Modeling injection-induced fault slip using long short-term memory networks

Stress changes due to changes in fluid pressure and temperature in a faulted formation may lead to the opening/shearing of the fault.This can be due to subsurface(geo)engineering activities such as fluid injections and geologic disposal of nuclear waste.Such activities are expected to rise in the future making it necessary to assess their short-and long-term safety.Here,a new machine learning(ML)approach to model pore pressure and fault displacements in response to high-pressure fluid injection cycles is developed.The focus is on fault behavior near the injection borehole.To capture the temporal dependencies in the data,long short-term memory(LSTM)networks are utilized.To prevent error accumulation within the forecast window,four critical measures to train a robust LSTM model for predicting fault response are highlighted:(i)setting an appropriate value of LSTM lag,(ii)calibrating the LSTM cell dimension,(iii)learning rate reduction during weight optimization,and(iv)not adopting an independent injection cycle as a validation set.Several numerical experiments were conducted,which demonstrated that the ML model can capture peaks in pressure and associated fault displacement that accompany an increase in fluid injection.The model also captured the decay in pressure and displacement during the injection shut-in period.Further,the ability of an ML model to highlight key changes in fault hydromechanical activation processes was investigated,which shows that ML can be used to monitor risk of fault activation and leakage during high pressure fluid injections.

Geomechanical analysis of the influence of CO2 injection location on fault stability

Large amounts of carbon dioxide(CO2) should be injected in deep saline formations to mitigate climate change,implying geomechanical challenges that require further understanding.Pressure build-up induced by CO2injection will decrease the effective stresses and may affect fault stability.Geomechanical effects of overpressure induced by CO2injection either in the hanging wall or in the foot wall on fault stability are investigated.CO2injection in the presence of a low-permeable fault induces pressurization of the storage formation between the injection well and the fault.The low permeability of the fault hinders fluid flow across it and leads to smaller overpressure on the other side of the fault.This variability in the fluid pressure distribution gives rise to differential total stress changes around the fault that reduce its stability.Despite a significant pressure build-up induced by the fault,caprock stability around the injection well is not compromised and thus,CO2leakage across the caprock is unlikely to happen.The decrease in fault stability is similar regardless of the side of the fault where CO2is injected.Simulation results show that fault core permeability has a significant effect on fault stability,becoming less affected for high-permeable faults.An appropriate pressure management will allow storing large quantities of CO2without inducing fault reactivation.

Adaptive restarting method for LCC-HVDC based on principle of fault location by current injection

The existing LCC-HVDC transmission project adopts the fixed-time delay restarting method.This method has disadvantages such as non-selectivity,long restart process,and high probability of restart failure.These issues cause a secondary impact on equipment and system power fluctuation.To solve this problem,an adaptive restarting method based on the principle of fault location by current injection is proposed.First,an additional control strategy is proposed to inject a current detection signal.Second,the propagation law of the current signal in the line is analyzed based on the distributed parameter model of transmission line.Finally,a method for identifying fault properties based on the principle of fault location is proposed.The method fully considers the influence of the long-distance transmission line with earth capacitance and overcomes the influence of the increasing effect of the opposite terminal.Simulation results show that the proposed method can accurately identify the fault properties under various complex fault conditions and subsequently realize the adaptive restarting process.

Gas injection for enhanced oil recovery in two-dimensional geology-based physical model of Tahe fractured-vuggy carbonate reservoirs:karst fault system

Gas injection serves as a main enhanced oil recovery(EOR)method in fractured-vuggy carbonate reservoir,but its effect differs among single wells and multi-well groups because of the diverse fractured-vuggy configuration.Many researchers conducted experiments for the observation of fluid flow and the evaluation of production performance,while most of their physical models were fabricated based on the probability distribution of fractures and caves in the reservoir.In this study,a two-dimensional physical model of the karst fault system was designed and fabricated based on the geological model of TK748 well group in the seventh block of the Tahe Oilfield.The fluid flow and production performance of primary gas flooding were discussed.Gas-assisted gravity flooding was firstly introduced to take full use of gas-oil gravity difference,and its feasibility in the karst fault system was examined.Experimental results showed that primary gas flooding created more flow paths and achieved a remarkable increment of oil recovery compared to water flooding.Gas injection at a lower location was recommended to delay gas breakthrough.Gas-assisted gravity flooding achieved more stable gas-displacing-oil because oil production was at a lower location,and thus,the oil recovery was further enhanced.

Fault injection system for automatic testing system

Considering the deficiency of the means for confirming the attribution of fault redundancy in the re-search of Automatic Testing System(ATS) , a fault-injection system has been proposed to study fault redundancyof automatic testing system through compurison. By means of a fault-imbeded environmental simulation, thefaults injected at the input level of the software are under test. These faults may induce inherent failure mode,thus bringing about unexpected output, and the anticipated goal of the test is attained. The fault injection con-sists of voltage signal generator, current signal generator and rear drive circuit which are specially developed,and the ATS can work regularly by means of software simulation. The experimental results indicate that the faultinjection system can find the deficiency of the automatic testing software, and identify the preference of fault re-dundancy. On the other hand, some soft deficiency never exposed before can be identified by analyzing the tes-ting results.

Study of fault injection system based on software

A software fault injection system SFIS is designed,which consists of the target system plus a fault injector,fault library,workload,data collector,and data analyzer. A serial communication mechanism is adopted to simulate the factual work environment. Then a fault model is built for single particle event,which can be denoted as FM=(FL,FT). FL stands for fault location,and FT stands for fault type. The fault model supports three temporal faults: transient,intermittent,and permanent. During the experiments implemented by SFIS,the software interruption method is adopted to inject transient faults,and step trace method is adopted to inject permanent faults into the target system. The experiment results indicate that for the injected transient code segment faults,2.8 % of them do not affect the program output,80.1% of them are detected by the built-in error detection in the system,and 17.1% of them are not detected by fault detection mechanism. The experiment results verify the validity of the fault injection method.

Single Phase-to-Ground Fault Line Identification and Section Location Method for Non-Effectively Grounded Distribution Systems Based on Signal Injection

A diagnostic signal current trace detecting based single phase-to-ground fault line identifica- tion and section location method for non-effectively grounded distribution systems is presented in this paper.A special diagnostic signal current is injected into the fault distribution system,and then it is detected at the outlet terminals to identify the fault line and at the sectionalizing or branching point along the fault line to locate the fault section.The method has been put into application in actual distribution network and field experience shows that it can identify the fault line and locate the fault section correctly and effectively.

A fault injection model-oriented testing strategy for component security

A fault injection model-oriented testing strategy was proposed for detecting component vulnerabilities.A fault injection model was defined,and the faults were injected into the tested component based on the fault injection model to trigger security exceptions.The testing process could be recorded by the monitoring mechanism of the strategy,and the monitoring information was written into the security log.The component vulnerabilities could be detected by the detecting algorithm through analyzing the security log.Lastly,some experiments were done in an integration testing platform to verify the applicability of the strategy.The experimental results show that the strategy is effective and operable.The detecting rate is more than 90%for vulnerability components.

Transient and Permanent Fault Injection in VHDL Description of Digital Circuits

The ability to evaluate the testability of digital circuits before they are actually implemented is critical for designing highly reliable systems. This feature enables designers to verify the fault detection capability of online as well as offline testable digital circuits for both permanent and transient faults, during the design stage of the circuits. This paper presents a technique for transient and permanent fault injection at the VHDL level description of both combinational and sequential digital circuits. Access to all VHDL blocks a system is straight forward using a specially designed single fault injection block. This capability of inserting transient and permanent faults should help in evaluating the testability of a digital system before it is actually implemented.

Study and Analysis of Defect Amplification Index in Technology Variant Business Application Development through Fault Injection Patterns

Software reliability for business applications is becoming a topic of interest in the IT community. An effective method to validate and understand defect behaviour in a software application is Fault Injection. Fault injection involves the deliberate insertion of faults or errors into software in order to determine its response and to study its behaviour. Fault Injection Modeling has demonstrated to be an effective method for study and analysis of defect response, validating fault-tolerant systems, and understanding systems behaviour in the presence of injected faults. The objectives of this study are to measure and analyze defect leakage;Amplification Index (AI) of errors and examine “Domino” effect of defects leaked into subsequent Software Development Life Cycle phases in a business application. The approach endeavour to demonstrate the phasewise impact of leaked defects, through causal analysis and quantitative analysis of defects leakage and amplification index patterns in system built using technology variants (C#, VB 6.0, Java).

Study on Injection-Production System Adjustment of Fault Block Reservoir Based on Equilibrium Displacement

This paper proposed a method of injection-production system adjustment to solve the problem that the water flooding effect was restricted because of the horizontal and vertical contradictions during the development process of fault block reservoirs. Considering the heterogeneity of reservoir, the Buckley-Leverett water flooding theory was applied to establish the relationship between the recovery and cumulative water injection. In order to achieve the goal of vertically balanced recovery of each section, the calculation method of vertical sectional injection allocation was proposed. The planar triangular seepage unit was assumed and sweep coefficients of different oil-water distribution patterns were characterized using multi-flow tube method. In order to balance and maximize the plane sweep coefficient, the calculation method of plane production system optimization was obtained. Then the injection-production system stereoscopic adjustment method based on equilibrium displacement was proposed with vertical sectional injection allocation and plane production system optimization. This method was applied to injection and production adjustment of BZ oilfield in southern Bohai. The effect of water control and oil increase was obvious. This method can greatly improve the effect of water flooding of offshore fault block reservoirs with the adjustment of injection-production system.

Research on Inter-turn Short-circuit Fault Diagnosis Method Based on High Frequency Voltage Residual for PMSM

Inter-turn fault is a serious stator winding short-circuit fault of permanent magnet synchronous machine(PMSM). Once it occurs, it produces a huge short-circuit current that poses a great risk to the safe operation of PMSM. Thus, an inter-turn short-circuit fault(ITSCF) diagnosis method based on high frequency(HF) voltage residual is proposed in this paper with proper HF signal injection. First, the analytical models of PMSM after the ITSCF are deduced. Based on the model, the voltage residual at low frequency(LF) and HF can be obtained. It is revealed that the HF voltage residual has a stronger ITSCF detection capability compared to the LF voltage residual. To obtain optimal fault signature, a 3-phase symmetrical HF voltage is injected into the machine drive system, and the HF voltage residuals are extracted. The fault indicator is defined as the standard deviation of the 3-phase HF voltage residuals. The effectiveness of the proposed ITSCF diagnosis method is verified by experiments on a triple 3-phase PMSM. It is worth noting that no extra hardware equipment is required to implement the proposed method.

基于固态断路器主动注入式直流故障测距方法

随着直流配电网的快速发展与深化应用,准确可靠的故障测距技术对直流故障检修和恢复至关重要。该文提出一种基于固态断路器(SSCB)主动注入式直流故障测距方法。首先,利用SSCB开断主动注入不同脉冲宽度的信号,并检测注入脉冲首末端和反射波首末端的时间差作为注入波形传播时间间隔,能够减小采样频率带来的误差。然后,提取电缆线路电压线模量作为检测量,削弱正负极线路之间的耦合作用,获得稳定波速。最后,基于小波变换原理提出改进自适应模极大值方法来检测脉冲首末端时刻,减小噪声和过渡电阻对测距精度的影响。仿真结果表明,基于SSCB主动注入式测距方法在直流配电网单极接地和极间短路故障情况下均能够实现准确且快速的定位。

断控缝洞型碳酸盐岩立式板状油藏注采井网构建

断控缝洞型碳酸盐岩油藏缝洞结构和连通关系复杂,传统井网部署易产生低产能井,需构建立体注采井网以提高产能。通过油藏数值模拟研究了不同因素对塔里木富满油田满深3和满深4井区立体注采井网波及系数的影响,并设计了先导试验方案预测产能。结果表明,满深3井区注气井与采油井单个交错排状分布时波及系数最大;采油井纵向深度越大,波及系数越大;平面注采井距在500~1000m波及系数相对稳定,井距增至1500m时,波及系数大幅度减小。满深4井区注气井、注水井与采油井单个交错排状分布时波及系数最大。先导试验中,满深3和满深4井区分别采取“浅部注N_(2),深部采油”和“顶部注N_(2),底部注水,中部采油”的井网构建方案,阶段末采出程度分别达到21.3%与22.4%,相比于基础衰竭式开发和注水开发方案有了显著提升。

基于多领域耦合建模的轴向柱塞泵故障诊断方法

针对轴向柱塞泵传统单一领域建模方法存在的建模困难、仿真精度低以及故障诊断所需故障样本不足的问题,开展基于多领域耦合建模的轴向柱塞泵故障诊断方法。利用Simscape构建轴向柱塞泵多领域耦合模型,并对柱塞泄漏、主轴轴承磨损以及组合故障3种常见的故障进行模拟,再通过故障注入技术和MATLAB快速重启功能获取多种工况、不同故障程度下的压力和流量数据;随后从时域和频域对故障数据进行特征提取,同时利用单因素方差分析对故障特征进行选择;最后利用得到的特征对K邻近、朴素贝叶斯、决策树、神经网络、支持向量机等5种故障诊断算法进行训练,得到故障诊断准确率最高的算法,其平均诊断准确率为98.5%。该方法提高了轴向柱塞泵多领域耦合建模的精确性,实现了对轴向柱塞泵的有效故障诊断。

超深层断控碳酸盐岩油藏地质力学建模及其在开发中的应用

为提高超深断控碳酸盐岩油藏的开发效益,通过开展大尺寸岩样力学实验,揭示高角度—近直立断裂面变形与连通机理;基于高压注水提采的力学与流动耦合原理,通过地质力学建模,明确了断控碳酸盐岩油藏现今地应力场和断裂活动性分布规律;发现不同方位的断裂活动性以及不同部位的缝洞体连通性有明显差异,进而分析了不同井眼轨迹的开发效果,提出了地质工程一体化工作方法,科学指导井眼轨迹设计和注水方案优化。结果表明:①走滑断裂变形中的大尺度破碎体和高角度裂缝系统是影响储层品质的关键因素,高压注水一方面能够激活先存裂缝,一方面还能在先存裂缝基础上发生延伸扩展,甚至可以产生新的裂缝,促进了断控缝洞体在纵横向上的互相连通;②高压注水过程中断裂体内部发生力学与流动之间的耦合变化,渗流环境得到改善,通过循环举升,从而提高油气采收率;③根据断裂体形态、产状以及断裂面动态剪切变形连通性,可优选定向井最佳井点和井眼轨迹,并优化注水方案;④塔里木盆地断控油藏试验区通过高压注水,采收率提高5个百分点,该方法为超深断控型油藏高效开发提供了较好的理论依据和技术支撑。

稠油开采注汽锅炉在线综合预警关键技术

为了对工作在高温高压下注汽锅炉的各项运行参数进行在线准确监测和异常预警,本文在对稠油开采注汽锅炉工况参数进行采集、处理、分析的基础上,提出对注汽锅炉显性故障和隐性故障进行检测的方案。采用长期短期记忆神经网络,利用锅炉的时序数据对系统进行分析和建模,完成锅炉显性故障检测和预警,并通过预测数据的方式缓解锅炉大时滞的特性;利用深度异常检测技术,将无故障判别标准的数据进行隐性故障分析和预警。本文提出的综合预警方案对克拉玛依油田注汽锅炉进行了实验验证,预测误差仅有0.08%,同时异常检测范围也在设定值范围内。

基于EEMD与极限提升树的传感器故障诊断方法

传感器在工业互联等关键领域扮演着重要角色,通过故障诊断方法保障其数据的可靠性至关重要。本文提出一种基于EEMD与极限提升树的传感器故障诊断方法,以提高对传感器故障的准确识别和及时处理能力。该方法通过采集电压电流传感器数据,以故障注入方式建立数据集,利用EEMD对数据进行降噪与特征提取,并通过极限提升树进行训练,从而建立故障诊断模型。通过划分的验证集对所构建的模型进行验证。试验表明,该方法的测试准确性指标显著优于其他方法,至少高于次优方法11.95%的F1得分,能够更好地捕捉传感器数据的故障特征,具有较高的诊断准确率和较强的鲁棒性,且消耗较低、实用价值强,能够有力保障工业互联、玻璃智能制造等领域的数据准确性和安全性。

断块油藏注采耦合提高采收率机理及矿场实践

针对渤海湾盆地济阳坳陷东营凹陷古近系断块油藏水驱开发后期流线固定导致注入水无效循环的问题,基于渗流力学和油藏工程原理,通过室内物模模拟和油藏数值模拟,提出了“细分开发层系、轮注轮采”的注采耦合开发调整技术,并验证了该技术可提高采收率的原理。研究结果表明:(1)利用注采耦合开发技术建立的“注入期间的高渗通道与低渗通道吸水量比模型”和“采油期间主流线和非主流线产油量比模型”均揭示了“改变压力场促进渗流场调整,实现均匀注入和均匀采出,扩大水驱波及系数和增加驱油效率”的注采耦合渗流力学机制。(2)注采耦合技术可以实现“扩大波及系数、增加驱油效率”,起到类似“调剖”的作用,高含水期通过此项技术可将低渗透岩心的分流率由1.0%提到18.6%,模型驱替更均衡;经过2个轮次的注采耦合调整,高、低渗透岩心的原油采收率分别提高了10.3%和16.1%。(3)研究区D断块古近系沙河街组沙二段Es236含油小层油藏注采耦合开发数值模拟结果显示,主流线和非主流线驱替更均匀,两者压力梯度极差由2.3下降至1.4。经过3个轮次注采耦合开发调整,沙二段3—6砂层组油藏平均综合含水率下降了3.2%,累计增油1 760 t,提高原油采收率2.1%,增油降水效果显著。