An adaptive physics-informed deep learning method for pore pressure prediction using seismic data

Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the great potential to deal with pore pressure prediction.However,most of the traditional deep learning models are less efficient to address generalization problems.To fill this technical gap,in this work,we developed a new adaptive physics-informed deep learning model with high generalization capability to predict pore pressure values directly from seismic data.Specifically,the new model,named CGP-NN,consists of a novel parametric features extraction approach(1DCPP),a stacked multilayer gated recurrent model(multilayer GRU),and an adaptive physics-informed loss function.Through machine training,the developed model can automatically select the optimal physical model to constrain the results for each pore pressure prediction.The CGP-NN model has the best generalization when the physicsrelated metricλ=0.5.A hybrid approach combining Eaton and Bowers methods is also proposed to build machine-learnable labels for solving the problem of few labels.To validate the developed model and methodology,a case study on a complex reservoir in Tarim Basin was further performed to demonstrate the high accuracy on the pore pressure prediction of new wells along with the strong generalization ability.The adaptive physics-informed deep learning approach presented here has potential application in the prediction of pore pressures coupled with multiple genesis mechanisms using seismic data.

Pressure Regulation for Earth Pressure Balance Control on Shield Tunneling Machine by Using Adaptive Robust Control

Most current studies about shield tunneling machine focus on the construction safety and tunnel structure stability during the excavation. Behaviors of the machine itself are also studied, like some tracking control of the machine. Yet, few works concern about the hydraulic components, especially the pressure and flow rate regulation components. This research focuses on pressure control strategies by using proportional pressure relief valve, which is widely applied on typical shield tunneling machines. Modeling of a commercial pressure relief valve is done. The modeling centers on the main valve, because the dynamic performance is determined by the main valve. To validate such modeling, a frequency-experiment result of the pressure relief valve, whose bandwidth is about 3 Hz, is presented as comparison. The modeling and the frequency experimental result show that it is reasonable to regard the pressure relief valve as a second-order system with two low corner frequencies. PID control, dead band compensation control and adaptive robust control（ARC） are proposed and simulation results are presented. For the ARC, implements by using first order approximation and second order approximation are presented. The simulation results show that the second order approximation implement with ARC can track 4 Hz sine signal very well, and the two ARC simulation errors are within 0.2 MPa. Finally, experiment results of dead band compensation control and adaptive robust control are given. The results show that dead band compensation had about 30° phase lag and about 20% off of the amplitude attenuation. ARC is tracking with little phase lag and almost no amplitude attenuation. In this research, ARC has been tested on a pressure relief valve. It is able to improve the valve＇s dynamic performances greatly, and it is capable of the pressure control of shield machine excavation.

Application of Single Neuron Adaptive PID Regulators with Auto-tuning Gain in Industrial Parameter(Pressure)Closed-loop Process Control Systems

A type of single neuron adaptive PID regulator with auto-tuning gain is proposed and applied to the work control of fans, waterpumps and air-pressers etc. in Handan Iron & Steel Compel China. The robusthess of induStrial parameter closed-loop process controlsystems is improved, and the work quality of the systems bettered.

Pressure observer based adaptive robust trajectory tracking control of a parallel manipulator driven by pneumatic muscles

This paper presents a pressure observer based adaptive robust controller (POARC) for posture trajectory tracking of a parallel manipulator driven by three pneumatic muscles without pressure sensors. Due to model errors of the static forces and friction forces of pneumatic muscles, simplified average flow rate characteristics of valves, unknown disturbances of entire system, and unmeasured pressures, there exist rather severe parametric uncertainties, nonlinear uncertainties and dynamic uncertainties in modeling of the parallel manipulator. A nonlinear pressure observer is constructed to estimate unknown pressures on the basis of a single-input-single-output (SISO) decoupling model that is simplified from the actual multiple-input-multiple-output (MIMO) coupling model of the parallel manipulator. Then, an adaptive robust controller integrated with the pressure observer is developed to accomplish high precision posture trajectory tracking of the parallel manipulator. The experimental results indicate that the system with the proposed POARC not only achieves good control accuracy and smooth movement but also maintains robustness to disturbances.

Managed Pressure Drilling Technology:A Research on the Formation Adaptability

Existing pressure drilling technologies are based on different principles and display distinct characteristics in terms of control pressure and degree of formation adaptability.In the present study,the constant-bottomhole-pressure(CBHP)and controlled-mud-level(CML)dual gradient drilling methods are considered.Models for the equivalent circulating density(ECD)are introduced for both drilling methods,taking into account the control pressure parameters(wellhead back pressure,displacement,mud level,etc.)and the relationship between the equivalent circulating density curve in the wellbore and two different types of pressure profiles in deep-water areas.The findings suggest that the main pressure control parameter for CBHP drilling is the wellhead back pressure,while for CML dual gradient drilling,it is the mud level.Two examples are considered(wells S1 and B2).For S1,CML dual gradient drilling only needs to adjust the ECD curve once to drill down to the target layer without risk.By comparison,CBHP drilling requires multiple adjustments to reach the target well depth avoiding a kick risk.In well B2,the CBHP method can drill down to the desired zone or even deeper after a single adjustment of the ECD curve.In contrast,CML dual-gradient drilling requires multiple adjustments to reach the target well depth(otherwise there is a risk of lost circulation).Therefore,CML dual-gradient drilling should be considered as a better choice for well S1,while CBHP drilling is more suitable for well B2.

Adaptive fuzzy integral sliding mode pressure control for cutter feeding system of trench cutter

A nonlinear pressure controller was presented to track desired feeding pressure for the cutter feeding system(CFS) of trench cutter(TC) in the presence of unknown external disturbances.The feeding pressure control of CFS is subjected to unknown load characteristics of rock or soil; in addition,the geological condition is time-varying.Due to the complex load characteristics of rock or soil,the feeding velocity of TC is related to geological conditions.What is worse,its dynamic model is subjected to uncertainties and its function is unknown.To deal with the particular characteristics of CFS,a novel adaptive fuzzy integral sliding mode control(AFISMC) was designed for feeding pressure control of CFS,which combines the robust characteristics of an integral sliding mode controller and the adaptive adjusting characteristics of an adaptive fuzzy controller.The AFISMC feeding pressure controller is synthesized using the backstepping technique.The stability of the overall closed-loop system consisting of the adaptive fuzzy inference system,integral sliding mode controller and the cutter feeding system is proved using Lyapunov theory.Experiments are conducted on a TC test bench with the AFISMC under different operating conditions.The experimental results demonstrate that the proposed AFISMC feeding pressure controller for CFS gives a superior and robust pressure tracking performance with maximum pressure tracking error within ?0.3 MPa.

Self-adaptive large neighborhood search algorithm for parallel machine scheduling problems

A self-adaptive large neighborhood search method for scheduling n jobs on m non-identical parallel machines with mul- tiple time windows is presented. The problems＇ another feature lies in oversubscription, namely not all jobs can be scheduled within specified scheduling horizons due to the limited machine capacity. The objective is thus to maximize the overall profits of processed jobs while respecting machine constraints. A first-in- first-out heuristic is applied to find an initial solution, and then a large neighborhood search procedure is employed to relax and re- optimize cumbersome solutions. A machine learning mechanism is also introduced to converge on the most efficient neighborhoods for the problem. Extensive computational results are presented based on data from an application involving the daily observation scheduling of a fleet of earth observing satellites. The method rapidly solves most problem instances to optimal or near optimal and shows a robust performance in sensitive analysis.

Design of the pressure regulation algorithm for active braking in vehicle ACC system

To develop the pressure control algorithm for active braking of adaptive cruise control（ACC） system,a test bench with real parts of the tested vehicle is built.With the dynamic analysis of the active braking actuators,it is demonstrated that different duty of pulse-width modulation（PWM） signals could control the pressure changing rate of the wheel cylinder.To obtain that signal,a modified proportional-integral-differential（PID） control algorithm is developed using the variable parameter method,the control value reset method,the dead zone method and the integral saturation method.Experimental results show that the delay and overshoot of the pressure response could be reduced considerably using the modified PID algorithm compared with the conventional one.The proposed pressure control algorithm could be used for the further development of the ACC＇s controller.

Automated postoperative blood pressure control

It is very important to maintain the level of mean arterial pressure （MAP）. The MAP control is applied in many clinical situations, including limiting bleeding during cardiac surgery and promoting healing for patient＇ s post-surgery. This paper presents a fuzzy controller-based multiple-model adaptive control system for postoperative blood pressure management. Multiple-model adaptive control （MMAC） algorithm is used to identify the patient model, and it is a feasible system identification method even in the presence of large noise. Fuzzy control （FC） method is used to design controller bank. Each fuzzy controller in the controller bank is in fact a nonlinear proportional-integral （PI） controller,whose proportional gain and integral gain are adjusted continuously according to error and rate of change of error of the plant output, resulting in better dynamic and stable control performance than the regular PI controller, especially when a nonlinear process is involved. For demonstration, a nonlinear, pulsatile-flow patient model is used for simulation, and the results show that the adaptive control system can effectively handle the changes in patient＇s dynamics and provide satisfactory performance in regulation of blood pressure of hypertension patients.

An efficient FEM for pressure analysis of oil film in a piston pump

The paper concerns numerical analysis of pressure distribution of an oil film on the valve plate in the variable height gap of an axial piston pump. The analysis employs the finite element method. For determination of oil pressure variations in the gap, the Reynolds equation, commonly applied in the theory of lubrication, is applied. The equation is solved numerically with the use of self-developed program based on the finite element method. In order to obtain high accuracy of the results, an adaptive mesh refinement based on residual estimations of solution errors is applied. The calculation results are represented as dependent on the geometric and working parameters of the pump.

Mechanism of localized severe plastic deformation and damage fracture in fine-blanking using mixed displacement and pressure FEM

A mixed displacement-pressure updated Lagrange FEM was used to simulate the severe plastic deformation, which can overcome shear locking and volume locking. Together with adaptive remeshing technique based on strain gradient and surface curvature, the strain localization in severe plastic deformation can be captured. Schiffmann damage density was used to predict the developments of damage and fracture in sheet metal. The intensive dislocation and slip appear under the action of severe shear deformation, and metallic grains are flattened and elongated in shear band. Because of the existence of large radius of die edge, the flow direction of grains changes, and the grains are elongated and simultaneous. As a result, it is not easy to cut the grains off, and outer surfaces with clean cut are formed.

Pressure control of PEMFC distributed power generator

Control design is important for PEMFC （proton exchange membrane fuel cell） distributed power generator to satisfy user requirement for safe and stable operation. For a complex multi-variable dynamic system, a dynamic simulation model is first established. In view of close coupling and non-linear relationships between variables, the intelligent auto-adapted PI decoupling control method is used. From the simulation results it is found that, by bringing quadratic performance index in the single neuron, constructing adaptive PI controller, and adjusting gas flow rates through the second pressure relief valve and air compressor coordinately, both anode and cathode pressures can be maintained at ideal levels.

人性化管理对新入职护理人员职业适应能力及职业压力的影响

目的探讨人性化管理对新入职护理人员职业适应能力及职业压力的影响。方法将2019年7月—2022年7月的80名新入职护理人员根据随机数字表法分为对照组和观察组。对照组40名护理人员进行常规管理干预,观察组40名护理人员则进行人性化管理干预。比较2组新入职护理人员管理干预前后的职业适应能力(职业适应能力量表)及职业压力状态(护士工作压力源量表)、对管理模式的满意度。结果管理干预前,2组职业适应能力量表及护士工作压力源量表评分比较,差异无统计学意义(P>0.05);管理干预后,2组新入职护理人员的职业适应能力量表评分高于管理干预前,护士工作压力源量表评分低于管理干预前;且管理干预后,观察组的职业适应能力量表评分高于对照组,护士工作压力源量表评分低于对照组,观察组对管理模式的总满意度为100%,高于对照组的82.50%,差异有统计学意义(P<0.05)。结论人性化管理可显著改善新入职护理人员的职业适应能力及职业压力状态,在新入职护理人员中的应用价值相对更高。

国产磁选态铯束频率标准环境特性研究

铯原子频率标准具有长期稳定性好、可靠性高的优点,在导航定位、守时授时、通信电力、时频计量等领域有着广泛的应用。近年来由于军事领域对高精度时间频率源的需求,铯原子频标的使用环境从实验室走向了战车、舰船等机动平台。本文针对铯原子频标在战车、舰船、高原等复杂环境下的环境适应性,研究环境因素对整机指标的影响机理。通过仿真与试验对整钟设计进行优化,以提高整机在力学、热、磁场、低气压等复杂环境下的适应性。经过优化设计后的国产铯束频率标准样机通过了相关环境试验项目的考核,各项指标均满足要求。研究结果表明,铯原子钟电性能样机的稳定度优于8.73×10^(-15)/5 d,磁敏感度3.15×10^(-14)/Gauss,工作温度特性-8.18×10^(-14),这项工作为国产化铯钟的进一步应用提供了基础。

比例减压阀控缸输出力的非线性自适应控制

针对所研制的一款采用双直动式三通比例减压阀控非对称液压缸驱动的刮板型输送带清扫器进行研究,提出了一种基于PI(Prandtl-Ishlinskii)逆模型前馈补偿的自适应控制算法,改善了比例减压阀固有的压力滞环、死区、增益等非线性,保证了清扫器刮板驱动扭矩的精度,实现了以恒定扭矩在刮板全寿命周期内的高效清洁.针对比例减压阀的滞环特性,采用带遗忘因子的递推最小二乘法在线辨识比例减压阀的PI模型参数,进而求解其逆模型作为线性自抗扰控制器的前馈补偿.仿真和实验结果表明,所提算法有效减小了比例减压阀的滞环、死区和增益等非线性,改善了比例减压阀控缸的动态响应,相较于PID算法,跟踪速度提升了65%,在100~700N·m范围内刮板驱动扭矩误差可控制在±2N·m以内.

集成式电液制动系统自适应压力控制

针对集成式电液制动系统(integrated electro-hydraulic brake system,IEHB)存在的复杂液压非线性特性和时变摩擦干扰,提出一种自适应压力控制策略。外环压力控制器引入液压特性的动态线性化模型并基于滑模观测器对模型参数实时辨识实现对非线性液压特性的自适应。内环伺服控制器采用基于压力的连续摩擦补偿和反步动态面控制应对传动机构摩擦阻碍。硬件在环实验结果表明,与现有的先进级联压力控制相比,设计的压力控制策略在多种工况下均表现出更高的控制精度和鲁棒性,并显著提升了IEHB在不同液压回路结构下的压力控制效果。

考虑多维非线性扰动的电子助力制动系统自适应压力控制

针对电子助力制动系统(EBBS)面临的机-电-液多维非线性扰动问题,提出了一种自适应压力控制策略。外层液压控制器引入自适应径向基函数神经网络和鲁棒滑模理论克服液压时变不确定性,中间层位置控制器采用Karnopp摩擦前馈补偿和滑模控制应对传动机构非线性摩擦阻碍,内层电流控制器通过李雅普诺夫理论解决电机电磁特性耦合问题。仿真和硬件在环试验结果表明,设计的压力控制策略能够在多种工况中将EBBS主动制动稳态压力跟随误差维持在0.15MPa之内。

高低温对碳纤维/环氧树脂复合材料高压气瓶的性能影响

为了获得T1000碳纤维/环氧树脂复合材料高压气瓶环境适应能力,有效地掌握气瓶高低温适应性固有规律,以容积50 L、工作压力30 MPa的复合材料气瓶(钛为内衬、碳纤维/环氧树脂为复合层)为研究对象,首先介绍了高低温循环下带压气瓶(在-40~80℃范围内成功通过热真空、热循环验证,具备高压承载能力)的热真空、热循环试验数据,然后采用与气瓶相同复合材料的拉伸试样(缠绕角分别为0°和90°),通过高低温极限摸底试验获得了复合材料经历不同梯度高低温后的拉伸性能数据,通过数据比对分析获得了高低温影响拉伸强度衰减的规律。同时,提出了一种高低温极限摸底试验的可靠性评估方法。结果表明,在-50~100℃范围内,试样拉伸强度及断裂伸长率变化较小;当温度高于100℃时,纤维和树脂的性能发生衰减,导致拉伸强度明显降低;当温度低于-50℃时,树脂的性能发生衰减,纤维受到的影响较小。试样高低温极限摸底试验的可靠度大于0.999,表明采用拉伸试样高低温拉伸强度数据的替代方式具有较高的等效性。

高压气动压力伺服系统的鲁棒控制

高压气动压力伺服系统的参数不确定性和未建模动态制约了其控制精度的提高,针对此提出了基于RISE的自适应鲁棒控制算法用于高压气动压力伺服系统的控制。考虑到核心元件高压电气伺服阀的控制性能对高压气动压力伺服系统高精度控制的影响,设计了交叉对比实验,实验结果表明,伺服阀位置控制算法有助于避免正弦信号失真、减小稳态压力抖动,系统压力控制算法能提高系统的响应速度和动态跟踪能力。

基于BP神经网络的爆炸用激波管峰值压力预测方法

针对爆炸用激波管缺乏相应的经验公式和数值模拟时效性差的问题,同时为了快速得到激波管内的峰值压力,建立预测爆炸用激波管试验段峰值压力的四层反向传播(back propagation,BP)神经网络。采用数值模拟方法计算激波管试验段峰值压力,计算结果与激波管爆炸试验结果进行对比,平均相对误差为2.69%。证明激波管数值模型的准确性后,将数值模拟得到的195组激波管测得的峰值压力作为输出层,激波管驱动段TNT的药量、药柱的长径比以及爆炸比例距离作为神经网络的输入层。为了加快神经网络迭代速度和提高预测精度,使用自适应矩估计(adaptive moment estimation,ADAM)算法作为神经网络误差梯度下降的优化算法。结果表明,训练好的神经网络得到的预测结果与模拟值基本吻合,预测结果与数值模拟结果的平均相对误差为3.26%。BP神经网络模型能够反映激波管爆炸的峰值压力与影响因素之间的映射关系,采用BP神经网络模型计算时比数值模拟节约了大量运算时间。