Min Qin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Min Qin has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Jinrui Wang
Shandong University of Science and Technology
3 shared publications - Baokun Han
Shandong University of Science and Technology
2 shared publications - Huaihai Chen
Nanjing University of Aeronautics and Astronautics
2 shared publications - Ronghui Zheng
State Key Laboratory of Mechanics and Control of Mechanical Structures, College of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
2 shared publications - Zongzhen Zhang
Shandong University of Science and Technology
2 shared publications - Fucan Huang
College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266000, People’s Republic of China
1 shared publication
Latest Publications
- 3 April 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (4) , 046125
Dual-domain fused vision transformer for mechanical fault diagnosis under fluctuating working conditions
Signal instability, noise interference and the inability of individual signals to accurately represent the operational state of the equipment present substantial challenges for traditional fault diagnosis methods under fluctuating conditions. Furthermore, the over-globalization of the self-attention mechanism in deep networks undermines feature diversity, while conventional inter-domain distance metrics lack the robustness required to address complex scenarios. To tackle these issues, we propose an innovative adversarial training network model based on a dual-domain fused vision transformer, which processes time-domain and frequency-domain signals in parallel. The model enhances feature diversity through a residual attention mechanism and dynamically fuses signals via self-attention. By co-optimizing a dual-domain distance metric that incorporates maximum mean discrepancy and Wasserstein distance to reduce domain distance, the ability of the model to transfer across domains is strengthened. Experimental results from three sets of tests demonstrate that the proposed model significantly improves fault diagnosis accuracy under fluctuating conditions, effectively mitigates instability and noise interference, and exhibits enhanced stability and generalization capabilities.
- 3 April 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (4) , 046125
Dual-domain fused vision transformer for mechanical fault diagnosis under fluctuating working conditions
Signal instability, noise interference and the inability of individual signals to accurately represent the operational state of the equipment present substantial challenges for traditional fault diagnosis methods under fluctuating conditions. Furthermore, the over-globalization of the self-attention mechanism in deep networks undermines feature diversity, while conventional inter-domain distance metrics lack the robustness required to address complex scenarios. To tackle these issues, we propose an innovative adversarial training network model based on a dual-domain fused vision transformer, which processes time-domain and frequency-domain signals in parallel. The model enhances feature diversity through a residual attention mechanism and dynamically fuses signals via self-attention. By co-optimizing a dual-domain distance metric that incorporates maximum mean discrepancy and Wasserstein distance to reduce domain distance, the ability of the model to transfer across domains is strengthened. Experimental results from three sets of tests demonstrate that the proposed model significantly improves fault diagnosis accuracy under fluctuating conditions, effectively mitigates instability and noise interference, and exhibits enhanced stability and generalization capabilities.
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
A Novel GAN-Based Signal Resolution Enhancement Method for Mechanical Fault Diagnosis Under Sample Insufficiency
The challenge of insufficient datasets is a significant issue in rotating machinery prediction and health management, particularly due to the scarcity of high-quality samples, which hampers the training of deep learning-based fault diagnosis models. generative adversarial networks (GANs) can effectively address the problem of insufficient samples. Therefore, in this article, a subpixel fully connected GAN (SPFCGAN) is proposed based on GANs to generate high-quality samples. Initially, the collected low-resolution (LR) signals are input into the generator of this network structure to produce high-resolution (HR) features through the fully connected layer and elemental rearrangement. The generated signals, along with the collected original HR signals, are then fed into the discriminator. By comparing the difference between the generated signals and the real signals, the discriminator performs signal discrimination, thereby improving the quality of the generated signal. The feasibility of the proposed SPFCGAN is validated by bearing data and gear data for fault diagnosis analysis.
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
A Novel GAN-Based Signal Resolution Enhancement Method for Mechanical Fault Diagnosis Under Sample Insufficiency
The challenge of insufficient datasets is a significant issue in rotating machinery prediction and health management, particularly due to the scarcity of high-quality samples, which hampers the training of deep learning-based fault diagnosis models. generative adversarial networks (GANs) can effectively address the problem of insufficient samples. Therefore, in this article, a subpixel fully connected GAN (SPFCGAN) is proposed based on GANs to generate high-quality samples. Initially, the collected low-resolution (LR) signals are input into the generator of this network structure to produce high-resolution (HR) features through the fully connected layer and elemental rearrangement. The generated signals, along with the collected original HR signals, are then fed into the discriminator. By comparing the difference between the generated signals and the real signals, the discriminator performs signal discrimination, thereby improving the quality of the generated signal. The feasibility of the proposed SPFCGAN is validated by bearing data and gear data for fault diagnosis analysis.
- Open Access
Automated Structural Bolt Micro Looseness Monitoring Method Using Deep Learning
The detection of bolt loosening in key components of aircraft engines faces problems such as complex and difficult-to-establish bolt loosening mechanism models, difficulty in identifying early loosening, and difficulty in extracting signal features with nonlinear and non-stationary characteristics. Therefore, the automated structural bolt micro looseness monitoring method using deep learning was proposed. Specifically, the addition of batch normalization methods enables the established Batch Normalized Stacked Autoencoders (BNSAEs) model to converge quickly and effectively, making the model easy to build and effective. Additionally, using characterization functions preprocess the original response signal not only simplifies the data structure but also ensures the integrity of features, which is beneficial for network training and reduces time costs. Finally, the effectiveness of the proposed method was verified by taking the bolted connection structures of two key components of aircraft engines, namely bolt connection structures and flange connection structures, as examples.
Open AccessAutomated Structural Bolt Micro Looseness Monitoring Method Using Deep Learning
The detection of bolt loosening in key components of aircraft engines faces problems such as complex and difficult-to-establish bolt loosening mechanism models, difficulty in identifying early loosening, and difficulty in extracting signal features with nonlinear and non-stationary characteristics. Therefore, the automated structural bolt micro looseness monitoring method using deep learning was proposed. Specifically, the addition of batch normalization methods enables the established Batch Normalized Stacked Autoencoders (BNSAEs) model to converge quickly and effectively, making the model easy to build and effective. Additionally, using characterization functions preprocess the original response signal not only simplifies the data structure but also ensures the integrity of features, which is beneficial for network training and reduces time costs. Finally, the effectiveness of the proposed method was verified by taking the bolted connection structures of two key components of aircraft engines, namely bolt connection structures and flange connection structures, as examples.
- Open Access
- 26 February 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (5) , 2471
An Adaptive Operational Modal Analysis under Non-White Noise Excitation Using Hybrid Neural Networks
To adaptively identify the modal parameters for time-invariant structures excited by non-white noise, this paper proposes a new operational modal analysis (OMA) method using hybrid neural networks. In this work, taking the acceleration response directly as the input data of the networks not only simplifies the data processing, but also retains all the characteristics of the data. The data processed by the output function is the output data of the network, and its peak corresponds to the modal frequency. The proposed output function greatly reduces the computational cost. In addition, a small sample dataset ensures that the hybrid neural networks identify the modal parameters with the highest accuracy in the shortest possible time. Interestingly, the hybrid neural networks combine the advantages of the convolutional neural network (CNN) and gate recurrent unit (GRU). To illustrate the advantages of the proposed method, the cantilever beam and the rudder surface excited by white and non-white noise are taken as examples for experimental verification. The results reveal that the proposed method has a strong anti-noise ability and high recognition accuracy, and is not limited by ambient excitation type.
- 26 February 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (5) , 2471
Open AccessAn Adaptive Operational Modal Analysis under Non-White Noise Excitation Using Hybrid Neural Networks
To adaptively identify the modal parameters for time-invariant structures excited by non-white noise, this paper proposes a new operational modal analysis (OMA) method using hybrid neural networks. In this work, taking the acceleration response directly as the input data of the networks not only simplifies the data processing, but also retains all the characteristics of the data. The data processed by the output function is the output data of the network, and its peak corresponds to the modal frequency. The proposed output function greatly reduces the computational cost. In addition, a small sample dataset ensures that the hybrid neural networks identify the modal parameters with the highest accuracy in the shortest possible time. Interestingly, the hybrid neural networks combine the advantages of the convolutional neural network (CNN) and gate recurrent unit (GRU). To illustrate the advantages of the proposed method, the cantilever beam and the rudder surface excited by white and non-white noise are taken as examples for experimental verification. The results reveal that the proposed method has a strong anti-noise ability and high recognition accuracy, and is not limited by ambient excitation type.
- Open Access
- 1 January 2021
- Published by Wiley in Journal of Sensors
- Vol. 2021 (1)
An Adaptive Operational Modal Analysis Method Using Encoder LSTM with Random Decrement Technique
A new parameter identification method under non‐white noise excitation using transformer encoder and long short‐term memory networks (LSTMs) is proposed in the paper. In this work, the random decrement technique (RDT) processing of the data is equivalent to eliminating the noise of the raw data. In general, the addition of the gate in LSTM allows the network to selectively store data, which avoids gradient disappearance and gradient explosion to a certain extent. It is worthwhile mentioning that the encoder can learn the essence of data, which reduces the burden for the LSTM. More specifically, establish as simple LSTM structure as possible to learn the data of this essence to achieve the best training effect. Finally, the proposed method is used for simulation and experimental verification, and the results show that the method has the advantages of high recognition accuracy, strong anti‐noise ability, and fast convergence rate. Specially, the results indicated appropriate accuracy proposed by deep learning combined with traditional method for parameter identification as well as proper performance of the proposed method.
- 1 January 2021
- Published by Wiley in Journal of Sensors
- Vol. 2021 (1)
Open AccessAn Adaptive Operational Modal Analysis Method Using Encoder LSTM with Random Decrement Technique
A new parameter identification method under non‐white noise excitation using transformer encoder and long short‐term memory networks (LSTMs) is proposed in the paper. In this work, the random decrement technique (RDT) processing of the data is equivalent to eliminating the noise of the raw data. In general, the addition of the gate in LSTM allows the network to selectively store data, which avoids gradient disappearance and gradient explosion to a certain extent. It is worthwhile mentioning that the encoder can learn the essence of data, which reduces the burden for the LSTM. More specifically, establish as simple LSTM structure as possible to learn the data of this essence to achieve the best training effect. Finally, the proposed method is used for simulation and experimental verification, and the results show that the method has the advantages of high recognition accuracy, strong anti‐noise ability, and fast convergence rate. Specially, the results indicated appropriate accuracy proposed by deep learning combined with traditional method for parameter identification as well as proper performance of the proposed method.