Yuhang Duan
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
Research Subjects
Yuhang Duan has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Honghui Li
School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China
4 shared publications - Dongdong Zhao
School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
1 shared publication - Jie Xiao
Beijing Chenzhu Technology Co., Ltd., Beijing 100091, China
1 shared publication - Jie Zhang
Beijing Chenzhu Technology Co., Ltd., Beijing 100091, China
1 shared publication Keng Yan
Provincial Key Lab of Advanced Welding Technology, Jiangsu University of Science and Technology, Zhenjiang, China
1 shared publication- Mengqi He
School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
1 shared publication
Latest Publications
- 28 June 2022
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 33 (9) , 094008
Mechanical health indicator construction and similarity remaining useful life prediction based on natural language processing model
Remaining useful life (RUL) prediction, as an essential task for prediction and health management, can improve the reliability of degradation systems. In this paper, multi-dimensional mechanical monitoring readings are treated as natural language sequences and inputted to a natural language processing model, Transformer, to extract semantic compression vectors. The health indicators (HIs) are constructed from the changes of compressed semantic vectors during the mechanical system operation, reflecting the mechanical health status at each monitoring point. Subsequently, combined with the similarity matching method, the RUL prediction is achieved by weighted summation. Transformer mainly consists of attention layers and residual connection layers, which contain no recurrence and convolution. The attention layer can highlight the critical time step information during the HI construction. Moreover, the output of different time steps can be obtained simultaneously in a parallel computation manner. The proposed scheme is conducted on two publicly available datasets for experimental and evaluation metrics comparison. The experimental results show that the proposed scheme can achieve competitive prediction results, with some of the metrics reaching the highest. An autoencoder only containing attention mechanism can effectively extract degradation feature representations for the adaptive construction of unsupervised HIs.
- 28 June 2022
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 33 (9) , 094008
Mechanical health indicator construction and similarity remaining useful life prediction based on natural language processing model
Remaining useful life (RUL) prediction, as an essential task for prediction and health management, can improve the reliability of degradation systems. In this paper, multi-dimensional mechanical monitoring readings are treated as natural language sequences and inputted to a natural language processing model, Transformer, to extract semantic compression vectors. The health indicators (HIs) are constructed from the changes of compressed semantic vectors during the mechanical system operation, reflecting the mechanical health status at each monitoring point. Subsequently, combined with the similarity matching method, the RUL prediction is achieved by weighted summation. Transformer mainly consists of attention layers and residual connection layers, which contain no recurrence and convolution. The attention layer can highlight the critical time step information during the HI construction. Moreover, the output of different time steps can be obtained simultaneously in a parallel computation manner. The proposed scheme is conducted on two publicly available datasets for experimental and evaluation metrics comparison. The experimental results show that the proposed scheme can achieve competitive prediction results, with some of the metrics reaching the highest. An autoencoder only containing attention mechanism can effectively extract degradation feature representations for the adaptive construction of unsupervised HIs.
- Open Access
Cross-Domain Remaining Useful Life Prediction Based on Adversarial Training
Remaining useful life prediction can assess the time to failure of degradation systems. Currently, numerous neural network-based prediction methods have been proposed by researchers. However, most of the work contains an implicit prerequisite: the network training and testing data have the same operating conditions. To solve this problem, an adversarial discriminative domain adaption prediction method based on adversarial training is proposed to improve the accuracy of cross-domain prediction under different working conditions. First, an LSTM feature extraction network is constructed to mine the source domain data and the target domain data for deep feature representation. Subsequently, the parameters of the target domain feature extraction network are adjusted based on the idea of adversarial training to achieve domain invariant feature mining. The proposed scheme is experimented on a publicly available dataset and achieves state-of-the-art prediction performance compared to recent unsupervised domain adaptation prediction methods.
Open AccessCross-Domain Remaining Useful Life Prediction Based on Adversarial Training
Remaining useful life prediction can assess the time to failure of degradation systems. Currently, numerous neural network-based prediction methods have been proposed by researchers. However, most of the work contains an implicit prerequisite: the network training and testing data have the same operating conditions. To solve this problem, an adversarial discriminative domain adaption prediction method based on adversarial training is proposed to improve the accuracy of cross-domain prediction under different working conditions. First, an LSTM feature extraction network is constructed to mine the source domain data and the target domain data for deep feature representation. Subsequently, the parameters of the target domain feature extraction network are adjusted based on the idea of adversarial training to achieve domain invariant feature mining. The proposed scheme is experimented on a publicly available dataset and achieves state-of-the-art prediction performance compared to recent unsupervised domain adaptation prediction methods.
- Open Access
- 22 March 2021
- Published by Atlantis Press SARL
- p. 162-166
Bilateral Trade Between China and Kazakhstan: Challenges and Opportunities in the Context of Belt and Road Initiative
- 22 March 2021
- Published by Atlantis Press SARL
- p. 162-166
Open AccessBilateral Trade Between China and Kazakhstan: Challenges and Opportunities in the Context of Belt and Road Initiative
- Top Cited Papers
- 19 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (9) , 10905-10914
A BiGRU Autoencoder Remaining Useful Life Prediction Scheme With Attention Mechanism and Skip Connection
Remaining Useful Life (RUL) prediction is one of the most common activities to ensure the reliability of a degradation system. In previous RUL prediction schemes based on RNN autoencoder, the multi-dimensional sensor data for each timestep made an equal contribution to the generation of the embedding vector during the encoding process. Besides, the single embedding vector carries the burden of decoding the entire multi-timestep information. To overcome the above shortcomings, two improvements are proposed: (1) For the embedding vectors to highlight critical timestep information, weights are assigned to each timestep information through an attention mechanism. (2) To reduce the decoding burden on a single embedding vector, a skip connection is introduced at each step of the decoding process to improve BiGRU decoding capabilities. The prognostic performance of the proposed method BiGRU-AS is evaluated on two publicly available datasets: the C-MAPSS dataset (simulation dataset) and the milling dataset (experimental dataset). Compared to the latest prediction methods, the experimental results show that the proposed method is competitive in RUL prediction for mechanical systems.
- 19 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (9) , 10905-10914
Top Cited PapersA BiGRU Autoencoder Remaining Useful Life Prediction Scheme With Attention Mechanism and Skip Connection
Remaining Useful Life (RUL) prediction is one of the most common activities to ensure the reliability of a degradation system. In previous RUL prediction schemes based on RNN autoencoder, the multi-dimensional sensor data for each timestep made an equal contribution to the generation of the embedding vector during the encoding process. Besides, the single embedding vector carries the burden of decoding the entire multi-timestep information. To overcome the above shortcomings, two improvements are proposed: (1) For the embedding vectors to highlight critical timestep information, weights are assigned to each timestep information through an attention mechanism. (2) To reduce the decoding burden on a single embedding vector, a skip connection is introduced at each step of the decoding process to improve BiGRU decoding capabilities. The prognostic performance of the proposed method BiGRU-AS is evaluated on two publicly available datasets: the C-MAPSS dataset (simulation dataset) and the milling dataset (experimental dataset). Compared to the latest prediction methods, the experimental results show that the proposed method is competitive in RUL prediction for mechanical systems.
- 19 March 2020
- Published by Springer Nature in Transactions of the Indian Institute of Metals
- Vol. 73 (4) , 1043-1051
Study on the Droplet Transition Models in Laser Welding with Filler Wire
- 19 March 2020
- Published by Springer Nature in Transactions of the Indian Institute of Metals
- Vol. 73 (4) , 1043-1051
Study on the Droplet Transition Models in Laser Welding with Filler Wire
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Wagon PHM State Model Based on AHP and Gray Clustering Model
In order to extend the service life of the wagon and improve the efficiency, this paper presents the index system of the PHM system of the wagon and builds a state model to analysis the wagon status based on AHP and the gray clustering.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Wagon PHM State Model Based on AHP and Gray Clustering Model
In order to extend the service life of the wagon and improve the efficiency, this paper presents the index system of the PHM system of the wagon and builds a state model to analysis the wagon status based on AHP and the gray clustering.