation results show that fracturing technology based on fracture control is suitable for tight oil reservoirs, and by optimizing fracture parameters, this technology makes it possible to produce the maximum amount of reserves in the well-controlled unit of unconventional reservoirs. The key points of fracturing design optimization based on fracture control include increasing lateral length of and reducing the row spacing between horizontal wells, increasing perforation clusters in one stage to decrease the spacing of neighboring fractures, and also avoiding interference of old and new fracturing wells. Field tests show that this technology can increase single well production and ultimate recovery. Using this technology in developing unconventional resources such as tight oil reservoirs in China will enhance the economics significantly.

摘要：尽管气举越来越多地被应用到大斜度井、水平井的举升采油中,但倾斜井气举设计与直井气举设计存在什么差异,这些差异随倾斜角度的增大将怎样变化,以及哪些气举设计所需参数对这种差异比较敏感,即如何对倾斜井气举设计所需参数进行合理选择,以便对倾斜井气举设计进行优化的研究较少,这也一直是倾斜井合理气举设计的难点问题。鉴于此,笔者以某油田一口倾斜井为例,通过实测数据进行了倾斜井产能预测方法优选和多相管流压力计算方法优选,然后在该基础上采用等套压降气举设计方法对比分析了倾斜井气举设计与同等条件下直井气举设计的差异,并逐一分析了各种气举设计所需重要参数分别取不同值时气举设计注气深度和产量随井斜角度的变化规律,从而得到了倾斜井气举设计的敏感性参数,可为倾斜井气举设计的参数优化和调整提供参考依据,是倾斜井气举高效生产的有力保障。

摘要：Wave equation wave field numerical modeling technology is applied to the observation that deep layer imaging is difficult below a screening layer of high-velocity basalt. Three simple high-velocity basalt models are designed on the basis of basalt formation characteristics. The analysis of deep-layer reflection seismic signal energy shows that lowfrequency seismic signals are capable of both penetrating the thin high-velocity basalt layer and reducing the diffraction noise caused by the rough surfaces. The simulation experiment of a complete 2D basalt model confirms that the low-frequency signals can be used to boost the quality of deep-layer imaging under the high-velocity basalt layer and achieve good results in low-pass filter processing of actual data.