Fluidic System Research Articles

Integrated intelligence of inverse multiquadric radial base neuro‐evolution for radiative MHD Prandtl–Eyring fluid flow model with convective heating

AbstractIn this communication, a new stochastic numerical paradigm is introduced for thorough scrutinization of the magnetohydrodynamic (MHD) boundary layer flow of Prandtl–Eyring fluidic model along a stretched sheet impact on thermal radiation as well as convective heating scenarios by exploiting the accurate approximation knacks of ANNs (artificial‐neural‐networks) modeling by using the inverse multiquadric (IMQ) function optimized/trained with well‐reputed global search with genetic algorithms (GAs) and local search efficacy of sequential quadratic programming (SQP), that is, ANNs‐IMQ‐GA‐SQP. The mathematical model of the Prandtl–Eyring fluid flow is portrayed in the form of PDEs and then converted in the form of a nonlinear system of ODEs by utilizing suitable similarity transformation to calculate/analyze the solution dynamics. The kinematic and thermodynamic properties of MHD Prandtl–Eyring fluid flow are examined/observed by varying the sundry physical parameters. The obtained intelligent computing designed solver‐based numerical results are consistently found in good agreement with reference results obtained through the Adams numerical technique. First and second‐order cumulant‐based statistical assessments are extensively exploited to endorse trustily the efficacy of ANNs‐IMQ‐GA‐SQP solver based on exhaustive simulations for the Prandtl–Eyring fluidic system.

Machine Learning based Sorting of Somatic Embryos for In-Line processing in Automated SE Fluidics System

Somatic embryogenesis (SE) can be a viable method for the clonal propagation of many economically significant forest trees, particularly coniferous trees like pines and spruces. However, large-scale production of SE plants requires automation to reduce manual labor and attain cost-efficiency. The most labor-intensive step of the SE process for SE plant production is selecting and harvesting mature embryos. Embryo maturation is not a synchronized process; selecting the most developed embryos capable of continuous development is necessary. However, there needs to be more research conducted on mapping morphological features to germination-competent mature somatic embryos. This paper lays down the preliminary work of employing machine learning techniques for classifying large volumes of images of mature somatic embryos processed using an automated SE processing system based on fluidics processing referred to as SE Fluidics system. The results show that machine learning could be an alternative classification methodology instead of the traditional manual morphology-based classification process based on image analysis. The paper discusses two popular image classification techniques, namely Convolution Neural Network (CNN) and Support Vector Machine (SVM), applying them to both binary (black and white) and grayscale images. It is observed that grayscale images provide better accuracy with the SVM technique and outperform morphology-based classification in terms of processing speed (17.6% faster) across the test envelope. On the other hand, CNN-based classification shows better processing speeds only at a lower number of convolution layers. Hence, the data scientist can optimally select the number of convolution layers to get the desired accuracy-processing speed combination.

Convergence of machine learning with microfluidics and metamaterials to build smart materials

AbstractRecent advances in machine learning have revolutionized numerous research domains by extracting the hidden features and properties of complex systems, which are not otherwise possible using conventional ways. One such development can be seen in designing smart materials, which intersects the ability of microfluidics and metamaterials with machine learning to achieve unprecedented abilities. Microfluidics involves generating and manipulating fluids in the form of liquid streams or droplets from microliter to femtoliter regimes. However, analysis of such fluid flows is always tiresome and challenging due to the complexity involved in the integration and detection of various chemical or biological processes. On the other hand, acoustic metamaterials manipulate acoustic waves to achieve unparalleled properties, which is not possible using natural materials. Nonetheless, the design of such metamaterials relies on the expertise of specialists or on analytical models that require an enormous number of expensive function evaluations, making this method extremely complex and time-consuming. These complexities and exorbitant function evaluations of both fluidic and metamaterial systems embark on the need for the support of computational tools that can identify, process, and quantify the large amounts of intricacy, thus machine learning techniques. This review discusses the shortcomings of microfluidics and acoustic metamaterials, which are overcome by neoteric machine learning approaches for building smart materials. The following review ends by providing the importance and future perspective of integrating machine learning and optimization approaches with microfluidic-based acoustic metamaterials to build smart and efficient intelligent next-generation materials.

A study on the flow behavior inside fluidic oscillation tools for friction-reduction in extended reach well

The drilling distance of extended-reach wells is limited by mechanical friction between the drill string and the borehole wall. The fluidic oscillator axial vibratory tools (AVTs) can effectively reduce friction and increase the weight on bit, thereby extending the reach of horizontal wells. However, few studies have delved into the evolutionary mechanism of the internal flow field of fluidic oscillator AVTs. In this paper, two types of fluidic oscillators with different flow path are presented. One is the reverse-feedback oscillator, and the other is sweeping-chamber oscillator. Through computational fluid dynamics method, the internal flow field of these two fluidic oscillator AVTs were analyzed, and the frequency and pressure drop were verified by experiments. The results show that the LES turbulence model provides more accurate simulations, showing an error range of less than 9%. The pressure drop and vibration frequency of the two tools are linearly related to the flow rate. The pressure drop of the reverse feedback oscillation tool is in the range of 0.1–1 MPa, and the vibration frequency is between 13 and 50 Hz. The sweeping-chamber oscillator can reduce vibration frequency to below 15 Hz. The results also show that it is crucial to consider the lag in pressure signals when designing and analyzing fluid oscillator systems, as it can affect the timing and behavior of the system. This research provides profound insights for understanding and optimizing fluidic oscillator systems.

Sustainable water decontamination in a fluidic sequential electrochemical reactor

Here, we demonstrate an integrated fluidic sequential electrochemical system for effective water decontamination. The system consists of a Ti mesh anode deposited with nanoscale IrO2 and a CNT filter functionalized with nanoconfined Fe2O3. By conducting anodic oxygen evolution reaction (OER) and 2e– oxygen reduction reaction (ORR) sequential electrolysis, our system enables sustainable O2 generation at the anode, followed by transformation of O2 into H2O2 at the cathode, which then led to the production of 1O2 in the presence of nanoconfined Fe2O3. No chemical inputs were needed nor side products occurred during the whole sequential electrochemical processes. The effectiveness of the system was evaluated using tetracycline as a model emerging contaminant. Recirculating at 3 mL min–1, the system exhibited negligible iron and iridium leaching (≤0.01 mg L–1) and high tetracycline degradation efficiency (≥95%). Such excellent efficacy can be maintained across a wide pH range and in complicated water matrices.

Importance of Activation Energy on Magnetized Dissipative Casson-Maxwell Fluid through Porous Medium Incorporating Chemical Reaction, Joule Heating, and Soret Effects: Numerical Study

In recent decades, the study of non-Newtonian fluids has attracted the interest of numerous researchers. Their study is encouraged by the significance of these fluids in fields including industrial implementations. Furthermore, the importance of heat and mass transfer is greatly increased by a variety of scientific and engineering processes, including air conditioning, crop damage, refrigeration, equipment power collectors, and heat exchangers. The key objective of this work is to use the mathematical representation of a chemically reactive Casson-Maxwell fluid over a stretched sheet circumstance. Arrhenius activation energy and aspects of the magnetic field also have a role. In addition, the consequences of both viscous dissipation, Joule heating, and nonlinear thermal radiation are considered. The method transforms partial differential equations originating in fluidic systems into nonlinear differential equation systems with the proper degree of similarity which is subsequently resolved utilizing the Lobatto IIIA technique’s powerful computing capabilities. It is important to recall that the velocity profile drops as the Maxwell fluid parameter increases. Additionally, the increase in the temperature ratio parameter raises both the fluid’s temperature and the corresponding thickness of the boundary layer.

Fluoride-triggered phase transition of metallogels for on-demand in situ containment of fluids.

Sol-gel transition regulates mass transport in fluidic systems. We designed pre-gelators that react with fluoride anions to form a metallogel barrier. A combination of spectroscopic, rheological, and X-ray spectroscopic studies elucidated the mechanism of gelation involving desilylation followed by metal coordination-driven self-assembly, the kinetics of which can be finely controlled by the chemical structure of the silyl substituents. Protonation-induced degelation restores flow, allowing the metallogel to function as a reversible chemical valve.

Programmable Droplet Manipulation on Superhydrophobic Surfaces with Charge Gradient

The controllable manipulation of droplets is pivotal for diverse applications spanning from microfluidics to biotechnology. In this paper, we present a novel droplet manipulation method leveraging a charge gradient on superhydrophobic surfaces. By shielding the charges on a superhydrophobic surface with uniform charges, a charge gradient is generated, which can drive a neutral droplet to move along the charge gradient. By controlling the motion trajectory of the metallic shield, a programmable droplet motion in a desired manner is achieved. This programmable droplet manipulation accompanied by non-contact, fast-responsive, ultrafast, and convenient performances is promising in many fluidic systems.

The variable viscosity and variable gravity field on the onset of convective motion in a porous layer with throughflow

In the present article, the combined influence of the changeable gravity field and temperature-reliant viscosity on the porous bed is considered for investigation numerically by the Galerkin technique in the presence of upward vertical throughflow. The temperature-reliant viscosity is known to be exponential. The porous matrix is subjected to continuous downward gravity fluctuations varying with distance across the medium and vertical upward throughflow. Four different cases of gravity variance were discussed. A parametric analysis is conducted by adjusting the following parameters: throughflow parameter, viscosity parameter, and gravity parameter. Results show that the beginning of the convective moment would be delayed by all three parameters throughflow, temperature-reliant viscosity, and gravity variance. It has been shown that the fluidic system is more inconsistent in case (iii) and more consistent in case (iv).

Design and Characterisation of Multi-cavity, Fluidic Haptic Feedback System for Mechano-tactile Feedback.

Numerous studies have indicated that the use of a closed-loop haptic feedback system, which offers various mechano-tactile stimuli patterns with different actuation methods, can improve the performance and grasp control of prosthetic hands. Purely mechanical-driven feedback approaches for various mechano-tactile stimuli patterns, however, have not been explored. In this paper, a multi-cavity fluidic haptic feedback system is introduced with details of design, fabrication, and validation. The multi-cavity haptic feedback system can detect the physical touch with direction at the fingertip sensor. The direction of the force is reflected in the form of pressure deviation in the multi-cavity fingertip sensor. The feedback actuator generates various mechano-tactile stimuli patterns according to the pressure deviation from the fingertip sensor. Hence, users can identify the force with direction according to the stimuli patterns. The haptic feedback system is validated through two experiments. The initial experiment characterises the system and establishes the relationship between the fingertip sensor and feedback actuator. The subsequent experiment, a human interaction test, confirms the system's capability to detect force with directions and generate corresponding tactile stimuli in the feedback actuator. The outcomes corroborate the idea that participants are generally capable of discerning changes in angle.

Development of a flow system for decentralized electrochemical analysis of heavy metals using screen-printed electrodes: the importance of sensor stability.

Year after year, the need for decentralized tools to tackle the monitoring of heavy metal levels in the environment gradually increases. In this context, suitable electrochemical methodologies are widely established and particularly attractive for the production of low-cost miniaturized field-deployable analytical platforms. This work focused on the development of an automatable portable system based on square-wave anodic stripping voltammetry (SWASV) for the on-line detection of heavy metals. The surface of the sensors is appropriately modified and coupled with a fluidic system equipped with an ad-hoc designed flow cell. A custom software tool was introduced to handle the remote-controlled potentiostat and automate the various steps of the procedure, including stirring operations, cleaning phases, SWASV measurements, and data collection. After studying technical and analytical challenges, the final system developed was applied to the simultaneous detection of Cd(II), Pb(II), and Cu(II) in solution, achieving sub-ppb detection limits. Additionally, the practical applicability of the method was successfully applied to river water samples collected from the Loire basin in France.

Engineering advancements in microfluidic systems for enhanced mixing at low Reynolds numbers.

Mixing within micro- and millichannels is a pivotal element across various applications, ranging from chemical synthesis to biomedical diagnostics and environmental monitoring. The inherent low Reynolds number flow in these channels often results in a parabolic velocity profile, leading to a broad residence time distribution. Achieving efficient mixing at such small scales presents unique challenges and opportunities. This review encompasses various techniques and strategies to evaluate and enhance mixing efficiency in these confined environments. It explores the significance of mixing in micro- and millichannels, highlighting its relevance for enhanced reaction kinetics, homogeneity in mixed fluids, and analytical accuracy. We discuss various mixing methodologies that have been employed to get a narrower residence time distribution. The role of channel geometry, flow conditions, and mixing mechanisms in influencing the mixing performance are also discussed. Various emerging technologies and advancements in microfluidic devices and tools specifically designed to enhance mixing efficiency are highlighted. We emphasize the potential applications of micro- and millichannels in fields of nanoparticle synthesis, which can be utilized for biological applications. Additionally, the prospects of machine learning and artificial intelligence are offered toward incorporating better mixing to achieve precise control over nanoparticle synthesis, ultimately enhancing the potential for applications in these miniature fluidic systems.

Reprogrammable Metamaterial Processors for Soft Machines.

Soft metamaterials have attracted extensive attention due to their remarkable properties. These materials hold the potential to program and control the morphing behavior of soft machines, however, their combination is limited by the poor reprogrammability of metamaterials and incompatible communication between them. Here, printable and recyclable soft metamaterials possessing reprogrammable embedded intelligence to regulate the morphing of soft machines are introduced. These metamaterials are constructed from interconnected and periodically arranged logic unit cells that are able to perform compound logic operations coupling multiplication and negation. The scalable computation capacity of the unit cell empowers it to simultaneously process multiple fluidic signals with different types and magnitudes, thereby allowing the execution of sophisticated and high-level control operations. By establishing the laws of physical Boolean algebra and formulating a universal design route, soft metamaterials capable of diverse logic operations can be readily created and reprogrammed. Besides, the metamaterials' potential of directly serving as fluidic processors for soft machines is validated by constructing a soft latched demultiplexer, soft controllers capable of universal and customizable morphing programming, and a reprogrammable processor without reconnection. This work provides a facile way to create reprogrammable soft fluidic control systems to meet on-demand requirements in dynamic situations.

An advanced miniature fluidic system in multilayer ceramic technology with precise temperature and flow control for in situ pollution monitoring

Rapid, on-site, water-quality monitoring is necessary to prevent and remediate environmental pollution. This study aims to develop a miniature, portable, fluidic system (MFS) designed for the easy insertion of disposable, screen-printed electrodes (SPEs) and the measurement of an electrochemical response (EC) under controlled temperature and flow conditions. The three-dimensional MFS, realised in low-temperature, cofired ceramic and multilayer ceramic technology, consist of three distinct cavities, each with separate inlet and outlet channels. These channels are designed to maintain an equivalent flow rate across all three cavities. The MFS allows simultaneous measurements at three measuring sites, temperature control of the fluid from room temperature to 125 °C via integrated heaters and temperature sensors, and flow regulation up to 20 mL/min via an external fluid pump. The EC values obtained from the SPEs in a standard solution of potassium ferrocyanide/potassium ferricyanide at room temperature and under stagnant conditions were consistent with measurements conducted in the MFS, droplet and conventional electrochemical cells, confirming the accuracy and reliability of the MFS. The EC response was confirmed in the MFS under flow conditions of 4 mL/min and temperatures of 25 °C, 35 °C, and 45 °C. This shows that multilayer ceramic technology enables the fabrication of a miniature, three-dimensional MFS with integrated fluidic and electronic components that provide reliable and accurate electrochemical measurements using a commercial SPE under controlled flow and temperature conditions.

Homogeneous-heterogeneous reactions on Darcy-Forchheimer nanofluid flow system

The use of artificial neural networks (ANNs) to solve complex fluid dynamics problems has revolutionized computational approaches. This article explores novel ANN solutions for fluid problems. ANNs have demonstrated unmatched effectiveness in comprehending and forecasting fluidic behaviors, from mimicking complex fluid flow trends to optimizing structures for dynamics. This study emphasizes the significance of neural networks in revolutionizing our understanding and control of fluidic systems by using ANNs and Bayesian Regularization. This study examined the 3D Darcy-Forchheimer stretching flow (TDDFSF) of nanofluid under convective conditions along with homogeneous and heterogeneous reactions by employing the scheme of Bayesian Regularization with the procedure of backpropagation in neural networks (SBR-BNNs). The flow is influenced by Brownian diffusion, thermophoresis and zero nanoparticles mass flux condition. The PDEs given in this model are converted into nonlinear ODEs. Results from MSE, regression analysis, and error histogram are used to verify the performance of SBR-BNNs. The absolute errors lie in the ranges up to 10−9, which depict the worth of the solver SBR-BNNs. The absolute error measures the discrepancy between the values actually observed and those predicted by the SBR-BNNs model. SBR-BNNs' high precision in TDDFSF models can lead to more effective and reliable solutions.

A novel on-a-chip system with a 3D-bioinspired gut mucus suitable to investigate bacterial endotoxins dynamics

The possible pathogenic impact of pro-inflammatory molecules produced by the gut microbiota is one of the hypotheses considered at the basis of the biomolecular dialogue governing the microbiota-gut-brain axis. Among these molecules, lipopolysaccharides (LPS) produced by Gram-negative gut microbiota strains may have a potential key role due to their toxic effects in both the gut and the brain.In this work, we engineered a new dynamic fluidic system, the MINERVA device (MI-device), with the potential to advance the current knowledge of the biological mechanisms regulating the microbiota-gut molecular crosstalk. The MI-device supported the growth of bacteria that are part of the intestinal microbiota under dynamic conditions within a 3D moving mucus model, with features comparable to the physiological conditions (storage modulus of 80 ± 19 Pa, network mesh size of 41 ± 3 nm), without affecting their viability (∼ 109 bacteria/mL). The integration of a fluidically optimized and user-friendly design with a bioinspired microenvironment enabled the sterile extraction and quantification of the LPS produced within the mucus by bacteria (from 423 ± 34 ng/mL to 1785 ± 91 ng/mL). Compatibility with commercially available Transwell-like inserts allows the user to precisely control the transport phenomena that occur between the two chambers by selecting the pore density of the insert membrane without changing the design of the system. The MI-device is able to provide the flow of sterile medium enriched with LPS directly produced by bacteria, opening up the possibility of studying the effects of bacteria-derived molecules on cells in depth, as well as the assessment and characterization of their effects in a physiological or pathological scenario.

Novel quartic spline method for boundary layer fluid flow problem of Falkner-Skan model with wall stretching and transfer of mass effects

The non-linear ordinary differential equations (NODEs) in this article are estimated and analyzed numerically using the capability of the Quartic Splines Method (QSM) for mathematical modeling of the Falkner-Skan fluidic system and its optimization through global search Genetic Algorithms (GAs) and local search Active-Set (AS) techniques. The concept of hybridization is used to optimize the obtained results and provide a boost to the suggested method, QSM, which allows for rapid iteration. Falkner-Skan fluid model (FSFM) is solved by the proposed technique QSM-GAs-AS. The FSFM is solved for three, seven, and twelve splines successfully. The problem is analyzed for three scenarios, in which each scenario is based on the variation of a parameter out of the three involved parameters, namely the wall mass transfer parameter (γ), the wall movement parameter (λ), and the stream-wise pressure gradient parameter (β), appearing in FSFM. The QSM-GAs-AS produces an interpolated function that is continuous up to its fourth derivative. The solution outcomes of FSFM, treated by the designed scheme QSM-GAs-AS, are presented graphically. The evaluation of the planned solution is done with a deterministic numerical solver, the Homotopy Analysis Method (HAM). Statistical analysis for multiple runs is used to examine the proposed scheme's convergence, exactness, and accuracy.

High-Voltage Electrodes in Moist Air Accumulate Charge That is Retained after Removing the Electric Field.

Applying a high voltage to a metal electrode that is disconnected from a circuit rapidly induces a capacitive charge, which quickly relaxes after removal of the applied voltage. Here, we report that if the electrode is placed in air at a sufficiently high relative humidity and provided the connection between the high-voltage supply and the electrode is composed of two different metals, the expected capacitive charge is followed by a gradual increase in charge. Surprisingly, this extra charge persists after the removal of the applied voltage and even after physically removing the electrode from the Faraday cup used to measure the charge. We report the median charge, average charge rate, and residual charge for different applied voltages, different metal-metal connections, and varied humidity. We interpret the results in terms of a proposed water ionization mechanism and discuss the implications of the findings for high-voltage fluidic systems.

Advancing CAR-T Therapy in Acute Lymphoblastic Leukemia: Multi-Omic Analyses of CD19-Directed CAR-T Cells Enabled By an Ex Vivo Co-Culture Platform

Background: Acute Lymphoblastic Leukemia (ALL) has witnessed remarkable progress in the treatment of patients with Chimeric Antigen Receptor T-cell (CAR-T) therapies, leading to high response rates and durable remissions. However, challenges persist for patients who do not respond to CAR-T treatment, experience relapse, or encounter adverse events such as cytokine release syndrome. Overcoming these challenges necessitates a deeper understanding of mechanisms and the development of advanced technologies and assays. This study focuses on harnessing the potential of an innovative microfluidic platform for high-throughput cell-based assays, enabling multi-omics and functional analysis using a minimal amount of primary patient cells. By utilizing this platform, we aim to gain insight into the dynamics of primary patient material by evaluating responses to aid in selection of promising CAR-T enhancements or combination therapies designed to overcome mechanisms of CAR-T failure or relapse to improve clinical outcomes. Methods: For the cytotoxicity assay, we utilized autologous or allogeneic pairs of CD19-directed CAR-T cells and T-cell negative fractions from ALL patients' blood apheresis samples, containing CD19-expressing cancer cells. A negative control was established using untransduced T-cells. To ensure high cell viability and purity, the cells underwent careful processing and were labeled with long-lived dyes for tracking. Multiple cell suspensions with precise Effector to Target to Negative Fraction ratios were prepared. Only a few thousand cells from each coculture suspension were seeded in microfluidic culture chambers, which required no fluidic control system. Experiments were conducted for up to 96 hours with media replacement every 24 hours. At each endpoint, media was collected for cytokine quantification, and cells were stained for live/dead counting as well as quantification of intracellular or surface marker expression by imaging. After image acquisition, cells were collected for RNA extraction and gene expression analysis. Results: Results demonstrated that the developed co-culture platform allows precise control over culture conditions, ensuring culture of accurate ratios of highly complex cell populations. The viability of primary cells in the device guaranteed functional relevance of the cytotoxicity assays for up to a 96-hour timepoint. Strong CAR-T-mediated cell killing was observed, with a dose-dependent effect depending on the co-culture's relative CAR-T content. Less than 50% cell survival was observed in cocultures with Effector to Target ratio 1:1, as compared to the untransduced T-cell control. Furthermore, strong CAR-T activation was observed with over 60% of CART expressing CD25 and CD69 surface markers, as measured by imaging. A multi-color staining panel allowed for precise monitoring of changes over time within the assay of immune cell populations, including cancer cells, monocytes/macrophages, and NK cells, among others. Cytokine analysis revealed an increased secretion of IL-2, TNFa, IFNg, and Granzyme B in coculture with CAR-T cells compared to untransduced T-cells, with a dose-dependent effect based on the CAR-T cell ratio. Finally, RNA isolated from remaining cells at the end of the assay was of high quality with yields sufficient to enable transcriptome analysis for each treatment condition. Discussion: This study contributes to the development of innovative multiplexed high throughput strategies for in vitro functionality assessments in cell therapy, including combination studies and deeper mechanistic understandings. The platform's ability to generate fully integrated, multi-omics readings from complex allogeneic and autologous cocultures of CAR-T and patient cells offers a new frontier in early discovery and translational cancer research. This opens new possibilities for drug discovery, drug screening, and disease modeling, ultimately advancing our understanding of complex biological processes and accelerating therapeutic development. Future directions include exploring mechanisms of resistance and sensitivity, including donor-specific effector cell functionality, combination studies, impacts of immunosuppressive cell types, patient heterogeneity of target antigen expression or other co-stimulatory molecules, and evaluation of product potency or fitness of incoming apheresis material.

Cattaneo-Christov heat flow model at mixed impulse stagnation point past a Riga plate: Levenberg-Marquardt backpropagation method

Applications of artificial intelligence (AI) via soft computing procedures have attracted the attention of researchers due to their effective modeling, simulation procedures, and detailed analysis. In this article, the designing of intelligence computing through a neural network that is backpropagated with the Levenberg-Marquardt method (NN-BLMM) to study the Cattaneo-Christov heat flow model at the mixed impulse stagnation point (CCHFM-MISP) past a Riga plate is investigated. The original model CCHFM-MISP in terms of PDEs is converted into non-linear ODEs through suitable similarity variables. A data set is generated for all scenarios of CCHFM-MISP through Lobatto IIIA numerical solver by varying Hartman number, velocity ratio parameter, inverse Darcy number, mixed impulse variable, non-dimensional constraint, Eckert number, heat generation variable, Prandtl number, thermal relaxation variable. To find the physical impacts of parameters of interest associated with the presented fluidic system CCHFM-MISP, the approximate solution of NN-BLMM is carried out by performing training (80 %), testing (10 %), and validation (10 %), and then the results are equated with the reference data to ensure the perfection of the proposed model. Through MSE, state transition, error histogram, and regression analysis, the outcomes of NN-BLMM are presented and analyzed. The graphical illustration and numerical outcomes confirm the authentication and effectiveness of the solver. Moreover, mean square errors for validation, training and testing data points along with performance measures lie around 10−10 and the solution plots generated through deterministic (Lobatto IIIA) approach and stochastic numerical solver are matching up to 10−6, which surely validate the solver NN-BLMM. The outcomes of M and B on velocity present the similar impacts. The velocity of material particles decreases under Da while, it increases through velocity ratio and magnetic parameters.