Active inspection for cost-effective fault prediction in manufacturing process. (September 2021)

• Record Type: Journal Article
• Authors: Shim, Jaewoong; Kang, Seokho; Cho, Sungzoon
• Is Part Of: Journal of process control. Volume 105(2021)
• Page Start: 250
• Page End: 258
• Publication Date: 2021-09
• Subjects: EPC expected prediction change -- DT decision tree -- GODA goal-oriented data acquisition -- RF random forest -- ANN artificial neural network -- kNN k-nearest neighbor -- AUROC area under the receiver operating characteristic curve -- ET extremely randomized tree; Fault prediction -- Active inspection -- Active feature-value acquisition -- Expected prediction change -- Semiconductor manufacturing; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2021.08.008
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: Manufacturing processes typically involves a number of inspections, including basic inspections for all products and advanced inspections for selected sampled products. The partial application of advanced inspections decreases processing time and cost, although it deteriorates the final quality of products. Recently, several studies have focused on using inspection data to train a prediction model that predicts faults in final products. The lack of advanced inspection data for some products limits the prediction accuracy of the model. Herein, we propose an active inspection framework, where products are intelligently sampled for advanced inspections to achieve high prediction accuracy in a cost-effective manner. Two prediction models are used in the framework: basic and advanced models. The basic model is trained with data from basic inspections, whereas the advanced model is trained with data from both basic and advanced inspections to predict whether a product is faulty. For a product that undergoes basic inspections, the basic model outputs a fault score and its uncertainty in terms of the expected prediction change. If the uncertainty is low, then the fault score of the product is finalized. If the uncertainty is high, then the product is subject to advanced inspections, and the fault score is updated using the advanced model. We demonstrate the effectiveness of the proposed active inspection framework through a case study using real-world data acquired from a semiconductor manufacturer. Highlights: Active inspection framework is proposed for product fault prediction. Products are intelligently sampled with prediction uncertainty. Expected prediction change (EPC) is proposed for uncertainty estimation. A higher accuracy can be achieved while maintaining low inspection costs.