Prediction of Wafer Map Categories Using Wafer Acceptance Test Parameters in Semiconductor Manufacturing

Lim, Martin Ying Song; Sharma, Anurag; Chin, Cheng Siong; Yip, Tommy Chun Ming; Ong, Jonathan Yoong Seang

doi:10.1007/978-3-031-08337-2_12

Cited by 2 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: The Review Of Wypmentioning

confidence: 99%

“…3) The shallow structured machine learning method refers to some artificial intelligent methods (such as the support vector machine (SVM), XGBoost [19,20]), which can predict the yield of the wafer based on some pre-designed models. Lim et al [20] compared the prediction performance of SVM and XGBoost models under different production scales when identifying two types of wafer maps on the premise of data balance. Jiang et al [21] designed a yield prediction method based on a support vector machine and other machine learning models, which uses the WAT parameters of the front end to predict the test yield of the back end.…”

Section: The Review Of Wypmentioning

confidence: 99%

“…The error represents the loss obtained by a given classier (the Support Vector Machine (SVM) classifier [20] is used here) with the new training set and loss is calculated by the (1-AUC) value. α and β are two parameters representing the weight of loss and selected feature rate in the whole fitness function, α ∈ [0, 1] and β = (1α).…”

Section: Fitness Functionmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: The Review Of Wypmentioning

confidence: 99%