Jiawei Xiao
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
Jiawei Xiao has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Chao Wei
State Key Laboratory of Mechanical Transmissions, Chongqing University, Chongqing, China
1 shared publication - Huiqiang Xu
China Xuchang Xuji Wind Power Technology Co., Ltd., Xuchang 461000, China
1 shared publication - Jian Tang
State Key Laboratory of Mechanical Transmissions, Chongqing University, Chongqing, China
1 shared publication - Jinling Mu
School of Artificial Intelligence, Luoyang Normal University, Luoyang 471934, China
1 shared publication - Liming Wang
State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing, China
1 shared publication Rui Liu
State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing, China
1 shared publication
Latest Publications
- Open Access
Line-Defect Phononic Crystal Structure for Directional Enhancement Detection of Weak Acoustic Signals
Effective detection of acoustic signals plays a crucial role in numerous fields, including industrial equipment fault prediction and environmental monitoring. Acoustic sensing technology, owing to its substantial information carrying capacity and non-contact measurement advantages, has garnered widespread attention in relevant applications. However, the effective detection of weak target acoustic signals amidst strong noise interference remains a critical challenge in this field. The core bottleneck lies in the difficulty of traditional detection methods to simultaneously achieve both high sensitivity and high directionality. To address this limitation, this work proposes a line-defect phononic crystal (PnC) structure that enables directional enhancement and detection of weak target signals under intense spatial noise interference by coupling defect state localization characteristics with anisotropy mechanisms. Through theoretical derivation and finite element numerical simulation, the directional enhancement properties of this structure were systematically validated. Furthermore, numerical simulations were conducted to validate the detection of weak harmonic signals and weak bearing fault signals under strong spatial noise interference. The results demonstrate that this line-defect phononic crystal (PnC) structure exhibits high feasibility and outstanding performance in detecting weak acoustic signals. This work provides novel insights for developing new acoustic detection methods combining high sensitivity with high directivity, showcasing unique advantages and broad application prospects in acoustic signal sensing, enhancement, and localization.
Open AccessLine-Defect Phononic Crystal Structure for Directional Enhancement Detection of Weak Acoustic Signals
Effective detection of acoustic signals plays a crucial role in numerous fields, including industrial equipment fault prediction and environmental monitoring. Acoustic sensing technology, owing to its substantial information carrying capacity and non-contact measurement advantages, has garnered widespread attention in relevant applications. However, the effective detection of weak target acoustic signals amidst strong noise interference remains a critical challenge in this field. The core bottleneck lies in the difficulty of traditional detection methods to simultaneously achieve both high sensitivity and high directionality. To address this limitation, this work proposes a line-defect phononic crystal (PnC) structure that enables directional enhancement and detection of weak target signals under intense spatial noise interference by coupling defect state localization characteristics with anisotropy mechanisms. Through theoretical derivation and finite element numerical simulation, the directional enhancement properties of this structure were systematically validated. Furthermore, numerical simulations were conducted to validate the detection of weak harmonic signals and weak bearing fault signals under strong spatial noise interference. The results demonstrate that this line-defect phononic crystal (PnC) structure exhibits high feasibility and outstanding performance in detecting weak acoustic signals. This work provides novel insights for developing new acoustic detection methods combining high sensitivity with high directivity, showcasing unique advantages and broad application prospects in acoustic signal sensing, enhancement, and localization.
- 31 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (5) , 7162-7172
HmmSeNet: A Novel Single Domain Generalization Equipment Fault Diagnosis Under Unknown Working Speed Using Histogram Matching Mixup
Equipments regularly change working speeds during real-time production owing to process requirements. Applying deep learning models trained in a single speed domain straightforwardly to other unknown speed domains is extremely challenging single-domain generalization problem. Therefore, this article proposes a histogram matching mixup based sequential embedding network (HmmSeNet) for single-domain generalization of intelligent fault diagnosis under unknown speeds. HmmSeNet consists of four components: histogram matching mixup (HMM); sequential embedding (SE); separable convolution; and decision making. First, inspired by histogram matching and Mixup, the HMM data augmentation method is proposed. HMM is capable of synthesizing data with the same semantic information, but different distributions from a single source domain data during the training process, thus augmenting the source speed domain to the unknown speed domains. Then, SE utilizes trainable linear dimensional boosting to approximate the distribution between samples, which reduces the effect of sample amplitude distribution shifts caused by speed changes and allows the model to learn domain-invariant features. Finally, three layers of separable convolution and global average pooling are used to accomplish an accurate and robust recognition task. Experimental results on three datasets show that the proposed approach is only trained on a single speed domain, while it has good diagnostic performance on other unknown speed domains, even varying speed domains. The powerful generality and flexible deployment capability of HmmSeNet for speed changes are also demonstrated by ablation experimental analysis and dimensional analysis.
- 31 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (5) , 7162-7172
HmmSeNet: A Novel Single Domain Generalization Equipment Fault Diagnosis Under Unknown Working Speed Using Histogram Matching Mixup
Equipments regularly change working speeds during real-time production owing to process requirements. Applying deep learning models trained in a single speed domain straightforwardly to other unknown speed domains is extremely challenging single-domain generalization problem. Therefore, this article proposes a histogram matching mixup based sequential embedding network (HmmSeNet) for single-domain generalization of intelligent fault diagnosis under unknown speeds. HmmSeNet consists of four components: histogram matching mixup (HMM); sequential embedding (SE); separable convolution; and decision making. First, inspired by histogram matching and Mixup, the HMM data augmentation method is proposed. HMM is capable of synthesizing data with the same semantic information, but different distributions from a single source domain data during the training process, thus augmenting the source speed domain to the unknown speed domains. Then, SE utilizes trainable linear dimensional boosting to approximate the distribution between samples, which reduces the effect of sample amplitude distribution shifts caused by speed changes and allows the model to learn domain-invariant features. Finally, three layers of separable convolution and global average pooling are used to accomplish an accurate and robust recognition task. Experimental results on three datasets show that the proposed approach is only trained on a single speed domain, while it has good diagnostic performance on other unknown speed domains, even varying speed domains. The powerful generality and flexible deployment capability of HmmSeNet for speed changes are also demonstrated by ablation experimental analysis and dimensional analysis.