Generation of synthetic dielectric dispersion logs in organic-rich shale formations using neural-network models

Geophysics ◽  
2019 ◽  
Vol 84 (3) ◽  
pp. D117-D129 ◽  
Author(s):  
Jiabo He ◽  
Siddharth Misra
Keyword(s):  
Neural Network ◽  
Reservoir Characterization ◽  
Network Models ◽  
Dielectric Dispersion ◽  
Ann Model ◽  
Neural Network Models ◽  
Shale Formations ◽  
The Third ◽  
Predictive Method ◽  
Predictive Methods

Dielectric dispersion (DD) logs acquired in subsurface geologic formations generally are composed of conductivity ([Formula: see text]) and relative permittivity ([Formula: see text]) measurements at four discrete frequencies in the range of 10 MHz to 1 GHz. Acquisition of DD logs in subsurface formations is operationally challenging, and it requires a hard-to-deploy infrastructure. We developed three supervised neural-network-based predictive methods to process conventional, easy-to-acquire subsurface logs for generating the eight DD logs acquired at four frequencies. These predictive methods will improve reservoir characterization in the absence of a DD logging tool. The predictive methods are tested in three wells intersecting organic-rich shale formations of the Permian Basin and the Bakken Shale. The first method predicts the eight dispersion logs simultaneously using a single artificial neural network (ANN) model, whereas the second method simultaneously predicts the four conductivity dispersion logs using one ANN model, followed by simultaneous prediction of four permittivity dispersion logs using a second ANN model. The third method sequentially predicts the eight dispersion logs, one at a time using eight sequential ANN models, based on a predetermined ranking of the prediction accuracy for each of the eight DD logs when simultaneously generated. Considering that the conventional and DD logs are recorded more than 10,000 ft deep in the subsurface using logging tools that are run at different times in rugose boreholes for sensing the near-wellbore geologic formation, the data used in this predictive work is prone to noise and biases that tend to adversely affect the prediction performances of the proposed methods. In terms of normalized root-mean square error (Nrms error), the prediction performances of the second predictive method are 8.5% worse and 6.2% better for the conductivity and permittivity dispersion logs, respectively, as compared with those of the first predictive method. The third method has best prediction performance for permittivity dispersion logs, which is 0.089 in terms of the Nrms error.

Development of Neural Network Models for a Crude Oil Distillation Column

2012 ◽  
Author(s):  
Khairiyah Mohd. Yusof ◽  
Fakhri Karray ◽  
Peter L. Douglas
Keyword(s):  
Neural Network ◽  
Steady State ◽  
Crude Oil ◽  
Distillation Column ◽  
Network Models ◽  
Ann Model ◽  
Neural Network Models ◽  
Ann Models ◽  
Artificial Neural Network Ann ◽  
Crude Oil Distillation

This paper discusses the development of artificial neural network (ANN) models for a crude oil distillation column. Since the model is developed for real time optimisation (RTO) applications they are steady state, multivariable models. Training and testing data used to develop the models were generated from a reconciled steady-state model simulated in a process simulator. The radial basis function networks (RBFN), a type of feedforward ANN model, were able to model the crude tower very well, with the root mean square error for the prediction of each variable less than 1%. Grouping related output variables in a network model was found to give better predictions than lumping all the variables in a single model; this also allowed the overall complex, multivariable model to be simplified into smaller models that are more manageable. In addition, the RBFN models were also able to satisfactorily perform range and dimensional extrapolation, which is necessary for models that are used in RTO.

Learning Nonlinear Constitutive Laws Using Neural Network Models Based on Indirectly Measurable Data

2020 ◽  
Vol 87 (8) ◽  
Author(s):  
Xin Liu ◽  
Fei Tao ◽  
Haodong Du ◽  
Wenbin Yu ◽  
Kailai Xu
Keyword(s):  
Neural Network ◽  
Damage Model ◽  
Network Models ◽  
Great Accuracy ◽  
Constitutive Laws ◽  
Constitutive Law ◽  
Ann Model ◽  
Neural Network Models ◽  
Plane Shear ◽  
Ann Models

Abstract Artificial neural network (ANN) models are used to learn the nonlinear constitutive laws based on indirectly measurable data. The real input and output of the ANN model are derived from indirect data using a mechanical system, which is composed of several subsystems including the ANN model. As the ANN model is coupled with other subsystems, the input of the ANN model needs to be determined during the training. This approach integrates measurable data, mechanics, and ANN models so that the ANN models can be trained without direct data which is usually not available from experiments. Two examples are provided as an illustration of the proposed approach. The first example uses two-dimensional (2D) finite element (FE) analysis to train an ANN model to learn the nonlinear in-plane shear constitutive law. The second example applies a continuum damage model to train an ANN model to learn the damage accumulation law. The results show that the trained ANN models achieve great accuracy based on the proposed approach.

COMPARISON OF PRODUCT QUALITY ESTIMATION OF PROPYLENE POLYMERIZATION IN LOOP REACTORS USING ARTIFICIAL NEURAL NETWORK MODELS

2016 ◽  
Vol 78 (6-13) ◽  
Author(s):  
Nur Fazirah Jumari ◽  
Khairiyah Mohd-Yusof
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Models ◽  
Melt Flow Index ◽  
Propylene Polymerization ◽  
Flow Index ◽  
Ann Model ◽  
Neural Network Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

One of the major challenges in polymerization industry is the lack of online instruments to measure polymer end-used properties such as xylene soluble, particle size distribution and melt flow index (MFI). As an alternative to the online instruments and conventional laboratory tests, these properties can be estimated using model based-soft sensor. This paper presents models for soft sensors to measure MFI in industrial polypropylene loop reactors using artificial neural network (ANN) model, serial hybrid neural network (HNN) model and stacked neural network (SNN) model. All models were developed and simulated in MATLAB. The simulation results of the MFI based on the ANN, HNN, and SNN models were compared and analyzed.  The MFI was divided into three grades, which are A (10-12g/10 min), B (12-14g/10 min) and C (14-16 g/10 min). The HNN model is the best model in predicting all range of MFI with the lowest root mean square error (RMSE) value, 0.010848, followed by ANN model (RMSE=0.019366) and SNN model (RMSE=0.059132). The SNN model is the best model when tested with each grade of the MFI. It has shown lowest RMSE value for each type of MFI (0.012072 for MFI A, 0.017527 for MFI B and 0.015287 for MFI C), compared to HNN model (0.014916 for MFI A, 0.041402 for MFI B and 0.046437 for MFI C) and ANN model (0.015156 for MFI A, 0.076682 for MFI B, and 0.037862 for MFI C).

Strategies for Building Artificial Neural Network Models

2000 ◽  
Author(s):  
R. L. Mahajan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
First Principles ◽  
Network Models ◽  
Ann Model ◽  
Neural Network Models ◽  
Optimal Network ◽  
Ann Models ◽  
Model Transfer ◽  
Artificial Neural

Abstract An artificial neural network (ANN) is a massively parallel, dynamic system of processing elements, neurons, which are connected in complicated patterns to allow for a variety of interactions among the inputs to produce the desired output. It has the ability to learn directly from example data rather than by following the programmed rules based on a knowledge base. There is virtually no limit to what an ANN can predict or decipher, so long as it has been trained properly through examples which encompass the entire range of desired predictions. This paper provides an overview of such strategies needed to build accurate ANN models. Following a general introduction to artificial neural networks, the paper will describe different techniques to build and train ANN models. Step-by-step procedures will be described to demonstrate the mechanics of building neural network models, with particular emphasis on feedforward neural networks using back-propagation learning algorithm. The network structure and pre-processing of data are two significant aspects of ANN model building. The former has a significant influence on the predictive capability of the network [1]. Several studies have addressed the issue of optimal network structure. Kim and May [2] use statistical experimental design to determine an optimal network for a specific application. Bhat and McAvoy [3] propose a stripping algorithm, starting with a large network and then reducing the network complexity by removing unnecessary weights/nodes. This ‘complex-to-simple’ procedure requires heavy and tedious computation. Villiers and Bernard [4] conclude that although there is no significant difference between the optimal performance of one or two hidden layer networks, single layer networks do better classification on average. Marwah et al. [5] advocate a simple-to-complex methodology in which the training starts with the simplest ANN structure. The complexity of the structure is incrementally stepped-up till an acceptable learning performance is obtained. Preprocessing of data can lead to substantial improvements in the training process. Kown et al. [6] propose a data pre-processing algorithm for a highly skewed data set. Marwah et al. [5] propose two different strategies for dealing with the data. For applications with a significant amount of historical data, smart select methodology is proposed that ensures equal weighted distribution of the data over the range of the input parameters. For applications, where there is scarcity of data or where the experiments are expensive to perform, a statistical design of experiments approach is suggested. In either case, it is shown that dividing the data into training, testing and validation ensures an accurate ANN model that has excellent predictive capabilities. The paper also describes recently developed concepts of physical-neural network models and model transfer techniques. In the former, an ANN model is built on the data generated through the ‘first-principles’ analytical or numerical model of the process under consideration. It is shown that such a model, termed as a physical-neural network model has the accuracy of the first-principles model but yet is orders of magnitude faster to execute. In recognition of the fact that such a model has all the approximations that are generally inherent in physical models for many complex processes, model transfer techniques have been developed [6] that allow economical development of accurate process equipment models. Examples from thermally-based materials processing will be described to illustrate the application of the basic concepts involved.

scholarly journals Forecasting stock index based on hybrid artificial neural network models

2019 ◽  
Vol 3 (1) ◽  
pp. 52-57
Author(s):  
Ta Quoc Bao ◽  
Le Nhat Tan ◽  
Le Thi Thanh An ◽  
Bui Thi Thien My
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Hybrid Model ◽  
Arima Model ◽  
Network Models ◽  
Stock Index ◽  
Ann Model ◽  
Neural Network Models ◽  
Artificial Neural

Forecasting stock index is a crucial financial problem which is recently received a lot of interests in the field of artificial intelligence. In this paper we are going to study some hybrid artificial neural network models. As main result, we show that hybrid models offer us effective tools to forecast stock index accurately. Within this study, we have analyzed the performance of classical models such as Autoregressive Integrated Moving Average (ARIMA), Artificial Neural Network (ANN) model and the Hybrid model, in connection with real data coming from Vietnam Index (VNINDEX). Based on some previous foreign data sets, for most of the complex time series, the novel hybrid models have a good performance comparing to individual models like ARIMA and ANN. Regarding Vietnamese stock market, our results also show that the Hybrid model gives much better forecasting accuracy compared with ARIMA and ANN models. Specifically, our results tell that the Hybrid combination model delivers smaller Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) than ARIMA and ANN models. The fitting curves demonstrate that the Hybrid model produces closer trend so better describing the actual data. Via our study with Vietnam Index, it is confirmed that the characteristics of ARIMA model are more suitable for linear time series while ANN model is good to work with nonlinear time series. The Hybrid model takes into account both of these features, so it could be employed in case of more generalized time series. As the financial market is increasingly complex, the time series corresponding to stock indexes naturally consist of linear and non-linear components. Because of these characteristic, the Hybrid ARIMA model with ANN produces better prediction and estimation than other traditional models.  

Geometry Optimization of Cylindrical Flaps of Oscillating Wave Surge Converters Using Artificial Neural Network Models

2019 ◽  
Author(s):  
Chen-Chou Lin ◽  
Yi-Chih Chow ◽  
Yu-Yu Huang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Geometry Optimization ◽  
Network Models ◽  
Upper And Lower Bounds ◽  
Design Parameters ◽  
Ann Model ◽  
Neural Network Models ◽  
Wave Condition ◽  
Artificial Neural

Abstract This paper presents an optimization algorithm based on the Artificial Neural Network (ANN) to determine the optimal shape, size, and density for the cylindrical flap of the Bottom-Hinged Oscillating Wave Surge Converter (BH-OWSC) that can extract maximal wave power under a given wave condition. Eight parameters are selected, and their upper and lower bounds are set at the initial stage, and then 64 cases with different combinatorial parametric settings are generated by the Design of Experiment process. The 64 cases are then fed into FLOW-3D to simulate the operations of the BH-OWSC under the given wave condition for calculating the capture factor, establishing a database for subsequent ANN data training purpose. To search the maximal capture factor in the specific range of the flap models, we fed 107 random models with various levels of design parameters into the ANN model, which adopts the backpropagation architecture and one hidden layer with ten neuron cells. After three complete random searches, and by simulating the ANN-derived flap’s geometry using FLOW-3D, the result shows that a maximal capture factor of 1.824 can be obtained. The major geometric features of the flap with maximal capture factor are (1) the cylinder axis of the flap inclines to the opposite direction of incident wave propagation, (2) the cylinder’s sectional diameters are about the same size, and (3) the smaller flap density the better power capturing performance.

Intrinsic Plasticity for Natural Competition in Koniocortex-Like Neural Networks

2016 ◽  
Vol 26 (05) ◽  
pp. 1650040 ◽  
Author(s):  
Francisco Javier Ropero Peláez ◽  
Mariana Antonia Aguiar-Furucho ◽  
Diego Andina
Keyword(s):  
Neural Network ◽  
Vector Quantization ◽  
Network Models ◽  
Activation Function ◽  
Inhibitory Interneurons ◽  
Neural Network Models ◽  
The Third ◽  
Initial Network ◽  
Sensory Cortices ◽  
Intrinsic Plasticity

In this paper, we use the neural property known as intrinsic plasticity to develop neural network models that resemble the koniocortex, the fourth layer of sensory cortices. These models evolved from a very basic two-layered neural network to a complex associative koniocortex network. In the initial network, intrinsic and synaptic plasticity govern the shifting of the activation function, and the modification of synaptic weights, respectively. In this first version, competition is forced, so that the most activated neuron is arbitrarily set to one and the others to zero, while in the second, competition occurs naturally due to inhibition between second layer neurons. In the third version of the network, whose architecture is similar to the koniocortex, competition also occurs naturally owing to the interplay between inhibitory interneurons and synaptic and intrinsic plasticity. A more complex associative neural network was developed based on this basic koniocortex-like neural network, capable of dealing with incomplete patterns and ideally suited to operating similarly to a learning vector quantization network. We also discuss the biological plausibility of the networks and their role in a more complex thalamocortical model.

Method of complex copper-zinc ore typification using neural network models

2020 ◽  
Vol 5 ◽  
pp. 140-147 ◽  
Author(s):  
T.N. Aleksandrova ◽  
◽  
E.K. Ushakov ◽  
A.V. Orlova ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Neural Network Models ◽  
Copper Zinc ◽  
Complex Copper

Digital twin of equipment as a basis for the consumer in digital production

2020 ◽  
Keyword(s):  
Neural Network ◽  
Tool Wear ◽  
Chip Formation ◽  
Network Models ◽  
Machining Accuracy ◽  
Neural Network Models ◽  
Digital Twin ◽  
The Neural Network ◽  
Digital Production ◽  
Cyberphysical System

The neural network models series used in the development of an aggregated digital twin of equipment as a cyber-physical system are presented. The twins of machining accuracy, chip formation and tool wear are examined in detail. On their basis, systems for stabilization of the chip formation process during cutting and diagnose of the cutting too wear are developed. Keywords cyberphysical system; neural network model of equipment; big data, digital twin of the chip formation; digital twin of the tool wear; digital twin of nanostructured coating choice

Sign in / Sign up

Export Citation Format

Share Document