A Novel Convolutional Neural Network Based on Time–Frequency Spectrogram of Arc Sound and Its Application on GTAW Penetration Classification

Ren, Wenjing; Wen, Guangrui; Xu, Bin; Zhang, Zhifen

doi:10.1109/tii.2020.2978114

Cited by 42 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The convolutional layer uses the adjustable convolutional kernel and the output of the previous layer to produce the output of the current layer, which is responsible for the feature extraction. 24 The output of convolutional operation is calculated as followswhere l is the sequence number of the layers, xkl is the kth feature of the output on the lth layer, xil−1 is the ith output feature on the (l−1)th layer, ωi,kl is the weight vector of the convolutional kernel between the ith feature on the layer lth, and kth feature on the (l…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Development of a calibration model for near infrared spectroscopy using a convolutional neural network

Pan

Bai

et al. 2022

Journal of Near Infrared Spectroscopy

View full text Add to dashboard Cite

Development of qualitative or quantitative models is essential to exploit the full potential of near infrared (NIR) spectroscopy. In tandem with one-dimensional convolutional neural network (1D-CNN), a data-driven model is developed using NIR spectroscopy to estimate organic contents. First, the 1D-CNN model is designed to capture the features of the NIR spectra by means of several convolutional and pooling operations. Then, the suitable hyper-parameters of 1D-CNN are obtained by using the grid search algorithm to achieve the optimal performance. Furthermore, the dropout operation is added into the 1D-CNN to suppress the overfitting problem by means of removing some neurons, and the probability distribution of throwing follows the Bernoulli distribution. The developed framework is validated by the application in the sugar content estimation of Huangshan Maofeng tea. The experimental results demonstrate that the key features of the NIR spectra are successfully extracted by the proposed strategy; thereby, a new effective scheme for analyzing NIR spectra is provided for food analysis.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Architecture Of the Proposed 1d-cnnmentioning

confidence: 99%

Development of a calibration model for near infrared spectroscopy using a convolutional neural network

Pan

Bai

et al. 2022

Journal of Near Infrared Spectroscopy

View full text Add to dashboard Cite

show abstract

“…These researchers mainly focused on the application of CNN model based on the visual images of welding pool. Besides, Ren et al [17] proposed a CNN model based on time-frequency spectrogram of pulsed-arc sound signal for predicting GTAW penetration states. However, to the best of our knowledge, this CNN approach has not been systematically explored for visual-acoustic multimodal fusion during the VPPAW process up to now.…”

Section: B Related Workmentioning

confidence: 99%

“…According to previous studies [10], [17], a skilled welder's auditory system is sensitive to spectrum property of arc sound and the spectrum analysis has certain robustness for external environment. Since the acoustic signal itself is a non-stationary 1-D data which instantaneous frequency varies with time, the 1-D frequency-domain processing can hardly capture the useful temporal information along the time-axis.…”

Section: A Data Preparationmentioning

confidence: 99%

Visual-Acoustic Penetration Recognition in Variable Polarity Plasma Arc Welding Process Using Hybrid Deep Learning Approach

Huang

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Accurate characterization of keyhole pool behavior is important to improve the penetration recognition and quality detection during the variable polarity plasma arc welding (VPPAW) of aluminum alloy. However, the low-level hand-crafted visual/acoustic features are often incapable of sufficiently representing the dynamic characteristics of keyhole pool under complex welding conditions. In this paper, we developed an end-to-end visual-acoustic penetration recognition (VAPR) framework based on a hybrid convolutional neural network (CNN) and extreme learning machine (ELM), which consists of three consecutive phases: (1) visual-acoustic data preparation, (2) multi-features extraction, and (3) penetration classification. Specifically, we applied a flexible dual-sensor acquisition system for synchronously collecting/preprocessing the visual-acoustic signals and exploring the internal correlation between the visual-acoustic features and keyhole pool behavior as well as weld penetration status. Then we established two individual CNNs for learning high-level visual-acoustic features directly from the raw visual images and 2-D time-frequency spectrograms. With the visualization of CNN-based deep learning features, we also explained the physical meanings of visual-acoustic features. To further improve the prediction performance of CNN model, we employed the ELM model as a strong tool to classify penetration status. By comparing with other state-of-the-art methods, our hybrid CNN-ELM approach with visual-acoustic fusion has a superior performance in terms of the classifying accuracy. The VAPR framework in this paper will provide some guidance for post-process quality inspection and realize an adaptive control of VPPAW process.

show abstract

“…As a result, the aim of this paper is to estimate the state of remote machines through the application of deep learning algorithms to remotely collected acoustic data. Our contributions are as follows: (1) We developed a technique that enables a readily available, reusable and portable sensor module to collect data from a remote machine and transfer the data to a base station; (2) We developed algorithms in the form of a light-weight neural network model to enable near real-time estimation of remote machine states and (3) We show that transfer learning can be used to reduce the time needed to collect training data for neural networks deployed on manufacturing floors.…”

Section: Introductionmentioning

confidence: 99%

Attention Augmented Convolutional Neural Network for acoustics based machine state estimation

Tan

Oyekan

2021

Applied Soft Computing

View full text Add to dashboard Cite

A Novel Convolutional Neural Network Based on Time–Frequency Spectrogram of Arc Sound and Its Application on GTAW Penetration Classification

Cited by 42 publications

References 28 publications

Development of a calibration model for near infrared spectroscopy using a convolutional neural network

Development of a calibration model for near infrared spectroscopy using a convolutional neural network

Visual-Acoustic Penetration Recognition in Variable Polarity Plasma Arc Welding Process Using Hybrid Deep Learning Approach

Attention Augmented Convolutional Neural Network for acoustics based machine state estimation

Contact Info

Product

Resources

About