A Novel Fault Diagnosis Method for Analog Circuits Based on Multi-Input Deep Residual Networks with an Improved Empirical Wavelet Transform

Liu, Zhen; Liu, Xuemei; Xie, Songlin; Wang, Junhai; Zhou, Xiaojian

doi:10.3390/app12031675

Cited by 13 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main controller located in the zero slot of the chassis is used as an upper computer and is connected with each instrument board card through a bus to control each instrument board card to carry out test tasks and acquire signals for data analysis [7]. The adapter circuit is an important part of this automatic test system.…”

Section: Hardware Overall Connectionmentioning

confidence: 99%

Overall Scheme Design of Fault Diagnosis for Complex Electronic Systems

Mao,

Pang,

Jin

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Traditional manual testing methods are no longer able to meet the maintenance needs of modern shipboard fire control system board-level circuits. Therefore, the development of intelligent and universal automatic test systems has become an important issue for shipboard fire control system fault detection. This article analyzes the performance and functional requirements of the automatic test system, develops the automatic test system based on PXI bus instruments, and designs an overall solution with signal time-frequency analysis capabilities that can carry out intelligent fault diagnosis for a variety of board-level circuits. On this basis, the design of hardware circuit and software solution is completed. The automatic test system was analyzed on hardware indicators and software functions. On the hardware side, the hardware resource selection was completed based on the hardware indicator requirements. On the software side, the overall software architecture design and the design of each functional module were completed based on the system software functional requirements. Finally, the composition and functions of each module of the system software and the overall operation process are introduced.

show abstract

Section: Hardware Overall Connectionmentioning

confidence: 99%

Overall Scheme Design of Fault Diagnosis for Complex Electronic Systems

Mao,

Pang,

Jin

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…The method is simple in operation, but the frequency domain information of the signal is ignored. The second method is based on time-frequency domain conversion, including Fourier Transform (FT) [16] and Wavelet transform (WT) [17]. Fourier Transform (FT) has poor ability to characterize non-stationary signals, which may lead to information loss when extracting deep features.…”

Section: Data Preprocessingmentioning

confidence: 99%

Tool Wear Monitoring Based on Transfer Learning and Improved Deep Residual Network

Zhang

Zhao

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Considering the complex structure weight of the existing tool wear state monitoring model based on deep learning, prone to over-fitting and requiring a large amount of training data, a monitoring method based on Transfer Learning and Improved Deep Residual Network is proposed. First, the data is preprocessed, one-dimensional cutting force data are transformed into two-dimensional spectrum by wavelet transform. Then, the Improved Deep Residual Network is built and the residual module structure is optimized. The Dropout layer is introduced and the global average pooling technique is used instead of the fully connected layer. Finally, the Improved Deep Residual Network is used as the pre-training network model and the tool wear state monitoring model combined with the model-based Transfer Learning method is constructed. The results show that the accuracy of the proposed monitoring method is up to 99.74%. The presented network model has the advantages of simple structure, small number of parameters, good robustness and reliability. The ideal classification effect can be achieved with fewer iterations.

show abstract

“…The first involves converting the original samples into frequency–domain signals, time–frequency diagrams, or amplitude-modulated–frequency-modulated components using techniques such as Fourier transform, wavelet transform, and empirical modal decomposition. Feature extraction and fusion are subsequently performed on these different forms of signals [ 34 , 35 ]. However, this approach is limited in obtaining additional feature information when applied to the smoothed data from gas sensors, and it also increases the complexity of the entire process.…”

Section: Introductionmentioning

confidence: 99%

Gas Sensor Array Fault Diagnosis Based on Multi-Dimensional Fusion, an Attention Mechanism, and Multi-Task Learning

Huang,

Wang,

Chen

et al. 2023

Sensors

View full text Add to dashboard Cite

With the development of gas sensor arrays and computational technology, machine olfactory systems have been widely used in environmental monitoring, medical diagnosis, and other fields. The reliable and stable operation of gas sensing systems depends heavily on the accuracy of the sensors outputs. Therefore, the realization of accurate gas sensor array fault diagnosis is essential to monitor the working status of sensor arrays and ensure the normal operation of the whole system. The existing methods extract features from a single dimension and require the separate training of models for multiple diagnosis tasks, which limits diagnostic accuracy and efficiency. To address these limitations, for this study, a novel fault diagnosis network based on multi-dimensional feature fusion, an attention mechanism, and multi-task learning, MAM-Net, was developed and applied to gas sensor arrays. First, feature fusion models were applied to extract deep and comprehensive features from the original data in multiple dimensions. A residual network equipped with convolutional block attention modules and a Bi-LSTM network were designed for two-dimensional and one-dimensional signals to capture spatial and temporal features simultaneously. Subsequently, a concatenation layer was constructed using feature stitching to integrate the fault details of different dimensions and avoid ignoring useful information. Finally, a multi-task learning module was designed for the parallel learning of the sensor fault diagnosis to effectively improve the diagnosis capability. The experimental results derived from using the proposed framework on gas sensor datasets across different amounts of data, balanced and unbalanced datasets, and different experimental settings show that the proposed framework outperforms the other available methods and demonstrates good recognition accuracy and robustness.

show abstract

A Novel Fault Diagnosis Method for Analog Circuits Based on Multi-Input Deep Residual Networks with an Improved Empirical Wavelet Transform

Cited by 13 publications

References 28 publications

Overall Scheme Design of Fault Diagnosis for Complex Electronic Systems

Overall Scheme Design of Fault Diagnosis for Complex Electronic Systems

Tool Wear Monitoring Based on Transfer Learning and Improved Deep Residual Network

Gas Sensor Array Fault Diagnosis Based on Multi-Dimensional Fusion, an Attention Mechanism, and Multi-Task Learning

Contact Info

Product

Resources

About