Soft Fault Diagnosis of Analog Circuits Based on a ResNet With Circuit Spectrum Map

Ji, Lipeng; Fu, Chenqi; Sun, Weiqing

doi:10.1109/tcsi.2021.3076282

Cited by 58 publications

(20 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This avoids the need for manual feature extraction and feature selection. For example, different 2D representations [30,31] have been developed for circuit outputs for use with state-of-the-art deep learning networks such as ResNet50 [32] to achieve fault diagnosis. However, the creation of an optimal custom deep learning network structure for the problem at hand requires subject matter expertise and extensive trial-and-error [33].…”

Section: Introductionmentioning

confidence: 99%

Learnable Wavelet Scattering Networks: Applications to Fault Diagnosis of Analog Circuits and Rotating Machinery

2022

View full text Add to dashboard Cite

Analog circuits are a critical part of industrial electronics and systems. Estimates in the literature show that, even though analog circuits comprise less than 20% of all circuits, they are responsible for more than 80% of faults. Hence, analog circuit fault diagnosis and isolation can be a valuable means of ensuring the reliability of circuits. This paper introduces a novel technique of learning time–frequency representations, using learnable wavelet scattering networks, for the fault diagnosis of circuits and rotating machinery. Wavelet scattering networks, which are fixed time–frequency representations based on existing wavelets, are modified to be learnable so that they can learn features that are optimal for fault diagnosis. The learnable wavelet scattering networks are developed using the genetic algorithm-based optimization of second-generation wavelet transform operators. The simulation and experimental results for the diagnosis of analog circuit faults demonstrates that the developed diagnosis scheme achieves greater fault diagnosis accuracy than other methods in the literature, even while considering a larger number of fault classes. The performance of the diagnosis scheme on benchmark datasets of bearing faults and gear faults shows that the developed method generalizes well to fault diagnosis in multiple domains and has good transfer learning performance, too.

show abstract

Section: Introductionmentioning

confidence: 99%

Learnable Wavelet Scattering Networks: Applications to Fault Diagnosis of Analog Circuits and Rotating Machinery

2022

View full text Add to dashboard Cite

show abstract

“…It is well known that the excitation response caused by the unit impulse function can reflect the circuit characteristics [2]. If the CUT has a system transfer function of h(t) and a unit shock function δ(t) as input, the time domain response y(t) of the system is the convolution of h(t) and δ(t):…”

Section: Excitation Signalmentioning

confidence: 99%

“…As electronic circuits continue to increase in integration, so do the requirements for their reliability, especially in industrial facilities such as military, aerospace, and medical [1][2][3][4]. Electronic circuits in machines are inevitably affected by the outside world and produce unexpected problems, which affect work progress and even life safety.…”

Section: Introductionmentioning

confidence: 99%

A Novel Analog Circuit Fault Diagnosis Method Based on Multi-channel 1D-Resnet and Wavelet Packet Transform

Zhou

Tang

Liang

2022

Preprint

View full text Add to dashboard Cite

Fault diagnosis techniques for analog circuits are widely applied in the diagnosis of electronic devices. It is of great significance to accurately and quickly find the fault location and the deviation of fault parameters in analog circuits. In this paper, we propose an innovative fault diagnosis approach for analog circuits. In this method, the wavelet packet transform (WPT) is employed to preprocess the time-domain response signals of analog circuit, and the proposed multi-channel one-dimensional residual networks (MC-1D-ResNet) is utilized for feature mining and fault diagnosis. Specifically, the two-level WPT is first carried out on the measured time-domain response signal to generate one approximate signal and three detailed signals. Additionally, the MC-1D-ResNet is developed by introducing a multi-channel structure based on 1D-ResNet, which can excavate and fuse various features from response signals and realize fault diagnosis. Through the simulation of the Sallen-key bandpass filter circuit and Four-opamp biquad high-pass filter circuit, the diagnostic reliability of this method has been fully verified. The results show that this method is very valuable for diagnosing faults of analog circuits and performs well on both test circuits. Even in the complex Four-opamp biquad high-pass filter circuit, the diagnostic accuracy can be up to 99.74%.

show abstract

“…Convolutional Neural Networks (CNN) have shown good performance in image rain removal with promising successes in recent years [9][10][11]. [12] considered the location information of rain streaks in the image by learning the rain content at different scales and using them to estimate the final de-rained output.…”

Section: Introductionmentioning

confidence: 99%

Multi-scale Fusion Residual Network For Single Image Rain Removal

He¹,

He²,

Fu³

2023

Journal of Computers

View full text Add to dashboard Cite

<p>Deep learning has been widely used in single image rain removal and demonstrated favorable universality. However, it is still challenging to remove rain streaks, especially in the nightscape rain map which exists heavy rain and rain streak accumulation. To solve this problem, a single image nightscape rain removal algorithm based on Multi-scale Fusion Residual Network is proposed in this paper. Firstly, based on the motion blur model, evenly distributed rain streaks are generated and the dataset is reconstructed to solve the lack of nightscape rain map datasets. Secondly, according to the characteristics of the night rain map, multi-scale residual blocks are drawn on to reuse and propagate the feature, so as to exploit the rain streaks details representation. Meanwhile, the linear sequential connection structure of multi-scale residual blocks is changed to a u-shaped codec structure, which tackles the problem that features cannot be extracted effectively due to insufficient scale. Finally, the features of different scales are combined with the global self-attention mechanism to get different rain streak components, then a cleaner restored image is obtained. The quantitative and qualitative results show that, compared to the existing algorithms, the proposed algorithm can effectively remove rain streaks while retaining detailed information and ensuring the integrity of image information.</p> <p> </p>

show abstract

Soft Fault Diagnosis of Analog Circuits Based on a ResNet With Circuit Spectrum Map

Cited by 58 publications

References 24 publications

Learnable Wavelet Scattering Networks: Applications to Fault Diagnosis of Analog Circuits and Rotating Machinery

Learnable Wavelet Scattering Networks: Applications to Fault Diagnosis of Analog Circuits and Rotating Machinery

A Novel Analog Circuit Fault Diagnosis Method Based on Multi-channel 1D-Resnet and Wavelet Packet Transform

Multi-scale Fusion Residual Network For Single Image Rain Removal

Contact Info

Product

Resources

About