Data Mining Approaches for Packaging Yield Prediction in the Post-fabrication Process

Park, Seung-Hwan; Park, Cheong-Sool; Kim, Jun Seok; Kim, Sung-Shick; Baek, Jun-Geol; An, Daewoong

doi:10.1109/bigdata.congress.2013.55

Cited by 13 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such research has investigated for predicting the fraction of pass dies on a wafer or whether a wafer is defective. Most of them focused on predicting the fab and probe yields [1], [11], [13]- [16], whereas relatively few aim to predict the final yield [6], [7]. There have also been several attempts to develop a virtual metrology system to predict the key properties of a wafer that are closely related to the yield [17] or to extract knowledge that can be utilized to enhance the yield [2], [3].…”

Section: A Yield Prediction In Semiconductor Manufacturingmentioning

confidence: 99%

See 1 more Smart Citation

Using Wafer Map Features to Better Predict Die-Level Failures in Final Test

Kang

Cho

et al. 2015

IEEE Trans. Semicond. Manufact.

View full text Add to dashboard Cite

In semiconductor manufacturing, wafer fabrication is followed by chip assembly where individual dies are assembled as a packaged chip. In between, dies are tested in terms of their electrical properties and those which fail to pass the "wafer test" are filtered out. However, some faulty dies pass the test and cause a packaged chip to fail in the final test. The inaccuracy of the wafer test leads to waste in manufacturing time and cost. In this paper, we propose to predict the result of the final test at the die-level before assembly using wafer test items and four derivations concerning wafer map features: 1) distance of the die from the wafer center; 2) previous final yield at the die position; 3) wafer test fail rate for the adjacent dies; and 4) abnormalities of the wafer map pattern. We build prediction models with these variables using a random forest algorithm. Preliminary experimental results on actual data show that the use of these derived variables improves the prediction performance with a statistical significance, thus merits further investigation. Index Terms-Die-level failure, wafer map feature, yield prediction, final test, wafer test, random forest.

show abstract

Section: A Yield Prediction In Semiconductor Manufacturingmentioning

confidence: 99%

“…During the wafer test, defective dies with a high probability of failing the final test are filtered out, and only repairable dies proceed to the subsequent steps [5]. However, some faulty dies pass the wafer test, which then ultimately fail the final test [6], [7]. There are a variety of possible reasons to explain this.…”

Section: Introductionmentioning

confidence: 99%

Using Wafer Map Features to Better Predict Die-Level Failures in Final Test

Kang

Cho

et al. 2015

IEEE Trans. Semicond. Manufact.

View full text Add to dashboard Cite

show abstract

“…Park et al [11] have suggested computational method for predicting packaging yield in semiconductor fabrication. An algorithm (random forest) has been employed to identify variables which are related in packaging yield.…”

Section: Introductionmentioning

confidence: 99%

Developing Computational Intelligence for Smart Qualification Testing of Electronic Products

et al. 2020

View full text Add to dashboard Cite

In electronics manufacturing, the necessary quality of electronic components and parts is ensured through qualification testing using standards and user requirements. The challenge is that product qualification testing is time-consuming and comes at a substantial cost. The work contributes to develop a novel prognostics framework for predicting qualification test outcomes of electronic components enabling the reduction of qualification test time and cost. The research focuses on the development of a new, prognostics-based approach to qualification of electronics parts that can enable ''smart testing'' using data-driven modelling techniques in order to ensure product robustness and reliability in operation. This work is both novel and original because at present such approach to qualification testing and the associated capability for test time reduction (respectively cost reduction) it offers are non-existent in the electronics industry. An effective way of using three different methods for development of prognostics models are identified and applied. Predictive models are constructed from historical qualification test data in the form of electrical parameter measurements using Machine Learning (ML) techniques. ML models can be imbedded within the sequential electrical tests qualification procedure and enable the forecasting of the pass/fail qualification outcome using only partial information from already completed electrical tests. Data-driven prognostics models are developed using the following machine learning techniques: (1) Support Vector Machine (SVM), (2) Neural Network (NN) and (3) K-Nearest Neighbor (KNN). The results show that with just over half of the individual tests completed, the models are capable of forecasting the final qualification outcome, pass or fail, with accuracy as high as 92.5%. The predictive power and overall performance of the researched models in predicting qualification test binary outcomes with varying ratios of Pass and Fail data in the processed datasets are analysed. INDEX TERMS Data-driven prognostics, data analysis, machine learning, modeling, electronics manufacturing, quality, qualification testing.

show abstract

“…Applications of data mining and machine learning in electronics manufacturing domain become more common and increasingly important as companies recognise that such smart expert systems and imbedded data-driven intelligence can provide competitive advantages in a global economy. Published research has addressed manufacturing challenges related to fabrication, yield optimisation, and automated fault/defect detection (Stoyanov et al 2016;Park et al 2013;Sohn and Lee 2012;Kupp and Makris 2012;Kim et al 2012Kim et al , 2015Chou et al 1997;Boubezoul et al 2007).…”

Section: Introductionmentioning

confidence: 99%

Predictive analytics methodology for smart qualification testing of electronic components

et al. 2019

View full text Add to dashboard Cite

In electronics manufacturing, the required quality of electronic modules (e.g. packaged electronic devices) are evaluated through qualification testing using standards and user-defined requirements. The challenge for the electronics industry is that product qualification testing is time-consuming and costly. This paper focuses on the development and demonstration of a novel approach for smarter qualification using test data from the production line along with integrated computational techniques for data mining/analytics and data-driven forecasting (i.e. prognostics) modelling. The most common type of testing in the electronics industry-sequentially run electrical multi-parameter tests on the Device-under-Test (DUT), is considered. The proposed data mining (DM) framework can identify the tests that have strong correlation to pending failure of the device in the qualification (tests sensitive to pending failure) as well as to evaluate the similarity in test measurements, thus generating knowledge on potentially redundant tests. Mining the data in this context and with the proposed approach represents a major new contribution because it uncovers embedded knowledge and information in the production test data that can enable intelligent optimisation of the tests' sequence and reduce the number of tests. The intelligent manufacturing concept behind the development of data-driven prognostics models using machine learning techniques is to use data only from a small number of tests from the full qualification specification as training data in the process of model construction. This model can then forecast the overall qualification outcome for a DUT-Pass or Fail-without performing all other remaining tests. The novelty in the context of machine learning is in the selection of the data features for the training dataset using results from tests sensitive to pending failure. Support Vector Machine (SVM) binary classifiers SVM models built with data from tests sensitive to the outcome that the module will fail are shown to have superior performance compared with models trained with other datasets of tests. Case studies based on the use of real industrial production test data for an electronic module are included in the paper to demonstrate and validate the computational approach. This work is both novel and original because at present, to the best knowledge of the authors, such predictive analytics methodology applied to qualification testing and providing benefits of test time and hence cost reduction are non-existent in the electronics industry. The integrated data analytics-prognostics approach, deployable for both off-line and in-line optimisation of production test procedures, has the potential to transform current practices by exploiting in a smarter way information and knowledge available with large datasets of qualification test data.

show abstract

Data Mining Approaches for Packaging Yield Prediction in the Post-fabrication Process

Cited by 13 publications

References 9 publications

Using Wafer Map Features to Better Predict Die-Level Failures in Final Test

Using Wafer Map Features to Better Predict Die-Level Failures in Final Test

Developing Computational Intelligence for Smart Qualification Testing of Electronic Products

Predictive analytics methodology for smart qualification testing of electronic components

Contact Info

Product

Resources

About