Using a classifier ensemble for proactive quality monitoring and control: The impact of the choice of classifiers types, selection criterion, and fusion process

Abstract

In recent times, the manufacturing processes are faced with many external or internal (the increase of customized product re-scheduling, process reliability,.. ) changes. Therefore, monitoring and quality management activities for these manufacturing processes are difficult. Thus, the managers need more proactive approaches to deal with this variability. In this study, a proactive quality monitoring and control approach based on classifiers to predict defect occurrences and provide optimal values for factors critical to the quality processes is proposed. In a previous work , the classification approach had been used in order to improve the quality of a lacquering process at a company plant; the results obtained are promising, but the accuracy of the classification model used needs to be improved. One way to achieve this is to construct a committee of classifiers (referred to as an ensemble) to obtain a better predictive model than its constituent models. However, the selection of the best classification methods and the construction of the final ensemble still poses a challenging issue. In this study, we focus and analyze the impact of the choice of classifier types on the accuracy of the classifier ensemble; in addition, we explore the effects of the selection criterion and fusion process on the ensemble accuracy as well. Several fusion scenarios were tested and compared based on a real-world case. Our results show that using an ensemble classification leads to an increase in the accuracy of the classifier models. Consequently, the monitoring and control of the considered real-world case can be improved. Computers in Industry 99 (2018) 193-204 2 1 IntroductionThe growing need for complex and customized products and services has led to increased complexity of the associated manufacturing processes as well; this complexity may be attributed to several different sources depending on the features of the product/service and the organizational structure of the companies. Consequently, the manufacturing and control tasks become difficult, including their monitoring and quality management. Despite the many methods and operational tools that have been developed in the last few decades, the executive management personnel of these companies are always seeking new approaches and tools to analyze their specific problems and devise potential improvement strategies at several levels.These approaches and tools can thus be regarded as decision-aiding tools to identify not only the root causes of defects but also factors critical to the quality of their products/services; in particular, the aim of the executive managers is to eliminate those causes or limit their impact by setting the factors critical to quality at adequate or optimal levels. Among these approaches, a common method is the Design of Experiments (DoE); however, the primary disadvantage of such an approach is that the improvement process is considered "off-line." Indeed, even if a robust process is established by successfully optimizing the controllable and uncontrol...

Adaptive melanoma diagnosis using evolving clustering, ensemble and deep neural networks

“…Their model outperformed other prediction methods, such as a MLP and a regression tree, for the evaluation of two real data sets. Moreover, ensemble classier construction techniques were also studied by Thomas et al [45] for proactive quality monitoring and control. They employed four types of base classifiers for ensemble construction, i.e.…”

Medoid-based MLP: An Application to Wood Sawing Simulator Metamodeling

“…Additionally, numerous methods have been proposed to select predictors from a set of previously trained models. (Thomas et al, 2018) reports that two such families of methods either perform a selection based solely on a performance score, for example the MSE, or perform a selection based on both a performance scores and a diversity score. However, when comparing two such methods on their industrial dataset, they found no significant advantage to the use of a diversity based method, compared to the use of a performance based method.…”

A postpruning decision algorithm based on loss minimization

“…Several researchers have adopted the idea of incorporating the general loss matrix into C4.5 decision tree algorithm to reduce the misclassification cost or to minimize the misclassification loss [31][32][33][34]. These algorithms introduced heuristic splitting methods that perform dual tasks.…”