Wavelet integrated attention network with multi-resolution frequency learning for mixed-type wafer defect recognition

Wei, Yuxiang; Wang, Huan

doi:10.1016/j.engappai.2023.105975

Cited by 9 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The studies investigating MixedWM38 included a deformable convolutional network (DC-Net) [43]. DC-Net integrated positional information and displacement adjustment through a deformable convolutional kernel to improve CNN-based classification.…”

Section: A Deep Learning For Mixed-type Wafer Map Defect Classificationmentioning

confidence: 99%

“…A multi-scale information fusion transformer (MSF-Trans) with a multi-head selfattention mechanism assigns weights to feature values for an optimized feature set learning proposed in [44]. A multiresolution wavelet-integrated attention network (MRWA-Net) expands the learning of frequency components from the wavelet domain proposed in [45]. WaferSegClassNet (WSCN) is an end-to-end encoder-decoder-based defect segmentation network proposed in [46].…”

Section: A Deep Learning For Mixed-type Wafer Map Defect Classificationmentioning

confidence: 99%

“…Figure 5 presents the aggregated values of the tests. Table 3 presents A2CNN's accuracy, precision, and recall, along with comparisons to WSCN [46], MSF-Trans [44], and DC-Net [43]. A2CNN achieved an average classification accuracy of 98.66%, outperforming the other methods (98.34%, 97.17%, and 93.20%).…”

Section: Loss Functionmentioning

confidence: 99%

“…TEST SET RESULTS OF THE PROPOSED A2CNN AND A COMPARISON WITH WSCN[46], MSF-TRANS[44], AND DC-NET[43] …”

mentioning

confidence: 99%

See 3 more Smart Citations

An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification

Batool,

Shapiai,

Mostafa

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Silicon wafer defect classification is crucial in improving fabrication and chip production. While deep learning methods have been successful in single-defect wafer classification, the increasing complexity of the fabrication process has introduced the challenge of multiple defects on wafers, which requires more robust feature learning and classification techniques. Attention mechanisms have been used to enhance feature learning for multiple wafer defects. However, they have limited use in a few mixed-type defect categories, and their performance declines as the number of mixed patterns increases. This work proposes an attention-augmented convolutional neural networks (A2CNN) model for enhanced discriminative feature learning of complex defects. The A2CNN model emphasizes the features in the channel and spatial dimensions. Additionally, the model adopts the focal loss function to reduce misclassification and a global average pooling layer to enhance the network's generalization by reducing overfitting. The A2CNN model is evaluated on the MixedWM38 wafer defect dataset using 10-fold cross-validation. It achieves impressive results, with accuracy, precision, recall, and F1-score reported as 98.66%, 99.0%, 98.55%, and 98.82% respectively. Compared to existing works, the A2CNN model performs better by effectively learning valuable information for complex mixed-type wafer defects.

show abstract

Section: A Deep Learning For Mixed-type Wafer Map Defect Classificationmentioning

confidence: 99%

Section: A Deep Learning For Mixed-type Wafer Map Defect Classificationmentioning

confidence: 99%

Section: Loss Functionmentioning

confidence: 99%

“…TEST SET RESULTS OF THE PROPOSED A2CNN AND A COMPARISON WITH WSCN[46], MSF-TRANS[44], AND DC-NET[43] …”

mentioning

confidence: 99%

See 2 more Smart Citations

An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification

Batool,

Shapiai,

Mostafa

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Wang et al [12] initially built the DWT-layer, and then alternatively used the DWT-layer and the CNN layer (CNNL) for signal decomposition and feature enhancement. Then, Wei and Wang [13] applied the DWT-layer to wafer defect identification, and the results showed that the DWT presents notable excellence. CWT can be effectively integrated into CNN because the principle of CNN also revolves around inner product operation.…”

Section: Introductionmentioning

confidence: 99%

A lightweight dynamic dual-damped wavelet-based convolutional neural network for interpretable bearing fault diagnosis

Zhao,

Mao,

Qin

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Wavelet-based convolutional neural networks (CNNS) have attracted widespread attention because they can improve the interpretability of intelligent fault diagnosis methods. However, the fault feature representation capability of typical wavelet-based convolution kernel frameworks must be strengthened to improve the diagnostic accuracy of complex faults. In the meantime, the large number of network parameters leads to high computational costs. To address these issues, a lightweight wavelet-based dynamic CNN, which comprises a dual-damping wavelet-based dynamic CNN (DWDC) block and a discrete wavelet transformation enhancement (DWTE) block, is put forward. In the DWDC block, a wavelet convolution layer is initially designed, where a dual-damping wavelet is used as the kernel function to improve the match of the convolution kernel with fault impulses. Subsequently, a dynamic convolution layer with multiple parallel small-size convolutional kernels is designed to screen the fault features instead of a multilayer network structure, thereby greatly reducing the number of network parameters. Finally, the DWTE block is constructed by combining the discrete wavelet transformation (DWT) and residual dense block (RDB), and it can mine more fault information from the previously extracted features. The experiments on the variable speed bearing dataset, locomotive bearing dataset with constant speed and the Case Western Reserve University (CWRU) dataset prove that the proposed approach outperforms five classical CNN models and six advanced wavelet-based CNN models. In addition, it can effectively solve the issue of data imbalance because of its powerful feature extraction capability.

show abstract

IDD-Net: Industrial defect detection method based on Deep-Learning

Zhang

Zhou

Wan

et al. 2023

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Wavelet integrated attention network with multi-resolution frequency learning for mixed-type wafer defect recognition

Cited by 9 publications

References 42 publications

An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification

An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification

A lightweight dynamic dual-damped wavelet-based convolutional neural network for interpretable bearing fault diagnosis

IDD-Net: Industrial defect detection method based on Deep-Learning

Contact Info

Product

Resources

About