A PRISMA-driven systematic review of data mining methods used for defects detection and classification in the manufacturing industry

Paper aims This research to analyze the primary studies published in recent years focusing on defect detection or classification manufacturing and extract information about frequently used data mining (DM) methods, their accuracy, strengths, limitations. Originality Industrial production is now undergoing a dynamic transformation context of Industry 4.0, where implementation discussed topic, such an overall summary missing. Research method In this study, PRISMA-driven systematic literature review combined with approach defined by Kitchenham (2004). Main findings The most methods for are Bayesian network (BN) Support vector machine (SVM). Besides previously mentioned Decision trees (DT) Clustering often classification. Neural Networks (NN) use common both DT, together Genetic algorithm (GA) SVM, achieved highest average accuracy. Recently, authors combine different DM also dimensionality reduction used. Implications theory practice study contributes quality management extending recently can help researchers choose suitable build models achieving its purpose.