Jinsong Yang

Dr. Jinsong Yang


Research Focus & Metrics

Academic Career Length

33Years (1994-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 October 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Jinsong YangJinsong Yang
Jinsong Yang
JLJie Liu
Jie Liu
JXjingsong xie
jingsong xie
CWChangda Wang
Changda Wang
TDTianqi Ding
Tianqi Ding
The rolling bearing is the key component of rotating machinery, and it is also a failure–prone component. The intelligent fault diagnosis method has been widely used to accurately diagnose bearing faults. However, in engineering practice, it is difficult to obtain sufficient sample data to train the intelligent diagnosis model. Therefore, in this article, a fusion diagnosis model CGAN-2-D-CNN that combines a conditional generative adversarial network (CGAN) and a two-dimensional convolutional neural network (2-D-CNN) is proposed for bearing fault diagnosis with small samples. Considering the problem of insufficient sample data, CGAN is used to learn the data distribution of real samples to generate new samples with similar data distribution by the confrontation training of the generator and discriminator. Then, 2-D preprocessing is conducted to convert the generated 1-D data into 2-D gray images. Finally, these images are input into the 2-D-CNN to extract the features and classify the bearing fault types. Two experimental cases are implemented to validate the effectiveness and feasibility of the proposed CGAN-2-D-CNN. The experimental results illustrate that the diagnosis accuracy of the proposed method used on the small sample data is close to that of the 2-D-CNN directly used on the enough original sample data whose size is equal to the expanded sample size. In addition, compared with the 1-D-CNN, support vector machine (SVM), and long short-term memory (LSTM) models, the 2-D-CNN model after 2-D preprocessing has the higher fault classification accuracy.

16 June 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Jinsong YangJinsong Yang
Jinsong Yang
YPYizhen Peng
Yizhen Peng
JXjingsong xie
jingsong xie
PWPengxi Wang
Pengxi Wang
To reduce the economic losses caused by bearing failures and prevent safety accidents, it is necessary to develop an effective method to predict the remaining useful life (RUL) of the rolling bearing. However, the degradation inside the bearing is difficult to monitor in real-time. Meanwhile, external uncertainties significantly impact bearing degradation. Therefore, this paper proposes a new bearing RUL prediction method based on long-short term memory (LSTM) with uncertainty quantification. First, a fusion metric related to runtime (or degradation) is proposed to reflect the latent degradation process. Then, an improved dropout method based on nonparametric kernel density is developed to improve estimation accuracy of RUL. The PHM2012 dataset is adopted to verify the proposed method, and comparison results illustrate that the proposed prediction model can accurately obtain the point estimation and probability distribution of the bearing RUL.

1 September 2025 in Mechanical Systems and Signal Processing
Verified
Journal Article
Closed access
Jinsong YangJinsong Yang
Jinsong Yang
YLYidan Liu
Yidan Liu
XLXuandong Lu
Xuandong Lu
TWTiantian Wang
Tiantian Wang

1 October 2024 in ISA Transactions
Verified
Journal Article
Closed access
YLYuyan Li
Yuyan Li
Tiantian WangTiantian Wang
Tiantian Wang
JXjingsong xie
jingsong xie
Jinsong YangJinsong Yang
Jinsong Yang
Tongyang PanTongyang Pan
Tongyang Pan
BYBuyao Yang
Buyao Yang

15 May 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
BYBuyao Yang
Buyao Yang
Tiantian WangTiantian Wang
Tiantian Wang
JXjingsong xie
jingsong xie
Jinsong YangJinsong Yang
Jinsong Yang
Because of uncertain working conditions and the lack of labels for most conditions, transfer learning has great potential in fault diagnosis for high-speed train bogies. This paper proposed a novel domain adaptation model for intelligent diagnosis under varying working conditions, namely Deep Adversarial Hybrid Domain-Adaptation Network (DAHAN). In the proposed method, to further improve the transfer learning performance at a low signal-to-noise ratio, the local domain adaptation by Wasserstein distance is developed to align category-level features which are combined with global domain adaptation to hybrid domain adaptation. In addition, an optimized training procedure is constructed to improve the stability and training speed of the proposed adversarial domain adaptation model to enhance the efficiency and real-time performance of the diagnosis method. The effectiveness and advantage of DAHAN are verified by the CRWU bearing data set. Finally, trained by train bogie gearbox fault dataset, the proposed method shows a great performance improvement and avoids the mismatch of weak fault features, proving its applicability on train bogie fault diagnosis.

28 November 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YZYan Zhu
Yan Zhu
XLXifeng Liang
Xifeng Liang
Tiantian WangTiantian Wang
Tiantian Wang
JXjingsong xie
jingsong xie
Jinsong YangJinsong Yang
Jinsong Yang
With the ever-accelerating development of information and sensor technology, plenty of data-driven fault diagnosis algorithms have shown impressive performance. However, in practical engineering scenarios, it is often difficult to obtain sufficient labeled data, and the signal fault characteristics of the bogie bearing are not obvious due to the influence of environmental noise and track excitation, which would seriously reduce the performance of the model. In this paper, we proposed a diagnostic algorithm based on a multi-information fusion technique and unsupervised representation alignment deep Q network (URADQN), to make full use of the fault information contained in each sensor and address the issue of the small sample size. Firstly, the acquired samples from several sensors are processed by a dual fusion module to dig the fault feature information from the original data; Then through unsupervised contrastive learning of similar feature representations, the URADQN is pre-trained to optimize the feature representation ability, to shorten the training time of deep Q-learning; Finally, the fault classification is realized by using the well-trained URADQN through reinforcement learning strategy. The effectiveness of the proposed algorithm is validated through two multi-sensor bearing datasets on the bogie. In comparison with other advanced methods under various data setups, the proposed algorithm demonstrates superior performance for small sample fault diagnosis.