New implementions of predictive alternate analog/RF test with augmented model redundancy

Haithem Ayari 1 Florence Azaïs 1 Serge Bernard 2 Mariane Comte 1 Vincent Kerzérho 2 Michel Renovell 1
1 TEST - TEST
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
2 SmartIES - Smart Integrated Electronic Systems
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : This paper discusses new implementations of the predictive alternate test strategy that exploit model redundancy in order to improve test confidence. The key idea is to build during the training phase, not only one regression model for each specification as in the classical implementation, but several regression models. This redundancy is then used during the testing phase to identify suspect predictions and remove the corresponding devices from the alternate test flow. In this paper, we explore various options for implementing model redundancy, based on the use of different indirect measurement combinations and/or different partitions of the training set. The proposed implementations are evaluated on a real case study for which we have production test data from 10,000 devices.
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00994714
Contributor : Mariane Comte <>
Submitted on : Thursday, May 22, 2014 - 12:53:40 AM
Last modification on : Wednesday, August 28, 2019 - 7:12:02 PM
Long-term archiving on : Friday, August 22, 2014 - 11:20:55 AM

File

DATE14_camera_ready.pdf
Files produced by the author(s)

Identifiers

Citation

Haithem Ayari, Florence Azaïs, Serge Bernard, Mariane Comte, Vincent Kerzérho, et al.. New implementions of predictive alternate analog/RF test with augmented model redundancy. DATE: Design, Automation and Test in Europe, Mar 2014, Dresden, Germany. ⟨10.7873/DATE2014.144⟩. ⟨lirmm-00994714⟩

Share

Metrics

Record views

522

Files downloads

469