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 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.

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.

scholarly journals Edible Gelatin Diagnosis Using Laser-Induced Breakdown Spectroscopy and Partial Least Square Assisted Support Vector Machine

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4225 ◽  
Author(s):  
Hao Zhang ◽  
Shun Wang ◽  
Dongxian Li ◽  
Yanyan Zhang ◽  
Jiandong Hu ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Partial Least Square ◽  
Least Square ◽  
Computational Time ◽  
Laser Induced Breakdown Spectroscopy ◽  
Accurate Estimation ◽  
Support Vector ◽  
Breakdown Spectroscopy ◽  
Svm Model ◽  
Laser Induced Breakdown

Edible gelatin has been widely used as a food additive in the food industry, and illegal adulteration with industrial gelatin will cause serious harm to human health. The present work used laser-induced breakdown spectroscopy (LIBS) coupled with the partial least square–support vector machine (PLS-SVM) method for the fast and accurate estimation of edible gelatin adulteration. Gelatin samples with 11 different adulteration ratios were prepared by mixing pure edible gelatin with industrial gelatin, and the LIBS spectra were recorded to analyze their elemental composition differences. The PLS, SVM, and PLS-SVM models were separately built for the prediction of gelatin adulteration ratios, and the hybrid PLS-SVM model yielded a better performance than only the PLS and SVM models. Besides, four different variable selection methods, including competitive adaptive reweighted sampling (CARS), Monte Carlo uninformative variable elimination (MC-UVE), random frog (RF), and principal component analysis (PCA), were adopted to combine with the SVM model for comparative study; the results further demonstrated that the PLS-SVM model was superior to the other SVM models. This study reveals that the hybrid PLS-SVM model, with the advantages of low computational time and high prediction accuracy, can be employed as a preferred method for the accurate estimation of edible gelatin adulteration.

Air Piston Calibrator for Microflow Delivery and Measurement Systems

2007 ◽  
Author(s):  
Chun-Min Su ◽  
Ting-Hsuan Chen ◽  
Cheng-Tsair Yang
Keyword(s):  
Relative Error ◽  
Flow Rate ◽  
Liquid Flow ◽  
Flow Measurement ◽  
Flow Rates ◽  
Measurement Systems ◽  
Absolute Relative Error ◽  
Time Period ◽  
Measurement Principle ◽  
The Mean

In view of the increasing need of microflow measurement and calibration, this paper presents a liquid flow measurement device to verify the performance of microflow sensors and pumps. The measurement principle of the air piston calibrator was based on the volumetric, time-of-flight approach. The device consisted of a micro-fabricated flow channel mounted on a base chip deployed with electrodes. A gas-liquid interface was introduced in the microchannel and moved along with the liquid flow. Upon passing by the electrodes, the interface brought about resistance variations due to the different permittivity of the gas and liquid. The time period between a pair of signal detected by the electrodes and the corresponding channel volume were then used to determine the flow rate. By the combination of different sized microchannels, a capability of measuring flow rates from 10 nL/min to 1 mL/min was demonstrated. The detection electrodes were optimized prior to their fabrication by numerical simulation. To provide a desired traceability, the volume in the channel between electrode nodes was corrected by the standard flow rate delivered by the calibrated syringe pump. Results showed that, for flow rates from 0.1 μ L/min to 1 mL/min, the mean absolute relative error and standard deviation of relative error of the measurements were lower than 1.1% and 4%, respectively.

scholarly journals Estimation of Monthly Total Dissolved Solids Using ANN and LS-SVM Techniques in the Aji Chay River, Iran

2021 ◽  
Vol 10 (1) ◽  
pp. 1-10
Author(s):  
Mahdieh JannatKhah ◽  
Abolghasem Akbari ◽  
Aida Bagheri Basmanji ◽  
Ebrahim Rahmani ◽  
Jonathan Peter Cox
Keyword(s):  
Back Propagation ◽  
Least Square ◽  
Urmia Lake ◽  
Accurate Estimation ◽  
Support Vector ◽  
Ann Model ◽  
North West ◽  
Feed Forward Back Propagation ◽  
Svm Model ◽  
Monthly Total

This research follows on from diverse international efforts to safeguard one of the largest natural lakes in the world, Urmia lake in North West Iran. In this research two new numerical packages based on Artificial Neural Networks (ANN) and the Least Square Support Vector Machine (LS-SVM) models were developed to estimate monthly Total Dissolved Solid (TDS) in the Aji Chay River, one the main tributaries of Urmia lake, Iran. A feed forward back propagation (FFB) model was used to obtain a set of coefficients for a linear model, and the radial basis function (RBF) kernel was employed for the LS-SVM model. The input data sets of both the ANN and LS-SVM models consists of six water quality parameters: TDS, Mg2+, Na+, Ca2+, Cl-, and SO4 2-, all collected on a monthly time scale over a period of 30 years from the Vanyar and Zarnagh stations, in the Aji Chay watershed. The research demonstrated that both models can effectively predict the variability of TDS, but for the Vanyar station with the ANN model (giving an R2 value of 0.913 and RMSE of 0.0032, a Nash-Sutcliffe Efficiency (NSE) coefficient 0.812 and as such has a more efficient and accurate estimation when compared to the LS-SVM model with R2=0.871 and RMSE =0.097 and NSE=0.86. The analysis of Zarnagh station data shows R2=0.853 and RMSE=0.0162, NSE= 0.854 for SVM and R2=0.903 and RMSE =0.0091 and NSE=0.85 for ANN.

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.

Sign in / Sign up

Export Citation Format

Share Document