Proceedings ArticleDOI
Understanding customer returns from a test perspective
Reads0
Chats0
TLDR
In this paper, a multivariate screening methodology is proposed to detect defective parts during the wafer test process, where the test signatures from parametric measurements can be used to separate the returned parts from the rest of population.Abstract:
Customer returns are defective parts that pass all functional and parametric tests, but fail in the field. To prevent customer returns, this paper analyzes wafer probe test data and tries to understand what it takes to screen them out during testing. Because these parts pass all tests, analyzing their signatures based on the original test perspective does not make sense. In this work, we search for a novel test perspective where the test signatures from parametric measurements can be used to separate the returned parts from the rest of population. Our study shows that in order to effectively screen customer returns during wafer test, a multivariate screening methodology is desired. This study is based on analyzing over 1000 parametric wafer probe tests and dies from seven lots, each lot containing one returned part. We demonstrate that analyzing customer returns from a multivariate test perspective leads to robust and conservative results.read more
Citations
More filters
Proceedings ArticleDOI
Screening customer returns with multivariate test analysis
TL;DR: This work studies the potential of capturing customer returns with models constructed based on multivariate analysis of parametric wafer sort test measurements and shows that each approach can capture returns not captured by the other.
Proceedings ArticleDOI
An experiment of burn-in time reduction based on parametric test analysis
TL;DR: It is shown that after 10 hours of burn-in, it is possible to identify a large portion of all parts that do not require longer burn- in time, potentially providing significant cost saving.
Proceedings ArticleDOI
Forward prediction based on wafer sort data — A case study
TL;DR: The potential of using wafer probe tests to predict the outcome of future tests is studied using test data based on an SoC design for the automotive market to show that an individual outlier model can be learned for each failing part.
Proceedings ArticleDOI
Multivariate outlier modeling for capturing customer returns — How simple it can be
TL;DR: This work explains that based on a Gaussian assumption, a simpler covariance-based outlier analysis approach can be sufficient over a more complex density-based approach such as one-class SVM and shows that correlation among tests can be a good metric to rank potential outlier models.
Proceedings ArticleDOI
Important test selection for screening potential customer returns
TL;DR: In this paper, the authors analyze seven lots of parametric wafer probe test data, where each lot contains one customer return, and suggest an outlier analysis based test strategy for screening potential customer returns.
References
More filters
Journal ArticleDOI
LIBSVM: A library for support vector machines
Chih-Chung Chang,Chih-Jen Lin +1 more
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
Journal ArticleDOI
Estimating the Support of a High-Dimensional Distribution
TL;DR: In this paper, the authors propose a method to estimate a function f that is positive on S and negative on the complement of S. The functional form of f is given by a kernel expansion in terms of a potentially small subset of the training data; it is regularized by controlling the length of the weight vector in an associated feature space.
Journal ArticleDOI
New Support Vector Algorithms
TL;DR: A new class of support vector algorithms for regression and classification that eliminates one of the other free parameters of the algorithm: the accuracy parameter in the regression case, and the regularization constant C in the classification case.
Journal Article
An extensive empirical study of feature selection metrics for text classification
TL;DR: An empirical comparison of twelve feature selection methods evaluated on a benchmark of 229 text classification problem instances, revealing that a new feature selection metric, called 'Bi-Normal Separation' (BNS), outperformed the others by a substantial margin in most situations and was the top single choice for all goals except precision.
Proceedings ArticleDOI
YALE: rapid prototyping for complex data mining tasks
TL;DR: Yale is described, a free open-source environment for KDD and machine learning which provides a rich variety of methods which allows rapid prototyping for new applications and makes costlyre-implementations unnecessary and offers extensive functionality for process evaluation and optimization.