Molero Esther, Fernández Juan Jesús, Rodríguez-Alabanda Oscar, Guerrero-Vaca Guillermo, Romero Pablo E
Department of Mechanical Engineering, University of Cordoba, Medina Azahara Avenue, 14071 Cordoba, Spain.
Polymers (Basel). 2020 Apr 6;12(4):840. doi: 10.3390/polym12040840.
In the present work, ten data mining algorithms have been used to generate models capable of predicting the surface roughness of parts printed on polylactic acid (PLA) by using fused deposition modeling (FDM). The models have been trained using experimental data measured on 27 horizontal (XY) and 27 vertical (XZ) specimens, printed using different values for the parameters studied (layer height, extrusion temperature, print speed, print acceleration and flow). The models generated by multilayer perceptron (MLP) and logistic model trees (LMT) have obtained the best results in a cross-validation. Although it does not obtain such optimal results, the J48 algorithm (C4.5) allows the generation of models in the form of a decision tree. These trees permit to determine which print parameters have an influence on the surface roughness. For XY specimens, the surface roughness measured in the direction parallel to the extrusion path (R ) depends on the flow, the print temperature and the layer height; in the direction perpendicular to the extrusion path, the surface roughness (R) depends only on the flow. For XZ specimens, the surface roughness measured in the direction parallel to the extrusion path (R) depends only on the print speed; in the direction perpendicular to the extrusion path (R), it depends on the layer height and the extrusion temperature. According to the study carried out, the most suitable set up provides values of R, R, R and R equal to 0.46, 1.18, 0.45 and 11.54, respectively. A practical application of this work is the manufacture of PLA frame glasses using FDM.
在本研究中，使用了十种数据挖掘算法来生成能够预测通过熔融沉积建模（FDM）在聚乳酸（PLA）上打印的零件表面粗糙度的模型。这些模型是使用在27个水平（XY）和27个垂直（XZ）试样上测量的实验数据进行训练的，这些试样使用所研究参数（层高、挤出温度、打印速度、打印加速度和流量）的不同值进行打印。多层感知器（MLP）和逻辑模型树（LMT）生成的模型在交叉验证中取得了最佳结果。尽管J48算法（C4.5）没有获得如此最佳的结果，但它允许生成决策树形式的模型。这些树能够确定哪些打印参数对表面粗糙度有影响。对于XY试样，在平行于挤出路径的方向上测量的表面粗糙度（R ）取决于流量、打印温度和层高；在垂直于挤出路径的方向上，表面粗糙度（R）仅取决于流量。对于XZ试样，在平行于挤出路径的方向上测量的表面粗糙度（R）仅取决于打印速度；在垂直于挤出路径的方向上（R），它取决于层高和挤出温度。根据所进行的研究，最合适的设置提供的R、R、R和R值分别等于0.46、1.18、0.45和11.54。这项工作的一个实际应用是使用FDM制造PLA框架眼镜。
