Jianwei Yang

Ms. Jianwei Yang

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
18 March 2021 in IEEE Access
Verified
Journal Article
Open access
MLMengliang Liao
Mengliang Liao
CLChang Liu
Chang Liu
CWCong Wang
Cong Wang
JYJianwei Yang
Jianwei Yang
Many deep learning models for fault diagnosis have not considered the prior diagnosis knowledge of the rolling bearing. Moreover, some measuring locations cannot collect adequate data to diagnose due to equipment size or installation space problems. This paper proposes a wavelet convolutional deep transfer learning model for rolling bearing fault detection on cross-measurement points. A new convolution layer includes a redesigned convolution kernel and a new energy pooling layer. The convolution kernel is designed based on wavelet construction for mining time-frequency characteristics. The energy pooling layer is proposed to extract the energy of different frequency bands. The associated location's fault information has been transferred to domain knowledge to enhance the target features. Different domain features have adaptive matches based on multiple kernel variants of maximum mean discrepancy. The experimental results demonstrate that the accuracy of fault detection can reach 99.73%, and the robustness of the proposed method is also verified.

11 June 2022 in Sensors
Verified
Journal Article
Open access
PDF file
FZFu Zhu
Fu Zhu
CLChang Liu
Chang Liu
JYJianwei Yang
Jianwei Yang
SWSen Wang
Sen Wang
In recent years, neural networks have shown good performance in terms of accuracy and efficiency. However, along with the continuous improvement in diagnostic accuracy, the number of parameters in the network is increasing and the models can often only be run in servers with high computing power. Embedded devices are widely used in on-site monitoring and fault diagnosis. However, due to the limitation of hardware resources, it is difficult to effectively deploy complex models trained by deep learning, which limits the application of deep learning methods in engineering practice. To address this problem, this article carries out research on network lightweight and performance optimization based on the MobileNet network. The network structure is modified to make it directly suitable for one-dimensional signal processing. The wavelet convolution is introduced into the convolution structure to enhance the feature extraction ability and robustness of the model. The excessive number of network parameters is a challenge for the deployment of networks and also for the running performance problems. This article analyzes the influence of the full connection layer size on the total network. A network parameter reduction method is proposed based on GAP to reduce the network parameters. Experiments on gears and bearings show that the proposed method can achieve more than 97% classification accuracy under the strong noise interference of −6 dB, showing good anti-noise performance. In terms of performance, the network proposed in this article has only one-tenth of the number of parameters and one-third of the running time of standard networks. The method proposed in this article provides a good reference for the deployment of deep learning intelligent diagnosis methods in embedded node systems.

30 March 2022 in Sensors
Verified
Journal Article
Open access
PDF file
JYJianwei Yang
Jianwei Yang
CLChang Liu
Chang Liu
QXQitong Xu
Qitong Xu
JTJinyi Tai
Jinyi Tai
The rotate vector (RV) reducer has a complex structure and highly coupled internal components. Acoustic emission (AE) signal, which is more sensitive to a weak fault, is selected for fault diagnosis of the RV reducer. The high sampling frequency and big data are the challenges for AE signal store and analysis. This study combines compressed sensing (CS) and convolutional neural networks. As a result, data redundancy is significantly reduced while retaining most of the information, and the analysis efficiency is improved. Firstly, the time-domain AE signal was projected into the compression domain to obtain the compression signal; then, the wavelet packet decomposition in the compressed domain was performed to obtain the information of each frequency band. Next, the frequency band information was sent into the input layer of the multi-channel convolutional layer, and the energy pooling layer mines the energy characteristics of each frequency band. Finally, the softmax classifier was used to classify and predict different fault types of RV reducers. The self-fabricated RV reducer experimental platform was used to verify the proposed method. The experimental results show that the proposed method can effectively extract the fault features in the AE signal of the RV reducer, improve the efficiency of signal processing and analysis, and achieve the accurate classification of RV reducer faults.

1 October 2017 in Journal of Semiconductors
Verified
Journal Article
Closed access
PDF file
STShudong Tian
Shudong Tian
JHJun Han
Jun Han
JYJianwei Yang
Jianwei Yang
XZXiaoyang Zeng
Xiaoyang Zeng
Electrocardiogram (ECG) can be used as a valid way for diagnosing heart disease. To fulfill ECG processing in wearable devices by reducing computation complexity and hardware cost, two kinds of adaptive filters are designed to perform QRS complex detection and motion artifacts removal, respectively. The proposed design achieves a sensitivity of 99.49% and a positive predictivity of 99.72%, tested under the MIT-BIH ECG database. The proposed design is synthesized under the SMIC 65-nm CMOS technology and verified by post-synthesis simulation. Experimental results show that the power consumption and area cost of this design are of 160 μW and 1.09 × 10 5 μm2, respectively.