To model complex relationships between input and output data, (ANN) algorithms are extensively used in engineering and fluid mechanics. They are able to predict outcomes, enhance quality control, optimize processes, predict material properties, and recognize images and patterns. ANNs are also utilized in control systems to govern the parameters of various engineering systems in an adaptive manner. ANNs are used for fluid flow prediction, turbulence modeling, heat transfer analysis, airfoil design, environmental modeling, pipeline monitoring, hydraulic systems simulation, and cavitation prediction in fluid dynamics. In order to account for the effects of Hall and ions on a (CC) double heat flow model, this investigation employs an artificial neural network (ANN) and (LMS) to find a solution for the HIE-PNF-NFDDT model. The focus of this paper is the investigation of the temperature, velocity, and concentration of (HIE-PNF-NFDDT) flow. Researchers use the bvp4c solver to get the initial dataset and then apply the Levenberg Marquardt Scheme of Neural Network Algorithm (LMS-NNA) to analyze the flow dynamics. They use the partial differential equations (PDEs) that reflect the flow of the HIE-PNF-NFDDT to construct a chain of ordinary differential equations (ODEs), which they then employ to evaluate the reference dataset for the evolutionary method, i.e. LMS-NNA. The velocities have a direct relation with non-dimensional parameters Prandtl fluid parameters and ratio parameters. Temperature enhances while it falls for ion slip and hall parameters. Similarly, the concentration increases with the increase Hartman parameter and has an inverse relation to concentration relaxation parameters.