基于ANN的定向井有杆抽油系统悬点示功图特征参数的计算

有杆抽油系统悬点示功图的特征参数是合理选择地面机电设备的主要依据.由于井下工况的复杂性和部分参数难以确定,使得基于求解高维时变非线性方程的传统方法的计算结果存在偏差.本文将传统方法和神经网络相结合,给出了一种能比较精确地确定定向井有杆抽油系统悬点示功图特征参数的方法,避免了建立和求解复杂的非线性动力学方程.首先依据传统方法,计算出简化悬点示功图的特征参数.然后考虑抽油杆柱弹性振动、抽油杆与油管之问的库仑和粘性摩擦、气体和供液能力等因素的影响,利用BP神经网络和RBF神经网络建立了不同工况下悬点示功图特征参数的计算模型.利用现场实测数据对建立的神经网络进行了训练和测试.测试结果表明了本文方法的正确性和有效性.     

Parameter identification for a damage phase field model using a physics-informed neural network

This work applies concepts of artificial neural networks to identify the parameters of a mathematical model based on phase fields for damage and fracture. Damage mechanics is the part of the continuum mechanics that models the effects of micro-defect formation using state variables at the macroscopic level. The equations that define the model are derived from fundamental laws of physics and provide important relationships among state variables. Simulations using the model considered in this work produce good qualitative and quantitative results, but many parameters must be adjusted to reproduce certain material behavior. The identification of model parameters is considered by solving an inverse problem that uses pseudo-experimental data to find the best values that fit the data. We apply physics informed neural network and combine some classical estimation methods to identify the material parameters that appear in the damage equation of the model. Our strategy consists of a neural network that acts as an approximating function of the damage evolution with output regularized using the residue of the differential equation. Three stages of optimization seek the best possible values for the neural network and the material parameters. The training alternates between the fitting of only the pseudo-experimental data or the total loss that includes the regularizing terms. We test the robustness of the method to noisy data and its generalization capabilities using a simple physical case for the damage model. This procedure deals better with noisy data in comparison with a more standard PDE-constrained optimization method, and it also provides good approximations of the material parameters and the evolution of damage.     

参数灵敏度分析的神经网络方法及其工程应用

在系统分析中，参数灵敏度分析不仅为判断各系统参数的重要性大小提供了依据，量化的灵敏度指标也是后续参数估计的前提。然而，在多效实际系统中，系统参数与系统状态间的显式函数关系不易得到，导致一阶灵敏度指标无法直接求取。简化的单因素分析方法亦存在模型粗糙、精度不高的缺点。本文研究采用人工神经网络的高精度泛化映射，通过少量样本的训练，建立复杂系统中多个系统参数与系统状态间的近似映射关系，继而推导得到统一的灵敏度计算列式。简单结构的神经网络方法和解析方法的对比计算显示了方法的有效性和可靠性。最后，应用该法对某斜拉桥结构的荷载参数和刚度参数进行了考查，得到一般性结论。     

方钢管混凝土短柱轴心受压承载力的神经网络模拟

由于方钢管混凝土的侧向约束机构复杂,对方钢管混凝土柱强度承载力的计算至今仍没有一种统一的方法。本文拟采用神经网络方法对轴心受压方钢管混凝土短柱的承载力进行模拟。以混凝土抗压强度、钢管的屈服强度、套箍指标、截面尺寸和宽厚比等五个参数为网络输入,以构件的极限承载力为网络输出,构建多层前馈神经网络来描述它们之间的非线性关系。利用55组试验数据对网络进行训练和测试,并将其预测值与三种承载力计算模型的预测值进行比较。对比结果表明本文建立的神经网络模型对55组试验数据给出了最好的模拟精度,可作为预测方钢管混凝土柱承载能力的一种新方法。     

Correlation of viscosity in nanofluids using genetic algorithm-neural network (GA-NN)

An accurate and efficient artificial neural network based on genetic algorithm (GA) is developed for predicting of nanofluids viscosity. The genetic algorithm (GA) is used to optimize the neural network parameters. The experimental viscosity in eight nanofluids in the range 238.15–343.15 K with the nanoparticle volume fraction up to 9.4% was used. The obtained results show that the GA-NN model has a good agreement with the experimental data with absolute deviation 2.48% and high correlation coefficient (R ≥ 0.98). The Results also reveals that GA-NN model outperforms to the conventional neural nets in predicting the viscosity of nanofluids with the overall percentage improvement of 39%. Furthermore, the results have also been compared with Einstein, Batchelor and Masoumi et al. models. The findings demonstrate that this model is an efficient method and have better accuracy.     

水下发射水动力的多尺度预测网络研究

空泡的演化和水动力特征的预测在航行体发射的设计中有非常重要的意义. 人工智能技术已经成为了参数预测的重要手段.为了能够快速预测航行体水下发射过程的尾部压力的复杂变化, 提出了一种多尺度深度学习网络.该网络模型以一维卷积网络(1DCNN)为基础,构建了一种编码-解码型网络结构,通过不同的采样频率将原始数据分解为光滑部分和脉动部分,进而训练低保真度的大尺度网络和高保真度的小尺度网络.从而实现对不同物理过程的响应和捕捉.首先,通过数值模拟获得了不同发射条件下的尾部压力曲线,并结合空泡的理论机理构建了具有物理性的输入数据集.其次,将数据集进行分解处理,分别训练了两个尺度的深度学习网络. 最终将两组输出数据整合在一起,建立了底部压力预测模型.并通过测试和验证说明本文提出的多尺度网络对于多种常见的发射条件,能够实现航行体受力特征的快速准确的预测,光滑曲线、压力突变、震荡的频率和幅值都和数值模拟的结果吻合.证明本文的方法能够为运动和弹道的预测提供依据.      

Condition Monitoring of Ground Anchorages by Dynamic Impulses: GRANIT System

The GRANIT system operates by applying an impulse of known force by means of an impact device that is attached to the tendon of the anchorage. The vibration response signals resulting from this impulse are complex in nature and require analysis to be undertaken in order to extract information from the vibrational response signatures that is relevant to the condition of the anchorage. In the system, the complicated relationship that exists between characteristics of an anchorage and its response to an impulse is identified and learned by a novel artificial intelligence network based on artificial intelligence techniques.The results presented in this paper demonstrate the potential of the GRANIT system to diagnose the integrity of ground anchorages at a site near Stone, England, by using a trained neural network capable of diagnosing the post-tension level of the anchorage. This neural network was used for the diagnosis of load in a second ground anchorage adjacent to the original anchorage used for the training of the neural network. Further tests were taken with a different anchor head configuration of the anchorage and a different relationship between the signature response of the anchorage to an applied impulse and its post-tension level was found.Problems encountered during the diagnosis of this second set of test signatures by the trained neural network are investigated with the use of a lumped parameter dynamic model. This model is able to identify the parameters in the anchorage system that affect this change in response signature. The results from the investigation lead to a new form of classification for the installed anchorages, based on their anchor head configuration.Laboratory strand anchorage tests were undertaken in order to compare with and validate the results obtained from the field tests and the lumped parameter dynamic model.     

车载紧耦合MIMUs/GPS的神经网络辅助强跟踪滤波方法

微惯性测量单元由三轴正交的微机械陀螺、加速度计和微型地磁传感器组成.将上述装置与GPS接收机组合,可构成最佳导航定位模型,其中紧耦合MIMUs/GPS对全导航参数(位置、速度及姿态)的测量精度可大幅提高.由于微惯性传感器具有大漂移特性,为获得具有自适应的线性参数模型,提出了融合滤波的信息处理方法,利用强跟踪滤波实现状态预测,二阶EKF实现测量更新,并借用神经网络技术完成对状态预测的修正.由于系统组件具有非线性,该神经网络辅助的强跟踪滤波方法旨在逼近MIMUs/GPS的真实特性,并为车载用户提供更为精准的导航参数信息.动态环境下的仿真试验表明,尽管MEMS惯性传感器的精度有限,所提出的方法能够有效用于实际的导航参数解算.     

基于人工神经网络的湍流大涡模拟方法

大涡模拟方法(LES)是研究复杂湍流问题的重要工具,在航空航天、湍流燃烧、气动声学、大气边界层等众多工程领域中具有广泛的应用前景.大涡模拟方法采用粗网格计算大尺度上的湍流结构,并用亚格子(SGS)模型近似表达滤波尺度以下的流动结构对大尺度流场的作用.传统的亚格子模型由于只利用了单点流场信息和简单的函数关系,在先验验证中相对误差较大, 在后验验证中耗散过强. 近几年来,机器学习方法在湍流建模问题中得到了越来越多的应用.本文介绍了基于人工神经网络(ANN)的湍流亚格子模型的最新进展.详细地讨论了人工神经网络混合模型、空间人工神经网络模型和反卷积人工神经网络模型的构造方法.借助于人工神经网络强大的数据插值能力,新的亚格子模型的先验精度和后验精度均有显著提升. 在先验验证中,新模型所预测的亚格子应力的相关系数超过了0.99,在预测精度上远高于传统的大涡模拟模型. 在后验验证中,新模型对各类湍流统计量和瞬态流动结构的预测都优于隐式大涡模拟方法、动态Smagorinsky模型、动态混合模型等传统模型.因此, 人工神经网络方法在发展复杂湍流的先进大涡模拟模型中具有很大的潜力.      

基于BP神经网络与小冲杆试验确定在役管道钢弹塑性性能方法研究

为了能够在不停输油气工况下获得在役管道材料的弹塑性力学性能, 提出了一种人工智能BP (back-propagation)神经网络、小冲杆试验与有限元模拟相结合,通过确定材料真应力-应变曲线从而获得材料弹塑性力学性能的方法. 首先,通过系统改变Hollomon公式中的参数$K$, $n$值,获得457组具有不同弹塑性力学性能的假想材料本构关系, 其次,将得到的本构关系代入经试验验证的含有Gurson-Tvergaard-Needleman(GTN)损伤参数的小冲杆试验二维轴对称有限元模型,通过有限元计算得到了与真应力-应变曲线一一对应的457条不同假想材料的载荷-位移曲线,最终将两组数据作为数据库输入BP神经网络进行训练,建立了同种材料小冲杆试验载荷-位移曲线与真应力-应变曲线之间的关联关系.通过此关联关系,可利用试验得到的小冲杆载荷-位移曲线获取在役管道钢的真应力-应变曲线,从而确定其弹塑性力学性能.通过对比BP神经网络得到的X80管道钢真应力-应变曲线与单轴拉伸试验的结果以及引用现有文献中不同材料的试验数据对此关系进行验证,证明了该方法的准确性与广泛适用性.      

基坑支护结构水平变形预测的遗传神经网络方法

采用遗传算法和误差反向传播算法相结合的混合算法来训练前馈人工神经网络,先用遗传学习算法进行全局训练,再用BP算法进行精确训练。就遗传算法过程中的选择、变异进行了探索,提出了用BP网络训练产生变异的遗传算法。作为实例,将该方法应用于预测基坑支护结构水平变形中。结果表明,该方法有收敛速度较快、预测精度高等优点。     

基于神经网络方法的包装件非线性特性识别的研究

结合模糊集合理论，将结构化神经网络方法用于包装件缓冲垫层非线性特性识别问题．对于两种典型的包装件缓冲垫层材料模型的模拟识别结果表明，据此方法可以较好地获得其非线性特性．模糊自适应技术的引入，提高了网络训练速度，减少了对于训练参数的人为干预，使得结构化神经网络方法更适于实际应用．     

红板岩材料隐式本构模型的建立及其应用研究

针对红板岩材料在岩土工程中所表现的大量模糊的和不确定的因素等特点,基于人工神经网络的学习能力,借助于室内岩石力学试验,进行了对该材料的力学本构特性进行了神经网络模拟研究,提出了隐式本构模型的思想和方法,并通过该方法对该岩石的流变试验结果进行学习,获得了以网络权值结构保存的力学特性知识,由此得到了表征红板岩应力应变本构关系的隐式本构模型。应用结果表明,该方法对岩土类材料本构关系的模拟研究具有很好的应用前景。     

Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulence

The subgrid-scale(SGS) stress and SGS heat flux are modeled by using an artificial neural network(ANN) for large eddy simulation(LES) of compressible turbulence. The input features of ANN model are based on the first-order and second-order derivatives of filtered velocity and temperature at different spatial locations. The proposed spatial artificial neural network(SANN)model gives much larger correlation coefficients and much smaller relative errors than the gradient model in an a priori analysis. In an a posteriori analysis, the SANN model performs better than the dynamic mixed model(DMM) in the prediction of spectra and statistical properties of velocity and temperature, and the instantaneous flow structures.     

人工神经网络用于识别受内压弹塑性圆管内壁腐蚀的反问题

为确定因腐蚀，圆管内壁几何形状的改变，可通过观察外壁若干点在工作内压下发生的弹塑性应变值，用三层人工神经网络作逆分析。该网络则是由计算力学提供在不同内壁半径和偏心距时的多组应变值进行学习，计算机数值实验表明，这种方法是有效的，识别内壁几何参数有相当的精度。     

APPLICATION OF ARTIFICIAL NEURAL NETWORK TO INVERSE PROBLEMS OF ESTIMATING INNER ETCH OF ELASTOPLASTIC PIPE UNDER PRESSURE

To determine a variation of pipe's inner geometric shape as due to etch,the three-lay-ered feedforward artificial neural network is used in the inverse analysis through observing the elasto-plastic strains of the outer wall under the working inner pressure.Becausc of different kinds of innerwall radii and eccentricity,several groups of strains calculated with computational mechanics are usedfor the network to do learning.Numerical calculation demonstrates that this method is effective and theestimated inner wall geometric parameters have high precision.     

null

Based on the preferred plane theory for regional stability assessment, princIple and methods of artificial neural network (ANN), the model of back propagation (BP) neural network and its algorithm for the preferredfault recognition are discussed in this paper. Practical examples indicate that the new method using BP neural network to determine preferred fault is effective and the prediction result is good.     

Reconstruction of road defects and road roughness classification using vehicle responses with artificial neural networks simulation

The road damage assessment methodology in this paper utilizes an artificial neural network that reconstructs road surface profiles from measured vehicle accelerations. The paper numerically demonstrates the capabilities of such a methodology in the presence of noise, changing vehicle mass, changing vehicle speeds and road defects. In order to avoid crowding out understanding of the methodology, a simple linear pitch-plane model is employed. Initially, road profiles from known roughness classes were applied to a physical model to calculate vehicle responses. The calculated responses and road profiles were used to train an artificial neural network. In this way, the network renders corresponding road profiles on the availability of fresh data on model responses. The results show that the road profiles and associated defects can be reconstructed to within a 20% error at a minimum correlation value of 94%.     

涡激响应尾流双振子模型的参数反演方法

尾流双振子模型是研究圆柱结构涡激振动响应的重要模型,模型参数的准确确定对悬浮隧道设计理论具有重要意义.首先通过降阶法将多变量二阶非线性常微分方程组的尾流双振子模型变换为一阶方程组.然后给出一种新型的圆柱结构水槽试验设计方案,其中试验模型的刚度能够较好反映悬浮隧道等实际工程结构的刚度,基于相机动态捕捉和视频识别计算机程序,获取圆柱结构在水平和竖直方向的位移试验数据.基于试验结果和龙格-库塔方法求解一阶方程组,采用BP神经网络智能算法对模型参数进行反演,同时利用遗传算法对神经元的初始权值和阈值进行优化,所得结果平均误差仅为5.50％,优于遗传算法和未优化的BP神经网络模型.结果表明,基于遗传算法优化的BP神经网络智能算法能够精确实现尾流双振子模型的参数确定,为圆柱结构涡激振动响应分析提供理论基础.