Present research evaluates a wide range of methods to boost the performance of microchannel via ANN & lattice Boltzmann method (LBM). Hence Artificial Nueral Network method by Levenberg–Marquardt algorithm is applied to find all the data in the specific domain. LBM is developed to join with the artificial neural network (ANN) to study the effects of magneto hydro dynamic (MHD) on the slip velocity of FMWNT/water nanofluid flow inside a microchannel. Two methods are used to increase the efficiency of the cooling system. One is the effect of several fins (rectangular, triangular, and trapezoidal) and the second is the effect of magnetic field on thermo-hydraulic behavior. The magnetic field is caused to reduce the thermal boundary layer in the vicinity of the microchannels which means augmenting the performance by diminishing the vortexes. Finally, by rising the slip velocity coefficient from 0 to 0.1, the heat transfer saw a substantial enhancement of 6.1% and 5.4% in microchannel with rectangular at the lowest and highest amount of magnetic field, respectively. The original correlations regarding calculation of Nu_ave was obtained with R-square around 0.99.

目前的研究评估了多种通过 ANN 和格子玻尔兹曼方法 (LBM) 提高微通道性能的方法。因此，应用 Levenberg-Marquardt 算法的人工神经网络方法来查找特定域中的所有数据。LBM 被开发用于与人工神经网络 (ANN) 结合，以研究磁流体动力学 (MHD) 对 FMWNT/水纳米流体在微通道内的滑移速度的影响。有两种方法用于提高冷却系统的效率。一是几个翅片（矩形、三角形和梯形）的影响，二是磁场对热液性能的影响。导致磁场减少微通道附近的热边界层，这意味着通过减少涡流来提高性能。最后，通过将滑移速度系数从 0 提高到 0.1，在最低和最高磁场量的矩形微通道中，传热分别显着提高了 6.1% 和 5.4%。关于 Nu 计算的原始相关性_ave是用 0.99 左右的 R 方得到的。