Quality Prediction in Semiconductor Manufacturing processes Using Multilayer Perceptron Feedforward Artificial Neural Network

Al-Kharaz, Mohammed; Ananou, Bouchra; Ouladsine, Mustapha; Combal, Michel; Pinaton, Jacques

doi:10.1109/icsc47195.2019.8950664

Cited by 8 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As opposed to the process-oriented approach, analysis in the product-oriented ZDM approach begins on the product level. For instance, Al-Kharaz et al (2019) created a multilayer perceptron feed-forward artificial neural network for semi-conductor manufacturing processes to anticipate and enhance product quality [56]. In a tubing extrusion process, Garcia et al (2018) suggest models that accurately forecast product quality [57].…”

Section: Product-oriented and Process-oriented Zdmmentioning

confidence: 99%

A Systematic Analysis for Mapping Product-Oriented and Process-Oriented Zero-Defect Manufacturing (ZDM) in the Industry 4.0 Era

Psarommatis

May

2023

Sustainability

View full text Add to dashboard Cite

Quality is a key aspect in the era of Industry 4.0. Zero-defect manufacturing (ZDM) as the latest quality assurance approach. It can be implemented in two different approaches: the product-oriented and the process-oriented ZDM. It is important to know how and when to consider adopting one approach over the other. To achieve that there is the need for analyzing the differences of the two ZDM approaches. However, the current literature lacks a detailed analysis and comparison of these two approaches to ZDM implementation. Earlier studies on the topic have adopted one of these approaches over the other without evaluating how it fits with specific cases. The literature of the last decade indicates a movement towards product-oriented approaches, but it has not shown proof why product oriented was used over process oriented. Guided by these gaps, this research work creates a model for quantifying the effects of the implementation of both the product-oriented and process-oriented ZDM approaches. The proposed model considers all the critical parameters that affect the problem and serves as an assisting tool to engineers during the design or re-configure manufacturing systems, for choosing the most efficient ZDM approach for their specific cases. The robustness of the model was analyzed using the design of experiments method. The results from both the designed experiments and an industrial use case illustrate that in most cases, product-oriented ZDM performs better than the process-oriented approach. Nevertheless, in our analysis, we also highlight strong interactions between some factors that make the selection between product-oriented and process-oriented ZDM difficult and complex.

show abstract

Section: Product-oriented and Process-oriented Zdmmentioning

confidence: 99%

A Systematic Analysis for Mapping Product-Oriented and Process-Oriented Zero-Defect Manufacturing (ZDM) in the Industry 4.0 Era

Psarommatis

May

2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…This is the most traditionally used practical neural network and is named after its hierarchical structure. MLP is also recognized as a feed-forward neural network, which is broadly used in some prominent research related to real-world classification problems and computer vision mostly [44], [45], [46], [47], [48]. MLP is also widely applied in the semiconductor industry like the quality prediction in semiconductor manufacturing [49], extraction of device parameters [50], the self-heating effect of MOSFET [51], and so on.…”

Section: A Multi-layer Perceptrons (Mlp)mentioning

confidence: 99%

A Hybrid 1D-CNN-LSTM Technique for WKF-Induced Variability of Multi-Channel GAA NS- and NF-FETs

Dash

Sung

2023

IEEE Access

View full text Add to dashboard Cite

Presently deep learning (DL) techniques are massively used in the semiconductor industry. At the same time, applying a deep learning approach for small datasets is also an immense challenge as larger dataset generation needs more computational time-cost factors for technology computer-aided design (TCAD) simulation. In this paper, to overcome the aforesaid issue, a hybrid DL-aided prediction of electrical characteristics of the multichannel devices induced by work function fluctuation (WKF) with a smaller dataset is proposed. For the first time, an amalgamation approach of two deep learning algorithms (i.e.1D-CNN and LSTM) is implemented for all four channels (1 to 4 channels) of gate-all-around (GAA) silicon Nanosheet and Nanofin MOSFETs (NS-FETs and NF-FETs). The proposed joint learning framework combines a one-dimensional convolutional neural network (1D-CNN) with long short-term memory (LSTM) model. In this architecture, CNN can extract the features efficiently from the input WKF, and LSTM identifies the historical sequence of the captured features of the input regression data. To illustrate the excellency of the proposed approach, a comparative study of our hybrid model along with three individual DL models i.e. 1D-CNN and LSTM including a baseline multilevel perceptron (MLP) model are demonstrated for a promising small dataset (i.e.1100 samples). The results indicate a superior prediction of 1D-CNN-LSTM in terms of root mean square error (RMSE) with an average value of 1.7943 X10 −7 and R 2 Score with an average value of 96.18% within the shortest time span in contrast to the other three algorithms. Finally, it can be quantified according to the evaluation and performance that hybrid methodology not only adopts the complexity of both NS-and NF-FETs, but also estimates the characteristics of all four channels of it efficiently with a smaller dataset, lesser time span, and reduced computational cost.

show abstract

“…Alagic et al [5] proposed an approach combining image processing and statistical modeling to quantify and predict the damage intensity in SAM images. Kharaz et al [4] applied Artificial Neural Network (ANN) to reveal the relationship between semiconductor products end quality state and processes alarm events. Kim et al [37] used an ensemble of ordinary least squares (OLS) regression and ridge regression to consider the wafer-level and field-level overlay error signatures.…”

Section: Figure 1 Stages Of Semiconductor Manufacturingmentioning

confidence: 99%

A novel quality prediction method based on feature selection considering high dimensional product quality data

Hu¹,

Qian²,

Pei³

et al. 2022

JIMO

View full text Add to dashboard Cite

Product quality is the lifeline of enterprise survival and development. With the rapid development of information technology, the semiconductor manufacturing process produces multitude of quality features. Due to the increasing quality features, the requirement on the training time and classification accuracy of quality prediction methods becomes increasingly higher. Aiming at realizing the quality prediction for semiconductor manufacturing process, this paper proposes a modified support vector machine (SVM) model based on feature selection, considering the high dimensional and nonlinear characteristics of data. The model first improves the Radial Basis Function (RBF) in SVM, and then combines the Duelist algorithm (DA) and variable neighborhood search algorithm (VNS) for feature selection and parameters optimization. Compared with some other SVM models that are based on DA, genetic algorithm (GA), and Information Gain algorithm (IG), the experiment results show that our DA-VNS-SVM can obtain higher classification accuracy rate with a smaller feature subset. In addition, we compare the DA-VNS-SVM with some common machine learning algorithms such as logistic regression, naive Bayes, decision tree, random forest, and artificial neural network. The results indicate that our model outperform these machine learning algorithms for the quality prediction of semiconductor.

show abstract

Quality Prediction in Semiconductor Manufacturing processes Using Multilayer Perceptron Feedforward Artificial Neural Network

Cited by 8 publications

References 20 publications

A Systematic Analysis for Mapping Product-Oriented and Process-Oriented Zero-Defect Manufacturing (ZDM) in the Industry 4.0 Era

A Systematic Analysis for Mapping Product-Oriented and Process-Oriented Zero-Defect Manufacturing (ZDM) in the Industry 4.0 Era

A Hybrid 1D-CNN-LSTM Technique for WKF-Induced Variability of Multi-Channel GAA NS- and NF-FETs

A novel quality prediction method based on feature selection considering high dimensional product quality data

Contact Info

Product

Resources

About