Answers are grounded in this paper and cite their sources.
The considering article considers the study of viscous fluid flow consisting of solid CNT used as nanoparticles passing over the moving needle through the use of ANNs. The proposed model has been considered for performing the study for the phenomena of heat transfer and flow. In order to determine whether a solution to the problem exists, the time dependent stability analysis is also given. In order to regulate the convective energy transfer phenomenon, a heat source is incorporated into the flow system. Additionally, the fluid has a thermal radiation effect and is regarded as HNF. For HNFs, the well-known Hamilton-Crosser model is used to express the characteristics of the nanoparticles in the fluid. The HNF flow model of PDEs is transformed into ODEs using similarity conditions, and a matrix data set is produced when it is numerically solved in Mathematica. To discuss numerical results on and profile, different parameters such as , , , , and , are varied to obtain graphical results in MATLAB by applying LMBNNs. By using ANNs total 100 samples are attained from matrix data. These samples are further divides in such a manner: 80 for training data, 10 for testing and 10 for validation. The training subset was used to boost the network weights and biases, however the validation subset was engaged to monitor the training process and avoid over fitting by picking the best network. The outstanding testing subset was kept for the independent assessment of the network's predictive performance. The assumed 80-10-10 partition is a standard and widely accepted practice in ANN applications, providing suitable balance between model learning, validation, and generalization. For every scenario, the graphical results for TSD, EHA, RG-A, FFO, solution graph, MSE, solution graph, and AE are obtained. profile becomes smaller with the increase of and differences, but increases with the increase of difference. becomes smaller with the increase of , but increases with increase of and difference. The MSE penalties (testing, validation, training,) of SWCNTs and MWCNTs through a moving thin heated needle lies between The gradients values lie around for SWCNTs and MWCNTs through a moving thin heated needle. EHA of SWCNTs and MWCNTs through a moving thin heated needle is around . The AE of SWCNTs and MWCNTs through a moving thin heated needle by using LMBNNs is almost for all six scenarios.
No takes yet. Share an insight, caveat, or question.
Islam et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: