Absolute Relative Error Research Articles

Modeling and forecasting biogas production from anaerobic digestion process for sustainable resource energy recovery

Anaerobic digestion (AD) is one of the most extensively accepted processes for organic waste cleanup, and production of both bioenergy and organic fertilizer. Numerous mathematical models have been conceived for modeling the anaerobic process.In this study, a new modified dynamic mathematical model for the simulation of the biochemical and physicochemical processes involved in the AD process for biogas production was proposed. The model was validated, and a sensitivity analysis based on the OAT approach (one-at-a-time) was carried out as a screening technique to identify the most sensitive parameters. The model was developed by updating the bio-chemical framework and including more details concerning the physico-chemical process. The fraction XP was incorporated into the model as a particulate inert product arising from biomass decay (inoculum). New components were included to distinguish between the substrate and inoculum, and a surface-based kinetics was used to model the substrate disintegration. Additionally, the sulfate reduction process and hydrogen sulfide production have been included. The model was validated using data extracted from the literature. The model's ability to generate accurate predictions was testified using statistical metrics. The model exhibited excellent performance in forecasting the parameters related to the biogas process, with measurements falling within a reasonable error margin. The relative absolute error (rAE) and root mean square error (RMSE) were both less than 5 %, indicating a high ability of the current model in comparison with the literature. Additionally, the scatter index (SI) was below 10 %, and the Nash-Sutcliffe efficiency (NES) approached one, which affirms the model's accuracy and reliability. Finally, the model was applied to investigate the performances of the AD of food waste (FW). The findings of this study support the robustness of the developed model and its applicability as a virtual platform to evaluate the efficiency of the AD treatment and to forecast biogas production and its quality, CO2 emission, and energy potential across various organic solid waste types.

Predictive modeling of CO2 solubility in piperazine aqueous solutions using boosting algorithms for carbon capture goals

Carbon dioxide (CO2) is the main greenhouse gas that drives global warming, climate change, and other environmental issues. CO2 absorption using amine solvents stands out as one of the most well-known industrial technologies of CO2 capture. However, accurate prediction of CO2 absorption in aqueous amine solutions under different operating conditions is crucial for designing an efficient amine scrubbing system in power plants. In this work, CO2 solubility in aqueous piperazine (PZ) solutions was modeled using 517 experimental data points covering a temperature range of 298 to 373 K, PZ concentration of 0.1 to 6.2 mol/L (M), and CO2 partial pressure of 0.03 to 7399 kPa. To this end, four robust machine learning algorithms, including gradient boosting with categorical features support (CatBoost), light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost), and adaptive boosting decision trees (AdaBoost-DT) were utilized. Among the developed models, the CatBoost model presented the highest accuracy with an overall determination coefficient (R2) of 0.9953 and an average absolute relative error of 2.36%. Sensitivity analysis revealed that CO2 partial pressure had the greatest influence on CO2 absorption in aqueous PZ solutions, followed by PZ concentration and temperature. Moreover, CO2 partial pressure positively influenced CO2 absorption in aqueous PZ solutions, while PZ concentration and temperature exhibited negative effects. Finally, the leverage technique indicated that both the experimental data bank used for modeling and the model’s estimates were statistically acceptable and valid showing only 8 points (∼1.5% of total data) as possible suspected data.

Efficacy of machine learning algorithm in estimating oxyhydrogen gas generation system: Electrolyte concentration and current influence on sustainable energy production

Hydrogen gas has emerged as a promising and ecologically friendly substitute for fossil fuels, providing a long-term energy alternative. This research study applies machine learning regression models for estimating the volume of HHO gas generated using two distinct electrolytes with varying concentrations, namely sodium hydroxide (NaOH) and potassium hydroxide (KOH). The efficiency of the HHO gas production system hinges on various factors, such as the type of electrolyte and electrode, distance between electrodes, applied current and voltage. This investigation employed a comprehensive array of 29 multiple-regression algorithms to predict gas production. Notably, the input data for these algorithms were directly fed from the collected experimental data without any preprocessing. The input variables include the electrolyte concentration, current, and voltage, while the output is the estimated production of HHO gas. The findings of this study revealed that the multilayer perceptron (MLP) regression algorithm yielded the highest correlation coefficients, registering values of 0.9945 for NaOH and 0.9942 for KOH, respectively. Root relative squared error, relative absolute error, root mean squared error, mean fundamental error, and correlation coefficient were the metrics used to determine the model performance in predicting the volume of HHO gas produced. Furthermore, the experimental analysis demonstrated a direct relationship between the concentration of the electrolyte solution and the current with the rate of HHO gas production. Notably, the study identified that operating the cell at 40 A with KOH resulted in the maximum productivity of 0.9 litres per minute (LPM) of HHO gas, representing a 16 % increase compared to NaOH. These findings underscore the potential of machine learning regression models in optimizing hydrogen production and highlight the advantages of KOH as an electrolyte in this context.

Mass Transfer during Boric Acid Dissolution

The process of mass transfer during the dissolution of boric acid spheres in water was investigated in the temperature range from 293 K to 323 K, and at stirring rotation rates from 1.67 to 6.67 s-1. The study aimed to determine the dependence of the dissolution rate on the stirring rotation rate and water temperature. The analysis of the experimentally obtained results revealed that the most significant factor affecting the intensification of the dissolution process is an increase in the solution temperature. The phenomena of external and internal diffusion during the dissolution of boric acid spheres in water under agitation were also examined. To evaluate the mass transfer process, a generalized criterion equation was used that takes into account all the factors under study. Comparison of experimental and theoretically calculated values showed that the maximum absolute relative error does not exceed 6%. The results obtained are valuable for further research and potential applications in the chemical industry, pharmacology, and cosmetology.

Billet Size Optimization for Hot Forging of AISI 1045 Medium Carbon Steel Using Zener-Hollomon and Cingara-McQueen Model

This study investigates the effects of initial billet size variations on material flow behavior in hot forging processes, aiming to optimize the forging process using validated predictive models. Material and high-temperature compressive tests inform mathematical models, while simulations are conducted via the finite element method (FEM). Results align with the Zener-Hollomon and Cingara-McQueen approaches. The Arrhenius model predicts AISI 1045 steel flow stress with an R2 of 0.968 and an average absolute relative error (AARE) of 7.079%. The Cingara-McQueen equation achieves an R2 of 0.997 and an AARE of 2.960%. Reducing billets size from 260 mm to 230 mm decreases the material usage by up to 11.5%, while maintaining workpiece integrity. Experimental and simulated loads exhibit an AARE of about 2.69%, thereby indicating potential cost and efficiency improvements in hot forging processes.

Optimization of Motor Rotor Punch Wear Parameters Based on Response Surface Method

To reduce the wear of the motor rotor punching punch and ensure the efficiency is the highest in actual production, the finite element analysis software Deform-3Dv11 is used to simulate the punch wear based on the Archard model theory. With punch wear as the response target and punch speed, punch clearance, and punch edge fillet as the main factors, 17 groups of response surface Box–Behnken test designs are established, as well as a quadratic polynomial regression model between the main factors and the response. The results revealed that: the influence of various parameters on punch wear is in the order of punch edge fillet C > punch clearance B > punch speed A; the order of the interactive influence of various factors is as follows: punch speed and punch edge fillet AC > punch speed and punch clearance AB > punch clearance and punch edge fillet BC. The optimal blanking process combination obtained by using Design-Expert13 software is as follows: blanking speed 50 mm/s, blanking clearance 0.036 mm, and die cutting edge rounded corner 0.076 mm; the predicted response surface value is 6.95 × 10−12 mm. Through simulation verification, the actual optimized simulation value is 6.93 × 10−12 mm, with an absolute relative error of 2.5% for the predicted response value. Moreover, the optimized simulation value is reduced by 30.4% compared to the one before optimization, effectively reducing the punch wear of the motor rotor punching forming and providing a theoretical foundation for further wear optimization.

An Accurate Critical Total Drawdown Prediction Model for Sand Production: Adaptive Neuro-fuzzy Inference System (ANFIS) Technique

AbstractSand production causes many problems in the petroleum industry. The sand production is predicted to control it in the early stages. Therefore, accurate prediction of sand production has been considered substantial in achieving successful sand control. Critical total drawdown (CTD) can indicate the sand production. The main drawback of the previous studies in predicting CTD is their lack of accuracy. Thus, this study aims to develop an accurate CTD estimation prediction model employing a trend analysis and adaptive neuro-fuzzy inference system (ANFIS). The method is chosen because of its higher performance; the model is built based on 23 published datasets from the Adriatic Sea. The developed ANFIS model is evaluated using various methods, namely, trend analyses. Trend analyses are conducted to show the effects of the features on the CTD to present the physical behavior. The model’s performance was also evaluated using statistical error analyses. In addition, the ANFIS and previously published models were assessed. The trend analyses show the correct relationship between all features and the CTD. In addition, the trend analyses for the previous models are discussed. The results show that the proposed ANFIS method outperforms published methods with an R of 0.9984 and an absolute average percentage relative error (AAPRE) of 4.293%.

Ground Surface Effect of Earth Pressure Balance Tunnelling in Deltaic Deposits: A Case Study of Line 9 of the Barcelona Metro

The 47.8 km long Line 9 of the Barcelona Metro is one of Europe’s longest urban metro lines. Its southern section connects the city to the airport, being entirely excavated through soft deltaic deposits, promoting more sustainable mobility by reducing significant road traffic. This study identifies the most accurate method for predicting surface settlements caused by tunnel excavation using ground movement monitoring data. Several methodologies were assessed, with the Mean Absolute Error (MAE) and Mean Relative Error (MRE) calculated to evaluate their performances. The methods considered were Peck’s Gaussian curve method, Sagaseta’s method, and Verruijt and Booker’s method, with MAE values of 0.66 mm, 0.50 mm, and 0.48 mm and MRE values of 49%, 45%, and 36%, respectively. Verruijt and Booker’s method proved the most effective for predicting settlement, minimising surface impacts, improving building sustainability, and reducing environmental contamination from chemical injections. A sensitivity analysis was also conducted by comparing the monitoring data from Line 9 with data from 45 other tunnels excavated worldwide in deltaic soils. This analysis aimed to develop rapid predictive models applicable to different locations. The methodologies proposed for estimating ground settlements relied on specific parameters, particularly the K value, which was consistent across all deltaic soil locations, with values ranging from 0.45 to 0.55.

Simplified Neural Network-Based Models for Oil Flow Rate Prediction

Available neural network-based models for predicting the oil flow rate (q<sub>o</sub>) in the Niger Delta are not simplified and are developed from limited data sources. The reproducibility of these models is not feasible as the models’ details are not published. This study developed simplified and reproducible three, five, and six-input variables neural-based models for estimating q<sub>o</sub> using 283 datasets from 21 wells across fields in the Niger Delta. The neural-based models were developed using maximum-minimum (max.-min.) normalized and clip-normalized datasets. The performances and the generalizability of the developed models with published datasets were determined using some statistical indices: coefficient of determination (R<sup>2</sup>), mean square error (MSE), root mean square error (RMSE), average relative error (ARE) and average absolute relative error (AARE). The results indicate that the 3-input-based neural models had overall R<sup>2</sup>, MSE, and RMSE values of 0.9689, 9.6185x10<sup>-4 </sup>and 0.0310, respectively, for the max.-min. normalizing method and R<sup>2</sup> of 0.9663, MSE of 5.7986x10<sup>-3</sup> and RMSE of 0.0762 for the clip scaling approach. The 5-input-based models resulted in R<sup>2</sup> of 0.9865, MSE of 5.7790×10<sup>-4</sup> and RMSE of 0.0240 for the max.-min. scaling method and R<sup>2</sup> of 0.9720, MSE of 3.7243x10<sup>-3</sup> and RMSE of 0.0610 for the clip scaling approach. Also, the 6-input-based models had R<sup>2</sup> of 0.9809, MSE of 8.7520x10<sup>-4</sup> and RMSE of 0.0296 for the max.-min. normalizing approach and R<sup>2</sup> of 0.9791, MSE of 3.8859 x 10<sup>-3</sup> and RMSE of 0.0623 for the clip scaling method. Furthermore, the generality performance of the simplified neural-based models resulted in R<sup>2</sup>, RMSE, ARE, and AAPRE of 0.9644, 205.78, 0.0248, and 0.1275, respectively, for the 3-input-based neural model and R<sup>2</sup> of 0.9264, RMSE of 2089.93, ARE of 0.1656 and AARE of 0.2267 for the 6-input-based neural model. The neural-based models predicted q<sub>o</sub> were more comparable to the test datasets than some existing correlations, as the predicted q<sub>o</sub> result was the lowest error indices. Besides, the overall relative importance of the neural-based models’ input variables on q<sub>o</sub> prediction is S>GLR>P<sub>wh</sub>>T/T<sub>sc</sub>>γ<sub>o</sub>>BS&W>γ<sub>g</sub>. The simplified neural-based models performed better than some empirical correlations from the assessment indicators. Therefore, the models should apply as tools for oil flow rate prediction in the Niger Delta fields, as the necessary details to implement the models are made visible.

New and Highly Accurate Static Young's Modulus Model Using Machine Learning Techniques.

Static Young's modulus (E s) is a critical property required in numerous petroleum calculations. Various models to forecast E s have been proposed in the literature. However, existing models, by and large, lack precision and are confined to specific data set ranges. This study proposes an alternative approach for E s determination, utilizing different machine learning methods, such as an adaptive neuro-fuzzy inference system (ANFIS). In these proposed methods, the predictor variables include bulk formation density (RHOB), shear wave velocity (DTs), and compressional wave velocity (DTc). The models were trained on a data set comprising 1853 hydrocarbon reservoir rock samples from globally diverse locations. They were evaluated using trend, group error, and statistical error analyses. To test the efficacy of the proposed models, the optimally performing model was identified and used to detect the rock types along with the previously published models. Results indicated that ANFIS is the optimum model and can predict E s with an average absolute percentage relative error (AAPRE) of 5.1% and a correlation coefficient (R) of 0.9602. The ANFIS method has some benefits over other machine learning approaches insofar as its superiority in reaching a quicker decision about the mapped relationship between the inputs and outputs because it combines artificial neural networks and fuzzy logic in one tool. The ANFIS can perform a highly nonlinear mapping and displays a better learning ability. The proposed ANFIS model demonstrates its ability to capture accurate physical relationships between input rock properties and E s through trend analysis, which shows that increasing the RHOB increases the E s. Contrarily, increasing the DTc and DTs reduces the E s. Furthermore, the ANFIS model can accurately detect the rock types based on its E s determinations. This research demonstrates the importance of accurately predicting E s for the proper identification of rock types. Thus, this study offers potential advancements in geological assessments of hydrocarbon reservoirs and improvements in many petroleum engineering applications.

Developing discharge-head equation for radial-gated spillways based on physical modeling

Determination of the discharge through the spillways with radial gates is essential, depending on the application of these spillways in check dams and flood discharge systems in larger dams. On the other hand, physical modeling is often required due to the complexity and impact of various factors. This study investigated the efficiency of various methods in estimating the discharge through the spillways with radial gates using 958 experimental datasets from physical models of flood discharge systems in 17 large reservoir dams in Iran. In addition to dimensional analysis of the parameters, affecting the discharge of spillways with radial gates, new equations were proposed to determine the gate opening and the deviation angle of the gate. The mean absolute relative error in estimating the discharge at every flow condition showed a decreasing trend from about 9.1 % (for the previous methods) to about 3.9 % (the proposed equation in the present study). Later, the effects of different factors on the discharge through the spillways with the radial gate in large dams were evaluated. The results showed the errors of the previous methods in estimating the discharge for transient flow conditions, non-standard spillways, increase in the number of gates, and operation of only one gate with up to 22.2 %, 11.8 %, 21.5 %, and 10.5 %, respectively. However, under the abovementioned conditions, the mean absolute relative error of the proposed method error of discharge estimation, in the present study, decreased to about 4 %, 4.3 %, 3.3 %, and 3.5 %, respectively. Accordingly, using the new proposed equation involving the different factors to determine the discharge through the spillways with the radial gates in larger dams is recommended.

Accuracy and longitudinal consistency of PET/MR attenuation correction in amyloid PET imaging amid software and hardware upgrades.

Integrated PET/MR allows the simultaneous acquisition of PET biomarkers and structural and functional MRI to study Alzheimer disease (AD). Attenuation correction (AC), crucial for PET quantification, can be performed using a deep learning approach, DL-Dixon, based on standard Dixon images. Longitudinal amyloid PET imaging, which provides important information about disease progression or treatment responses in AD, is usually acquired over several years. Hardware and software upgrades often occur during a multiple-year study period, resulting in data variability. This study aims to harmonize PET/MR DL-Dixon AC amid software and head coil updates and evaluate its accuracy and longitudinal consistency. Tri-modality PET/MR and CT images were obtained from 329 participants, with a subset of 38 undergoing tri-modality scans twice within approximately three years. Transfer learning was employed to fine-tune DL-Dixon models on images from two scanner software versions (VB20P and VE11P) and two head coils (16-channel and 32-channel coils). The accuracy and longitudinal consistency of the DL-Dixon AC were evaluated. Power analyses were performed to estimate the sample size needed to detect various levels of longitudinal changes in the PET standardized uptake value ratio (SUVR). The DL-Dixon method demonstrated high accuracy across all data, irrespective of scanner software versions and head coils. More than 95.6% of brain voxels showed less than 10% PET relative absolute error in all participants. The median [interquartile range] PET mean relative absolute error was 1.10% [0.93%, 1.26%], 1.24% [1.03%, 1.54%], 0.99% [0.86%, 1.13%] in the cortical summary region, and 1.04% [0.83%, 1.36%], 1.08% [0.84%, 1.34%], 1.05% [0.72%, 1.32%] in cerebellum using the DL-Dixon models for the VB20P-16-channel-coil, VE11P-16-channel-coil and VE11P-32-channel-coil data, respectively. The within-subject coefficient of variation and intra-class correlation coefficient of PET SUVR in the cortical regions were comparable between the DL-Dixon and CT AC. Power analysis indicated that similar numbers of participants would be needed to detect the same level of PET changes using DL-Dixon and CT AC. DL-Dixon exhibited excellent accuracy and longitudinal consistency across the two software versions and head coils, demonstrating its robustness for longitudinal PET/MR neuroimaging studies in AD. AC = attenuation correction; AD = Alzheimer disease; HU = Hounsfield unit; ICC = intraclass correlation coefficient; MAE = mean absolute error; MRAE = mean relative absolute error; pCT = pseudo-CT; PiB = Pittsburgh Compound B; SD = standard deviation; SUVR = standardized uptake value ratio; wCV = within-subject coefficient of variation.

Soybean Yield Simulation and Sustainability Assessment Based on the DSSAT-CROPGRO-Soybean Model.

In order to ensure national grain and oil security, it is imperative to expand the soybean planting area in the Xinjiang region. However, the scarcity of water resources in southern Xinjiang, the relatively backward soybean planting technology, and the lack of a supporting irrigation system have negatively impacted soybean planting and yield. In 2022 and 2023, we conducted an experiment which included three irrigation amounts of 27 mm, 36 mm, and 45 mm and analyzed the changes in dry mass and yield. Additionally, we simulated the potential yield using the corrected DSSAT-CROPGRO-Soybean model and biomass based on the meteorological data from 1994 to 2023. The results demonstrated that the model was capable of accurately predicting soybean emergence (the relative root mean square error (nRMSE) = 0, the absolute relative error (ARE) = 0), flowering (nRMSE = 0, ARE = 2.78%), maturity (nRMSE = 0, ARE = 3.21%). The model demonstrated high levels of accuracy in predicting soybean biomass (R2 = 0.98, nRMSE = 20.50%, ARE = 20.63%), 0-80 cm soil water storage (R2 = 0.64, nRMSE = 7.78%, ARE = 3.24%), and yield (R2 = 0.81, nRMSE = 10.83%, ARE = 8.79%). The biomass of soybean plants increases with the increase in irrigation amount. The highest biomass of 63 mm is 9379.19 kg·hm-2. When the irrigation yield is 36-45 mm (p < 0.05), the maximum yield can reach 4984.73 kg·hm-2; the maximum efficiency of soybean irrigation water was 33-36 mm. In light of the impact of soybean yield and irrigation water use efficiency, the optimal irrigation amount for soybean cultivation in southern Xinjiang is estimated to be between 36 and 42 mm. The simulation results provide a theoretical foundation for soybean cultivation in southern Xinjiang.

Raman laser intensity and sample clarification on biochemical monitoring over Zika-VLP upstream stages

In the current biopharmaceutical scenario, constant bioprocess monitoring is crucial for the quality and integrity of final products. Thus, process analytical techniques, such as those based on Raman spectroscopy, have been used as multiparameter tracking methods in pharma bioprocesses, which can be combined with chemometric tools, like Partial Least Squares (PLS) and Artificial Neural Networks (ANN). In some cases, applying spectra pre-processing techniques before modeling can improve the accuracy of chemometric model fittings to observed values. One of the biological applications of these techniques could have as a target the virus-like particles (VLP), a vaccine production platform for viral diseases. A disease that has drawn attention in recent years is Zika, with large-scale production sometimes challenging without an appropriate monitoring approach. This work aimed to define global models for Zika VLP upstream production monitoring with Raman considering different laser intensities (200 mW and 495 mW), sample clarification (with or without cells), spectra pre-processing approaches, and PLS and ANN modeling techniques. Six experiments were performed in a benchtop bioreactor to collect the Raman spectral and biochemical datasets for modeling calibration. The best models generated presented a mean absolute error and mean relative error respectively of 3.46 × 105 cell/mL and 35 % for viable cell density (Xv); 4.1 % and 5 % for cell viability (CV); 0.245 g/L and 3 % for glucose (Glc); 0.006 g/L and 18 % for lactate (Lac); 0.115 g/L and 26 % for glutamine (Gln); 0.132 g/L and 18 % for glutamate (Glu); 0.0029 g/L and 3 % for ammonium (NH4+); and 0.0103 g/L and 2 % for potassium (K+). Sample without conditioning (with cells) improved the models' adequacy, except for Glutamine. ANN better predicted CV, Gln, Glu, and K+, while Xv, Glc, Lac, and NH4+ presented no statistical difference between the chemometric tools. For most of the assessed experimental parameters, there was no statistical need for spectra pre-filtering, for which the models based on the raw spectra were selected as the best ones. Laser intensity impacts quality model predictions in some parameters, Xv, Gln, and K+ had a better performance with 200 mW of intensity (for PLS, ANN, and ANN, respectively), for CV the 495 mW laser intensity was better (for PLS), and for the other biochemical variables, the use of 200 or 495 mW did not impact model fitting adequacy.

Constitutive model and microstructure evolution of thermal deformation behavior of in situ TiB2p/Al-Zn-Mg-Cu composites with high Zn content

The deformation behavior of in situ TiB2 particle reinforced Al-Zn-Mg-Cu matrix composites with high Zn content was investigated through thermal compression tests. A comparative analysis of several constitutive models was performed, including the phenomenological modified Johnson-Cook (JC) and strain-compensated Arrhenius-type models, as well as the physically based modified and optimized Zerilli-Armstrong (ZA) models. In contrast to other materials, it is found that the accuracy of the modified JC and ZA models is significantly affected by the reference strain rate. When this was factored in, the optimized ZA model demonstrated superior accuracy, with a correlation coefficient (R) of 0.9986 and an average absolute relative error (AARE) of 2.15 %, while requiring the fewest calculation efforts amongst all of the models attempted. The mechanisms of the microstructural evolution in the composites after thermal deformation were also investigated. This work advances the understanding of TiB2p/Al-Zn-Mg-Cu composites and introduces an improved modeling framework, which is expected to benefit future material design and performance.

Adaptive and self-learning Bayesian filtering algorithm to statistically characterize and improve signal-to-noise ratio of heart-rate data in wearable devices.

The use of wearable sensors to monitor vital signs is increasingly important in assessing individual health. However, their accuracy often falls short of that of dedicated medical devices, limiting their usefulness in a clinical setting. This study introduces a new Bayesian filtering (BF) algorithm that is designed to learn the statistical characteristics of signal and noise, allowing for optimal smoothing. The algorithm is able to adapt to changes in the signal-to-noise ratio (SNR) over time, improving performance through windowed analysis and Bayesian criterion-based smoothing. By evaluating the algorithm on heart-rate (HR) data collected from Garmin Vivoactive 4 smartwatches worn by individuals with amyotrophic lateral sclerosis and multiple sclerosis, it is demonstrated that BF provides superior SNR tracking and smoothing compared with non-adaptive methods. The results show that BF accurately captures SNR variability, reducing the root mean square error from 2.84 bpm to 1.21 bpm and the mean absolute relative error from 3.46% to 1.36%. These findings highlight the potential of BF as a preprocessing tool to enhance signal quality from wearable sensors, particularly in HR data, thereby expanding their applications in clinical and research settings.

Investigation of hot deformation behavior and three-roll skew rolling process for hollow stepped shaft of Al–Zn–Mg–Cu alloy

The increasing demand for high-strength lightweight hollow shafts in transportation highlights the need for advanced fabrication techniques. Al–Zn–Mg–Cu alloys, noted for their superior properties, are selected for three-roll skew rolling (TRSR). In TRSR, the material undergoes combined axial tensile and radial compressive stresses. This study evaluates the feasibility of TRSR for producing high-strength lightweight hollow stepped shafts from Al–Zn–Mg–Cu alloy. An integrated approach, including constitutive modeling, hot processing map development, and TRSR numerical simulations/experiments, is employed to optimize the TRSR forming process. The constitutive model was established based on 300°C–450 °C & 0.01–10 s−1 hot compression and 350°C–430 °C & 0.1–5 s−1 high-temperature tensile test data. The established Johnson-Cook optimization by genetic algorithms (GA-JC) model and unified viscoplastic constitutive model, accurately capture the alloy's hot deformation behavior, exhibiting minimal average absolute relative errors (AARE) of 5.431% and 5.808%, respectively. Microstructure evolution analyses shed light on the predominant softening mechanisms, emphasizing dynamic recovery (DRV) at elevated strain rates and diminishing texture intensity with escalating deformation temperatures. The composite hot processing map delineates optimal process parameters (400°C–450 °C & 0.1s−1-1s−1), facilitating informed decision-making in manufacturing practices. The validation of numerical simulations through TRSR forming experiments with initial temperature of 450 °C for the billet and axial moving speed of 10 mm/s for the chuck in affirms the feasibility of producing hollow stepped shafts from high-strength Al–Zn–Mg–Cu alloy. Close agreement was found between simulated and experimental wall thickness variations. This study enhances understanding and optimization of TRSR forming for high-strength lightweight alloys, advancing industrial manufacturing methodologies.

Enhancing shear strength predictions of rocks using a hierarchical ensemble model

Shear strength (SS) parameters are essential for understanding the mechanical behavior of materials, particularly in geotechnical engineering and rock mechanics. This study proposes a novel hierarchical ensemble model (HEM) to predict SS parameters: cohesion (C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document}) and angle of internal friction (φ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varphi$$\\end{document}). The HEM addresses the limitations of traditional machine learning models. Its performance was validated using leave-one-out cross-validation (LOOCV) and out-of-bag (OOB) evaluation methods. The model's accuracy was assessed with R-squared correlation (R2), absolute average relative error percentage (AAREP), Taylor diagrams, and quantile–quantile plots. The computational results demonstrated that the proposed HEM outperforms previous studies using the same database. The model predicted φ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varphi$$\\end{document} and C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document} with R2 values of 0.93 and 0.979, respectively. The AAREP values were 1.96% for φ and 4.7% for C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document}. These results indicate that the HEM significantly improves the prediction quality of φ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varphi$$\\end{document} and C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document}, and exhibits strong generalization capability. Sensitivity analysis revealed that σ_3maxσ3max (maximum principal stress) had the greatest impact on modeling both φ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varphi$$\\end{document} and C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document}. According to uncertainty analysis, the LOOCV and OOB had the widest uncertainty bands for the φ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varphi$$\\end{document} and C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document} parameters, respectively.

Modeling interfacial tension of methane-brine systems at high pressure high temperature conditions

In the present study, two white-box correlative models, namely gene expression programming (GEP) and group method of data handling (GMDH), were implemented to predict the interfacial tension (IFT) of brine-methane system. To achieve this, 790 data points were collected from literature, with pressure, temperature, and salinity as inputs and IFT as the output. The range of salinity, pressure, and temperature is from 0 to 107000 ppm, 0.01–260 MPa, and 278.1–477.59 K, respectively. The results show that the GMDH model with an R2 of 0.9321 and an average absolute percent relative error (AAPRE) of 3.68% outperforms the GEP, which has an AAPRE of 5.08% and an R2 of 0.8943. Based on our investigation, GMDH and GEP models follow the expected trend of IFT with the variation of pressure. It has been found that the GMDH model exhibits better performance compared to the previously developed correlations in the literature. Furthermore, the sensitivity analysis indicated that temperature has the greatest effect on IFT. By using the leverage approach, we proved that the GMDH model is statistically valid.

A new portfolio approach integrating three-way decision and Encoder–Decoder network

In the stock market, it can be challenging to predict stock trends and identify stocks with investment potential due to uncertainty and risk. Accurate predictive models and reliable asset preselection methods are essential for portfolio management. This paper proposes an integration of the deep learning model, the three-way decision (3WD) theory, and the Mean-Variance (MV) method for asset preselection and optimal asset allocation. In the initial stage, an attention-based Encoder–Decoder model is used to predict asset returns and calculate volatility. It outperforms other benchmark models regarding relative error, absolute error, and directional accuracy. The subsequent stage involves selecting stocks based on expected returns and volatility characteristics. The 3WD theory is then used to identify the delayed decision set for implementing additional investment strategies to hedge portfolio risk and enhance returns. Finally, the MV model is employed for investment portfolio optimization. The proposed model is validated using a substantial dataset from the A-share market’s SSE 50 Index from January 2010 to December 2022. Results indicate that the proposed model outperforms benchmark models in terms of daily average returns, annualized Information ratio, Sortino ratio, and other aspects under certain trading costs. However, further exploration is required to establish a mechanism that limits the quantity of preselected assets to ensure its broad applicability.