scholarly journals Comparative Study of Accurate Descriptions of Hot Flow Behaviors of BT22 Alloy by Intelligence Algorithm and Physical Modeling

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Shaoling Ding ◽  
Chao Fang ◽  
Shulin Zhang
Keyword(s):  
Physical Model ◽  
Relative Error ◽  
Nonlinear Flow ◽  
Support Vector ◽  
Experimental Stress ◽  
Stress Strain ◽  
Absolute Relative Error ◽  
Model Average ◽  
Average Absolute Relative Error ◽  
Strain Data

The nonlinear flow behaviors of BT22 alloy were investigated by thermal simulation experiments at different temperature and strain rates. Taking the experimental stress-strain data as samples, the support vector regression (SVR) model and back propagation artificial neural network (BPANN) model were established by cross-validation (CV) method to describe the nonlinear flow behaviors of BT22 alloy. Genetic algorithm (GA) was used to optimize the parameters of the SVR model and establish the GA-SVR model. At the same time, the physical model optimized by GA algorithm is compared with the machine learning model. Average absolute relative error (AARE), absolute relative error (ARE), and correlation coefficient (R) were used to evaluate the predictive ability of the four models. The results show that the order of model accuracy and generalization ability is GA-SVR > BPANN > SVR > physical model. The AARE value of the GA-SVR model is 1.5752%, and the R value is as high as 0.9984, which can accurately predict the flow behaviors of BT22 alloy. According to the GA-SVR model, the flow behaviors under other conditions could be predicted to expand the experimental stress-strain data and avoid a large number of artificial tests.

Application of Optimized Least Square Support Vector Machine and Genetic Programming for Accurate Estimation of Drilling Rate of Penetration

2018 ◽  
Vol 7 (4) ◽  
pp. 92-108
Author(s):  
Meysam Naderi ◽  
Ehsan Khamehchi
Keyword(s):  
Relative Error ◽  
Flow Rate ◽  
Rotation Speed ◽  
Gel Strength ◽  
Least Square ◽  
Accurate Estimation ◽  
Support Vector ◽  
Absolute Relative Error ◽  
Average Absolute Relative Error ◽  
Weight On Bit

This article describes how the accurate estimation of the rate of penetration (ROP) is essential to minimize drilling costs. There are various factors influencing ROP such as formation rock, drilling fluid properties, wellbore geometry, type of bit, hydraulics, weight on bit, flow rate and bit rotation speed. This paper presents two novel methods based on least square support vector machine (LSSVM) and genetic programming (GP). Models are a function of depth, weight on bit, rotation speed, stand pipe pressure, flow rate, mud weight, bit rotational hours, plastic viscosity, yield point, 10 second gel strength, 10 minute gel strength, and fluid loss. Results show that LSSVM estimates 92% of field data with average absolute relative error of less than 6%. In addition, sensitivity analysis showed that factors of depth, weight on bit, stand pipe pressure, flow rate and bit rotation speed account for 93% of total variation of ROP. Finally, results indicate that LSSVM is superior over GP in terms of average relative error, average absolute relative error, root mean square error, and the coefficient of determination.

scholarly journals An Improved CO2-Crude Oil Minimum Miscibility Pressure Correlation

2015 ◽  
Vol 2015 ◽  
pp. 1-10 ◽  
Author(s):  
Hao Zhang ◽  
Dali Hou ◽  
Kai Li
Keyword(s):  
Experimental Data ◽  
Crude Oil ◽  
Relative Error ◽  
Oil And Gas ◽  
Empirical Correlation ◽  
Volatile Components ◽  
Absolute Relative Error ◽  
Minimum Miscibility Pressure ◽  
New Correlation ◽  
Average Absolute Relative Error

Minimum miscibility pressure (MMP), which plays an important role in miscible flooding, is a key parameter in determining whether crude oil and gas are completely miscible. On the basis of 210 groups of CO2-crude oil system minimum miscibility pressure data, an improved CO2-crude oil system minimum miscibility pressure correlation was built by modified conjugate gradient method and global optimizing method. The new correlation is a uniform empirical correlation to calculate the MMP for both thin oil and heavy oil and is expressed as a function of reservoir temperature, C7+molecular weight of crude oil, and mole fractions of volatile components (CH4and N2) and intermediate components (CO2, H2S, and C2~C6) of crude oil. Compared to the eleven most popular and relatively high-accuracy CO2-oil system MMP correlations in the previous literature by other nine groups of CO2-oil MMP experimental data, which have not been used to develop the new correlation, it is found that the new empirical correlation provides the best reproduction of the nine groups of CO2-oil MMP experimental data with a percentage average absolute relative error (%AARE) of 8% and a percentage maximum absolute relative error (%MARE) of 21%, respectively.

scholarly journals Constitutive Equations for Describing the Warm and Hot Deformation Behavior of 20Cr2Ni4A Alloy Steel

Metals ◽  
2020 ◽  
Vol 10 (9) ◽  
pp. 1169
Author(s):  
Haoran Wang ◽  
Wei Wang ◽  
Ruixue Zhai ◽  
Rui Ma ◽  
Jun Zhao ◽  
...  
Keyword(s):  
Flow Stress ◽  
Alloy Steel ◽  
Relative Error ◽  
Constitutive Equations ◽  
Type Equation ◽  
Coefficient Of Determination ◽  
Original Strain ◽  
Compression Tests ◽  
Absolute Relative Error ◽  
Average Absolute Relative Error

Isothermal hot compression tests of 20Cr2Ni4A alloy steel were performed under temperatures of 973–1273 K and strain rates of 0.001–1 s−1. The behavior of the flow stress of 20Cr2Ni4A alloy steel at warm and hot temperatures is complicated because of the influence of the work hardening, the dynamic recovery, and the dynamic recrystallization. Four constitutive equations were used to predict the flow stress of 20Cr2Ni4A alloy steel, including the original strain-compensated Arrhenius-type (osA-type) equation, the new modified strain-compensated Arrhenius-type (msA-type) equation, the original Hensel–Spittel (oHS) equation and the modified Hensel–Spittel (mHS) equation. The msA-type and mHS are developed by revising the deformation temperatures, which can improve prediction accuracy. In addition, we propose a new method of solving the parameters by combining a linear search with multiple linear regression. The new solving method is used to establish the two modified constitutive equations instead of the traditional regression analysis. A comparison of the predicted values based on the four constitutive equations was performed via relative error, average absolute relative error (AARE) and the coefficient of determination (R2). These results show the msA-type and mHS equations are more accurate and efficient in terms of predicting the flow stress of the 20Cr2Ni4A steel at elevated temperature.

Fiber-Matrix Interactions in Tendon Anisotropic Tensile Behavior

2003 ◽  
Author(s):  
Heather Anne Lynch ◽  
Dawn M. Elliott
Keyword(s):  
Mechanical Behavior ◽  
Three Dimensional ◽  
Tensile Behavior ◽  
Experimental Stress ◽  
Anisotropic Model ◽  
Stress Strain ◽  
Matrix Interactions ◽  
Strain Data ◽  
Fiber Matrix

A three dimensional anisotropic model for tendon behavior was used to fit experimental stress-strain data. This model was motivated by tendon microstructure and included the contributions of fibers, matrix, and fiber-matrix interactions. Our results suggest that fiber-matrix interactions contribute to tendon mechanical behavior.

Fast Prediction Method of Radon Concentration in Environment Air

2014 ◽  
Vol 539 ◽  
pp. 819-822
Author(s):  
He Xi Wu ◽  
Qiang Lin Wei ◽  
Bo Yang ◽  
Qing Cheng Liu
Keyword(s):  
Relative Error ◽  
Radon Concentration ◽  
Gamma Ray ◽  
Transport Model ◽  
Prediction Method ◽  
Field Tests ◽  
Mean Value ◽  
Absolute Relative Error ◽  
Average Absolute Relative Error ◽  
Fast Prediction

Base on the theory that 222Rn can transport in any medium, fast prediction model of radon concentration in environment air can be acquired. And it has been proved accurate by an experiment in laboratory. Many field tests also showed that the average absolute relative error is 8.78% between mean value of measurement and that of fast prediction. It can be predict fleetly the radon concentration by 226Ra which is acquired from the airborne gamma-ray spectra. The relative error between measurement and model is-11.7%. Therefore, the transport model can be effectively applied to predict radon concentration in environment air.

scholarly journals Predicting the flow zone indicator of carbonate reservoirs using NMR echo transforms, and routine open-hole log measurements: Insights from a field case study spanning extreme micro-structure properties

2021 ◽  
Author(s):  
Mabkhout Al-Dousari ◽  
◽  
Salah Almudhhi ◽  
Ali A. Garrouch ◽  
◽  
...  
Keyword(s):  
Relative Error ◽  
Carbonate Reservoir ◽  
Micro Structure ◽  
Flow Zone ◽  
Hydraulic Flow ◽  
Absolute Relative Error ◽  
Flow Units ◽  
Average Absolute Relative Error ◽  
Open Hole ◽  
Hydraulic Flow Units

Predicting the flow zone indicator is essential for identifying the hydraulic flow units of hydrocarbon reservoirs. Delineation of hydraulic flow units is crucial for mapping petrophysical and rock mechanical properties. Precise prediction of the flow zone indicator (FZI) of carbonate rocks using well log measurements in un-cored intervals is still a daunting challenge for petrophysicists. This study presents a data mining methodology for predicting the rock FZI using NMR echo transforms, and conventional open-hole log measurements. The methodology is applied on a carbonate reservoir with extreme microstructure properties, from an oil “M” field characterized by a relatively high-permeability with a median of approximately 167 mD, and a maximum of 3480 mD. The reservoir from the M field features detritic, or vuggy structure, covering a wide range of rock fabrics varying from microcrystalline mudstones to coarse-grained grainstones. Porosity has a median of approximately 22%. Dimensional analysis and regression analysis are applied for the derivation of four transforms that appear to capture approximately 80% of the FZI variance. These four transforms are formulated using the geometric mean of the transverse NMR relaxation time (T2lm), the ratio of the free fluid index (FFI) to the bulk volume irreducible (BVI), the bulk density, the sonic compressional travel time, the true resistivity, the photo-electric absorption, and the effective porosity. Non-linear regression models have been developed for predicting the FZI using the derived transforms, for the carbonate reservoir from the M field. The average relative error for the estimated FZI values is approximately 52%. The same transforms are used as input for training a developed general regression neural network (GRNN), built for the purpose of predicting rock FZI. The constructed GRNN predicts FZI with a notable precision. The average absolute relative error on FZI for the training set is approximately 3.1%. The average absolute relative error on FZI for the blind testing set is approximately 22.0 %. The data mining approach presented in this study appears to suggest that (i) the relationship between the flow zone indicator and open-hole log attributes is highly non-linear, (ii) the FZI is highly affected by parameters that reflect rock texture, rock micro-structure geometry, and diagenetic alterations, and (iii) the derived transforms provide a means for further enhancement of the flow zone indicator prediction in carbonate reservoirs.

scholarly journals Comparative Analysis of Machine Learning Models for Nanofluids Viscosity Assessment

Nanomaterials ◽  
2020 ◽  
Vol 10 (9) ◽  
pp. 1767 ◽  
Author(s):  
Mohammadhadi Shateri ◽  
Zeinab Sobhanigavgani ◽  
Azin Alinasab ◽  
Amir Varamesh ◽  
Abdolhossein Hemmati-Sarapardeh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Volume Fraction ◽  
Intelligent System ◽  
Relative Viscosity ◽  
Support Vector ◽  
Absolute Relative Error ◽  
Average Absolute Relative Error ◽  
Rbf Kernel ◽  
Input Variables ◽  
Nanofluid Viscosity

The process of selecting a nanofluid for a particular application requires determining the thermophysical properties of nanofluid, such as viscosity. However, the experimental measurement of nanofluid viscosity is expensive. Several closed-form formulas for calculating the viscosity have been proposed by scientists based on theoretical and empirical methods, but these methods produce inaccurate results. Recently, a machine learning model based on the combination of seven baselines, which is called the committee machine intelligent system (CMIS), was proposed to predict the viscosity of nanofluids. CMIS was applied on 3144 experimental data of relative viscosity of 42 different nanofluid systems based on five features (temperature, the viscosity of the base fluid, nanoparticle volume fraction, size, and density) and returned an average absolute relative error (AARE) of 4.036% on the test. In this work, eight models (on the same dataset as the one used in CMIS), including two multilayer perceptron (MLP), each with Nesterov accelerated adaptive moment (Nadam) optimizer; two MLP, each with three hidden layers and Adamax optimizer; a support vector regression (SVR) with radial basis function (RBF) kernel; a decision tree (DT); tree-based ensemble models, including random forest (RF) and extra tree (ET), were proposed. The performance of these models at different ranges of input variables was assessed and compared with the ones presented in the literature. Based on our result, all the eight suggested models outperformed the baselines used in the literature, and five of our presented models outperformed the CMIS, where two of them returned an AARE less than 3% on the test data. Besides, the physical validity of models was studied by examining the physically expected trends of nanofluid viscosity due to changing volume fraction.

A Modified Constitutive Model for Tensile Flow Behaviors of BR1500HS Ultra-High-Strength Steel at Medium and Low Temperature Regions

2018 ◽  
Vol 37 (1) ◽  
pp. 39-57
Author(s):  
Jun Zhao ◽  
Guo-Zheng Quan ◽  
Jia Pan ◽  
Xuan Wang ◽  
Dong-Sen Wu ◽  
...  
Keyword(s):  
Low Temperature ◽  
Constitutive Model ◽  
Strain Rate ◽  
Relative Error ◽  
High Strength ◽  
Uniaxial Tensile ◽  
Stress Strain ◽  
Element Analysis ◽  
Strain And Strain Rate ◽  
Average Absolute Relative Error

AbstractConstitutive model of materials is one of the most requisite mathematical model in the finite element analysis, which describes the relationships of flow behaviors with strain, strain rate and temperature. In order to construct such constitutive relationships of ultra-high-strength BR1500HS steel at medium and low temperature regions, the true stress-strain data over a wide temperature range of 293–873 K and strain rate range of 0.01–10 s−1 were collected from a series of isothermal uniaxial tensile tests. The experimental results show that stress-strain relationships are highly non-linear and susceptible to three parameters involving temperature, strain and strain rate. By considering the impacts of strain rate and temperature on strain hardening, a modified constitutive model based on Johnson-Cook model was proposed to characterize flow behaviors in medium and low temperature ranges. The predictability of the improved model was also evaluated by the relative error ($W(\%)$), correlation coefficient (R) and average absolute relative error (AARE). The R-value and AARE-value for modified constitutive model at medium and low temperature regions are 0.9915 & 1.56 % and 0.9570 & 5.39 %, respectively, which indicates that the modified constitutive model can precisely estimate the flow behaviors for BR1500HS steel in the medium and low temperature regions.

Sign in / Sign up

Export Citation Format

Share Document