Artificial neural network aided SWCNT/Blood Casson fluid in biosensor-oriented stretching sheet with streamlines visualization and grid independent test

Purpose In this proposed study, SWCT/blood Casson fluid flow is considered to examine heat and mass transfer enhancement of biosensing stretching surface. Societal implications/Applications SWCNT's provide notable response in sensitive biomedical devices. Rural clinics will be benefitted by using miniaturized biosensors on Casson nanofluid models in getting laboratory-based blood analysis report by avoiding heavy laboratory equipment. Methodology Similarity transformation is considered to transform governing equations into the system of nonlinear coupled ordinary differential equations, which are solved with the finite difference collocation method built on the fourth-order Lobatto IIIa formula using MATLAB bvp4c solver. Novelty The most critical case of reaction rate <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mo stretchy="false">(</mml:mo> <mml:mrow> <mml:mi>γ</mml:mi> <mml:mo>=</mml:mo> <mml:mn>1</mml:mn> </mml:mrow> <mml:mo stretchy="false">)</mml:mo> </mml:math> is considered to make sure that mesh resolution precisely captures the steep gradients within the boundary layer through a grid-independent test, and the same grid settings were used for all variations in flow parameters. Streamline visualization is portrayed, which is exceptionally effective to examine the flow direction in complex geometries like a biosensor-oriented stretching sheet. An artificial neural network is incorporated to ensure real-time prediction and optimize flow parameters in biosensors. Findings Relative tolerance of 10 − 6 is obtained at 114 nodes by a grid-independent test for the most critical case <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mi>γ</mml:mi> <mml:mo>=</mml:mo> <mml:mn>1</mml:mn> </mml:math> . Mean squared error is utilized to perform model loss and is reported to be approximately <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mn>7</mml:mn> <mml:mo>×</mml:mo> <mml:msup> <mml:mn>10</mml:mn> <mml:mrow> <mml:mo>−</mml:mo> <mml:mn>5</mml:mn> </mml:mrow> </mml:msup> </mml:math> . Further, an artificial neural network has perfectly represented convective heat transfer characteristics, which can be confirmed by the convergence of data points for the Nusselt number.