A Convolutional Autoencoder Approach for Feature Extraction in Virtual Metrology

Maggipinto, Marco; Masiero, Chiara; Beghi, Alessandro; Susto, Gian Antonio

doi:10.1016/j.promfg.2018.10.023

Cited by 74 publications

(23 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, a CAE model learns the pattern of normal signal data. CAE is one of the most advanced algorithms in the field of time series anomaly detection [37] and can capture the pattern of high-dimensional time series data without manual feature engineering in advance [39]. Convolutional layers learn spatially invariant features and capture spatially local correlations.…”

Section: A Channelwise Reconstructionmentioning

confidence: 99%

Unsupervised Abnormal Sensor Signal Detection With Channelwise Reconstruction Errors

Kwak

Kim

2021

IEEE Access

View full text Add to dashboard Cite

Detecting an anomaly in multichannel signal data is a challenging task in various domains. It should take into account the cross-channel relationship and temporal relationship within each channel. Moreover, the signal data is high-dimensional and making it difficult to gather sufficient abnormal labels. Consequently, unsupervised reconstruction-based anomaly detection methods have been applied successfully in many studies. However, they lose valuable channel information inherent in the reconstruction errors by merely averaging the errors for both the channel and time, then consider the average value as an anomaly score. In this study, we propose a method to explicitly employ channelwise reconstruction errors as a feature to detect abnormal signals. After a convolutional autoencoder produces the channelwise reconstruction errors, a machine learning anomaly detection model aggregates the errors as an anomaly score. To demonstrate the effectiveness and applicability of the proposed model, we conduct experiments using simulated data and real-world automobile data. The results show that the proposed method remarkably enhances the detectability compared to the simple average of the reconstruction errors. The reconstruction errors of abnormal and normal channels are shown to be different; therefore, it can be considered as an appropriate feature for anomaly detection. The best performance is obtained by using local outlier factors in the following anomaly detection model.

show abstract

Section: A Channelwise Reconstructionmentioning

confidence: 99%

Unsupervised Abnormal Sensor Signal Detection With Channelwise Reconstruction Errors

Kwak

Kim

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…ere are many variants of the CNN architecture (Terzi et al, 2017;Lee and Kim, 2018;Maggipinto et al, 2018a;Tsutsui and Matsuzawa, 2019) for chemical processes in the literature, but the general structure of a CNN mainly comprises two parts. e rst part is used for feature extraction and is made up of convolution and sub-sampling layers arranged alternatively, which are then followed by an activation function and a batch normalization layer, altogether forming multi-layer convolving lters (Figure 1(a)).…”

Section: Preliminaries: Cnnmentioning

confidence: 99%

“…More importantly, they are tuned to extract appropriate features for making suitable regression models. However, the applications of deep structures in VM (Terzi et al, 2017;Lee and Kim, 2018;Maggipinto et al, 2018aMaggipinto et al, , 2018b) focus on single-stage data. Indeed, the integration of deep structures with VM applications for raw multi-stage process data is worthy of investigating.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks for Multi-Stage Semiconductor Processes

Chen

Xie

et al. 2021

J. Chem. Eng. Japan

View full text Add to dashboard Cite

In semiconductor manufacturing processes, there are certain quality measurements cannot be easily obtained at a low cost. In such cases, virtual metrology (VM) is typically used to predict the relevant quality variables without increasing the number of physical measurements. Faced with large volumes of raw data, the traditional data-driven VM methods adopt data pre-processing for feature extraction before modeling with a prede ned model. However, if the constructed model and the extracted features are not suitable, the identi ed VM model is generally not reliable. Moreover, almost no VM model has been proposed for multi-stage raw data. To improve the prediction performance of VM models, it is imperative that only suitable features are chosen and used in the modeling, especially for multi-stage raw process data. In this paper, we developed a convolutional neural network (CNN) based on the VM model for multi-stage raw semiconductor data. Owing to the intrinsic nature of CNN, the cascade-connected convolving lters and the regression part are trained together to provide appropriate features for the nal prediction. The construction of CNN makes it possible to reasonably extract information at each stage separately when processing multi-stage data. The proposed method is validated using real semiconductor process data and found to be superior to conventional methods with signi cantly improved accuracy.

show abstract

“…37,38 Convolutional DAEs that set hidden layers as convolutional layers receive increasing studies in feature extraction for image classification. 39,40 Actually, for time series, it has been demonstrated that the advantages of RNN over 1D CNN are largely absent in practice. 41 Therefore, 1D convolutional layers are utilized as the main hidden layers in DCDAE, where each convolutional layer is followed with a pooling layer.…”

Section: Dcdaementioning

confidence: 99%

Vibration-based damage detection for bridges by deep convolutional denoising autoencoder

Shang

Sun

Xia

et al. 2020

Structural Health Monitoring

View full text Add to dashboard Cite

One of the main challenges for structural damage detection using monitoring data is to acquire features that are sensitive to damages but insensitive to noise (e.g. sensor measurement noise) as well as environmental and operational effects (e.g. temperature effect). Inspired by the capabilities of deep learning methods in representation learning, various deep neural networks have been developed to obtain effective damage features from raw vibration data. However, most of the available deep neural networks are supervised, resulting in practical difficulties owing to the lack of damage labels. This article proposes a damage detection strategy based on an unsupervised deep neural network, referred to as deep convolutional denoising autoencoder, which accepts multi-dimensional cross-correlation functions as input. The strategy aims to extract damage features from field measurements of undamaged structures under the influence of noise and temperature uncertainties. In the proposed strategy, cross-correlation functions of vibration data are first calculated as basic features; then deep convolutional denoising autoencoder is developed to reconstruct cross-correlation functions from their noise-corrupted versions to extract desired features; exponentially weighted moving average control charts are finally established for these features to identify minor structural damages. The strategy is evaluated through a numerical simply supported beam model and an experimental continuous beam model. The mechanism of deep convolutional denoising autoencoder to extract damage features is interpreted by visualizing feature maps of convolutional layers in the encoder. It is found that these layers perform rough estimations of modal properties and preserve the damage information as the general trend of these properties in multiple extra frequency bands. The results show that the proposed strategy is competent for structural damage detection under the exposed environment and worth further exploring its capabilities in applications of real bridges.

show abstract

A Convolutional Autoencoder Approach for Feature Extraction in Virtual Metrology

Cited by 74 publications

References 22 publications

Unsupervised Abnormal Sensor Signal Detection With Channelwise Reconstruction Errors

Unsupervised Abnormal Sensor Signal Detection With Channelwise Reconstruction Errors

Convolutional Neural Networks for Multi-Stage Semiconductor Processes

Vibration-based damage detection for bridges by deep convolutional denoising autoencoder

Contact Info

Product

Resources

About