Wiciak-Pikuła Martyna, Twardowski Paweł, Bartkowska Aneta, Felusiak-Czyryca Agata
Faculty of Mechanical Engineering, Institute of Mechanical Technology Poznan, University of Technology, 3 Piotrowo St., 60-965 Poznan, Poland.
Faculty of Materials Engineering and Technical Physics, Institute of Materials Science and Engineering, University of Technology, 3 Piotrowo St., 60-965 Poznan, Poland.
Materials (Basel). 2021 Oct 12;14(20):6010. doi: 10.3390/ma14206010.
In today's developing aircraft and automotive industry, extremely durable and wear-resistant materials, especially in high temperatures, are applied. Due to this practical approach, conventional materials have been superseded by composite materials. In recent years, the application of metal matrix composites has become evident in industry 4.0. A study has been performed to analyze the surface roughness of aluminum matrix composites named Duralcan during end milling. Two roughness surface parameters have been selected: arithmetical mean roughness value and mean roughness depth regarding the variable cutting speed. Due to the classification of aluminum matrix composites as hard-to-cut materials concerning excessive tool wear, this paper describes the possibility of surface roughness prediction using machine learning algorithms. In order to find the best algorithm, Classification and Regression Tree (CART) and pattern recognition models based on artificial neural networks (ANN) have been compared. By following the obtained models, the experiment shows the effectiveness of roughness prediction based on verification models. Based on experimental research, the authors obtained the coefficient R for the CART model 0.91 and the mean square error for the model ANN 0.11.
在当今不断发展的航空航天和汽车工业中，人们应用了极其耐用且耐磨的材料，尤其是在高温环境下。由于这种实用的方法，传统材料已被复合材料所取代。近年来，金属基复合材料在工业4.0中的应用已变得十分明显。一项研究对名为Duralcan的铝基复合材料在端铣削过程中的表面粗糙度进行了分析。针对可变切削速度，选择了两个粗糙度表面参数：算术平均粗糙度值和平均粗糙度深度。由于铝基复合材料被归类为难加工材料，存在刀具过度磨损的问题，本文描述了使用机器学习算法预测表面粗糙度的可能性。为了找到最佳算法，对分类与回归树（CART）和基于人工神经网络（ANN）的模式识别模型进行了比较。通过遵循所获得的模型，实验表明了基于验证模型的粗糙度预测的有效性。基于实验研究，作者得出CART模型的系数R为0.91，ANN模型的均方误差为0.11。
