Production Multivariate Outlier Detection Using Principal Components

O'Neill, P.

doi:10.1109/test.2008.4700549

Cited by 29 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Principal Component Analysis (PCA) is a popular way to map high-dimensional data into a low-dimensional space. This is similar to the works proposed in [1] [13]. In our study we apply PCA to facilitate visualization of the learning result with a test perspective consisting of more than three tests.…”

Section: Introductionmentioning

confidence: 67%

See 1 more Smart Citation

Forward prediction based on wafer sort data — A case study

Sumikawa

Drmanac

Wang

et al. 2011

2011 IEEE International Test Conference

View full text Add to dashboard Cite

This paper studies the potential of using wafer probe tests to predict the outcome of future tests. The study is carried out using test data based on an SoC design for the automotive market. Given a set of known failing parts, there are two possible approaches to learn. First a single binary classification model can be learned to model all failing parts. We show that this approach can be effective if the failing parts are compatible in learning. Second, an individual outlier model can be learned for each failing part. We show that this approach is suitable for learning failing parts such as customer returns, where each may have a unique failing behavior. We also show that with Principal Component Analysis (PCA), a learning model can be visualized in two or three dimensional PC space, which facilitates an engineer to manually select or adjust the model.

show abstract

Section: Introductionmentioning

confidence: 67%

“…For predicting failing parts, the author in [13] projected parametric test data into the PCA space in order to identify common outlier signatures. The work demonstrates the benefits of using PCA to map a problem with many test dimensions into a problem with fewer dimensions, where the later problem is easier to solve.…”

Section: Related Workmentioning

confidence: 99%

Forward prediction based on wafer sort data — A case study

Sumikawa

Drmanac

Wang

et al. 2011

2011 IEEE International Test Conference

View full text Add to dashboard Cite

show abstract

“…Examples of algorithms used for this include Support Vector Machines and Principal Component Analysis [13,14].The results of the analysis will be:…”

Section: Example: Bi-variate Outliersmentioning

confidence: 99%

Reducing test time for selective populations in semiconductor manufacturing

Park¹,

Schuldenfrei²,

Levy³

2016

Int. J. DNE

View full text Add to dashboard Cite

As the semiconductor industry prepares for the Internet of Things, one of the major challenges it will face is to maintain quality levels as the volume of devices continues to grow. Semiconductor devices are moving from items of convenience (PCs) to necessity (smartphones) to mission-critical (autonomous automobiles). One aspect of manufacturing operations that can, and must change, in the face of ever-tightening quality requirements is how to test the devices that are shipped into the end market more efficiently while maintaining very high levels of quality. One of the ways to achieve these diametrically opposed goals is through the use of Big Data analytics. Semiconductor manufacturing test today is a 'one size fits all' process, with every device being made to go through the same battery of tests. Devices that initially do not pass are retested to be sure they are not bad, but what about the devices that are 'exceptionally good'? Testing devices that are so 'tight' in their tolerances that statistically they will easily pass any remaining test intended to catch marginal devices is a waste of time and manufacturing resources. Using Big Data analytics within a manufacturing environment can enable companies to establish a 'Quality Index' where every individual device can be 'scored' independently. If that device achieves a high-enough quality score, it can be 'excused' from any further testing to accelerate overall manufacturing throughput with zero impact on quality. This paper will show how semiconductor companies today are putting Big Data solutions in place to improve overall product quality and simultaneously reducing their manufacturing costs by using data they already have in their possession.

show abstract

“…Statistical test approaches have been used in several publications and mainly for chip-level testing. In [1,7,8,15], the authors employed the principal component analysis (PCA) technique for defect identification and test process development while measuring the integrated circuit quiescent current (I DDQ ) for an IC under test. Capacitive plate technique which extends boundary-scan testing for better test coverage [10] has been improved for its effectiveness by using PCA in [5].…”

Section: Related Workmentioning

confidence: 99%

“…9b. Table 2 collects the maximum values of z-score of each PCB test case within a 6 GHz interval. The deviations of the correct PCBs remain acceptable, while the defective PCBs 6 Open at BGA side 100.08 P CB 7 Open at BGA side 84.95 P CB 8 Open at socket side 132.41 P CB 9 Open at socket side 138.91 P CB 10 Bridge at socket side 447.63 P CB 11 Bridge at socket side 480.16 …”

Section: Bridged Socket Pinmentioning

confidence: 99%