A Novel Framework for Semiconductor Manufacturing Final Test Yield Classification Using Machine Learning Techniques

Abstract

Advanced data analysis tools and techniques are important for semiconductor companies to gain competitive advantage. In particular, yield prediction tools, which fully utilize production data, help to improve operational efficiency and reduce production costs. This paper introduces a novel and scalable framework for semiconductor manufacturing Final Test (FT) yield prediction leveraging machine learning techniques. This framework is able to predict FT yield at wafer fabrication stage, so that FT low yield problems can be caught at an earlier production stage compared to past studies. Our work presents a robust solution to automatically handle both numerical and categorical production related data without prior knowledge of the low yield root cause. Gaussian Mixture Models, One Hot Encoder and Label Encoder techniques are adopted for data pre-processing. To improve model performance for both binary and multiclass classification, model selection and model ensemble using the F1-macro method is demonstrated. The framework has been applied to three mass production products with different wafer technologies and manufacturing flows. All of them achieved high F1-macro test score indicative of the robustness of our framework.INDEX TERMS Semiconductor manufacturing, smart manufacturing, yield prediction, final test, Gaussian mixture models, clustering, ensemble methods.

Production Flow Analysis in a Semiconductor Fab Using Machine Learning Techniques

“…Identifying important input factors and the appropriate model is necessary to predict the system's target values appropriately. Target values to be estimated could be the quality of the wafer lots [20] or abnormality in the wafer lot flows [21].…”

“…In a study similar to this one, Jiang et al [20] attempted to classify wafer lots based on their yield levels. This was intended to minimize the defect wafer lots.…”

“…Other related studies on the yield model are [22,23]. Different from [20], this study focused on predicting the production system's operational factors that have important effects on the system's throughput, instead of observing the quality of the produced wafer lots. Lee and Cho [21] and Lauer and Legner [24] detected an abnormality in the semiconductor production line.…”

Semiconductor Manufacturing Final Test Yield Optimization and Wafer Acceptance Test Parameter Inverse Design Using Multi-Objective Optimization Algorithms

“…W Ith the increasing cost of semiconductor fabrication due to technology node shrinking and global supply shortage situations, the manufacturing yield optimization is becoming one of the most critical goals for semiconductor operations. Current production yield improvement strategies mainly rely on engineers' manual monitoring and hindsight and any corrective actions can only take place after integrated circuit (IC) finished assembly and testing as mentioned in [1]. Immense amount of data are generated during semiconductor manufacturing processes but are not fully utilized.…”

Visual Product Tracking System Using Siamese Neural Networks

“…Machine learning has been identified as a solution for many challenges in production [2]. These problems include machine speed prediction [18], rolling force and temperature prediction in steel manufacturing [19], subsurface defect detection in composite products [20], final test yield prediction in semiconductor manufacturing [21], and bearing time-to-failure (TTF) estimation [22], to name a few. For product tracking, we suggest using a Siamese neural network to learn the visual and positional transformations of the products.…”