Estimating Structural Collapse Responses Considering Modeling Uncertainties using Artificial Neural Networks and Response Surface Method

This paper studies the effects of spatial correlation between the structural components on probabilistic seismic performance of steel moment resisting frames, using extended incremental dynamic analysis (IDA) method to consider the effects of aleatoric uncertainties caused by ground motion records. In this probabilistic assessment, a combination of Latin hypercube sampling (LHS) and Cholesky decomposition (CD) methods are utilized to take the epistemic uncertainties of the numerical model into account. In case the target correlation matrix is not positive definite, two powerful optimization algorithms are employed to find the closest positive definite correlation matrix.

This study examined the modelling and optimisation of the electrocoagulation-flocculation (ECF) recovery of aquaculture effluent (AQE) using aluminium electrodes. The response surface methodology (RSM), artificial neural network (ANN), and adaptive neuro-fuzzy inference system (ANFIS) were used for the modelling, while the optimisation tools were the numerical RSM and genetic algorithm (GA). Furthermore, the kinetics of the ECF process was studied to provide insight into the mechanism governing the ECF of AQE. The experimental design was performed using the central composite design (CCD) of the RSM. The ANFIS modelling was accomplished via the Grid Partition (GP) of the data set, while the ANN used the multi-layer perceptron (MLP) based feed-forward system. Statistically, the prediction accuracy of the models followed the order: ANFIS (R2: 0.9990), ANN (R2: 0.9807), and RSM (R2: 0.9790). The process optimisation gave optimal turbidity (TD) removal efficiencies of 98.98, 97.81, and 96.01% for ANFIS-GA, ANN-GA, and RSM optimisation techniques, respectively. The ANFIS-GA gave the best optimization result at optimum conditions of pH 4, current intensity (3 A), electrolysis time (7.2min), settling time (23min), and temperature (43.8°C). In the kinetics study, the experimental data was analysed using pseudo-first-order (0.8787), pseudo-second-order (0.9395), and Elovich (R2: 0.9979) kinetic models; the Elovich model gave the best correlation with the experimental data showing that the process is governed by electrostatic interaction mechanism. This study effectively demonstrated that ECF recovery of AQE can effectively be modelled using RSM, ANN, and ANFIS and be optimised using RSM, ANN-GA, and ANFIS-GA techniques, and the order of performance is ANFIS > ANN > RSM and ANFIS-GA > ANN-GA > RSM, respectively.

Recent research has focused on assessing the effectiveness of response surface methodology (RSM), a non-machine learning technique, and artificial neural networks (ANN), a machine learning approach, for predicting concrete performance. This research aims to predict and simulate the compressive strength of concrete that replaces cement and fine aggregate with waste materials such as eggshell powder (ESP) and waste glass powder (WGP) for sustainable construction materials. In order to ensure concrete’s durability and structural integrity, a compressive strength evaluation is essential. Precise predictions maximize efficiency and advance sustainability, particularly when dealing with waste materials like ESP and WGP. The response surface methodology (RSM) and artificial neural network (ANN) techniques are used to accomplish this for practical applications in the built environment. A dataset comprising previously published research was used to assess ANN and RSM’s predictive and generalization abilities. To model and improve the model, ANN used seven independent variables, while three variables, cement, waste glass powder, and eggshell powder, improved the RSM. Both the ANN and RSM techniques are effective instruments for predicting compressive strength, according to the statistical results, which include mean squared error (MSE), determination coefficient (R2), and adjusted coefficient (R2 adj). RSM was able to achieve the R2 by 0.8729 and 0.7532 for compressive strength, while the accuracy of the results for ANN was 0.907 and 0.956 for compressive strength. Moreover, the correlation between ANN and RSM models and experimental data is high. The artificial neural network model, however, exhibits superior accuracy.

The kinetic of catalytic upgrading of anisole as a lignin−derived bio−oil component is investigated experimentally over Pt/γAl2O3 at 573−673 K and 14 bar. According to experimental results, benzene, phenol, 2−methylphenol, 2,6−dimethylphenol, 2,4,6−trimethylphenol, and hexamethylbenzene are identified as the main products. The results indicated that the kinetically significant reaction classes are hydrogenolysis, hydrodeoxygenation (HDO), alkylation, and hydrogenation. The response surface methodology (RSM) is applied to optimize the experimental data which obtained at suggested conditions by design of experiment (DOE). Due to the complex nature of the system, artificial neural networks (ANNs) were employed as an efficient tool to model the behavior of the system. RSM and ANN methods were constructed based upon the DOE’s points and then utilized for generating extra−simulated data. Data simulated by the RSM/ANN method were used to fit power law kinetic rate expressions for the reactions. The coefficient of determination (R2 ) was obtained 0.998 and 0.973 for anisole conversion model and benzene selectivity model which represented the high accuracy of model predictions. The correlation coefficient (R) and mean square error (MSE) of ANN model equaled to 0.97 and 8.3 × 10−12 respectively means high accuracy of the developed model. The results of kinetic modeling with simulated data from the ANN and RSM models revealed that the highest reaction order during the upgrading process of anisole belongs to hydrogenolysis of anisole to phenol. Also the activation energy of hydrogenolysis reaction was lower than HDO.

An algorithm is proposed for the rapid estimation of the influence of model parameter uncertainties on the seismic performance of structures using incremental dynamic analysis (IDA) and Monte Carlo simulation with Latin hypercube sampling. It builds upon existing methods that quantify the uncertainty for structural models with nondeterministic parameters by performing IDA with multiple ground motion records on each model realization out of a predetermined sample. However, their practical application is restricted due to (1) the inability to determine a priori the required number of samples and (2) the disproportionate increase of the number of analyses in realistic multiparameter models. To address these issues, two fundamental changes are incorporated. First, Latin hypercube sampling is applied progressively by starting with a small sample that is doubled successively until the desired accuracy is achieved. Second, parameter sampling is performed on a record-by-record basis rather than maintainin...

This study focuses on the modeling and optimization of geothermal binary Organic Rankine Cycle (ORC) systems to enhance power generation from geothermal systems using water as geofluid. Aspen HYSYS, utilizing the Peng-Robinson property package, was used to simulate the process, generating critical process data for subsequent modeling and optimization. Response Surface Methodology (RSM) and an Artificial Neural Network (ANN) were employed to model the relationships between input factors and output response, utilizing a Box-Behnken Design (BBD) for three key input variables: working fluid flow rate, working fluid outlet pressure, and turbine outlet pressure. Both RSM and ANN demonstrated strong predictive capabilities, with RSM achieving an R2 value of 0.9966 and an RMSE of 12.254, while ANN achieved an R2 value of 0.9886 and an RMSE of 23.722, indicating that RSM marginally outperformed ANN in terms of modelling accuracy. Optimization of the ORC system was conducted using RSM and ANN coupled with a Genetic Algorithm (ANN-GA), aimed at determining the optimal values for input and output parameters. The ANN-GA optimization results were validated using Aspen HYSYS and showed superior performance over RSM. ANN-GA predicted optimal values of working fluid flow rate, working fluid outlet pressure, and turbine outlet pressure as 12 kg/s, 19 bar, and 1.2 bar, respectively, which perfectly matched the Aspen HYSYS validation results. This optimization yielded a power output of 958.48 kW, which closely aligned with the Aspen HYSYS validation output of 952.9 kW, reflecting a minimal percentage error of 0.59%. Conversely, RSM predicted slightly deviated optimal values of 11.8 kg/s, 18.47 bar, and 1.2 bar, with a corresponding power output of 940.78 kW. When validated with HYSYS, the RSM-predicted output was 927.2 kW, resulting in a higher percentage error of 1.46%, thereby underperforming relative to ANN-GA. The study highlights the comparative strengths of RSM and ANN-GA, demonstrating that while RSM excels in accurately modeling the relationship and interactions between input factors and output responses, the ANN-GA framework exhibits a significantly higher capability in navigating complex nonlinear optimization landscapes. This highlights the effectiveness of integrating machine learning models with meta-heuristic algorithms for enhanced optimization performance. The findings contribute to advancing the methodology for optimizing geothermal ORC systems and offer a robust framework for improving power generation efficiency in geothermal energy applications.

The utilization of bioluminescent bacteria has served as a powerful bioassay in environmental monitoring as a result of simplicity of use, quick response and high sensitivity on the basis of the luminescence being produced. In the present study, the optimization process for the luminescence production of a newly isolated Photobacterium sp. NAA-MIE using response surface methodology (RSM) and artificial neural network (ANN) is investigated. RSM and ANN are the most favored techniques and efficient methods for the optimization of medium components, especially for nonlinear systems. This analysis presents the comparative evaluation between RSM and ANN aimed at their particular empirical modeling and predictive ability. RSM predicted the optimized condition with four major variables at glycerol concentration of 0.16%, NaCl of 2.49%, pH at 7.4 and tryptone of 2.97% with 260,748.94 RLU of the maximum luminescence production. The accuracy of the RSM model equations was measured with R2 of 0.9001 and adjusted R2 of 0.8001. ANN predicted optimum condition at a glycerol concentration of 0.10%, NaCl of 2.46%, pH at 7.5 and tryptone of 1.97% with 237,481.32 RLU. The study demonstrated that ANN accomplishes more than RSM with a higher R2 value of 0.968 and low mean percentage error and root mean square error, which were 0.003 and 3.66, respectively. Both models are presented as suitable predictive models on the basis of mathematical modeling to optimize and improve biological systems for future upscaling processes with ANN as more predictive and having more fitting potentiality compared to RSM.

This work focused on optimization of production of ethanol from saw dust using two empirical methods, the ANN and the RSM. It further investigated the modeling and optimization efficiencies of RSM and ANN in separate hydrolysis and fermentation of sawdust for ethanol production. Box - Behnken Design (BBD) was used to generate 17 individual experiments which were carried out, RSM and Genetic Algorithm (GA) of ANN which were used to optimize the production which was then compared. The optimum concentrations of ethanol yield predicted were 56.968 wt. % and 57. 387263 wt. % for RSM and ANN models respectively. R2 value obtained for ANN model was 0.9989 while R2 value of 0.9046 was obtained for RSM model. The Root Mean Square Error (RMSE) value for ANN was found to be 0.143 while the RMSE value for RSM was 2.17. It showed that ANN had relatively higher predictive model ability and thus shows to be a better optimization tool for the ethanol from saw dust compared to RSM which also a good modelling tool.

Comparative study using RSM and ANN modelling for performance-emission prediction of CI engine fuelled with bio-diesohol blends: A fuzzy optimization approach

The concept of orthometric heights system determination plays a major key role in geodesy, and it has broad applications in various fields and activities. In geodesy, one significant quantity is the orthometric height, the height above or below the geoid along the gravity plumbline. Conventionally, the orthometric height is determined by gravimetry and levelling techniques. However, the aforementioned techniques has its own demerits. Thus, the error is accumulated with the increase of the propagation measurement line, it is difficult to convert two separated points which is located in two continents or islands separated by sea. These techniques are tedious, time consuming and expensive. In order to resolve this challenge, many researchers resort to various techniques and approaches of obtaining orthometric heights for an area using various mathematical models. It is in this quest that, this study seek to estimate orthometric heights of a mine by utilizing plausible alternative techniques based on artificial neural networks (ANN), multivariate adaptive regression splines (MARS), polynomial regression models and multiple linear regression (MLR). The working efficiency and performance of each model has been assessed based on statistical indicators of Mean (M), Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Bias Error (MBE), Mean Absolute Error (MAE), Standard Deviation (SD), Correlation coefficient (R), Correction of determination (R2), and Signal to Noise Ratio (SNR). The statistical findings reveal that all the models produce satisfactory results in estimating the orthometric heights in the mine. MARS and ANN models compare to the MLR and polynomial models achieved higher results in terms of accuracy with mean and standard deviation of -0.000001888 m, +2.24736 m, and +0.005835 m and 0.095063 m respectively. This study will create the opportunity for geospatial practitioners to recognize the significant of ANN, MARS, MLR, and Polynomial model in solving some of the problems in geoscientific community.

Introduction: The greatest part of constructed dams belongs to embankment dams and there are many examples of their failures throughout history. About one-third of the world’s dam failures have been caused by flood overtopping, which indicates that flood overtopping is an important factor affecting reservoir projects’ safety. Moreover, because of a poor understanding of the randomness of floods, reservoir water levels during flood seasons are often lowered artificially in order to avoid overtopping and protect the lives and property of downstream residents. So, estimation of dam overtopping risk with regard to uncertainties is more important than achieving the dam’s safety. This study presents the procedure for risk evaluation of dam overtopping due to various uncertaintiess in inflows and reservoir initial condition. Materials and Methods: This study aims to present a practical approach and compare the different uncertainty analysis methods in the evaluation of dam overtopping risk due to flood. For this purpose, Monte Carlo simulation and Latin hypercube sampling methods were used to calculate the overtopping risk, evaluate the uncertainty, and calculate the highest water level during different flood events. To assess these methods from a practical point of view, the Maroon dam was chosen for the case study. Figure. 1 indicates the work procedure, including three parts: 1) Identification and evaluation of effective factors on flood routing and dam overtopping, 2) Data collection and analysis for reservoir routing and uncertainty analysis, 3) Uncertainty and risk analysis. Figure 1- Diagram of dam overtopping risk evaluation Results and Discussion: Figure 2 shows the results of the computed overtopping risks for the Maroon Dam without considering the wind effect, for the initial water level of 504 m as an example. As it is shown in Figure. 2, the trends of the risk curves computed by the different uncertainty analysis methods are similar. As it can be seen, the risk curves computed by the LHS are slightly higher than those curves computed by the MCS method. Also as it is observed, the differences between risk values of the two methods increase in longer return periods. Variations of overtopping risk with increasing the initial water level and return period related to overtopping risk in the 2-year return period for the initial water level of 470 m are shown in Table1. The results show that elongation of return period plays a more important role in increasing the risk, than the increase of initial water level. T Method 2→2 2→50 2→100 2→1000 2→5000 2→10000 470→470 MCS 1 5 9 23 42.36 58 470→478 2 7 15.6 37 58.34 79 470→485 5.6 13.6 28.6 55.6 85.67 112.6 470→493 10.3 32.6 54 95.6 127.34 152 470→504 40.3 83 117.3 165 200.34 224.3 470→470 LHS 1 5.34 11 25.3 43 60.3 470→478 2.3 8.6 18 39.3 60.67 84 470→485 5.3 17.3 32.6 58.3 89 114.6 470→493 13.3 37.6 57.6 97 133.34 160.3 470→504 41.6 87.3 119.6 173 205 233.3 Figure 2- Overtopping risk in the initial water level of 504 m, without considering the wind effect Conclusions: This study applies MCS and LHS methods to analyze the uncertainty and evaluate the dam overtopping risk consideringthe uncertainties in input variables, such as quintile of flood peak discharge, initial levels of water and spill coefficients. The results show that the uncertainty of water level calculated by MCS is higher than that calculated by LHS. In addition, the overtopping risk calculated by LHS is higher than that calculated by MCS. Furthermore, the increase of inflow rate influences the variations of the overtopping risk more than the increase of the return period. In addition, evaluation of the results indicates that the overtopping risk is an important issue in the Maroon dam. So, a comprehensiverisk analysis procedure in conjunction with uncertainty gives very important information for decision makers to make better judgments in dam operation based on uncertainty in inputs.

Performance and emission prediction of a compression ignition engine fueled with biodiesel-diesel blends: A combined application of ANN and RSM based optimization

Response surface methodology (RSM) and artificial neural network (ANN) on modeling and optimization of corrosion inhibition efficiencies of mild steel using water hyacinth as an inhibitor was carried out in this work. The optimization of the process was done using generic algorithm (GA) and RSM which were subsequently compared. The optimum inhibition efficiency predicted were 87.675924% and 82.89% by ANN and RSM respectively. The value of R2 obtained were 0.9695 and 0.85118 for ANN and RSM models respectively while RMSE values of 3.90 and 4.3089 were gotten for RSM and ANN models respectively. The model regression indicated that RSM best fit the experimental data thus perform better on mild steel corrosion inhibition.

Purpose – This paper aims to study the comparison between a response surface methodology (RSM) and artificial neural network (ANN) in the modelling and prediction of surface roughness during endmilling of glass-fibre-reinforced polymer composites. Design/methodology/approach – Aiming to achieve this goal, several milling experiments were performed with polycrystalline diamond inserts at different machining parameters, namely, feed rate, cutting speed, depth of cut and fibre orientation angle. Mathematical model is created using central composite face-centred second-order in RSM and the adequacy of the model was verified using analysis of variance. ANN model is created using the back propagation algorithm. Findings – With regard to the machining test, it was observed that feed rate is the dominant parameter that affects the surface roughness, followed by the fibre orientation. The comparison results show that models provide accurate prediction of surface roughness in which ANN performs better than RSM. Originality/value – The data predicted from ANN are very nearer to experimental results compared to RSM; therefore, this ANN model can be used to determine the surface roughness for various fibre-reinforced polymer composites and also for various machining parameters.

Introduction: Sagittal rocker profiles are one of the most commonly prescribed therapeutic footwear interventions to alter or adapt lower limb joints’ kinematics and kinetics. However, the prescription criteria for rocker profiles are commonly based on theoretical considerations. Thus, conducting experimental studies and experiment and error may result in their better prescription and use. A complementary approach is to use intelligent technology to predict curve profile to suit a specific joint position. The aim of this study was to predict sagittal curve profile of the rollover footwear from ankle kinematics while walking by applying an artificial neural network (ANN). Materials and Methods: In the present study, 20 healthy participants (with mean age of 33.1 years) walked on a straight path for 10 meters wearing two different shoes with two different sole curved profiles and ankle kinematic data were collected using reflective markers. The ANN was trained to associate set of ankle sagittal plane motions during stance phase with outsole curve profiles, and then, predict the latter based on the former. The ANN was trained using the data from 13 participants (control group) to obtain the model and the data from the remaining participants (intervention group) was used for the validation of the study purposes. Results: The achieved accuracy was very satisfactory, since the correlation coefficients between the predicted output and the actual curve profile in the validation data were higher than 0.95 for both types of rollover footwear. Conclusion: In this study, a novel algorithm was proposed for sole curve profile characterization of rollover footwear using an ANN model. The results of this study may be useful to designers of footwear, lower limb prostheses, orthoses, and walking casts/boots.