The multi- layers feedforward neural network is used for inversion ofmaterial constants of fluid-saturated porous media. The direct analysis of fluid-saturated porousmedia is carried out with the boundary element meth...The multi- layers feedforward neural network is used for inversion ofmaterial constants of fluid-saturated porous media. The direct analysis of fluid-saturated porousmedia is carried out with the boundary element method. The dynamic displacement responses obtainedfrom direct analysis for prescribed material parameters constitute the sample sets training neuralnetwork. By virtue of the effective L-M training algorithm and the Tikhonov regularization method aswell as the GCV method for an appropriate selection of regu-larization parameter, the inversemapping from dynamic displacement responses to material constants is performed. Numerical examplesdemonstrate the validity of the neural network method.展开更多
Traditional methods for judging the degree of insufficient fluid supply in oil wells have low efficiency and limited accuracy. To address this problem, a method for intelligently identifying the degree of insufficient...Traditional methods for judging the degree of insufficient fluid supply in oil wells have low efficiency and limited accuracy. To address this problem, a method for intelligently identifying the degree of insufficient fluid supply in oil wells based on convolutional neural networks is proposed in this paper. Firstly, 5000 indicator diagrams with insufficient liquid supply were collected from the oilfield site, and a sample set was established after preprocessing;then based on the AlexNet model, combined with the characteristics of the indicator diagram, a convolutional neural network model including 4 layers of convolutional layers, 3 layers of down-pooling layers and 2 layers of fully connected layers is established. The backpropagation, ReLu activation function and dropout regularization method are used to complete the training of the convolutional neural network;finally, the performance of the convolutional neural network under different iteration times and network structure is compared, and the super parameter optimization of the model is completed. It has laid a good foundation for realizing the self-adaptive and intelligent matching of oil well production parameters and formation fluid supply conditions. It has certain application prospects. The results show that the accuracy of training and verification of the method exceeds 98%, which can meet the actual application requirements on site.展开更多
Due to insufficiency of a platform based on experimental results for numerical simulation validation using computational fluid dynamic method(CFD) for different geometries and conditions,in this paper we propose a mod...Due to insufficiency of a platform based on experimental results for numerical simulation validation using computational fluid dynamic method(CFD) for different geometries and conditions,in this paper we propose a modeling approach based on the artificial neural network(ANN) to describe spatial distribution of the particles concentration in an indoor environment.This study was performed for a stationary flow regime.The database used to build the ANN model was deducted from bibliography literature and composed by 261 points of experimental measurement.Multilayer perceptron-type neural network(MLP-ANN) model was developed to map the relation between the input variables and the outputs.Several training algorithms were tested to give a choice of the Fletcher conjugate gradient algorithm(TrainCgf).The predictive ability of the results determined by simulation of the ANN model was compared with the results simulated by the CFD approach.The developed neural network was beneficial and easy to predict the particle dispersion curves compared to CFD model.The average absolute error given by the ANN model does not reach 5%against 18%by the Lagrangian model and 28% by the Euler drift-flux model of the CFD approach.展开更多
A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF ...A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF neural network with the initial parameters obtained by k-means learning method. During the iteration procedure of the algorithm, the centers of the neural network were optimized by using the gradient method with these optimized width values. The computational efficiency was maintained by using the multi-threading technique. SODM-RBFNN consists of two RBF neural network models: one is a running model used to predict the product yields of fluid catalytic cracking unit(FCCU) and optimize its operating parameters; the other is a learning model applied to construct or correct a RBF neural network. The running model can be updated by the learning model according to an accuracy criterion. The simulation results of a five-lump kinetic model exhibit its accuracy and generalization capabilities, and practical application in FCCU illustrates its effectiveness.展开更多
钻井液流变性是钻井液流动和变形的特性,对于携带与悬浮岩屑、提高钻进速度至关重要,准确掌握钻井液流变参数是保证井眼清洁与高效钻进的前提。提出一种基于卷积神经网络(Convolu-tionalNeuralNetwork,CNN)的钻井液流变参数智能识别方法...钻井液流变性是钻井液流动和变形的特性,对于携带与悬浮岩屑、提高钻进速度至关重要,准确掌握钻井液流变参数是保证井眼清洁与高效钻进的前提。提出一种基于卷积神经网络(Convolu-tionalNeuralNetwork,CNN)的钻井液流变参数智能识别方法,通过磁力搅拌产生稳定的钻井液流动图像,利用多种数据增强方法增加图像数量并建立数据库,增强模型的鲁棒性和泛化能力。优化AlexNet卷积神经网络算法,构建钻井液流变参数识别模型。将数据库划分为训练集:验证集:测试集=7:2:1,对训练集进行迭代训练并通过验证集调整参数获得最佳拟合模型。此外,运用混淆矩阵、卷积核可视化技术和类激活技术(Gradient-weighted Class Activation Mapping,Grad-CAM)对模型进行多方位评估。结果表明:(1)钻井液流变参数识别模型对钻井液塑性黏度测试的宏精确率为95.2%,宏召回率为94.7%,宏F1值为0.95。(2)对钻井液表观黏度测试的宏精确率为91.6%,宏召回率为91.5%,宏F1值为0.90。(3)利用卷积核可视化技术和Grad-CAM对特征提取进行可视化处理,发现钻井液波纹形状和大小会影响模型流变参数识别准确度。(4)室内测试结果表明,该模型的测试误差为±2 mPa·s,在设计允许范围以内,具有较高的识别精确度和稳定性。所提出的钻井液流变参数实时智能识别方法可为安全、快速和准确地进行钻井液流变性测试提供智能化技术思路。展开更多
基金the National Natural Science Foundation of China (Nos.19872002 and 10272003)Climbing Foundation of Northern Jiaotong University
文摘The multi- layers feedforward neural network is used for inversion ofmaterial constants of fluid-saturated porous media. The direct analysis of fluid-saturated porousmedia is carried out with the boundary element method. The dynamic displacement responses obtainedfrom direct analysis for prescribed material parameters constitute the sample sets training neuralnetwork. By virtue of the effective L-M training algorithm and the Tikhonov regularization method aswell as the GCV method for an appropriate selection of regu-larization parameter, the inversemapping from dynamic displacement responses to material constants is performed. Numerical examplesdemonstrate the validity of the neural network method.
文摘Traditional methods for judging the degree of insufficient fluid supply in oil wells have low efficiency and limited accuracy. To address this problem, a method for intelligently identifying the degree of insufficient fluid supply in oil wells based on convolutional neural networks is proposed in this paper. Firstly, 5000 indicator diagrams with insufficient liquid supply were collected from the oilfield site, and a sample set was established after preprocessing;then based on the AlexNet model, combined with the characteristics of the indicator diagram, a convolutional neural network model including 4 layers of convolutional layers, 3 layers of down-pooling layers and 2 layers of fully connected layers is established. The backpropagation, ReLu activation function and dropout regularization method are used to complete the training of the convolutional neural network;finally, the performance of the convolutional neural network under different iteration times and network structure is compared, and the super parameter optimization of the model is completed. It has laid a good foundation for realizing the self-adaptive and intelligent matching of oil well production parameters and formation fluid supply conditions. It has certain application prospects. The results show that the accuracy of training and verification of the method exceeds 98%, which can meet the actual application requirements on site.
基金supported by the Algerian Atomic Energy Commission
文摘Due to insufficiency of a platform based on experimental results for numerical simulation validation using computational fluid dynamic method(CFD) for different geometries and conditions,in this paper we propose a modeling approach based on the artificial neural network(ANN) to describe spatial distribution of the particles concentration in an indoor environment.This study was performed for a stationary flow regime.The database used to build the ANN model was deducted from bibliography literature and composed by 261 points of experimental measurement.Multilayer perceptron-type neural network(MLP-ANN) model was developed to map the relation between the input variables and the outputs.Several training algorithms were tested to give a choice of the Fletcher conjugate gradient algorithm(TrainCgf).The predictive ability of the results determined by simulation of the ANN model was compared with the results simulated by the CFD approach.The developed neural network was beneficial and easy to predict the particle dispersion curves compared to CFD model.The average absolute error given by the ANN model does not reach 5%against 18%by the Lagrangian model and 28% by the Euler drift-flux model of the CFD approach.
基金Projects(60974031,60704011,61174128)supported by the National Natural Science Foundation of China
文摘A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF neural network with the initial parameters obtained by k-means learning method. During the iteration procedure of the algorithm, the centers of the neural network were optimized by using the gradient method with these optimized width values. The computational efficiency was maintained by using the multi-threading technique. SODM-RBFNN consists of two RBF neural network models: one is a running model used to predict the product yields of fluid catalytic cracking unit(FCCU) and optimize its operating parameters; the other is a learning model applied to construct or correct a RBF neural network. The running model can be updated by the learning model according to an accuracy criterion. The simulation results of a five-lump kinetic model exhibit its accuracy and generalization capabilities, and practical application in FCCU illustrates its effectiveness.
文摘钻井液流变性是钻井液流动和变形的特性,对于携带与悬浮岩屑、提高钻进速度至关重要,准确掌握钻井液流变参数是保证井眼清洁与高效钻进的前提。提出一种基于卷积神经网络(Convolu-tionalNeuralNetwork,CNN)的钻井液流变参数智能识别方法,通过磁力搅拌产生稳定的钻井液流动图像,利用多种数据增强方法增加图像数量并建立数据库,增强模型的鲁棒性和泛化能力。优化AlexNet卷积神经网络算法,构建钻井液流变参数识别模型。将数据库划分为训练集:验证集:测试集=7:2:1,对训练集进行迭代训练并通过验证集调整参数获得最佳拟合模型。此外,运用混淆矩阵、卷积核可视化技术和类激活技术(Gradient-weighted Class Activation Mapping,Grad-CAM)对模型进行多方位评估。结果表明:(1)钻井液流变参数识别模型对钻井液塑性黏度测试的宏精确率为95.2%,宏召回率为94.7%,宏F1值为0.95。(2)对钻井液表观黏度测试的宏精确率为91.6%,宏召回率为91.5%,宏F1值为0.90。(3)利用卷积核可视化技术和Grad-CAM对特征提取进行可视化处理,发现钻井液波纹形状和大小会影响模型流变参数识别准确度。(4)室内测试结果表明,该模型的测试误差为±2 mPa·s,在设计允许范围以内,具有较高的识别精确度和稳定性。所提出的钻井液流变参数实时智能识别方法可为安全、快速和准确地进行钻井液流变性测试提供智能化技术思路。
