Artificial Neural Network Approach Research Articles

New strategy to optimize in-situ fenton oxidation for TPH contaminated soil remediation via artificial neural network approach

In-situ remediation of total petroleum hydrocarbon (TPH) contaminated soils via Fenton oxidation is a promising approach. However, determining the proper injection amount of H2O2 and Fe source over the Fenton reaction in the complex geological conditions for in-situ TPH soil remediation remains a daunting challenge. Herein, we introduced a practical and novel approach using soft computational models, a multilayer perception artificial neural network (MPLNN), for predicting the TPH removal performance. In this study, we conducted 48 sets of TPH removal experiments using Fenton oxidation to determine the TPH removal performance of a wide range of different ground conditions and generated 336 data points. As a result, a negative Pearson correlation coefficient was obtained in the Fe injection mass and the natural presence of Fe mineral in the soil, indicating that the excess of Fe could significantly retarded the TPH removal performance in the Fenton reaction. In addition, the MPLNN model with 6-6-1 training using Scaled conjugate gradient backpropagation (SCG) with tangent sigmoid as the transfer function demonstrated a high accuracy for TPH removal prediction with the correlation determination of 0.974 and mean square error value of 0.0259. The optimized MPLNN model achieved less than 20% error for predicting TPH removal performance in actual TPH-contaminated soil via Fenton oxidation. Hence, the proposed MPLNN can be useful in improving the Fenton oxidation of TPH removal performance in-situ soil remediation.

Prediction of Wear Properties of CaO and MgO Doped Stabilized Zirconia Ceramics with Artificial Neural Networks

In this research, the production and wear behavior of CaO and MgO doped stabilized zirconia ceramics prepared by powder metallurgy method were investigated and artificial neural network (ANN) models were established and predicted with the data produced as a result of real experiments. CaO/MgO doped stabilized zirconia ceramics were produced using a combination of ball milling, cold pressing - cold isostatic pressing and sintering methods. CaO and MgO were mixed with zirconia in different amounts (0-8 mol%). These mixtures were prepared by mechanical alloying. Green compacts were sintered at 1600°C. The wear experimental results produced from the trials were converted into data suitable for modelling with ANN. Wear load, wear time of the load, MgO and CaO were given as input to the ANN model. The amount of wear according to the pressing method was set as the output variable value of the ANN. An ANN approach model was established to predict the wear behavior characteristics of zirconia ceramic composites. In order to emphasize the success of the model, the test data set was presented to the ANN model and the results produced were compared with the results produced experimentally, and as a result of these tests, high R2 values of 0.99409 for 65N and 0.97512 for 80N were produced.

A Study on XANNs for Analyzing Failures in Guided Ultrasonic Wave-based Damage Localization

In the field of Structural Health Monitoring (SHM) using Guided Ultrasonic Waves (GUW), machine learning (ML) approaches for data analysis are becoming increasingly popular. Especially, deep learning with artificial neural networks (ANN) has proven effective due to its ability to process a large amount of data. ANN are commonly employed in damage localization tasks, where, with appropriate training, they deliver good results. However, a significant challenge persists in the application of ANN, namely, their "black-box" nature, which hinders the investigation of decision processes within the ANN and makes it difficult to understand why an ANN model fails under certain inputs. In the present work, an already introduced explainable artificial neural network (XANN) approach will be utilized to investigate when and why a trained XANN model fails with given inputs. The Open Guided Wave (GUW) platform's data is employed to train and test a XANN model designed to predict the location of artificial damage. Subsequently, individual inputs are modified (simulating malfunctions in specific sensor paths), and the impact on decision processes within the XANN architecture is examined. The aim of this study is to investigate and enhance the resilience and explainability of ANN approaches in the SHM domain.

An artificial neural network approach to enrich HAZOP analysis of complex processes

This paper proposes an innovative approach to enrich Hazard and operability (HAZOP) analysis for complex processes using process simulators and artificial neural networks (ANNs). HAZOP study is a systematic qualitative procedure aimed at identifying potential hazards and operability issues. It heavily relies on the collective knowledge and experience of the team during brainstorming sessions. Traditionally, HAZOP considers only “one failure at a time,” overlooking the effects of deviation causes amplitudes, their propagation, and subsequent domino effects. This simplification is necessary to manage time and costs during sessions. However, in complex systems, neglecting certain scenarios may result in overlooking critical situations. In our proposed method, we leverage process simulators to simulate upset scenarios comprehensively. By systematically varying all possible deviation causes and their combinations, we generate a substantial amount of simulation data. To facilitate evaluation, we introduce novel evaluation indexes. Additionally, we define a sensitivity index for ranking HAZOP scenarios based on severity of consequences. Furthermore, we classify scenarios into three severity levels according to their consequences. To enhance HAZOP analysis, we employ ANNs. These networks learn process behaviors and predict the evaluation indexes. They also classify scenarios based on pre-simulated data. With this approach, the HAZOP team can efficiently analyze the consequences of nearly any combination of deviation causes and failures, even with varying amplitudes. We validate our method by applying it to a real-world complex polymerization plant, demonstrating its value in practical scenarios.

Artificial neural network method in solving smart cities construction fuzzy multi-objective linear programming problems

Nowadays, the increasing demands of smart cities require innovative technologies to optimize resource utilization and minimize costs. This research focuses on the construction sector, specifically the production of advanced high-strength steel. We address practical application problems from the iron and steel factory in Annaba, Algeria, known as fuzzy multi-objective linear programming problems. Two methods are applied: a mathematical model and Artificial Neural Networks (ANNs). Results indicate that the ANN approach offers significant time and effort savings.

How Narcissism and Susceptibility to Emotional Contagion Affect Belief in Fake News on Social Media from a Dual Information Processing Perspective: A Hybrid SEM and ANN Approach

Objectives: To answer who believes in fake news and provide strategies to combat it, we examined how narcissism and susceptibility to emotional contagion influences belief in fake news on social media through heuristic and systematic processing; we also evaluated the moderating effect of media literacy. In addition, we ranked the relative importance of these factors to belief in fake news. Methods: We used a hybrid structural equation modeling (SEM) and artificial neural networks (ANN) approach to analyze data collected from 347 respondents in an online survey. Results: The SEM results showed that narcissism and susceptibility to emotional contagion positively influenced heuristic and systematic processing, thus positively influencing belief in fake news. Media literacy moderated the relationship between systematic processing and belief in fake news. Conclusion: The ANN results indicated that narcissism is a more critical factor for belief in fake news. ANN predicted belief in fake news with an accuracy of 99.9%.

Dew and Rain Evolution from Climate Change in Semi-Arid South-Western Madagascar between 1991 and 2033 (Extrapolated)

In the context of global warming and the increasing scarcity of fresh water resources, it becomes significant to evaluate the contribution and evolution of non-rainfall waters such as dew. This study therefore aims to evaluate the relative dew and rain contributions in three sites of south-western of Madagascar (Ifaty, Toliara, and Andremba), a semi-arid region which suffers from a strong water deficit. The studied period is 1/1991–7/2023, with extrapolation to 7/2033. Dew is calculated from meteo data by using a well-established energy model. The extrapolation of dew and rain follows an artificial neural network approach. It is found that dew forms regularly (2–3 days on average between events), in contrast to rain (10–15 days). The evolutions of dew and rain are similar, with an increase from 1991 to 2000, a decrease up to 2020 and a further increase until 2033. These oscillations follow the Indian Ocean dipole variations and should be influenced by climate change. Dew contributions to the water balance remain modest on a yearly basis (3–4%) but is important during the dry season (Apr.–Oct.), up to 30%. Dew therefore appears to be a reliable and sustainable resource for plants, small animals, and the population, especially during droughts.

Design of Battery Energy Storage System Torsional Damper for a Microgrid with Wind Generators Using Artificial Neural Network

Ancillary frequency controllers such as droop controllers are beneficial for frequency regulation of a microgrid with high penetration of wind generators. However, the use of such ancillary frequency controllers may cause torsional oscillation in the doubly fed induction generator (DFIG). In this paper, a supplementary torsional damper in a battery energy storage system (BESS) is designed to improve the damping ratio for the DFIG torsional mode. Since the optimal damper gain depends on system variables such as the number of diesel generators, the number of wind generators, and BESS droop gain, an artificial neural network (ANN) is trained using these system variables as inputs and the desired BESS damper gain as the output. After the ANN has been trained with the training patterns, it can provide the desired BESS damper gain in an accurate and efficient manner. The effectiveness of the proposed ANN approach for BESS damper design is demonstrated by MATLAB/SIMULINK R2022b simulations.

Numerical tackling for MHD Darcy-Forchheimer flow of water-based CNTs in a rotating frame with homogeneous-heterogeneous reactions: An artificial neural network approach

Numerous scientific fields rely heavily on rotating flows, such as jet engine design, geophysical flows, turbine engineering, vacuum cleaner design, and many others. Prior research on rotational flow has largely disregarded the impact of viscous dissipation and homogeneous-heterogeneous responses. The present study investigates the Darcy-Forchheimer flow of carbon nanotubes (CNTs) in a rotating frame caused by a biaxial stretched plate with heat consumption and radiation. Furthermore, the mass transport mechanism is treated in terms of homogeneous-heterogeneous chemical reactions. The equations governing the flow are reduced into ordinary differential equations by using appropriate transforms. An advanced computational technique, bvp4c, has been used to provide precise numerical solutions.The computation of the resulting systems is also performed using an artificial neural network (ANN) and also the machine learning study shows a high correlation between the numerical and ANN findings, with a mean squared error (MSE) of 0.000053 for SWCNT and 0.000268 for MWCNT. A comprehensive investigation of several parameters yields both graphical and numerical outcomes. It has been discovered that larger values of the Forchheimer number and porosity parameter result in the decay of fluid velocities. The x − direction skin friction coefficient reduced 50% and the y − direction skin friction coefficient improved 46% when the magnetic field enhanced 200%. The 200% porosity parameter leads to reducing the local Nusselt number by 22% for both CNTs.

A CMIP6-ensemble-based evaluation of precipitation and temperature projections

Understanding climate change’s effects on dam basins is very important for water resource management because of their important role in providing essential functions such as water storage, irrigation, and energy production. This study aims to investigate the impact of climate change on temperature and precipitation variables in the Altınkaya Dam Basin, which holds significant potential for hydroelectric power generation in Türkiye. These potential impacts were investigated by using ERA5 reanalysis data, six GCMs from the current CMIP6 archive, and two Shared Socioeconomic Pathways (SSP2 − 4.5 and SSP5 − 8.5) scenario data. Four Multi-Model Ensemble (MME) models were developed by using an Artificial Neural Network (ANN) approach (ENS1), simple averaging (ENS2), weighted correlation coefficients (ENS3), and the MARS algorithm (ENS4), and the results were compared to each other. Moreover, quantile delta mapping (QDM) bias correction was used. The 35-year period (1980–2014) was chosen as the reference period, and further evaluations were conducted by dividing it into three future periods (near (2025–2054), mid-far (2055–2084), and far (2085–2100)). Considering the results achieved from the MMEs, variations are expected in the monthly, seasonal, and annual assessments. Projections until the year 2100 indicate that under optimistic and pessimistic scenarios, temperature increases could reach up to 3.11 °C and 5.64 °C, respectively, while precipitation could decrease by as much as 19% and 43%, respectively. These results suggest that the potential changes in temperature and precipitation within the dam basin could significantly impact critical elements such as future water flow and energy production.

Comparison of a conventional image processing approach with an artificial neural network approach to three‐dimensionally trace multiple particles in dynamic x‐ray microtomography experiments under laboratory conditions

AbstractThis paper compares a classic digital image processing approach to trace particles in laboratory x‐ray micro‐computed tomography (µCT), which is based on a combination of random sample consensus (RANSAC) algorithm and least squares ellipse fitting (LSF), with an approach based on artificial neural networks (ANNs). In order to be able to perform the comparison, dynamic experiments were carried out in a laboratory microtomography facility. During active scans with a duration of 30–75 s several sedimentation experiments have been carried out with an exposure time of 0.13 s/projection. Through the movement of the particles during the scan curved motion artefacts in the reconstructed data occur, where the vertex marks the coordinate of the particle. It could be shown that both approaches enable the tracing of particles in laboratory x‐ray µCT with deviations from a manually evaluated result of exemplarily 1.25% for the conventional digital image processing (CDIP) and 0.48% for the ANN. It was found that ANNs are able to identify particle positions in non‐symmetrical motion artefacts, appearing around the first and last position of the particles in the scan, allowing an extension of the motion range of the particles that can be evaluated. Both methods have their advantages and disadvantages. Due to the high complexity and size as well as partly black box structures of neural networks, they are not 100% comprehensible whereas conventional image processing is 100% transparent and understandable. But because of the complexity of the tracing of particles, the CDIP code offers many parameters that can be set, which is why the application is therefore slightly more complex.

Exploring the influencing factors of blockchain technology adoption in national quality infrastructure: a Dual-Stage structural equation model and artificial neural network approach using TAM-TOE framework

Exploring the influencing factors of blockchain technology adoption in national quality infrastructure: a Dual-Stage structural equation model and artificial neural network approach using TAM-TOE framework

Nonlinear RF impairments modeling with OFDM symbol-based parallel Wiener–Hammerstein structure

In the paper, a novel orthogonal frequency division multiplexing (OFDM) symbol-based parallel Wiener–Hammerstein structure is proposed to deal with the problem of nonlinear radio frequency (RF) impairments modeling for a cyclic prefix OFDM (CP-OFDM) waveform in telecommunication systems. The aforementioned structure is an equivalent linear-in-parameters representation of the parallel Wiener–Hammerstein structure in the considered problem. The structure is formally derived enabling the usage of identification algorithms compared with the artificial neural network (ANN) approach. The solution is compliant with current telecommunication standards.

A Novel Approach for Mobility-Aware Energy-Efficient Clustering-Based Routing Using EANN With GA Algorithm on WSNs

Aim: This research aims to explore and evaluate various strategies for improving energy efficiency within wireless sensor networks (WSNs). Specifically, the study focuses on the critical challenge of extending network lifespan through energy conservation by establishing balanced clusters within the WSN architecture. Background: In wireless sensor networks (WSNs), ensuring prolonged network operation while conserving energy resources is a significant concern. One promising approach to address this challenge is the implementation of equalized clusters, which requires an effective selection of cluster heads (CHs). However, this task presents considerable complexity and demands innovative solutions to overcome. Objective: The primary objective of this study is to develop and assess a novel methodology for selecting precise cluster heads (CHs) within WSNs. This methodology is based on the utilization of Bluetooth low energy (BLE) sensors deployed in a randomly distributed manner across the study area. By employing an enhanced artificial neural network and greedy approach (EANN-GA), the proposed technique seeks to identify CHs with optimal proximity to the cluster center and substantial remaining energy reserves. Methods: The proposed methodology involves the deployment of BLE sensors distributed randomly throughout the study region, which are then organized into clusters. Using the enhanced artificial neural network and greedy approach (EANN-GA), the sensor node nearest to the cluster center with the highest remaining energy is selected as the cluster head (CH). Additionally, a mobile sink (MS) is introduced to harness the power of CHs, and the number of paths utilized by the MS is estimated through a genetic approach. Based on this path information, the MS enters each cluster to initiate the data-gathering process. Results: Performance analysis of the presented methodology demonstrates significant improvements in energy efficiency and the extension of network lifetime. By employing the proposed EANN-GA technique for CH selection and optimizing MS path utilization, the study showcases enhanced operational effectiveness within WSNs. Conclusion: The findings of this research underscore the effectiveness of the proposed methodology in enhancing energy efficiency and prolonging the lifespan of wireless sensor networks. Through the innovative integration of BLE sensors, EANN-GA CH selection, and genetic-based MS path estimation, the study contributes valuable insights toward addressing the critical challenges of energy conservation in WSNs.

Quantitative analysis of Maxwell fluid flow with dual diffusion through the variable porous canonical gap using artificial neural network approach

Quantitative analysis of Maxwell fluid flow with dual diffusion through the variable porous canonical gap using artificial neural network approach

Predictive Modeling of Wettability Characteristics in Developed Shielded Metal Arc Welding Electrode Coating Fluxes: A Regression and Artificial Neural Network Approach

Predictive Modeling of Wettability Characteristics in Developed Shielded Metal Arc Welding Electrode Coating Fluxes: A Regression and Artificial Neural Network Approach

Unlocking groundwater desalination potential for agriculture with fertilizer drawn forward osmosis: prediction and performance optimization via RSM and ANN.

The agricultural sector uses 70% of the world's freshwater. As clean water is extracted, groundwater quality decreases, making it difficult to grow crops. Brackish water desalination is a promising solution for agricultural areas, but the cost is a barrier to adoption. This study investigated the performance of the fertilizer drawn forward osmosis (FDFO) process for brackish water desalination using response surface methodology (RSM) and artificial neural network (ANN) approaches. The RSM model was used to identify the optimal operating conditions, and the ANN model was used to predict the water flux (Jw) and reverse solute flux (Js). Both models achieved high accuracy, with RSM excelling in predicting Js (R2 = 0.9614) and ANN performing better for Jw (R2 = 0.9801). Draw solution (DS) concentration emerged as the most critical factor for both models, having a relative importance of 100% for two outputs. The optimal operating conditions identified by RSM were a DS concentration of 22 mol L-1, and identical feed solution (FS) and DS velocities of 8.1 cm s-1. This configuration yielded a high Jw of 4.386 LMH and a low Js of 0.392 gMH. Furthermore, the study evaluated the applicability of FDFO for real brackish groundwater. The results confirm FDFO's potential as a viable technology for water recovery in agriculture. The standalone FO system proves to be less energy-intensive than other desalination technologies. However, FO exhibits a low recovery rate, which may necessitate further dilution for fertigation purposes.

Artificial intelligence-based neural network modeling of adsorptive removal of phenol from aquatic environment

In this study, adsorptive uptake of phenol from aqueous system using Arachis hypogaea (groundnut) shell-based adsorbent was experimentally investigated and modelled using artificial intelligence-based neural network approach. Artificial neural networks with different number of neurons were designed using Levenberg-Marquardt algorithm to find the best model for phenol adsorption. The feedforward back propagation neural network comprising TRAINLM, LARNGDM and TANSIG as training, adaptation learning and transfer functions, respectively, with ten neurons in the hidden layer exhibited the optimal architecture with the strongest correlation R2=0.9901 and the smallest mean square error MSE=0.045. The studies indicated a maximum adsorptive uptake of phenol to be 37.31 mg/g onto the activated shell powder. The kinetic analysis favored pseudo second order R2=0.9999and the equilibrium data was best represented by Freundlich isotherm modelR2=0.9976. Phenolic remediation phenomenon ensued in a spontaneous manner, was exothermic ∆H0=−34.25kJ/moland involved physisorption. The experimental results are agreement with model.

Prediction and optimization of performance parameters of solar collectors with flat and porous plates using ANN and RSM: Case study of Shahrekord, Iran

It is necessary to adopt measures to make optimal use of rich sources of solar energy, considering the limit resources of fossil fuels and increasing demand for energy. Using solar collectors is one of the methods to collect solar energy. The aim of this study was an investigation and prediction of the effect of the collector's slope angle and plate type on the collector performance using artificial neural network (ANN) approaches. Two different ANN models, multi-layer perceptron (MLP) and radial basis function (RBF), were applied to predict the performance parameters of solar collectors. The results indicated that the ANN-MLP and ANN-RBF models were acceptable, but the ANN-RBF model with structure of 2-16-5 had higher acceptability for prediction of output parameters at various input variables. The highest R and lowest root mean square error (RMSE) values in training set of ANN-RBF for air speed (AS) were obtained as 0.984 and 0.015, respectively. The results showed that increasing the slope angle from 0 to 60 caused to increase in the amount of received radiation by the collector, and so leading to an increase in the air temperature inside the collector. On the other hand, the maximum value of thermal power (TP) and collector efficiency (CE) for the porous plate were more than the simple plate by 28.2 % and 41.5 %, respectively.

Optimizing Landslide Susceptibility Model Using Artificial Neural Network (ANN) Approach in Sawla-Laska Road Corridor and Surroundings, Southwest Ethiopia

Natural disasters such as landslides have potential to jeopardize human life and seriously harm ecosystems. Ethiopia is among the countries most susceptible to landslides because of its mountainous terrain, strong and sustained rainfall, and dense development near steep hillsides. This study aimed to produce a landslide susceptibility map for the Sawla-Laska road corridor and its surroundings in Ethiopia using an Artificial Neural Network (ANN) model. The QGIS model builder module was used to intersect 195 landslide polygons and 12 thematic raster pixels for the topographic, hydrological, proximity, geological, and environmental elements. The Generalized Weight (GW) results revealed strong correlations between proximity variables, slope, plane curvature, humicalisols, agricultural areas, settlements, scant vegetation, and barren terrain. In contrast, other factors exhibited negative and neutral interactions. The Receiver Operating Characteristics (ROC) curve showed acceptable results. The accuracy of the model ranges from 88% to 94%. Data were assorted into low, medium, and highly vulnerable zones representing 183.85 (75%), 14.55 (6%), and 47.6 (19.34%). The model performances demonstrate that the model can accurately predict the current situation in the future. Therefore, adequate land-use planning and environmental protection should be implemented based on the findings of this study and landslide susceptibility map.