A Convolutional Neural Network for Fault Classification and Diagnosis in Semiconductor Manufacturing Processes
The DOI matches its Crossref record; 12 of the 13 references it cites were found in a registry or an index.
Abstract
Many studies on the prediction of manufacturing results using sensor signals have been conducted in the field of fault detection and classification (FDC) for semiconductor manufacturing processes. However, fault diagnosis used to find clues as to root causes remains a challenging area. In particular, process monitoring using neural networks has been employed to only a limited extent because it is a black box model, making the relationships between input data and output results difficult to interpret in actual manufacturing settings, despite its high classification performance. In this paper, we propose a convolutional neural network (CNN) model, named FDC-CNN, in which a receptive field tailored to multivariate sensor signals slides along the time axis, to extract fault features. This approach enables the association of the output of the first convolutional layer with the structural meaning of the raw data, making it possible to locate the variable and time information that represents process faults. In an experiment on a chemical vapor deposition process, the proposed method outperformed other deep learning models.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In the actual fabrication process, discrepancies between the actual and the design values may occur due to process errors [24].”
From High-Efficiency Polarization-Independent LCoS Utilizing a Silicon-Based Metasurface (2025) · cites this paper as [24]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 2×
“CNN is a deep learning model [5] evolved from artificial neural networks (ANNs), a type of machine learning algo-”
Background(2014) · Cited by 33,419
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570 · cited 1×
“As a result of dedicated efforts to improve weight learning methods of ANNs, critical low-performance problems were solved in the 2000s, caused by gradient vanishing occurring when the number of hidden layers increases, overfitting, and computing power constraints [6].”
BackgroundLearning Deconvolution Network for Semantic Segmentation
Noh, H., Hong, S., & Han, B. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.178 · Cited by 4,422 · cited 1×
“However, de-convolutional neural networks [13], which are being extensively studied in the field of image classification as a method for assigning pixel-wise class labels to raw image pixels using switch variables, can be applied to fault classification; information contained in deep convolutional…”
Method(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051 · cited 1×
“First, the working mechanism of a standard CNN, which underlies the proposed algorithm, is explained in detail, followed by a brief introduction of the stacked autoen-coder (SAE) and stacked denoising autoencoder (SdA) [10].”
MethodFault Detection and Diagnosis in Engineering Systems
Gertler, J. J. (2017) · CRC Press eBooks · doi:10.1201/9780203756126 · Cited by 1,999
The identification of multiple outliers
Davies, L., & Gather, U. (1993) · Journal of the American Statistical Association · doi:10.1080/01621459.1993.10476339 · Cited by 709 · cited 1×
“CLV is a variable selection measure based on the Hampel’s outlier detector [12].”
MethodTime Series Classification Using Multi-Channels Deep Convolutional Neural Networks
Zheng, Y., Liu, Q., Chen, E., Ge, Y., & Zhao, J. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-08010-9_33 · Cited by 652 · cited 1×
“[9] proposed a CNN application in which a multivariate time-series dataset is decomposed into univariate time-series data for each variable, and feature extraction was conducted for each variable in parallel, followed by a classification task with a multilayer perceptron (MLP) with the extracted features.”
MethodGearbox Fault Identification and Classification with Convolutional Neural Networks
Chen, Z., Li, C., & Sanchez, R.-V. (2015) · Shock and Vibration · doi:10.1155/2015/390134 · Cited by 391 · cited 1×
“[8] conducted a fault pattern diagnosis of gearboxes using the statistical measures and spectral information collected from time and frequency domains as the CNN input data.”
MethodFault detection and diagnosis in process data using one-class support vector machines
Mahadevan, S., & Shah, S. L. (2009) · Journal of Process Control · doi:10.1016/j.jprocont.2009.07.011 · Cited by 368 · cited 1×
“Among them, Mahadevan and Shah [4] detected abnormal process behaviors in the semiconductor etching process using a one-class SVM.”
Method
Research works printed but not linked: 1
- lee, 2016, Convolutional neural net and bearing fault analysis, Proc Int Conf Data Min, 194
Cited by
1D convolutional neural networks and applications: A survey
Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., & Inman, D. J. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2020.107398 · Cited by 2,835
Deep learning and its applications to machine health monitoring
Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., & Gao, R. X. (2019) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.05.050 · Cited by 2,894
Guo, L., Lei, Y., Xing, S., Yan, T., & Li, N. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2877090 · Cited by 1,234
“[6] built a convolutional neural network (CNN) to recognize the health conditions of machines.”
BackgroundConceptual Understanding of Convolutional Neural Network- A Deep Learning Approach
Indolia, S., Goswami, A. K., Mishra, S. P., & Asopa, P. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.05.069 · Cited by 748
Machine learning and data mining in manufacturing
Dogan, A., & Birant, D. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114060 · Cited by 677
Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines
Choi, K., Yi, J., Park, C., & Yoon, S. (2021) · IEEE Access · doi:10.1109/access.2021.3107975 · Cited by 588
“CNN-based fault detection and diagnosis models showed their competence in handling multivariate time-series data captured from semiconductor manufacturing processes in [33]–[35].”
BackgroundJia, F., Lei, Y., Lu, N., & Xing, S. (2018) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.03.025 · Cited by 587
Long short-term memory for machine remaining life prediction
Zhang, J., Wang, P., Yan, R., & Gao, R. X. (2018) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2018.05.011 · Cited by 463
Jalayer, M., Orsenigo, C., & Vercellis, C. (2021) · Computers in Industry · doi:10.1016/j.compind.2020.103378 · Cited by 382
AI-based modeling and data-driven evaluation for smart manufacturing processes
Ghahramani, M., Qiao, Y., Zhou, M. C., O'Hagan, A., & Sweeney, J. (2020) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2020.1003114 · Cited by 334
Xu, G., Liu, M., Jiang, Z., Söffker, D., & Shen, W. (2019) · Sensors · doi:10.3390/s19051088 · Cited by 311
Cheon, S., Lee, H., Kim, C. O., & Lee, S. H. (2019) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2019.2902657 · Cited by 304
“[9] modi-”
Self-citationA Review on Fault Detection and Process Diagnostics in Industrial Processes
Park, Y.-J., Fan, S.-K. S., & Hsu, C.-Y. (2020) · Processes · doi:10.3390/pr8091123 · Cited by 277
“Thus, over the past three decades, various effective FDD techniques for semiconductor production processes have been studied [57,62,63,68].”
BackgroundMethodWang, S., Xiang, J., Zhong, Y., & Zhou, Y. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2017.12.027 · Cited by 269
Artificial intelligence-based smart quality inspection for manufacturing
Sundaram, S., & Zeid, A. (2023) · Micromachines · doi:10.3390/mi14030570 · Cited by 260
“[32] propose a CNN model that is receptive to time series data.”
BackgroundA Review on Deep Learning Applications in Prognostics and Health Management
Zhang, L., Lin, J., Liu, B., Zhang, Z., Yan, X., & Wei, M. (2019) · IEEE Access · doi:10.1109/access.2019.2950985 · Cited by 232
“Data-level methods use phase space embedding representation in which a sequence of data instances is generated via a fixed-length sliding window; see [145]–[148].”
MethodRecent Advances of Artificial Intelligence in Manufacturing Industrial Sectors: A Review
Kim, S. W., Kong, J. H., Lee, S. W., & Lee, S. (2022) · International Journal of Precision Engineering and Manufacturing · doi:10.1007/s12541-021-00600-3 · Cited by 193
“[86] Sensor signal (temperature, pressure, gas flow rate, etc.”
BackgroundMethodAnomaly Detection Using Autoencoders in High Performance Computing Systems
Borghesi, A., Bartolini, A., Lombardi, M., Milano, M., & Benini, L. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33019428 · Cited by 210
Deformable convolutional networks for efficient mixed-type wafer defect pattern recognition
Wang, J., Xu, C., Yang, Z., Zhang, J., & Li, X. (2020) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2020.3020985 · Cited by 229
“After the wafer manufacturing, wafer test is conducted to evaluate the electrical function of each die by probe test [2], which consists of many test items that measure the performance of the operations of required die electronic functions.”
MethodMachine Learning in Nanoscience: Big Data at Small Scales
Brown, K. A., Brittman, S., Maccaferri, N., Jariwala, D., & Celano, U. (2020) · Nano Letters · doi:10.1021/acs.nanolett.9b04090 · Cited by 229
“32 Rather than inspecting every location on a sample, a recent trend in semiconductor processing is virtual metrology (VM) in which a selection of wafers are sampled and used to train models that correlate process sensor data to the performance metric of interest.”
MethodRoadmap on multiscale materials modeling
van der Giessen, E., Schultz, P. A., Bertin, N., Bulatov, V. V., Cai, W., Csányi, G., Foiles, S. M., Geers, M. G. D., González, C., Hütter, M., et al. (2020) · Modelling and Simulation in Materials Science and Engineering · doi:10.1088/1361-651x/ab7150 · Cited by 210
“Thus, deep learning and artificial intelligence algorithms can be used to solve the inverse problem to determine on-the-fly the actions to minimize defects during processing [122, 123].”
An, Y., Zhang, K., Chai, Y., Liu, Q., & Huang, X. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118802 · Cited by 206
Saqlain, M., Abbas, Q., & Lee, J. Y. (2020) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2020.2994357 · Cited by 211
“Recently, many studies have been conducted that used CNN models to classify wafer defect patterns from the original WM images [9].”
BackgroundChallenges and opportunities of deep learning-based process fault detection and diagnosis: a review
Yu, J., & Zhang, Y. (2023) · Neural Computing and Applications · doi:10.1007/s00521-022-08017-3 · Cited by 190
“(2) It needs to be trained with sufficient labeled samples TEP [170, 172, 181–184, 186, 187], FBFP [170, 182], CSTR [172], chemical processes [177], multivariable process [179], semiconductor manufacturing process [178, 180, 185]”
BackgroundMethodQian, Q., Qin, Y., Wang, Y., & Liu, F. (2021) · Measurement · doi:10.1016/j.measurement.2021.109352 · Cited by 206
Jiao, Z., Hu, P., Xu, H., & Wang, Q. (2020) · ACS Chemical Health & Safety · doi:10.1021/acs.chas.0c00075 · Cited by 198
Data-Driven Approach for Fault Detection and Diagnostic in Semiconductor Manufacturing
Fan, S.-K. S., Hsu, C.-Y., Tsai, D.-M., He, F., & Cheng, C.-C. (2020) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.2983061 · Cited by 193
“network [58], and hybrid machine learning methods [9] were also applied for fault detection in semiconductor manufacturing.”
MethodHsu, C.-Y., & Liu, W. (2020) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-020-01591-0 · Cited by 184
“In addition, fault diagnosis is to identify excursion and to provide critical information for analyzing root cause of abnormality (Gertler 1998; Chien et al. 2013; Lee et al. 2017b).”
BackgroundMethodInfluentialZheng, S., & Zhao, J. (2020) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2020.106755 · Cited by 160
Evaluation of turned and milled surfaces roughness using convolutional neural network
Rifai, A. P., Aoyama, H., Tho, N. H., Dawal, S. Z. M., & Masruroh, N. A. (2020) · Measurement · doi:10.1016/j.measurement.2020.107860 · Cited by 159
Qiao, H., Wang, T., Wang, P., Qiao, S.-B., & Zhang, L. (2018) · Sensors · doi:10.3390/s18092932 · Cited by 155
“addressed a CNN model for fault classification and diagnosis in semiconductor manufacturing processes with multivariate time-series data as the input [29].”
MethodFault detection and identification using Bayesian recurrent neural networks
Sun, W., Paiva, A. R. C., Xu, P., Sundaram, A., & Braatz, R. D. (2020) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2020.106991 · Cited by 165
A Deep Supervised Learning Framework for Data-Driven Soft Sensor Modeling of Industrial Processes
Yuan, X., Gu, Y., Wang, Y., Yang, C., & Gui, W. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2957366 · Cited by 151
“long short-term memory (LSTM) [30], convolutional NN (CNN) [31], and stacked autoencoder (SAE) [32] are some”
BackgroundWang, J., Yang, Z., Zhang, J., Zhang, Q., & Chien, W.-T. K. (2019) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2019.2925361 · Cited by 154
“After the wafer fabrication, wafer test is conducted to evaluate the electrical function of each die [4].”
MethodObstructive sleep apnoea detection using convolutional neural network based deep learning framework
Dey, D., Chaudhuri, S., & Munshi, S. (2017) · Biomedical Engineering Letters · doi:10.1007/s13534-017-0055-y · Cited by 145
“Details of the CNN structures can be found in different sources [11, 12].”
BackgroundA Neural Adaptive Approach for Active Fault-Tolerant Control Design in UAV
Abbaspour, A., Yen, K. K., Forouzannezhad, P., & Sargolzaei, A. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2850701 · Cited by 138
“Unlike the direct ANN modeling procedures that use an ANN to simulate the system behavior [27], [38], the NNAS detects faults based on the output of the nonlinear observer”
MethodSoft sensor model for dynamic processes based on multichannel convolutional neural network
Yuan, X., Qi, S., Shardt, Y. A. W., Wang, Y., Yang, C., & Gui, W. (2020) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2020.104050 · Cited by 138
Transfer Relation Network for Fault Diagnosis of Rotating Machinery With Small Data
Lü, N., Hu, H., Yin, T., Lei, Y., & Wang, S. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3085476 · Cited by 141
“[34] developed a CNN for fault diagnosis in semiconductor manufacturing processes, which tailored a receptive field to extract fault features of multivariate sensor signals.”
BackgroundDynamic Soft Sensor Development Based on Convolutional Neural Networks
Wang, K., Shang, C., Liu, L., Jiang, Y., Huang, D., & Yang, F. (2019) · Industrial & Engineering Chemistry Research · doi:10.1021/acs.iecr.9b02513 · Cited by 128
Geng, Z., Zhang, Y., Li, C., Han, Y. M., Cui, Y., & Yu, B. (2019) · Energy · doi:10.1016/j.energy.2019.116851 · Cited by 130
A Review on Data‐Driven Learning Approaches for Fault Detection and Diagnosis in Chemical Processes
Taqvi, S. A. A., Zabiri, H. B., Tufa, L. D., Uddin, F., Fatima, S. A., & Maulud, A. S. (2021) · ChemBioEng Reviews · doi:10.1002/cben.202000027 · Cited by 134
Jiang, Q., Yan, S., Cheng, H., & Yan, X. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2985223 · Cited by 125
Fault Diagnosis System for Induction Motors by CNN Using Empirical Wavelet Transform
Hsueh, Y.-M., Ittangihala, V. R., Wu, W., Chang, H., & Kuo, C. (2019) · Symmetry · doi:10.3390/sym11101212 · Cited by 134
“The convolutional neural network (CNN), known as one of the proven deep learning models, has delivered promising results in learning useful features [14,19].”
BackgroundKuang, J., Xu, G., Tao, T., & Wu, Q. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3136175 · Cited by 143
Bai, M., Yang, X., Liu, J., Liu, J., & Yu, D. (2021) · Applied Energy · doi:10.1016/j.apenergy.2021.117509 · Cited by 117
Lee, J., Lee, Y. C., & Kim, J. T. (2020) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2020.10.013 · Cited by 117
Stacked Enhanced Auto-Encoder for Data-Driven Soft Sensing of Quality Variable
Yuan, X., Qi, S., & Wang, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2985614 · Cited by 110
“By far, many DL models like stacked auto-encoder (SAE) [31], deep belief network (DBN) [32], convolutional neural network (CNN) [33], and long short-term memory”
BackgroundDuan, A., Guo, L., Gao, H., Xiang-dong, W., & Dong, X. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2998233 · Cited by 107
“Thus, several studies have applied CNN to machinery fault diagnostics [15]–[19].”
BackgroundTime-series pattern recognition in Smart Manufacturing Systems: A literature review and ontology
Farahani, M. A., McCormick, M. R., Gianinny, R., Hudacheck, F., Harik, R., Liu, Z., & Wuest, T. (2023) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2023.05.025 · Cited by 117
“1D-CNN (3) [154] [159] [152] Residual Neural Network (ResNet) (2) [145] [155] HHO-ConvNet (1) [39] FDC-CNN Model (1) [74] Explainable DCNN (1) [40]”
Mechanical Properties Prediction for Hot Rolled Alloy Steel Using Convolutional Neural Network
Xu, Z., Liu, X., & Zhang, K. (2019) · IEEE Access · doi:10.1109/access.2019.2909586 · Cited by 105
“Actually, CNN-based approaches have not only made tremendous progress in the image recognition [16] and the activity recognition fields [17], but also become the research hotspot in the fields of fault detection [18], financial forecasting [19], energy environmental protection [20], medical disease prediction [21], tr…”
BackgroundYu, J., & Yan, X. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2948202 · Cited by 100
“[22] proposed a method called FDCCNN based on the CNN for fault classification and diagnosis in semiconductor manufacturing processes.”
MethodQin, Y., Qian, Q., Luo, J., & Pu, H. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3162957 · Cited by 107
“[9] utilized CNN to achieve end-to-end fault detection of chemical vapor deposition.”
MethodPaturi, U. M. R., Cheruku, S., & Reddy, N. S. (2022) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-021-09691-7 · Cited by 98
“Max pooling and average pooling are the two main pooling techniques used for decreasing the map size significantly [73].”
MethodYu, J., Zheng, X., & Liu, J. (2019) · Computers in Industry · doi:10.1016/j.compind.2019.04.015 · Cited by 105
Stacked isomorphic autoencoder based soft analyzer and its application to sulfur recovery unit
Yuan, X., Wang, Y., Yang, C., & Gui, W. (2020) · Information Sciences · doi:10.1016/j.ins.2020.03.018 · Cited by 96
LDA-based deep transfer learning for fault diagnosis in industrial chemical processes
Wang, Y., Wu, D., & Yuan, X. (2020) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2020.106964 · Cited by 97
Replicating a Trading Strategy by Means of LSTM for Financial Industry Applications
Troiano, L., Mejuto-Villa, E., & Loia, V. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2811377 · Cited by 102
“Architectures and models have been investigated in the past two decades, but availability of GPU computing enabled DL industrial applications such as automotive [1], control systems [2], fault detection and recovery [3], [4] and biomedicine [5], [6], just to mention some.”
BackgroundKnowledge-informed deep networks for robust fault diagnosis of rolling bearings
Su, Y., Shi, L., Zhou, K., Bai, G., & Wang, Z. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109863 · Cited by 93
Eang, C., & Lee, S. (2024) · Sensors · doi:10.3390/s25010025 · Cited by 99
Kim, E., Cho, S., Lee, B., & Cho, M. (2019) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2019.2917521 · Cited by 91
“[4] and Kim [8] used a convolution that sweeps the sequence only along the time axis with receptive fields of size D × F like:”
BackgroundMethodInfluentialFault diagnosis of multi-channel data by the CNN with the multilinear principal component analysis
Guo, Y., Zhou, Y., & Zhang, Z. (2020) · Measurement · doi:10.1016/j.measurement.2020.108513 · Cited by 91
Yu, J., Liu, X., & Ye, L. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3039614 · Cited by 117
Piccialli, F., Giampaolo, F., Prezioso, E., Camacho, D., & Acampora, G. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.03.004 · Cited by 108
Deep Learning-Based Domain Adaptation Method for Fault Diagnosis in Semiconductor Manufacturing
Azamfar, M., Li, X., & Lee, J. (2020) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2020.2995548 · Cited by 93
“[29] proposed using time series signal directly in a CNN model for electric motor fault diagnosis and using time series signal in a CNN architecture and for fault diagnosis in semiconductor manufacturing was proposed in [30].”
BackgroundMethodYu, J., & Zhang, C. (2020) · Journal of Process Control · doi:10.1016/j.jprocont.2020.06.001 · Cited by 89
Siddique, F., Sakib, S., & Siddique, M. A. B. (2019) · International Conference on Advances in Electrical Engineering · doi:10.1109/icaee48663.2019.8975496 · Cited by 105
“Even, in nano-technologies like manufacturing semiconductors, CNN is used for fault detection and classification [13].”
MethodInterpretable and Accurate Convolutional Neural Networks for Human Activity Recognition
Kim, E. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2972628 · Cited by 84
“,W (M) with the same size as the matrix to take into account the correlation among all signals at once [28], [29].”
BackgroundChen, Z., Wu, J., Deng, C., Wang, C., & Wang, Y. (2021) · Mechanism and Machine Theory · doi:10.1016/j.mechmachtheory.2021.104635 · Cited by 86
Taeyoung, K., & Kim, H. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2941486 · Cited by 83
“classification and segmentation [17], and have also recently been applied to industrial problems [18], [19].”
BackgroundBridging TCAD and AI: Its Application to Semiconductor Design
Jeong, C., Myung, S., Huh, I., Choi, B., Kim, J., Jang, H., Lee, H., Park, D., Lee, K., Jang, W., et al. (2021) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2021.3093844 · Cited by 85
Self-citationFarahani, M. A., McCormick, M. R., Harik, R., & Wuest, T. (2024) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2024.102839 · Cited by 93
“CNN[54], Time-CNN[19], FDC-CNN[56], Fully Convolutional Networks (FCN)[53], t-LeNet[19], HHOConvNet[57], 1DCNN[58,59], Encoder[19], MCDCNN[19], Multiple Time-Series Convolutional Neural Network (MTS-CNN)[20], MCNN[19], Dilated CNN[60], ResNet[23,53], Temporal Convolutional Networks (TCN)[61], InceptionTime[62], Incept…”
MethodDeep‐learning–based method for faults classification of PV system
Zaki, S. A., Zhu, H., Fakih, M. A., Sayed, A. R., & Yao, J. (2021) · IET Renewable Power Generation · doi:10.1049/rpg2.12016 · Cited by 81
“The one-dimensional CNN, which is used in this study, consists of two consecutive steps [26] as illustrated in Figure 7:”
MethodSchlosser, T., Friedrich, M., Beuth, F., & Kowerko, D. (2022) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-021-01906-9 · Cited by 88
“For this purpose, an important quality property is calculated based on the ratio of flawless to total chips, also called yield (Lee et al. 2017).”
BackgroundMethodAjagekar, A., & You, F. (2020) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2020.107119 · Cited by 85
Yu, J., Zhang, C., & Wang, S. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05171-4 · Cited by 80
Park, S.-Y., & Ahn, J. (2020) · Acta Astronautica · doi:10.1016/j.actaastro.2020.08.019 · Cited by 80
Fault Detection for Motor Drive Control System of Industrial Robots Using CNN-LSTM-based Observers
Wang, T., Zhang, L., & Wang, X. (2023) · CES Transactions on Electrical Machines and Systems · doi:10.30941/cestems.2023.00014 · Cited by 83
Defective wafer detection using a denoising autoencoder for semiconductor manufacturing processes
Fan, S. S., Hsu, C.-Y., Jen, C., Chen, K.-L., & Juan, L.-T. (2020) · Advanced Engineering Informatics · doi:10.1016/j.aei.2020.101166 · Cited by 91
Knaak, C., von Eßen, J., Kröger, M., Schulze, F., Abels, P., & Gillner, A. (2021) · Sensors · doi:10.3390/s21124205 · Cited by 73
“Convolutional Neural Network + Gated Recurrent Units (CNN-GRU) Activation: The activation function for convolution and fully connected layer conv_1_depth: The number of output filters in the first convolutional layer conv_2_depth: The number of output filters in the 2nd convolutional layer GRU_units: Number of units i…”
BackgroundDey, D., Chatterjee, B., Dalai, S., Munshi, S., & Chakravorti, S. (2017) · IEEE Transactions on Dielectrics and Electrical Insulation · doi:10.1109/tdei.2017.006793 · Cited by 73
Lee, K. B., & Kim, C. O. (2018) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-018-1437-4 · Cited by 74
Self-citationHan, Y. M., Fan, C., Xu, M., Geng, Z., & Zhong, Y. (2019) · Applied Thermal Engineering · doi:10.1016/j.applthermaleng.2019.114072 · Cited by 73
Active Learning of Convolutional Neural Network for Cost-Effective Wafer Map Pattern Classification
Shim, J., Kang, S., & Cho, S. (2020) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2020.2974867 · Cited by 76
“[9] used a CNN to extract useful features for fault detection.”
MethodKnaak, C., Masseling, L., Duong, E., Abels, P., & Gillner, A. (2021) · IEEE Access · doi:10.1109/access.2021.3067302 · Cited by 76
“The output of a convolutional layer can be denoted as follows [62]:”
MethodO'Leary, J., Sawlani, K., & Mesbah, A. (2020) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2019.2963656 · Cited by 76
“Neural networks for the classification of these patterns have also been investigated [11], [12], [13].”
BackgroundA new ensemble convolutional neural network with diversity regularization for fault diagnosis
Wen, L., Xie, X., Li, X., & Gao, L. (2020) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2020.12.002 · Cited by 70
Maggipinto, M., Terzi, M., Masiero, C., Beghi, A., & Susto, G. A. (2018) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2018.2849206 · Cited by 69
“In [16] and [17] DL solutions are proposed to deal with an ensemble of time series coming form various monitoring sensors.”
BackgroundMethodInfluentialMulti-Fault Bearing Classification Using Sensors and ConvNet-Based Transfer Learning Approach
Udmale, S. S., Singh, S. K., Singh, R., & Sangaiah, A. K. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2947026 · Cited by 69
“Finally, nonlinear activation function like ReLU is used on each element of fmap due to its decent performance [14], [16], [27] and it is given by”
BackgroundMethodInfluentialWu, Y., Liu, D., Yuan, X., & Wang, Y. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3025805 · Cited by 73
“For example, stack autoen-coders (SAE) [26], convolutional neural network (CNN) [27], deep belief network (DBN) [28], long-short-term memory network (LSTM) [29] and other popular deep learning models have made significant achievements in image processing, natural language processing, and other fields [30], [31].”
BackgroundMachine Learning-Based Detection Method for Wafer Test Induced Defects
Cheng, K. C.-C., Chen, L. L.-Y., Li, J., Li, K. S.-M., Tsai, N. C.-Y., Wang, S.-J., Huang, A. Y.-A., Chou, L., Lee, C.-S., Chen, J.-E., et al. (2021) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2021.3065405 · Cited by 68
“Other machine learning based classification methods have been proposed, including decision tree [5] and variations of convolutional neural networks (CNN) [6], [7], and [8].”
MethodRoadmap to semi-automatic generation of digital twins for brownfield process plants
Sierla, S., Azangoo, M., Rainio, K., Papakonstantinou, N., Fay, A., Honkamaa, P., & Vyatkin, V. (2021) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2021.100282 · Cited by 55
Zhu, X., Cai, Z., Wu, J., Cheng, Y., & Huang, Q. (2019) · Acta Astronautica · doi:10.1016/j.actaastro.2019.03.072 · Cited by 70
Mixed-Type Wafer Defect Recognition With Multi-Scale Information Fusion Transformer
Wei, Y., & Wang, H. (2022) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2022.3156583 · Cited by 67
Wong, S. Y., Choe, C. W. C., Goh, H. H., Low, Y. W., Cheah, D. Y. S., & Pang, C. (2021) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-021-05522-w · Cited by 66
“The second part that contains the fully connected layers and an output layer is responsible for the classification whereby the features are obtained from the last pooling layer [77].”
BackgroundInfluentialWu, D., Hu, M., Huang, Y., Zhang, P., & Yu, Z. (2021) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2021.04.007 · Cited by 68
Zhang, Y., & Yu, J. (2022) · Journal of Process Control · doi:10.1016/j.jprocont.2022.03.010 · Cited by 65
Manufacturing quality assessment in the industry 4.0 era: a review
Markatos, N. G., & Mousavi, A. (2023) · Total Quality Management & Business Excellence · doi:10.1080/14783363.2023.2194524 · Cited by 74
“ANN, Regression Trees, Ensembles of Adaboost decision stumps (Lee et al., 2017) CNN for Semiconductor Manufacturing Process Fault Classification and Diagnosis.”
MethodPredictive Maintenance in Industry 4.0
Sang, G. M., Xu, L., de Vrieze, P. T., Bai, Y., & Pan, F. (2020) · International Conference on Information Systems and Technologies (ICIST) · doi:10.1145/3447568.3448537 · Cited by 73
“With advanced technologies such as big data and cloud computing, neural networks have been widely used in machine learning models [19, 33, 34, 62].”
MethodZhu, J., Shi, H., Song, B., Tao, Y., & Tan, S. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3124578 · Cited by 68
“trial data, CNN can only consider partial variables, and which variables are considered are associated with the initial order of variables [23].”
Ribeiro, R. F., Areias, I. A. D. S., Campos, M. M., Teixeira, C. E., da Silva, L. E. B., & Gomes, G. F. (2022) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-022-00501-3 · Cited by 67
Metadata
- Authors
- Lee, K. B., Cheon, S., & Kim, C. O.
- Affiliations
- Yonsei University (KR)
- Venue
- IEEE Transactions on Semiconductor Manufacturing
- Published
- 2017-05
- Volume
- 30
- Issue
- 2
- Pages
- 135-142
- ISSN
- 0894-6507 (ISSN-L)
- 1558-2345
- OpenAlex
- W2594332903
- Cited by
- 483
- References
- 13
- Citations by year
- 2026: 25 · 2025: 32 · 2024: 60 · 2023: 61 · 2022: 71 · 2021: 82 · 2020: 80 · 2019: 45 · 2018: 22 · 2017: 5
- FWCI
- 26.11
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Semiconductor Manufacturing (publishedVersion)
- Funders
- Global Ph.D. Fellowship Program through the National Research Foundation of Korea (NRF) (NRF-2015H1A2A1031081)
- Technology Innovation Program (Development of Big Data-Based Analysis and Control Platform for Semiconductor Manufacturing Plants) through the Ministry of Trade, Industry and Energy, South Korea (10045913)
- NRF through the Ministry of Science, ICT and Future Planning, South Korea (NRF-2016R1A2B4008337)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Keywords
- semiconductor manufacturing, convolutional neural networks, chemical vapor deposition, process monitoring, fault feature extraction, root cause analysis, interpretability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.