Back-propagation Artificial Neural Network Research Articles

Artificial neural network model of non-Darcy MHD Sutterby hybrid nanofluid flow over a curved permeable surface: Solar energy applications

The conversion of solar radiation to thermal energy has recently much interest as the requirement for renewable heat and power grows. Due to their enhanced ability to promote heat transmission, nanofluids can significantly improve solar-thermal systems' efficiency. This section aims to study the heat transfer behavior of the Sutterby hybrid nanofluid flow of magnetohydrodynamics in the presence of a non-uniform heat source/sink and linear thermal radiation over a non-Darcy curved permeable surface. A novel implementation of an intelligent numerical computing solver based on multi-layer perceptron (MLP) feed-forward back-propagation artificial neural network (ANN) with the Levenberg-Marquard algorithm is provided in the current study. Data were gathered for the ANN model's testing, certification, and training. Established mathematical equations are nonlinear, which are resolved for velocity, the temperature in addition to the skin friction coefficient, and the rate of heat transfer by using the bvp4c with MATLAB solver. The ANN model selects data, constructs and trains a network, then evaluates its efficacy via mean square error. Graphs illustrate the impact of a wide range of physical factors on variables, including pressure, velocity, and temperature. In the entire study, the thermal energy improved by the SiO2 (silicon dioxide) - Au (gold) hybrid nanofluid than the SiO2-TiO2 (titanium dioxide) hybrid nanofluid. The higher internal heat generation/absorption parameter values increase the temperature.

A temporally and spatially local spike-based backpropagation algorithm to enable training in hardware

Spiking neural networks (SNNs) have emerged as a hardware efficient architecture for classification tasks. The challenge of spike-based encoding has been the lack of a universal training mechanism performed entirely using spikes. There have been several attempts to adopt the powerful backpropagation (BP) technique used in non-spiking artificial neural networks (ANNs): (1) SNNs can be trained by externally computed numerical gradients. (2) A major advancement towards native spike-based learning has been the use of approximate BP using spike-time dependent plasticity with phased forward/backward passes. However, the transfer of information between such phases for gradient and weight update calculation necessitates external memory and computational access. This is a challenge for standard neuromorphic hardware implementations. In this paper, we propose a stochastic SNN based back-prop (SSNN-BP) algorithm that utilizes a composite neuron to simultaneously compute the forward pass activations and backward pass gradients explicitly with spikes. Although signed gradient values are a challenge for spike-based representation, we tackle this by splitting the gradient signal into positive and negative streams. The composite neuron encodes information in the form of stochastic spike-trains and converts BP weight updates into temporally and spatially local spike coincidence updates compatible with hardware-friendly resistive processing units. Furthermore, we characterize the quantization effect of discrete spike-based weight update to show that our method approaches BP ANN baseline with sufficiently long spike-trains. Finally, we show that the well-performing softmax cross-entropy loss function can be implemented through inhibitory lateral connections enforcing a winner take all rule. Our SNN with a two-layer network shows excellent generalization through comparable performance to ANNs with equivalent architecture and regularization parameters on static image datasets like MNIST, Fashion-MNIST, Extended MNIST, and temporally encoded image datasets like Neuromorphic MNIST datasets. Thus, SSNN-BP enables BP compatible with purely spike-based neuromorphic hardware.

Estimating Forest Aboveground Biomass Combining Pléiades Satellite Imagery and Field Inventory Data in the Peak–Cluster Karst Region of Southwestern China

The mountainous region of southwest China has the largest karst geomorphology in China and in the world. Quantifying the forest aboveground biomass in this karst region is of great significance for the investigation of carbon storage and carbon cycling in terrestrial ecosystems. In this study, the actual measured aboveground biomass was calculated based on the allometric functions of 106 quadrats from 2012 to 2015. A backpropagation artificial neural network (BPANN) inversion model was constructed by combining very high-resolution satellite imagery, field inventory data, and land use/land cover data to estimate the forest aboveground biomass in the Banzhai watershed, a typical peak–cluster karst basin in southern Guizhou Province. We used 70% of the actual measured aboveground biomass for training the BPANN model, 20% for accuracy verification, and 10% to prevent overtraining. The results show that the absolute root mean square error of the BPANN model was 11.80 t/ha, which accounted for 9.92% of the mean value of aboveground biomass. Based on the BPANN inversion model, the average value of the forests’ aboveground biomass was 135.63 t/ha. The results showed that our study presented a quick, easy, and relatively high-precision method for estimating forest aboveground biomass in the Banzhai watershed. This indicates that the Pléiades image-based BPANN model displayed satisfactory results for estimating the forests’ aboveground biomass in a typical peak–cluster karst basin. This method can be applied to the estimation of forest AGB in the karst mountainous areas of southwest China.

Prediction of inhibition performance of agro-waste extract in simulated acidizing media via machine learning

The study aims to employ machine learning modelling approach to model the measurement of corrosion rate on AISI 316 stainless steel when corrosion inhibitor is added in different dosages and dose schedules. To achieve this, experimental data was analyzed statistically and modeled using Levenberg-Marquardt’s back-propagation artificial neural network (LMBP-ANN), and adaptive neuro-fuzzy inference system (ANFIS) algorithms. Maximum inhibition efficiencies of 96.44%, 94.74%, and 90.24% were obtained from experimental at a concentration of 10 g and temperatures of 288, 298, and 308 K respectively. The experiment shows that the corrosion rate time profile depends on the dosing schedule, whereas the final rate mainly depends on the environmental severity. The corrosion rates are predicted by the developed models while their capabilities were compared in terms of Mean Absolute Percentage Error root (MAPE), determination coefficient (R2), Mean Absolute Deviation (MAD), and Root Mean Square Error (RMSE) for all outputs. From the statistical metrics obtained, credence was given to ANFIS as the best predictive model compared to the LMBP-ANN with MAPE, R2, MAD, and RMSE value of 15.242,0.893, 0.105,0.372 for corrosion rate, 13.135,0.904, 0.725,1.036, for weight loss and 18.342, 0.835, 20.417, 24.238 for inhibition efficiency at the testing stage. The effect of inhibitor concentration and exposure time are the most significant parameters for predicting eggshell extract as potential inhibitor for stainless steel in oilfield pickling and acidizing media.

Exploring the Influence of Induced Magnetic Fields and Double-Diffusive Convection on Carreau Nanofluid Flow through Diverse Geometries: A Comparative Study Using Numerical and ANN Approaches

This current investigation aims to explore the significance of induced magnetic fields and double-diffusive convection in the radiative flow of Carreau nanofluid through three distinct geometries. To simplify the fluid transport equations, appropriate self-similarity variables were employed, converting them into ordinary differential equations. These equations were subsequently solved using the Runge–Kutta–Fehlberg (RKF) method. Through graphical representations like graphs and tables, the study demonstrates how various dynamic factors influence the fluid’s transport characteristics. Additionally, the artificial neural network (ANN) approach is considered an alternative method to handle fluid flow issues, significantly reducing processing time. In this study, a novel intelligent numerical computing approach was adopted, implementing a Levenberg–Marquardt algorithm-based MLP feed-forward back-propagation ANN. Data collection was conducted to evaluate, validate, and guide the artificial neural network model. Throughout all the investigated geometries, both velocity and induced magnetic profiles exhibit a declining trend for higher values of the magnetic parameter. An increase in the Dufour number corresponds to a rise in the nanofluid temperature. The concentration of nanofluid increases with higher values of the Soret number. Similarly, the nanofluid velocity increases with higher velocity slip parameter values, while the fluid temperature exhibits opposite behavior, decreasing with increasing velocity slip parameter values.

Modelling crash severity outcomes for low speed urban roads using back propagation – Artificial neural network (BP – ANN) – A case study in Indian context

This work analyses influence of road, weather and crash-specific factors on crash severity outcomes for low-speed urban midblock sections and intersections, for day and night time, using Backpropagation–Artificial Neural Network (BP–ANN). Five-year crash data (2015–2019) from 82Km urban road network of Patna, India was used for the study. The road factors include pavement width, distress condition, marking; shoulder type, condition; road section type as mid-block, intersection and intersection control. Weather factors include season of crash, fog or rain at crash time. Crash factor include collision partner, type and crash time. The most appropriate BP–ANN model architecture was estimated using Misclassification-Rate. It was observed that midblock segments witness higher severities during daytime, whereas intersections witness higher severities during night. Controlled intersections are safer compared to un-controlled intersections. Pavement distress greatly increase the chance of higher severities. Narrow roads record greater severities during day due to lack of surveillance.

Detection of apple moldy cores using transmittance spectroscopy combined with supervised classifier comparison and parameter optimization

It is difficult to determine which apples have moldy cores just by looking at the outside of the apple. In the present study, we investigated identifying moldy cores using near-infrared transmittance spectra. First, input spectral features selected by noise adjusted principal component analysis (NAPCA) for back propagation artificial neural network (BP ANN) was used to reduce the dimensions of the original data. Then, four factors and five levels uniform design of the input nodes, training functions, transfer layer functions and output layer functions for NAPCA-BP ANN optimization is proposed. And the original data were input into NAPCA-BP ANN to obtain the recognition accuracy and NAPCA-support vector machine (SVM) was as a comparative recognition model. The results showed that through the uniform design-based NAPCA-BP ANN optimization, the NAPCA method had higher identification accuracy, precision, recall and F1 score, than either full spectrum or principal component analysis. Being assessed by different ratio of model test, functions in the hidden layer and output layer of NAPCA-BP ANN, the proposed method achieved the best accuracy to 98.03%. The accuracy, precision, recall and F1 score based on NAPCA-BP ANN were 3.92%, 2.86%, 2.78% and 2.82% higher than those based on NAPCA-SVM, respectively. This method provides a theoretical basis for the development of on-line monitoring of the internal quality of apples.

Comparison Of Artificial Neural Network Backpropagation and Garch Methods In Predicting Stock Price (Case Study: Indosat Shares 2012 – 2022)

Abstract: One of the problems encountered in the forecasting process is the problem of heteroscedasticity. Heteroscedasticity occurs a lot, especially in stock data. Pt Share Price Indosat (tbk) from March 6 2012 – January 18 2022 has fluctuated from time to time, so the variance is heteroscedasticity. The Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model and Artificial Neural Network Backpropagation (ANNBP) are methods that can be used on data with heteroscedasticity. The aim of this research is to obtain models and forecasting results from GARCH and ANN Backpropagation. In this study, the two models were compared based on the smallest MAPE value. This study uses daily data on the closing of Indosat shares. Forecasting is done on Indosat stock closing data, the total data is 2453 data divided into two parts, namely 80% training data totaling 1962 data and 20% training data totaling 491 data. Forecasting results from the GARCH model obtained a MAPE value of 11.04%, and the ANN Backpropagation model with 7 input layers, 20 hidden layers, obtained a MAPE value of 7.01%. Thus, the best model for predicting Indosat's share price in this study is the backpropagation model.

Rapid and Non-Invasive Assessment of Texture Profile Analysis of Common Carp (Cyprinus carpio L.) Using Hyperspectral Imaging and Machine Learning.

Hyperspectral imaging (HSI) has been applied to assess the texture profile analysis (TPA) of processed meat. However, whether the texture profiles of live fish muscle could be assessed using HSI has not been determined. In this study, we evaluated the texture profile of four muscle regions of live common carp by scanning the corresponding skin regions using HSI. We collected skin hyperspectral information from four regions of 387 scaled and live common carp. Eight texture indicators of the muscle corresponding to each skin region were measured. With the skin HSI of live common carp, six machine learning (ML) models were used to predict the muscle texture indicators. Backpropagation artificial neural network (BP-ANN), partial least-square regression (PLSR), and least-square support vector machine (LS-SVM) were identified as the optimal models for predicting the texture parameters of the dorsal (coefficients of determination for prediction (rp) ranged from 0.9191 to 0.9847, and the root-mean-square error for prediction ranged from 0.1070 to 0.3165), pectoral (rp ranged from 0.9033 to 0.9574, and RMSEP ranged from 0.2285 to 0.3930), abdominal (rp ranged from 0.9070 to 0.9776, and RMSEP ranged from 0.1649 to 0.3601), and gluteal (rp ranged from 0.8726 to 0.9768, and RMSEP ranged from 0.1804 to 0.3938) regions. The optimal ML models and skin HSI data were employed to generate visual prediction maps of TPA values in common carp muscles. These results demonstrated that skin HSI and the optimal models can be used to rapidly and accurately determine the texture qualities of different muscle regions in common carp.

Independent parallel pyrolysis kinetics of model components in sewage sludge analyzed by BPM neural network.

Analyzing the kinetic behavior of sewage sludge pyrolysis is essential for the design of efficient reactors to produce biofuel and syngas. To understand the complex pyrolysis process of sewage sludge, we pyrolyzed six model components (i.e., cellulose, hemicellulose, lignin, protein, soluble sugars, and lipid) using a thermogravimetric analyzer. The effects of the heating rate on the pyrolysis process were examined at four different heating rates (5, 15, 25, and 50 °C/min). As temperature increased, the derivative thermogravimetric peaks shifted to higher temperature zones. The temperature ranges of the maximum mass loss rate for cellulose, hemicellulose, lignin, protein, soluble sugars, and lipid were within 326.1-368.0 °C, 288.7-315.5 °C, 375.1-429.4 °C, 291.9-308.0 °C, 251.0-314.1 °C, and 410.8-454.1 °C, respectively. The apparent activation energies of the model components were obtained using non-isothermal kinetic analysis methods (Flynn-Wall-Ozawa and Kissinger-Akahira-Sunose). In addition, a back-propagation artificial neural network with a momentum algorithm (BPM) was developed to predict the relationship between the pyrolysis experiment and the activation value. The best BPM model (BPM5) for predicting the cellulose pyrolysis was identified.

Color Conversion of Wide-Color-Gamut Cameras Using Optimal Training Groups.

The colorimetric conversion of wide-color-gamut cameras plays an important role in the field of wide-color-gamut displays. However, it is rather difficult for us to establish the conversion models with desired approximation accuracy in the case of wide color gamut. In this paper, we propose using an optimal method to establish the color conversion models that change the RGB space of cameras to the XYZ space of a CIEXYZ system. The method makes use of the Pearson correlation coefficient to evaluate the linear correlation between the RGB values and the XYZ values in a training group so that a training group with optimal linear correlation can be obtained. By using the training group with optimal linear correlation, the color conversion models can be established, and the desired color conversion accuracy can be obtained in the whole color space. In the experiments, the wide-color-gamut sample groups were designed and then divided into different groups according to their hue angles and chromas in the CIE1976L*a*b* space, with the Pearson correlation coefficient being used to evaluate the linearity between RGB and XYZ space. Particularly, two kinds of color conversion models employing polynomial formulas with different terms and a BP artificial neural network (BP-ANN) were trained and tested with the same sample groups. The experimental results show that the color conversion errors (CIE1976L*a*b* color difference) of the polynomial transforms with the training groups divided by hue angles can be decreased efficiently.

Artificial Neural Network Analysis of Determinants of Tacrolimus Pharmacokinetics in Liver Transplant Recipients.

The efficacy and toxicity of tacrolimus are closely related to its trough blood concentrations. Identifying the influencing factors of pharmacokinetics of tacrolimus in the early postoperative period is conducive to the optimization of the individualized tacrolimus administration protocol and to help liver transplant (LT) recipients achieve the target blood concentrations. This study aimed to develop an artificial neural network (ANN) for predicting the blood concentration of tacrolimus soon after liver transplantation and for identifying determinants of the concentration based on Shapley additive explanation (SHAP). In this retrospective study, we enrolled 31 recipients who were first treated with liver transplantation from the Department of Liver Transplantation and Hepatic Surgery, the First Affiliated Hospital of Shandong First Medical University (Shandong Provincial Qianfoshan Hospital) from November 2020 to May 2021. The basic information, biochemical indexes, use of concomitant drugs, and genetic factors of organ donors and recipients were used for the ANN model inputs, and the output was the steady-state trough concentration (C0) of tacrolimus after oral administration in LT recipients. The ANN model was established to predict C0 of tacrolimus, SHAP was applied to the trained model, and the SHAP value of each input was calculated to analyze quantitatively the influencing factors for the output C0. A back-propagation ANN model with 3 hidden layers was established using deep learning. The mean prediction error was 0.27 ± 0.75 ng/mL; mean absolute error, 0.60 ± 0.52 ng/mL; correlation coefficient between predicted and actual C0 values, 0.9677; and absolute prediction error of all blood concentrations obtained by the ANN model, ≤3.0 ng/mL. The results indicated that the following factors had the most significant effect on C0: age, daily drug dose, genotype at CYP3A5 polymorphism rs776746 in both recipient and donor, and concomitant use of caspofungin. The predicted C0 value of tacrolimus in LT recipients increased in a dose-dependent manner when the daily dose exceeded 3 mg, whereas it decreased with age when LT recipients were older than 48 years. The predicted C0 was higher when recipients and donors had the genotype CYP3A5*3*3 than when they had the genotype CYP3A5*1. The predicted C0 value also increased with the use of caspofungin or Wuzhi capsule. The established ANN model can be used to predict the C0 value of tacrolimus in LT recipients with high accuracy and good predictive ability, serving as a reference for personalized treatment in the early stage after liver transplantation.

Modeling and optimization of Graphene Oxide (GO) membranes for nanofiltration with artificial neural networks

It is important to understand the correlation between the nanostructure and membrane performances (water flux and rejection) in membrane separation technology, which is helpful to develop novel membranes. In this study, a back propagation artificial neural network model optimized with genetic algorithms was proposed to predict the nanofiltration performances (water flux and rejection) of GO membranes. The aim is to explore the feature importance of the membrane structure parameters (such as interlayer spacing, Zeta potential, water contact angle, roughness and thickness) and the operating condition (operation pressure) on the membrane properties, so as to provide clues for improving the membrane performances. The obtained results showed that genetic algorithm-back propagation artificial neural network (GABPANN) exhibited more accurate performance to predict the correlation between the parameters (including membrane structure and operation pressure) and the membrane performances according to the published experimental results. Moreover, the GABPANN results indicated that the water contact angle is the most powerful parameter determining the water flux, while the surface charge is the most powerful one determining the rejection of GO membranes. This work provided a novel strategy to efficiently optimize the nanofiltration performance of GO membranes, beneficial for better understanding and controlling the structural design of GO membranes.

A machine learning strategy-incorporated BiFeO3/Ti3C2 MXene electrochemical platform for simple, rapid detection of Pb2+ with high sensitivity

The electrochemical technique has been increasingly used for the detection of heavy metal ions in the water system. However, the process for determining the optimum experimental conditions was cumbersome, time-consuming, and unsynchronized, resulting in unsatisfactory detection efficiency. Herein, a new machine learning (ML) strategy combined with BiFeO3/Ti3C2 MXene (BiFeO3/MXene) was used to fabricate a simple but efficient electrochemical Pb2+ sensor. The interconnected BiFeO3/MXene composites prepared by a hydrothermal method possessed an interconnected conductive framework, abundant active sites, and a large surface area, which gave them excellent electronic conductivity and high accumulation of Pb2+. Meanwhile, ML methods such as back-propagation artificial neural network (BPANN) and genetic algorithm (GA) combined with orthogonal experimental design (OED) were used to optimize sensor parameters such as the pH of the supporting electrolyte, the BiFeO3/MXene content, deposition potential, and deposition time. Compared with OED and the one factor at a time (OFAT) methods, the OED-ML method greatly simplified the experimental procedures and improved the electrochemical detection performance. The developed sensor showed superior detection performance for Pb2+ with a detection limit of 0.0001 μg L−1 using the OED-ML method, which was much lower than that of the OED and OFAT methods (0.0003 μg L−1). In addition, the sensor showed good repeatability, reproducibility, stability, and interference capability. The feasibility of the method was verified by detecting Pb2+ in lake samples with recoveries ranging from 98.79% to 101.3%. To our knowledge, the ML strategy was introduced for the first time in an electrochemical sensor for Pb2+ detection, which proved the feasibility and practicality of ML.

Cadmium Elimination via Magnetic Biochar Derived from Cow Manure: Parameter Optimization and Mechanism Insights

Designing an efficient and recyclable adsorbent for cadmium pollution control is an urgent necessity. In this paper, cow manure, an abundant agricultural/animal husbandry byproduct, was employed as the raw material for the synthesis of magnetic cow manure biochar. The optimal preparation conditions were found using the response surface methodology model: 160 °C for the hydrothermal temperature, 600 °C for the pyrolysis temperature, and Fe-loading with 10 wt%. The optimal reaction conditions were also identified via the response surface methodology model: a dosage of 1 g·L−1, a pH of 7, and an initial concentration of 100 mg·L−1. The pseudo-second-order model and the Langmuir model were used to fit the Cd(II) adsorption, and the adsorption capacity was 612.43 mg·g−1. The adsorption was dominated by chemisorption with the mechanisms of ion-exchange, electrostatic attraction, pore-filling, co-precipitation, and the formation of complexations. Compared to the response surface methodology model, the back-propagation artificial neural network model fit the Cd(II) adsorption better as the error values were less. All these results demonstrate the potential application of CM for Cd(II) removal and its optimization through machine-learning processes.

Comparison of Data Fusion Methods in Fusing Satellite Products and Model Simulations for Estimating Soil Moisture on Semi-Arid Grasslands

In arid and semi-arid areas, soil moisture (SM) plays a crucial role in land-atmosphere interactions, hydrological processes, and ecosystem sustainability. SM data at large scales are critical for related climatic, hydrological, and ecohydrological research. Data fusion based on satellite products and model simulations is an important way to obtain SM data at large scales; however, little has been reported on the comparison of the data fusion methods in different categories. Here, we compared the performance of two widely used data fusion methods, the Ensemble Kalman Filter (EnKF) and the Back-Propagation Artificial Neural Network (BPANN), in the degraded grassland site (DGS) and the alpine grassland site (AGS). The SM data from the Community Land Model 5.0 (CLM5.0) and the Soil Moisture Active and Passive (SMAP) were fused and validated against the observations of the Cosmic-Ray Neutron Sensor (CRNS) to avoid the impacts of scale-mismatch. Results show that compared with the original data sets at both sites, the RMSE of the fused data by BPANN (FD-BPANN) and EnKF (FD-EnKF) had improved by more than 50% and 31%, respectively. Overall, the FD-BPANN performs better than the FD-EnKF because the BPANN method assigned higher weights to input data with better performance and the EnKF method is affected by the strong variabilities of both the fused CLM5.0 and SMAP data and the CRNS data. However, in terms of the percentile range, the FD-BPANN showed the worst performance, with overestimations in the low SM range of 25th percentile (<Q25), because the BPANN method tends to be trapped in a local minimum. The BPANN method performed better in humid areas, then followed by semi-humid areas, and finally arid and semi-arid areas. Moreover, compared with the previous studies in arid and semi-arid areas, the BPANN method in this study performed better.

Prediction of Soil Water Content Based on Hyperspectral Reflectance Combined with Competitive Adaptive Reweighted Sampling and Random Frog Feature Extraction and the Back-Propagation Artificial Neural Network Method

The soil water content (SWC) is a critical factor in agricultural production. To achieve real-time and nondestructive monitoring of the SWC, an experiment was conducted to measure the hyperspectral reflectance of soil samples with varying levels of water content. The soil samples were divided into two parts, SWC higher than field capacity (super-θf) and SWC lower than field capacity (sub-θf), and the outliers were detected by Monte Carlo cross-validation (MCCV). The raw spectra were processed using Savitzky–Golay (SG) smoothing and then the spectral feature variable of SWC was extracted by using a combination of competitive adaptive reweighted sampling (CARS) and random frog (Rfrog). Based on the extracted feature variables, an extreme learning machine (ELM), a back-propagation artificial neural network (BPANN), and a support vector machine (SVM) were used to establish the prediction model. The results showed that the accuracy of retrieving the SWC using the same model was poor, under two conditions, i.e., SWC above and below θf, mainly due to the influence of the lower accuracy of the super-θf part. The number of feature variables extracted by the sub-θf and super-θf datasets were 25 and 18, respectively, accounting for 1.85% and 1.33% of the raw spectra, and the variables were widely distributed in the NIR range. Among the models, the best results were achieved by the BPANN model for both the sub-θf and the super-θf datasets; the R2p, RMSEp, and RRMSE of the sub-θf samples were 0.941, 1.570%, and 6.685%, respectively. The R2p, RMSEp, and RRMSE of the super-θf samples were 0.764, 1.479%, and 4.205%, respectively. This study demonstrates that the CARS–Rfrog–BPANN method was reliable for the prediction of SWC.

A creep life prediction model of P91 steel coupled with back-propagation artificial neural network (BP-ANN) and θ projection method

In order to predict the long-term creep life of P91 steel, this work proposed a coupled model, combining the error-trained back-propagation artificial neural network (BP-ANN) and an improved θ model. Both the short-term rupture life obtained by creep experiments and the related creep data of National Institute for Materials Science (NIMS) database were used to validate the above model. In this model, creep parameters (temperature, stress) were used as the input and relative error of 5 θ model extrapolations as the output. Then, the prediction errors of BP-ANN method were introduced to correct the 5 θ model extrapolation results to achieve a more accurate prediction. Consequently, the long-term creep life of P91 steel was predicted. It demonstrated that with the proposed model, the prediction capability for long-term creep life of P91 steel with 200,000 h is much better than those of other θ methods, which has a prediction uncertainty less than 5%.

Hybrid Artificial Neural Network-Based Models to Investigate Deformation Behavior of AZ31B Magnesium Alloy at Warm Tensile Deformation.

The uniaxial warm tensile experiments were carried out in deformation temperatures (50-250 °C) and strain rates (0.005 to 0.0167 s-1) to investigate the material workability and to predict flow stress of AZ31B magnesium alloy. The back-propagation artificial neural network (BP-ANN) model, a hybrid models with a genetic algorithm (GABP-ANN), and a constrained nonlinear function (CFBP-ANN) were investigated. In order to train the exploited machine learning models, the process parameters such as strain, strain rate, and temperature were accounted as inputs and flow stress was considered as output; moreover, the experimental flow stress values were also normalized to constructively run the neural networks and to achieve better generalization and stabilization in the trained network. Additionally, the proposed model's closeness and validness were quantified by coefficient of determination (R2), relative mean square error (RMSE), and average absolute relative error (AARE) metrics. The computed statistical outcomes disclose that the flow stress predicted by both GABP-ANN and CFBP-ANN models exhibited better closeness with the experimental data. Moreover, compared with the GABP-ANN model outcomes, the CFBP-ANN model has a relatively higher predictability. Thus, the outcomes confirm that the proposed CFBP-ANN model can result in the accurate description of AZ31 magnesium alloy deformation behavior, showing potential for the purpose of practicing finite element analysis.

Modeling Height–Diameter Relationship Using Artificial Neural Networks for Durango Pine (Pinus durangensis Martínez) Species in Mexico

The total tree height (h) and diameter at breast height (dbh) relationship is an essential tool in forest management and planning. Nonlinear mixed effect modeling (NLMEM) has been extensively used, and lately the artificial neural network (ANN) and the resilient backpropagation artificial neural network (RBPANN) approach has been a trending topic for modeling this relationship. The objective of this study was to evaluate and contrast the NLMEN and RBPANN approaches for modeling the h-dbh relationship for the Durango pine species (Pinus durangensis Martínez) for both training and testing datasets in a mixed-species forest in Mexico. The knowledge of this relationship is important for forest management and planning in Mexican Forestry. The total dataset considered 1000 plots (each plot 0.10 ha) (11,472 measured trees) randomly selected from 14,390 temporary forest inventory plots and the dataset was randomly divided into two parts: 50% for training and 50% for testing. An unsupervised clustering analysis was used to group the dataset into 10 cluster-groups based on the k-means clustering method. An RBPANN was performed for tangent hyperbolicus (RBPANN-tanh), softplus (RBPANN-softplus), and logistic (RBPANN-logistic) activation functions in the cross product of the covariate or neurons and the weights for the ANN analysis. Also, a different vector of hidden layers was used for training of ANNs. For both training and testing, 10 classical statistics (e.g., RMSE, AIC, BIC, and logLik) were computed for the residual values and to assess the approaches for the h-dbh relationship. For training and testing, the ANN approach outperformed the NLMEM approach, and the RBPANN-tanh had the best performance in both the training and testing of ANNs.