This study introduces machine learning approach for mathematical models of wire coating analysis involving non-Newtonian Eyring-Powell fluidic system (NEPFS) by adopting the Bayesian regularization optimized neural network method (BRNNM) to increase the predictive performance of model. Two models of NEPFS namely the constant velocity model and the Reynolds Model are examined in this study by investigating the influence of Brinkman number, porous parameter, heat generation parameter, flow behavior index parameter and Eyring-Powel fluid parameters on temperature profile. Datasets for said stiff NEPFS models are generated by exploiting the strength of Adam Bashforth numerical method for each scenario to portray the evidence of heat generation parameters as an important factor that affected the uniformity and effectiveness of the coating. The adaptive parameter tuning allowed better control of the industrial processes, and less material was wasted while the quality of the products was enhanced. The Reynolds numbers were kept low to ensure fluid stability and a stable solution that can easily be applied to a real situation. It is observed that the BRNNM framework has a high level of predictive accuracy with mean squared error of 10-12 to 10-13, and regression coefficients close to unity (R approximate to 1) over training, testing and validation data. Increasing Brinkman number, heat generation parameter, flow behavior parameter and Eyring-Powell viscosity parameter enhanced temperature profiles, while porous parameter had minimal influence on thermal distribution. Moreover, the work demonstrates the possibility to apply non-Newtonian fluid mechanics in optimization of wire coating technologies in particular at thermal and dynamic operation. The best training performance is observed in relation to epoch number index at epoch 85, 881, 306, 806 and 1000 respectively to all the scenarios. Furthermore, observed mean squared errors (MSE) between target and output data of approximately 4.469 x 10- -12, 1.439 x 10-13, 1.391 x 10-12, 4.451 x 10-13 and 1.838 x 10-13, recorded at times of 1 s, 3 s, 2 s, 3 s and 4 s respectively. These quantitative results indicate only a very small margin of error, confirming a reliable agreement with the numerical data.

The current study investigates the variations in heat transfer-based thermophysical characteristics that have significant impact on blood flow dynamics by the incorporation of hybrid nanomaterials with the help of Adam–Bashforth–Moulton informatics-driven Bayesian regularized neural networks (ABM-BR-NNs). The characteristics of a blood-based tri-hybrid nanofluid are analyzed using a tangent hyperbolic fluid model in a complex sinuous medium bounded by vertical walls, where the heat transport properties are further enhanced by the interaction of Hall current, Joule heating, and thermal radiation. Physical properties are used to describe the model for interacting alloy nanoparticles AA7072 and AA7075 with zirconium oxide ZrO2 in base liquid blood. Similarity transformations are used to convert the designed model into a non-dimensional form. The primary objectives of the present study are to investigate recent advancements in nanofluid-based peristaltic transport relevant to biomedical applications, particularly within complex sinuous channels bounded by vertical walls, and to evaluate the potential of employing machine learning to enhance the performance of blood-based nanofluid suspension. The effectiveness of the machine learning procedure ABM-BR-NNs is evaluated using data produced by the Adam–Bashforth–Moulton numerical scheme. The dataset is partitioned into training, testing, and validation subsets in proportions of 80

Hybrid nanofluids have shown substantial attention owing to their superior thermal conductivity and magnetohydrodynamic (MHD) response, enabling their use in advanced biomedical, electronic, and energy systems. The present research investigation provides the effects of Hall currents and Ohmic heating based on the ciliary-driven TiO2-Ag/EG hybrid nanofluids flow in a curved channel, by integrating viscous dissipation, slip effects, and thermal sources. By employing lubrication approximations, the governing nonlinear systems of equations are solved using bvp4c scheme, which is trained through the Bayesian regularization neural network in order to ensure robustness and accuracy. The calculated solutions of the model indicate that enhancing the magnetic field and Brinkman number expressively raises temperature because of viscous dissipation and intensified Joule heating, while higher values of the Hall parameter, slip and Biot number decrease the temperature. Velocity decreases with magnetic field strength due to Lorentz force effects; however, it enhances with slip because of reduced wall resistance. Moreover, an enhancement is performed in pressure gradients using Hartmann number and curvature, whereas a decrease is observed using Hall and slip parameters. Furthermore, pressure gradients increase with Hartmann number and curvature, while decreasing with Hall and slip parameters. This research also performs that stronger magnetic fields lessen bolus size, representing improved flow confinement. These findings provide quantitative insights into controlling heat and fluid transport in various applications such as targeted drug delivery, hyperthermia treatment, and microfluidic cooling systems.

Nanofluids play a vital role in different investigations due to their supercilious thermo-physical properties in comparison with the conventional fluids. Magnesium oxide (MgO) nanoparticles have attracted significant scientific attention due to their remarkable biocompatibility, chemical stability, and wide-ranging biomedical applications. These include antimicrobial, anticancer, antioxidant and anti-diabetic functionalities, along with promising roles in tissue engineering, bio-imaging, and targeted drug delivery systems. The objective of the current study is to examine MgO/H2O nanofluid-based peristaltic transport for biomedical purposes, particularly within porous asymmetric channel configurations using the artificial neural networks (ANNs) for enhancing the performance of nanofluid suspension. The study investigates the combined effects of temperature-dependent viscosity and MHD, incorporating velocity slip and convective boundary conditions, while the energy equation accounts for thermal radiation and a nonuniform heat source/sink. The reference dataset for the nanofluidic system's estimated solution is generated using the Adam numerical method, while the performance of the ANNs is optimized via a Bayesian regularization neural network (BRNN) approach and assessed using reference dataset split into 80 % for training, 15 % for testing, and 5 % for validation. The accuracy of the proposed BRNN framework is validated through close agreement with reference results, optimal training performance, and minimal absolute error, while its robustness is further demonstrated through regression analysis, transition state evaluation, and error histogram assessment. The results for magnetic interaction parameter M, velocity slip parameter beta, radiation parameter Rd, Brinkman number Br, pore diameter dp, and nanomaterial amount phi are also discussed to optimize nanofluidic system. MHD authoritative effects help in controlling the flow patterns and enhancement of heat transfer. The amount of nanomaterials and pores diameter significantly influences the viscosity, heat transfer and stability parameters.

Current study deals with the peristaltic transport of graphene oxide-water (GO-H2O) nanomaterial in a tapered inclined channel involving the simultaneous effects of transverse magnetic field, thermal radiation and viscous dissipation. Homogeneous-heterogeneous chemical reactions along with slippage phenomenon at channel walls has been analyzed to present the essential physics of realistic physiological transport. The governing differential system has been modelled and a high-fidelity dataset is generated via the Adams-Bashforth method for sundry parameters such as Grashof number, Hartmann number, velocity slip parameter, heat generation and absorption parameter, thermal radiation parameter. Neural network model invoking intelligent Bayesian regularization neural network method is constructed to foresee the flow and thermal features with great accuracy, representative excellent regression and small error. The calculated results disclose that the coupled impact of magnetic and thermal mechanisms assists effective control of flow and heat transfer. Integration of homogeneous-heterogeneous reactions with GO-H2O nanoparticles are investigated with magneto-thermal effects in an asymmetric geometry. The trained IBRNNM demonstrated excellent capability in accurately predicting the profiles of the nanofluid flow, regression coefficients (R-values), and minimal deviation in error histograms The proposed numerical approach presents a strong and effective approach for examining complex nanofluid systems with relevance to biomedical and engineering applications.

Wind power prediction is a critical goal for power engineers, aimed at forecasting the power output for applicable power plants. However, the complex, nonlinear, non-stationary, and dynamic nature of wind power makes accurate prediction challenging, leading to inefficient grid integration and reduced profitability. Additionally, the vanishing gradient problem diminishes accuracy, causing poor retention of long-term patterns in the data, particularly with traditional short-term machine learning algorithms. In response, this research proposes a novel application of the Long Short-Term Memory (LSTM) algorithm integrated with Seasonal Mean Imputation (SMI), designed for multivariate time series analysis to predict the power output using various parameters including humidity, pressure, temperature, wind velocity, and wind direction at the Fauji Wind Energy Limited-I (50MW) in Gharo, Thatta District, Pakistan. The results from the proposed LSTM-SMI are compared with state-of-the-art counterparts, namely, the Autoregressive Integrated Moving Average (ARIMA) and traditional Mean Imputation (MI) method, using performance metrics such as Symmetric Mean Absolute Percentage Error (SMAPE), Normalized Root Mean Square Error (NRMSE), and Normalized Mean Absolute Error (NMAE). Beside promising results from LSTM-SMI, the study expanded to include comparative performance with state of the art Deep Learning and Machine Learning counterpart models such as Gated Recurrent Units (GRU), Extreme Gradient Boosting (XGBoost) and Recurrent Neural Networks (RNN) for better assessment. The GRU model achieved a SMAPE of 7.68%, compared to 9.13% with LSTM, while application to a univariate dataset with both SMI and MI, the GRU demonstrated robust performance, with the GRU-SMI variant showing a SMAPE of 5.49%, that illustrate the effectiveness. Outcomes demonstrates the potential of advanced recurrent neural network GRU architectures for enhanced predictive accuracy in wind power forecasting.

The purpose of the current study is to design a feed forward Gudermannian neural networks for a singular Lane–Emden model based Neumann, Neumann-Robin and Dirichlet boundary conditions arising in numerous physical systems. The procedure based on the GNNs is exploited through the optimization of global and local search methods, i.e., genetic algorithm and active-set technique. A fitness function is constructed using the model and its boundary conditions, while the efficiency of the scheme is observed through the optimization with the hybridization of global and local search schemes. Four different nonlinear variants of the singular Lane–Emden model based Neumann, Neumann-Robin and Dirichlet boundary conditions have been numerically presented to validate the efficiency and accuracy of the model. The comparison of the obtained and exact results is used to verify the validity of the designed procedure. Moreover, different statistical measures have been implemented to certify the reliability of the proposed technique.

Current study aims to implement a novel intelligent numerical computing framework by applying a computational artificial neural network designated with Bayesian regularization network (BRN) to underscore a comparative analysis for the impact of unsteady shear-thinning behavior of the flow of nanofluid through an exponentially stretching or shrinking cylinder. Transformed governing model of ordinary differential equations in cylindrical coordinates based on Buongiorno model is analyzed. The reference dataset for Buongiorno model is obtained by using Adam numerical solver against six scenarios with the variation of parameters namely, stretching/shrinking parameter, Weissenberg number, Reynold number, Brownian motion parameter, Prandtl number, and Lewis number. The acquired datasets are feed into a supervised computational framework utilizing BRN to approximate solutions for the unsteady shear-thinning behavior of flow system. The robustness of the stochastic process based on the BRN is validated through extensive simulation including convergence plots using the mean square errors, the performance of adaptive control parameters in the optimization algorithm, error distribution histograms and regression analysis. The optimal validation performance is observed in relation to epoch number index at epoch 621, 239, 548, 427, 580, 826 and 717 respective to all the scenarios. Further, observed mean squared errors (MSE) between target and output data of approximately 1.1383 x 10- 11, 4.4409 x 10- 11, 4.3824 x 10-12, 3.7145 x 10-12, 3.4385 x 10- 13, 1.0341 x 10-11and 3.1188 x 10- 11, recorded at times of 2 s, 1 s, 2 s, 2 s, 3 s, and 2 s respectively. These quantitative measures demonstrate minimal error margin which ensure the reliable alignment with numerical data.

Double-layer coated optical fibers provide vital protection against signal attenuation and mechanical damage, necessitating coatings that offer comprehensive surface coverage to meet stringent mechanical, chemical, and electrical standards. In the current study, a pressure-type die is utilized to coat double-layer optical fibers along with molten polymer, conforming to the Oldroyd 8-constant fluid model. The presented investigation analyzes the influence of magnetohydrodynamic effects during the coating process by leveraging a novel design of intelligent Bayesian regularization scheme (IBRS) to effectively investigate several important physical aspects. Adams numerical solver is employed to solve the associated differential systems, generating reference datasets for a double-layer optical fiber-coated model under various scenarios by variation of wall magnetic parameter, dilatant constant, pseudoplastic constant, and pressure gradient. These parameters play a vital role in enhancing the thickness of coated optical fibers, thereby implying their potential use as controlling parameters for thickness regulation. An intelligent solution strategy is implemented by using supervised artificial neural networks with IBRS. This approach enables immediate numerical approximation outcomes through simulations conducted on training, testing, and validation samples derived from reference datasets of complex geometry. The reliability of the IBRS networks is confirmed through convergence plots depicting mean squared errors (MSEs), effective outputs indicating adaptive control parameters of the optimization algorithm, and histograms based on errors and regression statistics derived from comprehensive simulation studies across several scenarios.

Current study presents a novel application of an intelligent network for a second-order nonlinear ordinary differential equation that portrays the electrohydrodynamic (EHD) fluidic flow model in a cylindrical conduit with an ion drag configuration. An intelligent network-based numerical solver is designed via a neural network optimized with Levenberg-Marquardt back propagation (NNLMBP). The NNLMBP network is applied to achieve a precise solution to the EHD fluid flow-based boundary value problem. A dataset of the EHD model is formulated by exploiting the strength of the Runge Kutta method for implementing NNLMBP with evaluation of different values for nonlinearity constant and electric Hartmann’s number to analyze the radial flow velocity numerically. The approximate solutions of the NNLMBP networks-based solver for various scenarios and cases of the EHD ion drag flow model are through training, testing, and validation procedures and compared with reference solutions for the validation and correctness of the NNLMBP approach. The worth and value of the designed NNLMBP are recognized by regression analysis with R 1, error-histogram plots with zero line error bin have central value around E-06 to E-07, and convergence curves having negligible mean square error in the range E-12 to E-10, for the exhaustive numerical experimentations.

The protective system is an essential part of all power network subsystems, including the protection systems of generation, transmission, and distribution networks, in order to ensure the integrity of the power system components, such as generators, bus bars, transformers, and feeder lines thus, a combination of different types of protection relays is utilized in the protection system, i.e., the prevention of the overcurrent, line to ground, line to line, double line to ground, faults in the associated system. In the current study, the performance of legacy power system protection is enhanced by means of reducing the total time of operation, including the directional over current relay (DOCR) operating time and coordination time among primary and backup DOCRs, while keeping the coordination time of interval (CTI), pickup tap setting (PTS), and time dial setting (TDS) within acceptable limits, during the protection of standard power system. In order to reduce the fitness evaluation function in IEEE 3-bus, 8-bus, and 15-bus systems, a new approach called fractional particle swarm optimization gravitational search algorithm entropy metric (FPSOGSA-EM) is designed for determining the optimal settings of the CTI, PTS, and TDS. The FPSOGSA-EM incorporates the underlying theories of fractional derivatives inside the mathematical framework of canonical particle swarm optimization aided with gravitational search algorithm along with entropy metric to improve its convergence rate and avoid sub optimality. The yielded results from FPSOGSAEM are compared to those from other cutting-edge counterpart algorithms such as modified particle swarm optimization, modified water cycle technique, modified electromagnetic field optimization, enhanced grey wolf optimization, seeker algorithm, teaching learning-based optimization, harmony search algorithm and FPSOGSA. By sharply reducing the period of operation of DOCRs in traditional IEEE 3-bus, 8-bus, and 15-bus test systems, the FPSOGSA-EM has outperformed these previously described methods. While the consistency, robustness, optimization brilliance, reliability and stability of the proposed scheme are ascertained by means of statistical interpretations such as minimum fitness evolution, cumulative distribution function (CDF), Boxplot representations, histograms plots and quantile-quantile plot demonstrations as a measure of center tendency and diversity.

Dual-layer optical fiber coating systems rely on magnetohydrodynamic (MHD) flow mechanisms to ensure uniform coating thickness and optimal mechanical performance. However, the coupled nonlinear interactions between electromagnetic fields and fluid dynamics pose significant modeling challenges, particularly for real-time industrial applications. Bayesian Distributed Backpropagation (BDBP), a probabilistic deep learning framework, has emerged as a powerful surrogate modeling approach for these complex Multiphysics systems. This systematic review and meta-analysis aim to consolidate current research on the application of BDBP for modeling MHD flow in optical fiber coating processes. The review evaluates BDBP’s predictive accuracy, computational efficiency, and uncertainty quantification capabilities, while identifying methodological gaps and outlining future research priorities. Following PRISMA 2020 guidelines, a structured search of Scopus, Web of Science, IEEE Xplore, and PubMed databases from 2018 to 2024 yielded 1243 unique records. After duplicate removal and two-stage screening, 58 peer-reviewed studies were included in the final synthesis, with 49 subjected to quantitative meta-analysis. Key variables extracted included neural architecture, prior distribution, RMSE, runtime, and credible interval calibration. Risk of bias was assessed using the ROBINS-I tool. Meta-analytical models were implemented using the DerSimonian–Laird estimator within a random-effects framework. BDBP significantly outperformed conventional CFD solvers in predictive accuracy, achieving a pooled RMSE of 0.12 (95

In this research work, the concept of fractional calculus is integrated inside the mathematical model of the canonical particle swarm optimization (i.e., FPSO) to enhance its optimization characteristics, namely its convergence rate, for solving the combined economic emission and load dispatch problems in the power systems. The proposed FPSO is exploited by tuning the output of the thermal and photovoltaic generation to reduce the overall operational cost, emissions, and line losses while meeting the consumer power demand in the standard Institute of Electrical and Electronic Engineering (IEEE) 30 bus network. The outcomes of the FPSO are compared with their recent state-of-the-art counterparts to endorse its efficacy for solving economic load dispatch problem, while the reliability and consistency of the FPSO are additionally confirmed through statistical illustrations that include the minimum fitness gauges in each independent execution, boxplot illustrations, histograms, plots for normal distribution, boxplots for time complexity, plots for Weibull distribution, plots for the cumulative distribution function, and quantile-quantile plots as a gauge of the diversity and central tendency.

In current study innovative approach is presented to improve the accuracy and efficiency of machine learning models on the dataset for each of the 31 US states, solely comprising a single power output column in Terra watt-hours (TWh) spanning from January 2013 to November 2020 by exploiting the knacks of Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), hybrid GRU-LSTM, Polynomial Feature Transform (PFT) and Polynomial Abet (PA) data augmentation with GRU for efficacious prediction. Achieving sufficient accuracy, a small univariate dataset of 95 rows was augmented through the PFT method, resulting in a significant reduction in prediction errors. Encouraged by this improvement, a novel algorithm PA data augmentation with GRU is introduced for further enhancing the accuracy, correlation, and computational efficiency of the prediction model. This research not only demonstrates the superior performance of the proposed PA data augmentation method but also highlights the benefit of using 31 individual univariate datasets for each state, allowing comprehensive testing and validation of the novel algorithm, providing compelling evidence of its efficacy in nuclear power prediction. The results from the proposed algorithms are evaluated using Root Mean Square Error (RMSE) and Relative Root Mean Square Error (RRMSE). A quantitative overview of PA and PFT data augmentation techniques’ comparison show the result in terms of accuracy (PA’s 0.464% RRMSE versus PFT’s 1.088 % RRMSE), correlation (PA’s −0.5877 versus PFT’s 0.4892), and computational efficiency (PA’s 14.02 % less computational time then PFT) for the nuclear power prediction model. The research framework introduced in this study, with its focus on utilizing state-specific data for nuclear energy prediction, holds significant implications for governmental decision-making policies. It provides a comprehensive overview of the trends in power generation and can be utilized for both renewable and thermal sources across different states. This information becomes instrumental in allocating funding and setting priorities for states to enhance their generation and transmission infrastructure. Moreover, the research effectively addresses the challenges posed by limited data, offering valuable insights in scenarios where only small datasets are available. The methodological approach and outcomes of this study contribute to the advancement of decision-making processes and policy formulation in the realm of energy governance.

This research implements an evolutionary optimized finite differences scheme (FDS) for nonlinear electrohydrodynamics ion drag flow dynamics in a cylindrical conduit (EHD-IDFCC). In the scheme, finite differences are exploited to discretize governing expressions of EHD-IDFCC, represented with a nonlinear singular seconder order differential equation, into a nonlinear equations-based system. The fitness function based on residual error is constructed for the FDS-based discretized EHD-IDFCC model. Its optimization is conducted with the global search capability of genetic algorithms (GAs) aided by the local search efficacy of the interior-point method (IPM), i.e., FDS-GA-IPM. The performance of the designed stochastic numerical solver FDS-GA-IPM is evaluated for a variant of the EHD-IDFCC model for different scenarios to measure the effect of axial flow velocity by varying the electric Hartmann numbers, as well as the nonlinearity factor. Statistical interpretations based on histogram illustrations, probability plots, and boxplots in terms of the cost function, mean absolute error (MAE), Thai inequality coefficients (TIC), and coefficient of determination metrics (R2) are used to endorse the accuracy, convergence, stability, and strength of the FDS-GA-IPM.

In this investigation, a comprehensive study has been made to reveal electro osmosis flow through a tapered ciliated symmetric porous channel. The flow is initiated due to metachronal dynamics of cilia. Axial electric field is deployed and thermal radiation phenomenon is scrutinised by applying convective conditions. The equations tackling the flow are non dimensionalized and simplified by capitalizing the low Reynolds number and long wave length approximations. Analytical solution is presented for well reputed Poissson equation and the axial velocity. Whereas, traverse velocity, temperature and nanofluids concentration profiles are examined numerically in MATHEMATICA. Variation of emerging crucial parameters on the velocity profile, temperature and concentration profiles, pressure gradient, pressure rise per wavelength, and on the velocity distribution inside the micro ciliated are exhibited with the aid of graphical deliberations. It worth to mention in this work that in case of tapered channel transverse velocity also has significant contribution in the flow, which is observed trivial in symmetric and non-symmetric channel flows. Temperature of the nanofluid in the ciliated tapered channel is raised with permeability and thermal radiations phenomena and can be controlled with Helmholtz Smoluchowski velocity, and electroosmotic parameter. Pumping phenomena is affected with increase in Helmholtz Smoluchowski velocity and permeability. Reported investigation cover a informative insight about biological fluid system, may be beneficial for the understanding the flow through ductus efferentes of human reproductive tract since it assumed that cilia are responsible for the transport of sperm from rete testis to the epididymis, also have worth in cilia designed bio-sensors and in certain drug delivery systems.

Heat transfer rate is numerically analyzed in convective flow of Al 2 O 3 ‐Ag/ H 2 O hybrid nanoliquid through a stretching sheet by incorporating induced magnetic field. Results of entropy generation in system are evaluated as well. Considered physical factors associated with heat transfer are heat generation parameter and viscous dissipation. The system of nonlinear partial differential equations is modeled and dimensionally simplified by implementing boundary layer approximation assumption and proper similarity transformations. Adam's Bashforth method is applied to get highly accurate and stable numerical solutions. Numerical results of flow variables, entropy generation number and physical quantities are interpreted by way of graphs and bar charts to perceive the extensive significance of the problem. It is visualized that rise in numeric values of mixed convection parameter λ 1 leads to enhance velocity; entropy generation number and Nusselt number while suppress temperature. High magnitude of heat generation parameter δ augments velocity and temperature but reverse behavior is observed for Nusselt number and entropy generation number. Moreover, the factor of viscous dissipation significantly modifies rate of flow and heat transfer under the effect of no‐slip condition on sheet. The present study is useful in different fields of industries, technological processes, mechanical processes, and electrical processes due to the applications of magnetic hybrid nanofluid with improved heat and mass transfer.

Current study aims to numerically investigate the bi-directional flow of nanofluids in the presence of Cattaneo-Christov double diffusion for two heat sources, namely, prescribed surface temperature (PST) along with prescribed heat flux (PHF). The conventional mathematical model in partial differential equations (PDEs) of the system have been reduced into an equivalent set of ordinary differential equations (ODEs). The system dynamics in the form of approximate solutions of the ODEs is presented by Adams and Explicit Runge Kutta numerical solvers. For better understanding the influence of physical parameter of interest including Brownian movement parameter, thermophoresis parameter, concentration relaxation parameter, Schmidt number, Prandtl number, thermal relaxation parameter, temperature ratio parameter, stretching ratio parameter and Deborah number on temperature, as well as concentration profiles are presented exhaustively. Appropriateness of the scheme is ascertained through close resemblance of results for different state of the art counterparts with negligible error around 10-05 to 10-09.

A novel mathematical investigation is carried out to reveal the significance of thermal radiation on the dissipative magneto hydrodynamic electroosmotic ciliary propulsion of a Newtonian nanofluid (DMHECP-NNF) in an symmetric micro-channel by implementing the impact of an axial electrical as well as transverse magnetic fields. The ciliary transport model is explored by using conservation of mass and momentum, heat, nanoparticle concentration, and electric potential expressions along with associated boundary conditions. The pertinent system for the proposed flow problem DMHECP-NNF consisting of partial differential equations are converted into ordinary differential equations system by incorporating the strengths dimensionless mechanism. Then analytical expressions are found for electrical potential, axial velocity, stream function, pressure gradient, temperature and concentration profiles. Whereas numerical computations are carried out to study transverse velocity and rise of pressure as per wavelength. The impacts of significant physical quantities of DMHECP-NNF are investigated with the help of graphical manipulations. It is observed in this novel study that axial velocity rises initially and then decline with increase in the magnitude of electro-osmotic parameter and Helmholtz-Smoluchowski velocity. Also, it is seen that with the rising value of electric-osmotic parameter the complexion of the trapped bolus is inflated and surrounded by few streamlines.

The research community has shown great interest for investigation in the nanofluids models involving Aluminum Alloys AA7072 and AA7072 +AA7075 due to their advantageous impact on heat transfer, physical and mechanical characteristic exploiting in broad engineering applications such as manufacturing of spacecraft, aircraft parts and building testing. The hybrid nanomaterial AA7072-AA7075 based fluidic system is investigated in this paper using an artificial neural network with Bayesian regularization scheme (ANNs-BRS). The derived partial differential equations (PDEs) are transformed into ordinary differential equations system ODEs and obtained the reference datasets for the estimated solution dynamics of hybrid nanofluidic system. For prominent parameters, the influence of flow on the temperature distribution and velocity plot are investigated. The performance on 80% training samples, 5% testing and 15% validation dataset for ANNs-BRS is well-established in terms of error histogram plots, regression analysis, and MSE based statistics. The results for entropy generation, Eckert number Ec, magnetic interaction parameter M, suction parameter S, and heat generation parameter Q are also discussed. The results show that the Eckert number Ec has the effect of slowing down the rate of heat transfer while increasing the temperature and increases in suction parameter causes decrease in temperature while increase in temperature profile due to enhancement of suction parameter.