当前位置: X-MOL 学术Eng. Appl. Comput. Fluid Mech. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Energetic thermo-physical analysis of MLP-RBF feed-forward neural network compared with RLS Fuzzy to predict CuO/liquid paraffin mixture properties
Engineering Applications of Computational Fluid Mechanics ( IF 6.1 ) Pub Date : 2022-03-14 , DOI: 10.1080/19942060.2022.2046167
Xiaoluan Zhang, Xinni Liu, Xifeng Wang, Shahab S. Band, Seyed Amin Bagherzadeh, Somaye Taherifar, Ali Abdollahi, Mehrdad Bahrami, Arash Karimipour, Kwok-Wing Chau, Amir Mosavi

Dynamic viscosity of novel generated Copper Oxide (CuO)/Liquid Paraffin nanofluids is obtained experimentally for various temperatures and concentrations. To optimize the empirical process and for cost-efficiency, Feed-Forward Neural Networks (FFNNs) were modeled and compared with Recursive Least Squares (RLS) Fuzzy model. To prepare CuO/ liquid paraffin nanofluids, CuO nanoparticles are dispersed within paraffin. Then an input-target dataset containing 30 input-target pairs is available for T=25,35,40,50,55,70(C), and φ=0.1,0.5,1.0,3.0,5.0(%). Based on the empirical results, two types of FFNNs are examined and compared with RLSF model to predict CuO/liquid paraffin nanofluids. To evaluate the best optimization methods of nanofluid viscosity, Multi-Layer Feed forward (MLF), Radial Basis Function (RBF), and RLSF are compared and discussed. The MLF network provides a global approximation while the RBF acts more locally, further, RLSF provides a better fit. On the contrary, the RBF network has better properties from the generalization and noise rejection points of view. Also, RBF networks can be applied in an online manner. Further, three curves of RLS Fuzzy model by Parabola2D, ExtremeCum, and Poly2D models were fitted on the empirical data and compared. The ExtremeCum model showed the least margin of error and can be employed to predict the data.



中文翻译:

MLP-RBF前馈神经网络的高能热物理分析与RLS模糊比较预测CuO/液体石蜡混合物的性质

新生成的氧化铜 (CuO)/液体石蜡纳米流体的动态粘度是在各种温度和浓度下通过实验获得的。为了优化经验过程并提高成本效益,对前馈神经网络 (FFNN) 进行建模并与递归最小二乘法 (RLS) 模糊模型进行比较。为了制备 CuO/液体石蜡纳米流体,CuO 纳米颗粒分散在石蜡中。然后包含 30 个输入-目标对的输入-目标数据集可用于=25,35,40,50,55,70(C), 和φ=0.1,0.5,1.0,3.0,5.0(%). 基于经验结果,对两种类型的 FFNN 进行了检查,并与 RLSF 模型进行了比较,以预测 CuO/液体石蜡纳米流体。为了评估纳米流体粘度的最佳优化方法,对多层前馈 (MLF)、径向基函数 (RBF) 和 RLSF 进行了比较和讨论。MLF 网络提供全局近似,而 RBF 更局部地起作用,此外,RLSF 提供更好的拟合。相反,从泛化和噪声抑制的角度来看,RBF 网络具有更好的特性。此外,RBF 网络可以在线方式应用。此外,在经验数据上拟合并比较了 Parabola2D、ExtremeCum 和 Poly2D 模型的 RLS 模糊模型的三个曲线。ExtremeCum 模型显示出最小的误差范围,可用于预测数据。

更新日期:2022-03-14
down
wechat
bug