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

Abstract

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

Improvement Activities in Stamping Die Manufacturing: A Systematic Literature Review

“…It was subsequently enhanced as PRISMA 2020, which includes reporting guidance that advance sophisticated methodologies for identifying, selecting, assessing, and synthesising research [33]. A few examples of the PRISMA method in the manufacturing area are sustainable development [28], sustainable manufacturing [35], lean manual assembly [30], manufacturing data mining [7], factory planning [10], additive manufacturing [27], manufacturing methodology [19], augmented reality manufacturing [22] and Industry 4.0 [39]. As a result, this technique is suited for systematically describing the actions and methods for improving stamping die production via searching and identification, screening, eligibility, data abstraction, and analysis.…”

A Novel Data Mining Approach for Defect Detection in the Printed Circuit Board Manufacturing Process

“…Based on a previously developed PRISMA-based systematic review (Bartova, Bina & Vachova, 2022), the method Support Vector Machine (SVM) was chosen for further research on effective defect detection. The PCA method for feature extraction was used as a preprocessing step.…”

“…The research authors aimed to find a solution or propose a model for the higher accuracy of defect detection. Based on the previous literature review (Bartova, Bina & Vachova, 2022), the chosen method for this classification task was the support vector machine (SVM). SVMs are currently a hot topic in the machine learning community, creating a similar enthusiasm now as previously encountered by Artificial Neural Networks.…”