The hardness test is considered one of the easiest mechanical tests in terms of preparing its specimens, as it does not need machining, unlike the tensile test that needs special machining and preparation. Six groups of Aluminium-Silicon alloys have been produced with different Si contents at different modifier and grains refiner. The correlations between the hardness with yield strength, ultimate tensile strength, and elongation for these groups were investigated by the regression analysis and an artificial neural network model.

The measured Brinell hardness, yield strength, ultimate tensile strength, and elongation for these groups ranged between 48 - 98 HB, 49 - 103 MPa, 90 - 202 MPa, and 3 - 10.4%, respectively. The best results were obtained for a mixture of modifier (Na₂SiF₆) and refiner (Al-3Ti-3B). The results indicated that the trainable cascade-forward back-propagation algorithm has the best forecast accuracy for determining the percentage of Si in the produced alloys based on material properties or predicting the properties of these alloys based on the Si percentage.

就硬度而言，硬度测试被认为是最简单的机械测试之一，因为它不需要机械加工，而拉伸试验则不需要特殊的机械加工和准备。在不同的改性剂和晶粒细化剂下，已生产出六组铝硅含量不同的铝硅合金。通过回归分析和人工神经网络模型研究了这些组的硬度与屈服强度，极限抗拉强度和伸长率之间的相关性。

这些组测得的布氏硬度，屈服强度，极限抗拉强度和伸长率分别在48-98 HB，49-103 MPa，90-202 MPa和3-10.4％之间。使用改性剂（Na ₂ SiF ₆）和精炼剂（Al-3Ti-3B）的混合物可获得最佳结果。结果表明，可训练的级联正向反向传播算法对于基于材料性能确定所生产合金中的Si百分比或基于Si百分比预测这些合金的性能具有最佳的预测精度。