Hybrid Polymer Composite Tensile Strength Estimation Using K-Nearest Neighboring Classification Algorithm

The aim of this research work is to characterize the tensile strength of ABS-Cu and ABS-Al composites of different proportions of percentage compositions, as well as the incorporation of surfactant material. For the analysis carried out in the present study, the k-Nearest Neighboring (kNN) classification algorithm is used in order to predict the tensile strength of the various compositions of the ABS-Al and ABS-Cu composites. Real data was not used to train the model due to the time-consuming process; instead, they resorted to synthetic data for the classification model, and for the tensile strength data, they were trained and predicted with better results. The kNN classification algorithm of the ABS-Cu predicted the k-value accuracy to be ۸۰% for k=۱ and k=۲, and ۸۵% for k=۳ and k=۵. Similarly, the prediction accuracy for the ABS-Al composition yielded the same results: As the value of k is increased, the required percentage of samples is ۸۰% for k=۱ and k=۲, ۸۵% for k=۳, and ۹۰% for k=۵, respectively. The kNN classification algorithm model was also successful in predicting tensile strength, with a recall of more than ۸۰% and an F۱ score of ۹۰-۹۵%. A higher quantity of copper and aluminium is said to have the ability to improve the tensile strength of the specimens.

کلیدواژه ها:

Acrylonitrile Butadiene Styrene ، Copper ، K-nearest neighbor ، surfactant