Integrating support vector machine and genetic algorithm to implement dynamic wafer quality prediction system

Chou, Pao-Hua; Wu, Menq-Jiun; Chen, Kuang-Ku

doi:10.1016/j.eswa.2009.11.087

Cited by 51 publications

(22 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[14] adopted a system using back propagation neural network for establishing a model for the etching process in semiconductor manufacturing. [7] compared the performance of the radial basis network and the back propagation neural network on the thin-film transistor liquid crystal display industry. The radial basis function network and the back propagation neural network produced quite similar results.…”

Section: Virtual Metrologymentioning

confidence: 99%

See 1 more Smart Citation

Classification algorithms for virtual metrology

Tilouche

Bassetto

Nia

2014

2014 IEEE International Conference on Management of Innovation and Technology

View full text Add to dashboard Cite

Virtual metrology in quality control deals with drifts in product quality that occur during non-sampling periods. This approach enables a hundred percent control and improves the precision of statistical control, specially while there is no sampling activity in manufacturing process. The main challenge in virtual metrology is inaccurate predictions. As such, the choice of an appropriate algorithm for prediction is crucial. We compare several algorithms that can be used for prediction in virtual metrology. The comparison over different prediction algorithms is made on a simulated data inspired from virtual metrology application.

show abstract

Section: Virtual Metrologymentioning

confidence: 99%

“…[7] reports that the support vector machines approach give a better prediction accuracy compared with the radial basis function network and also compared with the back-propagation approach, see also [1].…”

Section: Virtual Metrologymentioning

confidence: 99%

Classification algorithms for virtual metrology

Tilouche

Bassetto

Nia

2014

2014 IEEE International Conference on Management of Innovation and Technology

View full text Add to dashboard Cite

show abstract

“…On the other hand, the major issues related with neural networks for modeling of general non-linear dependencies, such as the choice of the network topology 2 , selection of the type of the activation functions, initialization of network parameters, as well as problems associated with extrapolation 3 and over fitting 4 , are inherited in the realm of neural networks based VM. The abovementioned drawbacks of linear regression models and neural networks motivated further research and recent introduction of GPR [15], SVR [17] and Kalman filter [27] based models into VM. GPR and SVR methods provide non-linear modeling frameworks with more 2 Number of nodes, their allocation into layers and connections between the nodes and layers.…”

Section: Introductionmentioning

confidence: 99%

“…The vast majority of work in VM focuses on increasing prediction accuracy using socalled global models 1 , which can be classified either as linear models, such as multivariate linear regression (MLR) [12], and partial least squares (PLS) regression [13], or non-linear models, such as back propagation (feed-forward) neural networks (BPNN) [12], [14], radial basis neural networks (RBNN) [12], [14], Gaussian process regression (GPR) [12], [15], and support vector regression (SVR) [12], [16], [17].…”

Section: Introductionmentioning

confidence: 99%

“…As for SVR, Chou et al[17] combine a genetic algorithm with the SVR to search for the best number of inputs and model parameters. They show better accuracy than both BPNN and RBNN on a CVD process, though it is acknowledged that retraining the SVR model and making predictions can be slower in the VM context.Additionally, Purwins et al[16] compare SVR with different linear regression models and show that SVR is more accurate and is more robust in adapting to process changes than all the models they benchmarked against.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Growing Structure Multiple Model System for Quality Estimation in Manufacturing Processes

Bleakie

Djurdjanović

2016

IEEE Trans. Semicond. Manufact.

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

A virtual metrology system based on least angle regression and statistical clustering

Susto

Beghi

2012

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

In semiconductor manufacturing plants, monitoring physical properties of all wafers is crucial to maintain good yield and high quality standards. However, such an approach is too costly, and in practice, only few wafers in a lot are actually monitored. Virtual metrology (VM) systems allow to partly overcome the lack of physical metrology. In a VM scheme, tool data are used to predict, for every wafer, metrology measurements. In this paper, we present a VM system for a chemical vapor deposition (CVD) process. On the basis of the available metrology results and of the knowledge, for every wafer, of equipment variables, it is possible to predict CVD thickness. In this work, we propose a VM module based on least angle regression to overcome the problem of high dimensionality and model interpretability. We also present a statistical distance-based clustering approach for the modeling of the whole tool production. The proposed VM models have been tested on industrial production data sets.

show abstract

Integrating support vector machine and genetic algorithm to implement dynamic wafer quality prediction system

Cited by 51 publications

References 28 publications

Classification algorithms for virtual metrology

Classification algorithms for virtual metrology

Growing Structure Multiple Model System for Quality Estimation in Manufacturing Processes

A virtual metrology system based on least angle regression and statistical clustering

Contact Info

Product

Resources

About