Mixed response surface models and Bayesian analysis of variance components for electrically conductive adhesives

Berni, Rossella; Scarano, Valeria L.; Bertocci, Francesco; Catelani, Marcantonio

doi:10.1002/asmb.1978

Cited by 10 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, our proposal, which is widely studied in literature, among the others [28] and [30], is related to the RS methodology and mixed effects to analyze variance components in this context. The application of this method could be considered an attempt to improve the analysis of the variability sources; in [32], a comparison between mixed RS models and a Bayesian approach is performed to consider the relevance of variance components for the evaluation of process optimization. Another novelty is the role of variability sources in optimizing the process in this field [33].…”

Section: Statistical Theory: Mixed Response Surface Models and Thmentioning

confidence: 99%

Assessment and Optimization for Novel Gas Materials Through the Evaluation of Mixed Response Surface Models

Bertocci

Fort

Vignoli

et al. 2015

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

In this paper, an innovative methodology aimed at improving the development of novel gas sensors through a process optimization is carried out by applying mixed response surface (RS) models. High accuracy measurements of new conductometric metal oxide gas sensors, obtained by an efficient control of the working conditions, are gathered. The response of metal–oxide–semiconductor gas sensors changes significantly when the sensors operate at different temperatures and target gas concentrations. To consider all the sources of variability there involved, the RS methodology was applied, including random effects, to improve and optimize the performance of these new gas sensors. More precisely, the optimization is performed exploiting a limited number of observations, systematically collected with an ad hoc measurement system, and it considers external sources of variability, satisfying at the same time stringent requirements. Furthermore, the statistical results and the relative assessment of novel gas materials are obtained by considering fixed as well as random effects, where random variables are considered for\ud better controlling the optimization step

show abstract

Section: Statistical Theory: Mixed Response Surface Models and Thmentioning

confidence: 99%

Assessment and Optimization for Novel Gas Materials Through the Evaluation of Mixed Response Surface Models

Bertocci

Fort

Vignoli

et al. 2015

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

show abstract

“…To properly evaluate the data, certain steps are 978-1-4673-6386-0/14/$31.00 ©2014 IEEE required: Weibull probability distribution and recent contributes are evaluated in order to consider the specific features of lifetime experimental data and modeling. In particular, the structure of the experimental data relating to the statistical modeling approach implies the consideration of random effects and Bayesian methods, [16].…”

Section: Introductionmentioning

confidence: 99%

Wideband measurement method for prognosis of soldering failure on electronic boards

Adamo

Andria

Nisio

et al. 2014

2014 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings

View full text Add to dashboard Cite

Reliability specifications for solder joints, as well as for all electronic components, become a fundamental element in the qualification of an electronic product. This importance increases if new lead-free alloys are considered and then under test. An accelerated thermal test is proposed for an early reliability evaluation and the definition of failure parameters is addressed. The traditional technique employed for failure monitoring of solder joints is the DC resistance measurement. This paper reviews and assesses the DC resistance monitoring during reliability tests of lead-free solder materials used for electronic boards production. Moreover through a failure prognosis measurement technique, considering wideband measurements, the possibility to identify the failure occurrence earlier than the DC resistance method is evaluated. An experimental study on a pass band filter soldered by a new lead free alloy is performed to evaluate reliability performance.

show abstract

“…Statistical process control [2], regression-based modeling methods [3], and designed experiments [4][5][6] are widely used. Yield is a key process performance characteristic in the semiconductor fabrication process.…”

Section: Introductionmentioning

confidence: 99%

Modeling and analyzing semiconductor yield with generalized linear mixed models

Krueger

Montgomery

2014

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

As the challenges and opportunities of using 'big data' expand, there is a need to explore different ways of analyzing large datasets. The semiconductor industry is a good example of a manufacturing process where many data are collected throughout the fabrication of the product. These massive datasets are used for various purposes, primarily to detect problems and determine root causes, control the process, and build models that predict yield. The yield predictions are used for process planning, optimization, and control. However, many current approaches to yield modeling are limited because the actual processes violate the model assumptions, limiting the power of the models' use. This paper explores the use of generalized linear mixed models (GLMMs) to predict semiconductor yield and to provide significant information about the process using a large semiconductor yield dataset. Both batch-specific and population-averaged GLMM approaches are used and compared. Differences in link functions, sample sizes, and levels of aggregation (die-level and wafer-level models) are also compared with each other and with the results from generalized linear models (GLMs). The results of this study show that GLMMs are a reasonable approach to analyzing large datasets by providing additional insight into the fabrication process while maintaining or even improving prediction power compared with GLMs and some prior yield models found in the literature. This paper also provides a modeling strategy through suggestions regarding level of aggregation, link function, and sample size that are appropriate for different research goals.

show abstract

Mixed response surface models and Bayesian analysis of variance components for electrically conductive adhesives

Cited by 10 publications

References 17 publications

Assessment and Optimization for Novel Gas Materials Through the Evaluation of Mixed Response Surface Models

Assessment and Optimization for Novel Gas Materials Through the Evaluation of Mixed Response Surface Models

Wideband measurement method for prognosis of soldering failure on electronic boards

Modeling and analyzing semiconductor yield with generalized linear mixed models

Contact Info

Product

Resources

About