CNT based nanofluids have great potential in the field of heat transfer due to their higher thermal conductivity compared to other categories of nanofluids. However, their applicability to different flow conditions is unknown. The flow behaviour of MWCNT/water nanofluids was investigated in this study under a variety of conditions, including concentration, temperature, and shear stress (0–35 Pa). Non-Newtonian flow properties of prepared samples have been found by experiments. MWCNT/Water nanofluids have shown that flow behaviour is strongly influenced by concentration. This contrasting rheological activity of MWCNT/water nanofluid at various concentrations was also attributed to SDS surfactant. The concept of molecular association of MWCNT and SDS molecules over the various structures formed by MWCNT at different concentrations and shear conditions is used to describe the insight flow characteristics of MWCNT. Power-law model-based curve fitting was used to study the variations in flow behaviour of MWCNT/water nanofluid. On the basis of qualitative results, this model was found to be the best-fitting model. Furthermore, an optimal Artificial Neural Network (ANN) was used to predict the complex viscosity of MWCNT/water nanofluid over flow behaviour variation, which is difficult to predict using traditional models. The influence of different parameters such as the weight percent concentration of nanofluid, temperature, shear time, and shear stress are all taken into account in this model. The model was trained on a dataset from current research and demonstrated outstanding accuracy in predicting viscosity (for the testing data, obtained R2 and RMSE are 0.9993 and 0.0035).

与其他类别的纳米流体相比，基于CNT的纳米流体的导热系数更高，因此在传热领域具有巨大的潜力。但是，它们在不同流动条件下的适用性未知。在这项研究中，研究了MWCNT /水纳米流体在各种条件下的流动行为，包括浓度，温度和剪切应力（0–35 Pa）。通过实验发现了所制备样品的非牛顿流动特性。MWCNT /水纳米流体已经表明，流动行为受到浓度的强烈影响。MWCNT /水纳米流体在各种浓度下的这种不同的流变活性也归因于SDS表面活性剂。MWCNT和SDS分子在不同浓度和剪切条件下由MWCNT形成的各种结构上的分子缔合概念被用来描述MWCNT的洞察流动特性。基于幂律模型的曲线拟合用于研究MWCNT /水纳米流体的流动行为变化。根据定性结果，该模型被认为是最合适的模型。此外，使用最佳人工神经网络（ANN）来预测MWCNT /水纳米流体在流动行为变化中的复数粘度，这是使用传统模型难以预测的。该模型考虑了不同参数的影响，例如纳米流体的重量百分比浓度，温度，剪切时间和剪切应力。