Hybrid Feature Selection for Wafer Acceptance Test Parameters in Semiconductor Manufacturing

Xu, Hongwei; Zhang, Jie; Lv, Youlong; Zheng, Peng

doi:10.1109/access.2020.2966520

Cited by 30 publications

(14 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The test results are comparable with the absolute error prediction results for probe yield in Ref. [15]. Therefore, our proposed GMM ensemble regressor is effective and robust for FT yield prediction.…”

Section: Resultssupporting

confidence: 73%

See 1 more Smart Citation

A Gaussian Mixture Model Clustering Ensemble Regressor for Semiconductor Manufacturing Final Test Yield Prediction

2021

View full text Add to dashboard Cite

In the semiconductor industry, many studies have been carried out for front-end related process improvement and yield prediction using machine learning techniques. However, very few research investigations have dealt with the backend Final Test (FT) yield prediction using the front-end wafer acceptance test (WAT) parameters. The manufacturing cycle time between wafer fabrication (WF) and FT can range anywhere between a few weeks to several months. It is therefore important for semiconductor manufacturers to detect wafer material related low yield problems at an earlier stage for effective cost and quality control. This is a challenging goal as the input data used for prediction is at a very early manufacturing stage and the output FT yield for packaged chips is the last stage of the fabrication chain. There are many unknown production variations caused by different manufacturing processes, equipment configurations and human interferences in this multi-stage sequential fabrication chain. In this paper, we proposed a novel procedure to predict the backend FT yield at the WF stage itself using a Gaussian Mixture Models (GMM) clustering approach that is applied to build a weighted ensemble regressor. Real production data for new chip product lines are verified with this method and show significant improvement in the prediction performance.

show abstract

Section: Resultssupporting

confidence: 73%

“…A novel feature selection method for identifying the key parameters of WAT measurements based on Hybrid Feature Selection (HFS) was proposed by Xu et al in their work of Ref. [15]. The HFS method can effectively filter out the noise parameters and achieve accurate prediction of wafer probe yield with reduced key WAT parameters.…”

Section: Related Workmentioning

confidence: 99%

A Gaussian Mixture Model Clustering Ensemble Regressor for Semiconductor Manufacturing Final Test Yield Prediction

2021

View full text Add to dashboard Cite

show abstract

“…Finally, the Genetic Algorithm-Backpropagation Neural Network (GA-BPNN) only uses 9 parameters and the prediction effect is the best. Xu et al [5] designed a hybrid feature selection method for identifying key parameters of wafer yield prediction. Then the key parameters are used as the input of the deep belief network (DBN) to predict the wafer yield.…”

Section: The Review Of Wypmentioning

confidence: 99%

Forecasting the yield of wafer by using improved genetic algorithm, high dimensional alternating feature selection and SVM with uneven distribution and high-dimensional data

Wang

2022

Auton. Intell. Syst.

View full text Add to dashboard Cite

Wafer yield prediction, as the basis of quality control, is dedicated to predicting quality indices of the wafer manufacturing process. In recent years, data-driven machine learning methods have received a lot of attention due to their accuracy, robustness, and convenience for the prediction of quality indices. However, the existing studies mainly focus on the model level to improve the accuracy of yield prediction does not consider the impact of data characteristics on yield prediction. To tackle the above issues, a novel wafer yield prediction method is proposed, in which the improved genetic algorithm (IGA) is an under-sampling method, which is used to solve the problem of data overlap between finished products and defective products caused by the similarity of manufacturing processes between finished products and defective products in the wafer manufacturing process, and the problem of data imbalance caused by too few defective samples, that is, the problem of uneven distribution of data. In addition, the high-dimensional alternating feature selection method (HAFS) is used to select key influencing processes, that is, key parameters to avoid overfitting in the prediction model caused by many input parameters. Finally, SVM is used to predict the yield. Furthermore, experiments are conducted on a public wafer yield prediction dataset collected from an actual wafer manufacturing system. IGA-HAFS-SVM achieves state-of-art results on this dataset, which confirms the effectiveness of IGA-HAFS-SVM. Additionally, on this dataset, the proposed method improves the AUC score, G-Mean and F1-score by 21.6%, 34.6% and 0.6% respectively compared with the conventional method. Moreover, the experimental results prove the influence of data characteristics on wafer yield prediction.

show abstract

“…To address the imbalanced classification issue, some researchers prefer to resolve from the perspective of a data set adopting a resampling algorithm [1~3], while others prefer to design new algorithms or improve upon existing algorithms [4~6]. On the other hand, for the issue of highdimensional features, feature selection [7] or feature extraction [8] are mostly applied.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Feature Selection Method RFSTL for Manufacturing Quality Prediction Based on a High Dimensional Imbalanced Dataset

Zhou

Chen

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Under Industry 4.0, manufacturing quality prediction has been gaining increased interest from researchers and manufacturers. From the analysis of previous studies on quality predictions using machine learning, it became clear that the high dimensionality and imbalance of data are major and common problems affecting the learning performance. This work uses a hybrid method to address this issue, applying a Synthetic Minority Oversampling Technique & TomekLinks balancing approach to create balanced data and using Random Forest as the feature selecting measurement to reduce the dimensionality of data. In addition, a Fine Gaussian Support Vector Machine (Fine Gaussian SVM) based on the representative set of features selected by the hybrid method utilized is employed in this work to predict product quality. The results of experimentation demonstrate that the hybrid method proposed in this work performs well for manufacturing quality prediction and offers a simple, quick and powerful way to address the problem of feature selection encountered by the imbalanced classification.

show abstract

Hybrid Feature Selection for Wafer Acceptance Test Parameters in Semiconductor Manufacturing

Cited by 30 publications

References 30 publications

A Gaussian Mixture Model Clustering Ensemble Regressor for Semiconductor Manufacturing Final Test Yield Prediction

A Gaussian Mixture Model Clustering Ensemble Regressor for Semiconductor Manufacturing Final Test Yield Prediction

Forecasting the yield of wafer by using improved genetic algorithm, high dimensional alternating feature selection and SVM with uneven distribution and high-dimensional data

A Hybrid Feature Selection Method RFSTL for Manufacturing Quality Prediction Based on a High Dimensional Imbalanced Dataset

Contact Info

Product

Resources

About