A deep network solution for intelligent fault detection in analog circuit

Shokrolahi, Seyed Moslem; Karimiziarani, Mohammadsepehr

doi:10.1007/s10470-020-01732-8

Cited by 17 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms and predictive analytics techniques enable the prediction of disaster-related events, user behaviors, and resource needs. Researchers have utilized supervised learning methods, such as support vector machines and random forests, to classify social media posts based on their relevance to disasters [58]- [60]. Unsupervised learning approaches, including clustering and anomaly detection, have also been employed to identify patterns and outliers in social media data [61]- [63].…”

Section: Machine Learning and Predictive Analyticsmentioning

confidence: 99%

Social Response and Disaster Management: Insights from Twitter Data Assimilation on Hurricane Ian

Karimiziarani

Moradkhani

2022

SSRN Journal

View full text Add to dashboard Cite

Section: Machine Learning and Predictive Analyticsmentioning

confidence: 99%

Social Response and Disaster Management: Insights from Twitter Data Assimilation on Hurricane Ian

Karimiziarani

Moradkhani

2022

SSRN Journal

View full text Add to dashboard Cite

“…Recently, a deep neural network islanding detection technique based on statistical features was proposed in reference [9], and non-islanding disturbances were classified for hybrid systems based on synchronous and inverter distributed generators, which is a highlight in the field of fault diagnosis. The authors of [10] propose a novel technique for analog circuit fault detection using the application of image recognition, converting the power spectral density of the output signal into a two-dimensional image and inputting it into a deep convolutional neural network to achieve image classification and achieve the purpose of fault detection. Yu et al [11] conducted research on a novel method for fault detection and diagnosis, which is predicated on a fusion of the firefly algorithm, tent chaos mapping, and extreme learning machine.…”

Section: Introductionmentioning

confidence: 99%

A Fault Diagnosis Strategy for Analog Circuits with Limited Samples Based on the Combination of the Transformer and Generative Models

Jia,

Yang,

et al. 2023

Sensors

View full text Add to dashboard Cite

As a pivotal integral component within electronic systems, analog circuits are of paramount importance for the timely detection and precise diagnosis of their faults. However, the objective reality of limited fault samples in operational devices with analog circuitry poses challenges to the direct applicability of existing diagnostic methods. This study proposes an innovative approach for fault diagnosis in analog circuits by integrating deep convolutional generative adversarial networks (DCGANs) with the Transformer architecture, addressing the problem of insufficient fault samples affecting diagnostic performance. Firstly, the employment of the continuous wavelet transform in combination with Morlet wavelet basis functions serves as a means to derive time–frequency images, enhancing fault feature recognition while converting time-domain signals into time–frequency representations. Furthermore, the augmentation of datasets utilizing deep convolutional GANs is employed to generate synthetic time–frequency signals from existing fault data. The Transformer-based fault diagnosis model was trained using a mixture of original signals and generated signals, and the model was subsequently tested. Through experiments involving single and multiple fault scenarios in three simulated circuits, a comparative analysis of the proposed approach was conducted with a number of established benchmark methods, and its effectiveness in various scenarios was evaluated. In addition, the ability of the proposed fault diagnosis technique was investigated in the presence of limited fault data samples. The outcome reveals that the proposed diagnostic method exhibits a consistently high overall accuracy of over 96% in diverse test scenarios. Moreover, it delivers satisfactory performance even when real sample sizes are as small as 150 instances in various fault categories.

show abstract

“…In this time of rapid development, deep learning based methods have been widely used in the field of fault diagnosis for their powerful computing power, perfect learning ability, and deep feature extraction ability [17][18][19][20]. Zhang et al proposed a deep belief network (DBN) with the optimal learning rate optimized by PSO, which can effectively extract fault features and input them into SVM for diagnosis, thus improving the diagnosis efficiency [20].…”

Section: Introductionmentioning

confidence: 99%

“…Zhang et al used a soft fault diagnosis method for analog circuits that processes data using a backward differencing strategy and uses a new variant of convolutional neural networks, i.e., convolutional neural networks with a global average pooling layer, for feature extraction and fault classification [24]. Shokrolahi et al proposed a deep CNN method for fault detection using the real component of the power spectral intensity of the fault signal provided as the input image to the CNN to realize fault diagnosis [18]. Deng et al combined the improved discrete Volterra series (IDVS) with CNN and proposed the IDVS-CNN fault diagnosis method, which facilitates the efficient application of fault diagnosis [25].…”

Section: Introductionmentioning

confidence: 99%

Analog circuit fault diagnosis based on feature attention

Cao

2023

Preprint

View full text Add to dashboard Cite

Aiming at the troubles of effective extraction of fault features, large model calculation, low-accuracy diagnosis and poor stability, this paper proposes an analog circuit fault diagnosis method that is based on an improved CNN-Transformer model. To achieve comprehensive and effective extraction of fault features, one-dimensional convolution is implemented to obtain the local features in the data, and multi-head attention is employed to catch the global features. A Sallen-Key band-pass filter, a fourth-order state-variable filter and a Butterworth low-pass filter circuits are applied as the experimental subjects for comparison to verify the effectiveness and advancement of the proposed CNN-Transformer method. The results indicate that of the suggested CNN-Transformer model is able to effectively enhance diagnostic accuracy and stability, achieve accurate diagnosis and localization of circuit fault components, which could be a helpful reference for engineering practice in analog circuit fault diagnosis.

show abstract

A deep network solution for intelligent fault detection in analog circuit

Cited by 17 publications

References 20 publications

Social Response and Disaster Management: Insights from Twitter Data Assimilation on Hurricane Ian

Social Response and Disaster Management: Insights from Twitter Data Assimilation on Hurricane Ian

A Fault Diagnosis Strategy for Analog Circuits with Limited Samples Based on the Combination of the Transformer and Generative Models

Analog circuit fault diagnosis based on feature attention

Contact Info

Product

Resources

About