Board-level fault diagnosis using Bayesian inference

Zhang, Zhaobo; Wang, Zhanglei; Gu, Xinli; Chakrabarty, Krishnendu

doi:10.1109/vts.2010.5469569

Cited by 30 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare the diagnosis success ratio obtained using the proposed ANNs to that obtained using traditional ANNs and Bayesian inference (BI) [49], with the same training cases and test cases. For traditional ANNs, we consider a 3-layer network [60].…”

Section: Diagnostic Results Using the Anns-based Learning Systemmentioning

confidence: 99%

“…Therefore, the final probability of an action being correct is obtained using the information reflected by all the fault syndromes. More details are described in [49].…”

Section: Diagnostic Results Using the Anns-based Learning Systemmentioning

confidence: 99%

“…An advantage of using machine learning is that it avoids the difficulties associated with knowledge acquisition and rule-base development required for expert systems [3,4,49]. Without the need to understand the complex functionality of boards, diagnostic systems based on machine learning are able to automatically derive and exploit knowledge from repair logs of previously documented cases.…”

Section: Problem Statement and Prior Workmentioning

confidence: 99%

See 2 more Smart Citations

Knowledge-Driven Board-Level Functional Fault Diagnosis

Zhang

Chakrabarty

et al. 2017

Self Cite

View full text Add to dashboard Cite

The semiconductor industry continues to relentlessly advance silicon technology scaling into the deep-submicron (DSM) era. High integration levels and structured design methods enable complex systems that can be manufactured in high volume.However, due to increasing integration densities and high operating speeds, subtle manifestation of defects leads to functional failures at the board level. Functional fault diagnosis is, therefore, necessary for board-level product qualification. However, ambiguous diagnosis results can lead to long debug times and wrong repair actions, which significantly increase repair cost and adversely impact yield.

show abstract

Section: Diagnostic Results Using the Anns-based Learning Systemmentioning

confidence: 99%

“…Therefore, the final probability of an action being correct is obtained using the information reflected by all the fault syndromes. More details are described in [49].…”

Section: Diagnostic Results Using the Anns-based Learning Systemmentioning

confidence: 99%

Section: Problem Statement and Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

Knowledge-Driven Board-Level Functional Fault Diagnosis

Zhang

Chakrabarty

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…The main problem addressed by most of the available techniques, such as the ones presented in [2], [3], [4], [5], is the extraction of an effective system model starting from a limited amount of data belonging to previously performed testing/diagnosis activities. The extracted model is then used in a "traditional" way, i.e., by applying all the available tests and collecting all outcomes (referred to as a complete syndrome).…”

Section: Introduction and Related Workmentioning

confidence: 99%

A configurable board-level adaptive incremental diagnosis technique based on decision trees

Bolchini

Cassano

2015

2015 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFTS)

View full text Add to dashboard Cite

Abstract-Functional diagnosis for complex electronic boards is a time-consuming task that requires big expertise to the diagnosis engineers. In this paper we propose a new engine for board-level adaptive incremental functional diagnosis based on decision trees. The engine incrementally selects the tests that have to be executed and based on the test outcomes it automatically stops the diagnosis as soon as one or more faulty candidates can be identified, thus allowing to reduce the number of executed tests. Moreover, we propose a configurable early stop condition for the engine that allows to further reduce the number of executed tests leveraging the diagnosis accuracy. The effectiveness of the proposed approach has been assessed using a set of synthetic but realistic boards and three industrial boards.

show abstract

“…Reasoning-based methods are becoming popular today since detailed system models are not needed to construct the diagnosis system [10], [15]- [17]. Repairs of faulty components are suggested through a ranked list of potential faulty components, e.g., based on Bayesian inference [15] and Dempster-Shafer theory [10].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Board-Level Functional Fault Diagnosis Using Decision Trees

Zhang

Chakrabarty

et al. 2012

2012 IEEE 21st Asian Test Symposium

Self Cite

View full text Add to dashboard Cite

Functional fault diagnosis at board-level is desirable for high-volume production since it improves product yield. However, to ensure diagnosis accuracy and effective board repair, a large number of syndromes must be used. Therefore, the diagnosis cost can be prohibitively high due to the increase in diagnosis time and the complexity of syndrome collection/analysis. We propose an adaptive diagnosis method based on decision trees (DTs). Faulty components are classified according to the discriminative ability of the syndromes in DT training. The diagnosis procedure is constructed as a binary tree, with the most discriminative syndrome as the root and final repair suggestions are available as the leaf nodes of the tree. The syndrome to be collected in the next step is determined based on the observations of syndromes collected thus far in the diagnosis procedure. The number of syndromes required for diagnosis can also be significantly reduced compared to the number of syndromes used for system training. Diagnosis results for two complex boards from industry, currently in volume production, and additional synthetic data highlight the effectiveness of the proposed approach.

show abstract

Board-level fault diagnosis using Bayesian inference

Cited by 30 publications

References 10 publications

Knowledge-Driven Board-Level Functional Fault Diagnosis

Knowledge-Driven Board-Level Functional Fault Diagnosis

A configurable board-level adaptive incremental diagnosis technique based on decision trees

Adaptive Board-Level Functional Fault Diagnosis Using Decision Trees

Contact Info

Product

Resources

About