Feature extraction, condition monitoring, and fault modeling in semiconductor manufacturing systems

Bleakie, Alexander; Djurdjanović, Dragan

doi:10.1016/j.compind.2012.10.002

Cited by 34 publications

(11 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is not surprising to see smart elements, such as active plasma diagnostics and variable process parameters, in recent developments of plasma-based surface engineering technologies, e.g. PE-CVD [9,10] 5 and Hi-PIMS [11,12]; for EPPs however this still remains in a rudimentary state despite some recent progress [13].…”

mentioning

confidence: 99%

Towards smart electrolytic plasma technologies: An overview of methodological approaches to process modelling

Парфенов

Yerokhin

Nev’yantseva

et al. 2015

Surface and Coatings Technology

156

View full text Add to dashboard Cite

Article:Parfenov, E.V., Yerokhin, A., Nevyantseva, R. ReuseUnless indicated otherwise, fulltext items are protected by copyright with all rights reserved. The copyright exception in section 29 of the Copyright, Designs and Patents Act 1988 allows the making of a single copy solely for the purpose of non-commercial research or private study within the limits of fair dealing. The publisher or other rights-holder may allow further reproduction and re-use of this version -refer to the White Rose Research Online record for this item. Where records identify the publisher as the copyright holder, users can verify any specific terms of use on the publisher's website. TakedownIf you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing eprints@whiterose.ac.uk including the URL of the record and the reason for the withdrawal request. Abstract This paper reviews the present understanding of electrolytic plasma processes (EPPs) and approaches to their modelling. Based on the EPP type, characteristics and classification, it presents a generalised phenomenological model as the most appropriate one from the process diagnostics and control point of view. The model describes the system 'power supply -electrolyser -electrode surface' as a system with lumped parameters characterising integral properties of the surface layer and integral parameters of the EPP. The complexity of EPPs does not allow the drawing of a set of differential equations describing the treatment, although a model can be formalised for a particular process as a black box regression. Evaluation of dynamic properties reveals the multiscale nature of electrolytic plasma processes, which can be described by three time constants separated by 2-3 orders of magnitude (minutes, seconds and milliseconds), corresponding to different groups of characteristics in the model. Further developments based on the phenomenological approach and providing deeper insights into EPPs are proposed using frequency response methodology and electromagnetic field modelling. Examples demonstrating the efficiency of the proposed approach are supplied for EPP modelling with static and dynamic neural networks, frequency response evaluations and electromagnetic field calculations.

show abstract

mentioning

confidence: 99%

Towards smart electrolytic plasma technologies: An overview of methodological approaches to process modelling

Парфенов

Yerokhin

Nev’yantseva

et al. 2015

Surface and Coatings Technology

156

View full text Add to dashboard Cite

show abstract

“…In addition, metrology information in the form of mean film thickness was available for each wafer (100% metrology information), allowing a deep and comprehensive VM study 8 For more information about the feature extraction process, see [44]- [45] Additionally, we wanted to explore if the quality characteristics of the currently processed wafer depend not only on the equipment signatures observed during its production, but also on the equipment signatures observed during the production of several recent wafers. In order to include such dynamic dependencies into the VM modeling, the aforementioned features obtained from wafers up to 25 cycles before the wafer whose metrology is estimated (26 wafers, including the current wafer) were included into the set of potential inputs for the VM model, yielding 1274 possible VM inputs 9 .…”

Section: Description Of the Tool Under Studymentioning

confidence: 99%

Growing Structure Multiple Model System for Quality Estimation in Manufacturing Processes

Bleakie

Djurdjanović

2016

IEEE Trans. Semicond. Manufact.

Self Cite

View full text Add to dashboard Cite

A new Virtual Metrology (VM) method for estimation of product quality characteristics will be presented using the recently introduced Growing Structure Multiple Model System (GSMMS) approach for modeling of non-linear dynamic systems. The underlying concept of local linear models enables representation of non-linear dependencies with non-Gaussian and non-stationary noise characteristics. In addition, localized analysis of VM inputs within the GSMMS framework enables detection of situations when the model is not adequate and needs to be improved. The newly proposed method was applied to an extensive dataset gathered from a plasma enhanced chemical vapor deposition tool operating in a major semiconductor manufacturing fab, with tool signatures being used to predict the mean film thicknesses on the wafers. The GSMMS based VM significantly decreased the number of measurements necessary for prediction, while improving VM accuracy, as compared to several linear and nonlinear benchmark VM methodologies. These beneficial results are credited to the GSMMS being able to store local models within its growing network of local VM models corresponding to various operating regimes of the underlying manufacturing machine, as well as to recognize situations when new physical measurements need to be taken and when new local VM models need to be added.Keywords: Virtual Metrology, nonlinear dynamic systems modeling, divide and conquer modeling of dynamic systems 0894-6507 (c)

show abstract

“…[39] and [41]. Further referencing [49], Table IV presents statistical sensory features that will be derived in this work. The use of these statistical sensory features in the prior photolithography VM works is also noted.…”

Section: A Descriptive Statistics For Process Representativesmentioning

confidence: 99%

A Realizable Overlay Virtual Metrology System in Semiconductor Manufacturing: Proposal, Challenges and Future Perspective

Tin

Tan

Yong³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Integrated circuits (IC) are fabricated on a wafer through stacked layers of circuit patterns. To ensure proper functionality, the overlay of each pattern layer must be within the tolerance. Inspecting each wafer's overlay is unrealistic and impractical. Hence, wafers are selectively inspected at metrology stations through sampling strategies. With virtual metrology (VM), the metrology quality of the uninspected wafers can be estimated. Motivated by a real-world production environment of a 200mm semiconductor manufacturing plant (fab), a VM to estimate the overlay of the photolithography process is envisioned. Past researches on overlay VM leveraged fault detection and classification (FDC) data to estimate the overlay errors. As such, for fabs in the progress of completing their FDC development for photolithography equipment, a different modeling approach is required to realize an overlay VM that sustains the production line until FDC data can be leveraged for VM. With practical gaps that must be addressed in real fabs, this paper focuses on realizing an overlay VM for the photolithography process without leveraging FDC data. Therefore, the objectives of this paper are two folds: First, to identify the research challenges towards realizing the overlay VM. Second, to propose the future research perspectives of the envisioned overlay VM. Based on the future research perspectives, a two-steps overlay VM modeling approach utilizing data mining techniques is proposed toward realizing the envisioned overlay VM system. The proposed approach first classifies the process stability at the wafer lot level, and subsequently, performs overlay error estimations for wafers in the wafer lots classified with stable process. Linear regression models are proposed to perform overlay error estimations in this work to augment the interpretability of the overlay VM.

show abstract

Feature extraction, condition monitoring, and fault modeling in semiconductor manufacturing systems

Cited by 34 publications

References 5 publications

Towards smart electrolytic plasma technologies: An overview of methodological approaches to process modelling

Towards smart electrolytic plasma technologies: An overview of methodological approaches to process modelling

Growing Structure Multiple Model System for Quality Estimation in Manufacturing Processes

A Realizable Overlay Virtual Metrology System in Semiconductor Manufacturing: Proposal, Challenges and Future Perspective

Contact Info

Product

Resources

About