Terms Of Correlation Research Articles

Modeling the Hot Deformation Behaviors of As-Extruded 7075 Aluminum Alloy by an Artificial Neural Network with Back-Propagation Algorithm

Abstract In order to investigate the hot deformation behaviors of as-extruded 7075 aluminum alloy, the isothermal compressive tests were conducted at the temperatures of 573, 623, 673 and 723 K and the strain rates of 0.01, 0.1, 1 and 10 s−1 on a Gleeble 1500 thermo-mechanical simulator. The flow behaviors showing complex characteristics are sensitive to strain, strain rate and temperature. The effects of strain, temperature and strain rate on flow stress were analyzed and dynamic recrystallization (DRX)-type softening characteristics of the flow behaviors with single peak were identified. An artificial neural network (ANN) with back-propagation (BP) algorithm was developed to deal with the complex deformation behavior characteristics based on the experimental data. The performance of ANN model has been evaluated in terms of correlation coefficient (R) and average absolute relative error (AARE). A comparative study on Arrhenius-type constitutive equation and ANN model for as-extruded 7075 aluminum alloy was conducted. Finally, the ANN model was successfully applied to the development of processing map and implanted into finite element simulation. The results have sufficiently articulated that the well-trained ANN model with BP algorithm has excellent capability to deal with the complex flow behaviors of as-extruded 7075 aluminum alloy and has great application potentiality in hot deformation processes.

Impedimetric non-enzymatic glucose sensor based on nickel hydroxide thin film onto gold electrode

A non-enzymatic glucose sensor based on a thin layer of nickel immobilized on a gold electrode (EAuNi(OH)2) was used to perform impedimetric determination of glucose. The electrodeposition solution, composed of 0.010M Ni(NO3)2·6H2O and 1M of chloride, allows only one active catalyst (NiOOH) to be present on the gold electrode surface after activation with 0.1M KOH.Electrochemical oxidation of glucose on EAuNi(OH)2 electrode was evaluated by Cyclic Voltammetry (CV) and Electrochemical Impedance Spectroscopy (EIS) in the concentration range of 0–14.8mM of analyte. Ip/v1/2 vs scan rate graph shows a typical catalytic behavior by EAuNi(OH)2 toward glucose oxidation. Measurements in the presence of possible interfering species (ascorbic acid, uric acid, dopamine) did not affect the response of the analyte of interest.EIS offers good sensibility and selectivity for the glucose detection by non-enzymatic glucose sensor as an alternative to conventional methods. A single-frequency impedance method is proposed as transduction principle. For that, the parameters of complex impedance (module, phase, real and imaginary impedance) at each frequency were evaluated in function of glucose concentration and in terms of correlation coefficient. These analyses show a better linear response for the module of impedance (|Z|) in the range of 0–2mM of glucose at 0.1Hz (R2=0.984) with a slope of 484.7ΩmM−1 of glucose. Finally, EAuNi(OH)2 was successfully applied to the assay of glucose in blood samples.

Clinical applicability of a new 3D portable stereo-photogrammetric opto-electronic device

s / Gait & Posture 42S (2015) S1–S27 S5 Fig. 1. (a) Reference image. Model generated after the manual identification of the relevant anatomical landmarks. (b) Tracked model in a dynamic frame. They wore an underwear garment with a coloured patch applied, and uniformly coloured ankle socks used as segmentalmarkers (for pelvis and feet, respectively). A RGB video camera (Vicon Bonita 720C, 60 fps) was placed laterally to the walkway. Synchronous 3D marker positions were captured with a Vicon system (Bonita10). Markers were positioned according to the Davis protocol [3] (GS). The proposed ML methodology requires a preliminary model calibration step, performed on a reference image of the subject standing upright (Fig. 1a), from which a foot contour model template is automatically identified, while the lateral malleolus, lateral epicondyle and greater trochanter are manually identified [2]. Model templates of the shank and thigh segments are defined bymeans of technical reference points identified on the silhouette contour. The pelvis orientation is assumed to coincidewith the orientation of the segment obtained by interpolating the points extracted from the pelvis patch. For eachgait trial, the silhouette contourof themoving subject was extracted using a background subtraction technique, and the foot and pelvis segmental markers were identified using colour filters. The foot orientation was determined by matching the foot template with the foot current image. The shank and thigh reference points on the deformed silhouette contour were identified for each frame, and the corresponding templates fitted using a SVD procedure (Fig. 1b) [2]. The kinematic estimations provided by theMLmethodwere compared to the GS in terms of correlation coefficient (CC) and root mean square deviation (RMSD). Results: The CC (and RMSD) between the ML and the GS estimations ranged from 0.91 (4.9◦) to 0.98 (7.3◦) for the hip flexextension, from0.94 (5.4◦) to 0.97 (8.3◦) for the knee flex-extension and from0.74 (5.9◦) to0.84 (9.9◦) for theankledorsi-plantarflexion. Discussion: Joint kinematics estimatedusingML showed a good correlation with the GS joint kinematics (0.74≤CC≤0.98), however the relevant errors are clearly larger than those found in healthy adults [2] (up to 9.9◦). This difference can be attributed partly to the children’s body segments small size (particularly for the foot) and in some cases to the presence of the arm swing that reduces the visibility of the pelvis segmental marker. Therefore, the extraction of the segmental markers will have to be improved in order for this method to be applied in clinical settings.

Strain-Compensated Arrhenius-Type Constitutive Model for Flow Behavior of Al-12Zn-2.4Mg-1.2Cu Alloy

Abstract The isothermal hot compression tests of as-extruded Al-12Zn-2.4Mg-1.2Cu alloy were performed on a Gleeble-3500 thermo-simulation machine. Based on the Arrhenius-type constitutive model, the experimental stress-strain data over a wide range of temperatures (523∼723 K), strains (0.1∼0.6) and strain rates (0.001, 0.01, 0.1 and 1 s−1) were employed to develop a suitable constitutive model to predict the elevated temperature flow behavior. The effects of temperature and strain rate on deformation behavior were represented by Zener-Holloman parameter in an exponent-type equation. The influence of strain was incorporated in constitutive analysis by considering the effect of strain on material constants. Suitability of the developed constitutive model was evaluated by comparing experimental and predicted data in terms of correlation coefficient (R) and average absolute relative error (AARE). Results show that the values of R and ARRE are 0.995 82 and 6.66%, respectively, which indicate that the developed model considering the compensation of stain can predict flow stress of experimental alloy and has good correlation and generalization.

Application of a markerless gait analysis methodology in children with cerebral palsy: Preliminary results

s / Gait & Posture 42S (2015) S1–S27 S5 Fig. 1. (a) Reference image. Model generated after the manual identification of the relevant anatomical landmarks. (b) Tracked model in a dynamic frame. They wore an underwear garment with a coloured patch applied, and uniformly coloured ankle socks used as segmentalmarkers (for pelvis and feet, respectively). A RGB video camera (Vicon Bonita 720C, 60 fps) was placed laterally to the walkway. Synchronous 3D marker positions were captured with a Vicon system (Bonita10). Markers were positioned according to the Davis protocol [3] (GS). The proposed ML methodology requires a preliminary model calibration step, performed on a reference image of the subject standing upright (Fig. 1a), from which a foot contour model template is automatically identified, while the lateral malleolus, lateral epicondyle and greater trochanter are manually identified [2]. Model templates of the shank and thigh segments are defined bymeans of technical reference points identified on the silhouette contour. The pelvis orientation is assumed to coincidewith the orientation of the segment obtained by interpolating the points extracted from the pelvis patch. For eachgait trial, the silhouette contourof themoving subject was extracted using a background subtraction technique, and the foot and pelvis segmental markers were identified using colour filters. The foot orientation was determined by matching the foot template with the foot current image. The shank and thigh reference points on the deformed silhouette contour were identified for each frame, and the corresponding templates fitted using a SVD procedure (Fig. 1b) [2]. The kinematic estimations provided by theMLmethodwere compared to the GS in terms of correlation coefficient (CC) and root mean square deviation (RMSD). Results: The CC (and RMSD) between the ML and the GS estimations ranged from 0.91 (4.9◦) to 0.98 (7.3◦) for the hip flexextension, from0.94 (5.4◦) to 0.97 (8.3◦) for the knee flex-extension and from0.74 (5.9◦) to0.84 (9.9◦) for theankledorsi-plantarflexion. Discussion: Joint kinematics estimatedusingML showed a good correlation with the GS joint kinematics (0.74≤CC≤0.98), however the relevant errors are clearly larger than those found in healthy adults [2] (up to 9.9◦). This difference can be attributed partly to the children’s body segments small size (particularly for the foot) and in some cases to the presence of the arm swing that reduces the visibility of the pelvis segmental marker. Therefore, the extraction of the segmental markers will have to be improved in order for this method to be applied in clinical settings.

Homomorphic Filter Based Image Watermarking

This paper proposes a spatial domain image watermarking method based on homomorphic filter. In the proposed method, after applying the homomorphic filter to the host color image, a watermark image is embedded into the natural logarithm reflectance component of the image. Based on the concept that the reflectance component contains most of the image details with low energy, the watermark energy added to this component will be imperceptually noticed by the human eye. The embedding watermark is also protected by a key-based stream cipher, so that without the correct secret key, one cannot reconstruct the watermark. To identify the existence of the embedded watermark, the semi-blind detection approach is applied. The performance of the proposed method in terms of correlation coefficient between the original and extracted watermarks is measured and presented. Its robustness against image blurring and image sharpening at various strengths is also evaluated. The results show the potential of the proposed method for a practical system.

Behavior and modeling of flow softening and ductile damage evolution in hot forming of TA15 alloy sheets

Abstract Flow softening and ductile damage behavior of TA15 titanium alloy with initial bimodal microstructure were studied using uniaxial hot tensile tests at different temperatures (750–850 °C) and strain rates (0.001–0.1 s− 1). SEM examination of deformed specimens shows that deformation mainly occurs in β and secondary α phase (αs). Globularization of αs is also observed. According to the SEM observations of the cracked specimens, the mechanism of ductile damage is attributed to the breakdown of the compatibility requirements at the α/β interface. Based on the experimental results, a set of mechanism-based unified elastic-viscoplastic constitutive equations have been formulated to model the flow behavior and the damage evolution of TA15 alloy in hot forming conditions. Dislocation density, ductile damage evolution, deformation heat, phase transformation and globularization of the αs have been modeled. The model constants have been determined by using a Genetic Algorithm (GA)-based optimization method. Furthermore, the proposed constitutive equations were evaluated in terms of correlation coefficient (R), average absolute relative error (AARE), and root mean square error (RMSE). The results indicate that the calibrated predictions, including flow stress, volume fraction of each phase, and fracture strain, are in good agreement with experimental results.

Effects Of Glucose And Bilirubin On The Kinetic Jaffe's And The Enzymatic Methods For Serum Creatinine Assay

Summary The enzymatic method for the determination of serum creatinine is accepted as one of the most accurate methods in a clinical laboratory. This method was used on a biochemistry auto analyzer (Cobas Integra 400) to determine serum creatinine at the laboratory of University Hospital – Pleven. The characteristics and reliability of this enzymatic method for creatinine were compared with the Jaffe kinetic method. Effects of some interfering substances like bilirubin and glucose on the Jaffe kinetic method and the enzymatic method were compared. Glucose and bilirubin inhibit the reaction between creatinine and alkaline picrate. Glucose slowly reduces picric acid to picrate, while the bilirubin present in a sample is oxidized to biliverdin under alkaline conditions. This leads to a decrease in absorbance at 520 nm. We measured creatinine in serum samples with the enzymatic method and the Jaffe kinetic method in samples divided into four groups: group I –samples without bilirubin and glucose ; group II –samples with high level of glucose; group III - samples with high level of bilirubin, group IV – all samples. For Group I, the correlation coefficient obtained by comparing the enzymatic creatinine method and Jaffe's kinetic method was R = 0.983. There was a very good agreement between the two methods in terms of correlation coefficient even in the samples with high levels of glucose or bilirubin.

The Contributions of Polycyclic Aromatic Hydrocarbons to Soil Biotoxicity

Principal component analysis was employed to identify the sources of polycyclic aromatic hydrocarbons soil contaminants, and then an artificial neural network was applied to investigate the contribution of the polycyclic aromatic hydrocarbons to soil biotoxicity. An artificial neural network model with a 4-9-1 architecture provided the most accurate results in terms of correlation coefficient (r, 0.7592), root-mean-square error (0.7396), and bias (-0.0879). The contamination sources included traffic emissions (13.2%), petroleum-related products (37.4%), coal combustion (36.0%), and combustion of other fossil fuels (13.4%).

Hot Deformation Behavior and Flow Stress Prediction of TC4-DT Alloy in Single-Phase Region and Dual-Phase Regions

Isothermal compression tests of TC4-DT titanium alloy at the deformation temperature ranging from 1181 to 1341 K covering α + β phase field and β-phase field, the strain rate ranging from 0.01 to 10.0 s−1 and the height reduction of 70% were conducted on a Gleeble-3500 thermo-mechanical simulator. The experimental true stress-true strain data were employed to develop the strain-compensated Arrhenius-type flow stress model and artificial neural network (ANN) model; the predictability of two models was quantified in terms of correlation coefficient (R) and average absolute relative error (AARE). The R and AARE for the Arrhenius-type flow stress model were 0.9952 and 5.78%, which were poorer linear relation and more deviation than 0.9997 and 1.04% for the feed-forward back-propagation ANN model, respectively. The results indicated that the trained ANN model was more efficient and accurate in predicting the flow behavior for TC4-DT titanium alloy at elevated temperature deformation than the strain-compensated Arrhenius-type constitutive equations. The constitutive relationship compensating strain could track the experimental data across the whole hot working domain other than that at high strain rates (≥1 s−1). The microstructure analysis illustrated that the deformation mechanisms existed at low strain rates (≤0.1 s−1), where dynamic recrystallization occurred, were far different from that at high strain rates (≥1 s−1) that presented bands of flow localization and cracking along grain boundary.

A LSSVM approach for determining well placement and conning phenomena in horizontal wells

Understanding the time of water/gas breakthrough has a prominent role in cost effective oil production, improve oil recovery and extension the reservoir production time. The importance lies in the fact that once water or gas has broken through, the fluid distribution and the fluid relative permeabilities in the system will change. Accordingly, applying robust predictive models in this area to arrive at a proper estimation of breakthrough times as well as optimal horizontal well placement in heterogeneous and homogeneous reservoirs as a function of density difference ratio and rate is of great interest in oil and gas production system. The current study plays emphasis on applying the predictive model with the aim of the LSSVM (least square support vector machine) to estimate breakthrough time and optimum fractional well placement. Genetic algorithm (GA) was utilized to choose and optimize hyper parameters (γ and σ2) which are embedded in LSSVM model. Utilization of this model showed high competence of the applied model in terms of correlation coefficient (R2) of 0.9999 and 0.9999, mean squared error (MSE) of 0.000000142 and 0.000000622 from actual values for estimated dimensionless breakthrough time and optimum fractional well placement, respectively.

Fusion of MS and PAN Images Preserving Spectral Quality

Image fusion aims at improving spectral information in a fused image as well as adding spatial details to it. Among the existing fusion algorithms, filter-based fusion methods are the most frequently discussed cases in recent publications due to their ability to improve spatial and spectral information of multispectral (MS) and panchromatic (PAN) images. Filter-based approaches extract spatial information from the PAN image and inject it into MS images. Designing an optimal filter that is able to extract relevant and nonredundant information from the PAN image is presented in this letter. The optimal filter coefficients extracted from statistical properties of the images are more consistent with type and texture of the remotely sensed images compared with other kernels such as wavelets. Visual and statistical assessments show that the proposed algorithm clearly improves the fusion quality in terms of correlation coefficient, relative dimensionless global error in synthesis, spectral angle mapper, universal image quality index, and quality without reference, as compared with fusion methods, including improved intensity-hue-saturation, multiscale Kalman filter, Bayesian, improved nonsubsampled contourlet transform, and sparse fusion of image.

A global comparison of alternate AMSR2 soil moisture products: Why do they differ?

This study assesses two remotely sensed soil moisture products from the Advanced Microwave Scanning Radiometer 2 (AMSR2), a sensor onboard the Global Change Observation Mission 1 — Water (GCOM-W1) that was launched in May 2012. The soil moisture products were retrieved by the Japan Aerospace Exploration Agency (JAXA) algorithm and the Land Parameter Retrieval Model (LPRM) developed by the VU University Amsterdam, in collaboration with the National Aeronautics and Space Administration (NASA). The two products are compared at the global scale. In addition, the products are evaluated against field measurements from 47 stations from the COsmic-ray Soil Moisture Observing System (COSMOS) network which are located in the United States (36 stations), Australia (7 stations), Europe (2 stations) and Africa (2 stations).After examining the retrieval algorithms, it is hypothesized that four factors, namely, physical surface temperatures, surface roughness, vegetation and ground soil wetness conditions, may affect the quality of soil moisture retrievals. From the inter-comparisons at the global scale, the correlations of the two products highlight differences in the representation of the seasonal cycle of soil moisture, with negative correlations found for several regions. Correlations of the anomaly time series were generally strong (R>0.6) as a result of soil moisture sensitivity to external meteorological forcing and possibly also random noise in the satellite observations. Due to the inherent differences in spatial coverage and measurement scale of the COSMOS and satellite data, the comparisons in terms of correlation coefficients are the most reliable. It was found that both products show rapid decreases in correlation coefficients under low mean temperature (<290K), high mean EVI (>0.3) and highly wetted conditions. These findings are further supported by the bias and RMSE estimates which show that JAXA has relatively better performance under dry conditions while the bias and RMSE of LPRM are generally smaller than JAXA, when considered against the four variables. These results provide information on appropriate parameterizations and model selection for the retrieval algorithms and a future research direction to improve the quality by leveraging the strengths of the JAXA and LPRM algorithms. With these, when a multi-year dataset is available, there will be more confidence in defining the seasonal cycle and the data can be decomposed to identify the anomalies where the bias is not relevant.

A Characterization of Hot Flow Behaviors Involving Different Softening Mechanisms by ANN for As-Forged Ti-10V-2Fe-3Al Alloy

Abstract The isothermal compressions of as-forged Ti-10V-2Fe-3Al alloy at the deformation temperature range of 948–1,123 K and the strain rates in the range of 0.001–10 s−1 with a height reduction of 60% were conducted on a Gleeble-3500 thermo-mechanical simulator. The flow behaviors show nonlinear sensitivity to strain, strain rate and temperature. Based on the experimental data, an artificial neural network (ANN) with back-propagation algorithm was developed to deal with the complex deformation behavior characteristics. In the present ANN model, strain, strain rate and temperature were taken as inputs, and flow stress as output. A comparative study on the constitutive relationships based on regression and ANN methods was conducted. According to the predicted and experimental results, the predictabilities of the two models have been evaluated in terms of correlation coefficient (R) and average absolute relative error (AARE). The R-value and the AARE-value at strain of 0.5 from the ANN model is 0.9998 and 0.572%, respectively, better than 0.9902 and 6.583% from the regression model. The predicted strain–stress curves outside of experimental conditions indicate similar characteristics with experimental curves. The results have sufficiently articulated that the well-trained ANN model with back-propagation algorithm has excellent capability to deal with the complex flow behaviors of as-forged Ti-10V-2Fe-3Al alloy.

Estimation of Stature from Footprint Anthropometry Using Regression Analysis : A Study on the Bidayuh Population of East Malaysia

The human foot has been studied for a variety of reasons, i.e., for forensic as well as non-forensic purposes by anatomists, forensic scientists, anthropologists, physicians, podiatrists, and numerous other groups. An aspect of human identification that has received scant attention from forensic anthropologists is the study of human feet and the footprints made by the feet. The present study, conducted during 2013-2014, aimed to derive population specific regression equations to estimate stature from the footprint anthropometry of indigenous adult Bidayuhs in the east of Malaysia. The study sample consisted of 480 bilateral footprints collected using a footprint kit from 240 Bidayuhs (120 males and 120 females), who consented to taking part in the study. Their ages ranged from 18 to 70 years. Stature was measured using a portable body meter device (SECA model 206. The data were analyzed using PASW Statistics version 20. In this investigation, better results were obtained in terms of correlation coefficient (R) between stature and various footprint measurements and regression analysis in estimating the stature. The (R) values showed a positive and statistically significant (p < 0.001) relationship between the two parameters. The correlation coefficients in the pooled sample (0.861–0.882) were comparatively higher than those of an individual male (0.762-0.795) and female (0.722-0.765). This study provided regression equations to estimate stature from footprints in the Bidayuh population. The result showed that the regression equations without sex indicators performed significantly better than models with gender indications. The regression equations derived for a pooled sample can be used to estimate stature, even when the sex of the footprint is unknown, as in real crime scenes.

Prediction of flow stress of 7017 aluminium alloy under high strain rate compression at elevated temperatures

An artificial neural network (ANN) constitutive model and Johnson–Cook (J–C) model were developed for 7017 aluminium alloy based on high strain rate data generated from split Hopkinson pressure bar (SHPB) experiments at various temperatures. A neural network configuration consists of both training and validation, which is effectively employed to predict flow stress. Temperature, strain rate and strain are considered as inputs, whereas flow stress is taken as output of the neural network. A comparative study on Johnson–Cook (J–C) model and neural network model was performed. It was observed that the developed neural network model could predict flow stress under various strain rates and temperatures. The experimental stress–strain data obtained from high strain rate compression tests using SHPB over a range of temperatures (25°–300 °C), strains (0.05–0.3) and strain rates (1500–4500 s −1 ) were employed to formulate J–C model to predict the flow stress behaviour of 7017 aluminium alloy under high strain rate loading. The J–C model and the back-propagation ANN model were developed to predict the flow stress of 7017 aluminium alloy under high strain rates, and their predictability was evaluated in terms of correlation coefficient ( R ) and average absolute relative error (AARE). R and AARE for the J-C model are found to be 0.8461 and 10.624%, respectively, while R and AARE for the ANN model are 0.9995 and 2.58%, respectively. The predictions of ANN model are observed to be in consistent with the experimental data for all strain rates and temperatures.

Quantification of sand fraction from seismic attributes using Neuro-Fuzzy approach

In this paper, we illustrate the modeling of a reservoir property (sand fraction) from seismic attributes namely seismic impedance, seismic amplitude, and instantaneous frequency using Neuro-Fuzzy (NF) approach. Input dataset includes 3D post-stacked seismic attributes and six well logs acquired from a hydrocarbon field located in the western coast of India. Presence of thin sand and shale layers in the basin area makes the modeling of reservoir characteristic a challenging task. Though seismic data is helpful in extrapolation of reservoir properties away from boreholes; yet, it could be challenging to delineate thin sand and shale reservoirs using seismic data due to its limited resolvability. Therefore, it is important to develop state-of-art intelligent methods for calibrating a nonlinear mapping between seismic data and target reservoir variables. Neural networks have shown its potential to model such nonlinear mappings; however, uncertainties associated with the model and datasets are still a concern. Hence, introduction of Fuzzy Logic (FL) is beneficial for handling these uncertainties. More specifically, hybrid variants of Artificial Neural Network (ANN) and fuzzy logic, i.e., NF methods, are capable for the modeling reservoir characteristics by integrating the explicit knowledge representation power of FL with the learning ability of neural networks. In this paper, we opt for ANN and three different categories of Adaptive Neuro-Fuzzy Inference System (ANFIS) based on clustering of the available datasets. A comparative analysis of these three different NF models (i.e., Sugeno-type fuzzy inference systems using a grid partition on the data (Model 1), using subtractive clustering (Model 2), and using Fuzzy c-means (FCM) clustering (Model 3)) and ANN suggests that Model 3 has outperformed its counterparts in terms of performance evaluators on the present dataset. Performance of the selected algorithms is evaluated in terms of correlation coefficients (CC), root mean square error (RMSE), absolute error mean (AEM) and scatter index (SI) between target and predicted sand fraction values. The achieved estimation accuracy may diverge minutely depending on geological characteristics of a particular study area. The documented results in this study demonstrate acceptable resemblance between target and predicted variables, and hence, encourage the application of integrated machine learning approaches such as Neuro-Fuzzy in reservoir characterization domain. Furthermore, visualization of the variation of sand probability in the study area would assist in identifying placement of potential wells for future drilling operations.

Non-linear feature selection-based hybrid computational intelligence models for improved natural gas reservoir characterization

With the recent state-of-the-art sensor-based data acquisition tools in the oil and gas industry, datasets sometimes come in very high dimensions. There is the need to extract the most relevant features out of these datasets to keep predictive models simple, accurate and free of pollution with irrelevant information. Multi-variate regression methods and evolutionary algorithms have been used to achieve this feat. However, the former could not handle the non-linearity in most problems that involve natural phenomena such as oil and gas reservoir characterization. The latter have been shown to introduce computational and time complexities, and are sometimes not very efficient. Accurate predictions of oil and gas reservoir properties are important for more efficient exploration and production of fossil energy resources. This paper proposes three non-linear feature selection based hybrid models in the prediction of porosity and permeability of two geographically and lithologically differentiated heterogeneous reservoirs. The hybrid models utilized the non-linear feature selection capabilities of Functional Networks (FN), Decision Trees (DT) and Fuzzy Ranking (FR) algorithms with the excellent functional approximation capability of Support Vector Machines (SVM). The results of the proposed models were then compared with a previously implemented FN-based Type-2 Fuzzy Logic hybrid model and the respective standalone components of the hybrid models. The comparative results provided more understanding of the architecture of these feature selection algorithms and further confirmed the importance of the feature selection process in oil and gas reservoir characterization. In the overall, the FN–SVM hybrid model showed superior performance in terms of correlation coefficient, root mean square error and execution time.

Neural network modeling to evaluate the dynamic flow stress of high strength armor steels under high strain rate compression

Abstract An artificial neural network (ANN) constitutive model is developed for high strength armor steel tempered at 500 °C, 600 °C and 650 °C based on high strain rate data generated from split Hopkinson pressure bar (SHPB) experiments. A new neural network configuration consisting of both training and validation is effectively employed to predict flow stress. Tempering temperature, strain rate and strain are considered as inputs, whereas flow stress is taken as output of the neural network. A comparative study on Johnson–Cook (J–C) model and neural network model is performed. It was observed that the developed neural network model could predict flow stress under various strain rates and tempering temperatures. The experimental stress–strain data obtained from high strain rate compression tests using SHPB, over a range of tempering temperatures (500–650 °C), strains (0.05–0.2) and strain rates (1000–5500/s) are employed to formulate J–C model to predict the high strain rate deformation behavior of high strength armor steels. The J-C model and the back-propagation ANN model were developed to predict the high strain rate deformation behavior of high strength armor steel and their predictability is evaluated in terms of correlation coefficient (R) and average absolute relative error (AARE). R and AARE for the J–C model are found to be 0.7461 and 27.624%, respectively, while R and AARE for the ANN model are 0.9995 and 2.58%, respectively. It was observed that the predictions by ANN model are in consistence with the experimental data for all tempering temperatures.

Recent advances in the application of computational intelligence techniques in oil and gas reservoir characterisation: a comparative study

A comparative study of the predictive capabilities of recent advances in computational intelligence (CI) is presented. This study utilised the machine learning paradigm to evaluate the CI techniques while applying them to the prediction of porosity and permeability of heterogeneous petroleum reservoirs using six diverse well data sets. Porosity and permeability are the major petroleum reservoir properties that serve as indicators of reservoir quality and quantity. The results showed that the performance of support vector machines (SVM) and functional networks (FN) is competitively better than that of Type-2 fuzzy logic system (T2FLS) in terms of correlation coefficient. With execution time, FN and SVM were faster than T2FLS, which took the most time for both training and testing. The results also demonstrated the capability of SVM to handle small data sets. This work will assist artificial intelligence practitioners to determine the most appropriate technique to use especially in conditions of limited amount of data and low processing power.