Adaptive Bayesian Diagnosis of Intermittent Faults

Gomez, Laura Rodriguez; Cook, Alejandro; Indlekofer, Thomas; Hellebrand, Sybille; Wunderlich, Hans-Joachim

doi:10.1007/s10836-014-5477-1

Cited by 17 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Zhou et al [ 28 ] reviewed different model-based and data-driven methods to find the most probable diagnosis in dynamic systems with intermittent faults. Gómez et al [ 29 ] proposed an approach for diagnosis in the presence of intermittent faults that applies Bayesian reasoning to distinguish between different types of faults [ 29 ]. During the diagnosis process, faults are not only found but also classified as either intermittent or transient faults.…”

Section: Background and Related Workmentioning

confidence: 99%

Minimal Cardinality Diagnosis in Problems with Multiple Observations

2021

View full text Add to dashboard Cite

Model-Based Diagnosis (MBD) is a well-known approach to diagnosis in medical domains. In this approach, the behavior of a system is modeled and used to identify faulty components, i.e., once a symptom of abnormal behavior is observed, an inference algorithm is run on the system model and returns possible explanations. Such explanations are referred to as diagnoses. A diagnosis is an assumption about which set of components are faulty and have caused the abnormal behavior. In this work, we focus on the case where multiple observations are available to the diagnoser, collected at different times, such that some of these observations exhibit symptoms of abnormal behavior. MBD with multiple observations is challenging because some components may fail intermittently, i.e., behave abnormally in one observation and behave normally in another, while other components may fail all the time (non-intermittently). Inspired by recent success in solving classical diagnosis problems using Boolean satisfiability (SAT) solvers, we describe two SAT-based approaches to solve this MBD with multiple observations problem. The first approach compiles the problem to a single SAT formula, and the second approach solves each observation independently and then merges them together. We compare these two approaches experimentally on a standard diagnosis benchmark and analyze their pros and cons.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Minimal Cardinality Diagnosis in Problems with Multiple Observations

2021

View full text Add to dashboard Cite

show abstract

“…They are usually concerned with two objectives: (a) defect identification, that is, mapping the diagnosed fault to a defect. This is challenging especially when it is based only on the failure response of the circuit (Gomez, Cook, Indlekofer, Hellebrand, & Wunderlich, 2017; L. R. Gómez & Wunderlich, 2016; Nelson et al, 2010); (b) improving diagnostic resolution, where the candidate faults are analyzed so as to further prune the set in order to improve the diagnostic resolution (Xue et al, 2013). The features used in both approaches are derived from the layout and logical information of the circuit and the output response of the failing chip.…”

Section: Yield Learning and Diagnosismentioning

confidence: 99%

“…Another set of faults which are targeted for classification consists of transient and intermittent faults (Gomez et al, 2017). Both types produce similar test results and it is difficult to distinguish them.…”

Section: Yield Learning and Diagnosismentioning

confidence: 99%

“…Both types produce similar test results and it is difficult to distinguish them. While intermittent faults lead to the degradation of the chip, transient faults contribute to unnecessary yield loss (Gomez et al, 2017). A tool based on Bayesian classifier is proposed in Gomez et al (2017) to distinguish these two types of faults.…”

Section: Yield Learning and Diagnosismentioning

confidence: 99%

See 1 more Smart Citation

A survey of digital circuit testing in the light of machine learning

Pradhan

Bhattacharya

2020

WIREs Data Min & Knowl

View full text Add to dashboard Cite

The insistent trend in today's nanoscale technology, to keep abreast of the Moore's law, has been continually opening up newer challenges to circuit designers. With rapid downscaling of integration, the intricacies involved in the manufacturing process have escalated significantly. Concomitantly, the nature of defects in silicon chips has become more complex and unpredictable, adding further difficulty in circuit testing and diagnosis. The volume of test data has surged and the parameters that govern testing of integrated circuits have increased not only in dimension but also in the complexity of their correlation. Evidently, the current scenario serves as a pertinent platform to explore new test solutions based on machine learning. In this survey, we look at various recent advances in this evolving domain in the context of digital logic testing and diagnosis. This article is categorized under: Algorithmic Development > Structure Discovery Technologies > Machine Learning Technologies > Prediction

show abstract

Machine Learning Support for Logic Diagnosis and Defect Classification

Wunderlich

2022

Machine Learning Support for Fault Diagnosis of System-on-Chip

View full text Add to dashboard Cite

Adaptive Bayesian Diagnosis of Intermittent Faults

Cited by 17 publications

References 14 publications

Minimal Cardinality Diagnosis in Problems with Multiple Observations

Minimal Cardinality Diagnosis in Problems with Multiple Observations

A survey of digital circuit testing in the light of machine learning

Machine Learning Support for Logic Diagnosis and Defect Classification

Contact Info

Product

Resources

About