The effective electrical conductivity (EEC) of low density polyethylene (LDPE) and linear low density polyethylene (LLDPE) polymer composites filled with copper has been studied. The nonlinear behavior has been observed for effective electrical conductivity versus filler content. Several approaches have been described to predict the electrical conductivities of polymer composites. EEC is described by artificial neural network (ANN) and it demonstrates the accurate match of experimental data for EEC with different training functions (TRAINOSS, TRAINLM, TRAINBR, TRAINSCG, TRAINBFG, and TRAINRP). The ANN approach satisfied the experimental data for EEC of polymer composites reasonably well. The complex structure encountered in LDPE/Cu and LLDPE/Cu, along with the difference in the EEC of the components, make it difficult to estimate the EEC exactly. This is the reason for which artificial neural network has been employed here. By using ANN approach experimental results indicate that EEC of polymer composites increases with increasing filler content at the same concentration.

中文翻译：

---

铜粉填充LDPE / LLDPE复合材料有效电导率的计算研究

研究了填充铜的低密度聚乙烯（LDPE）和线性低密度聚乙烯（LLDPE）聚合物复合材料的有效电导率（EEC）。已经观察到有效导电率与填料含量的非线性关系。已经描述了几种方法来预测聚合物复合材料的电导率。EEC由人工神经网络（ANN）描述，并演示了具有不同训练功能（TRAINOSS，TRAINLM，TRAINBR，TRAINSCG，TRAINBFG和TRAINRP）的EEC实验数据的精确匹配。人工神经网络方法较好地满足了聚合物复合材料EEC的实验数据。LDPE / Cu和LLDPE / Cu中遇到的复杂结构，以及组件EEC的差异，使得难以准确估计EEC。这就是在这里采用人工神经网络的原因。通过使用人工神经网络方法，实验结果表明，在相同浓度下，聚合物复合材料的EEC随着填料含量的增加而增加。