Xinghua Huang

Xinghua Huang

Auto-generated profile, based on publicly available information

Xinghua Huang

Chongqing University of Posts and Telecommunications, Chongqing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
24 August 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
AYAn Yiyao
An Yiyao
KZKe Zhang
Ke Zhang
YCYi Chai
Yi Chai
QLQie Liu
Qie Liu
XHXinghua Huang
Xinghua Huang
Lack of massive-labeled samples may cause the performance degradation of intelligent bearing fault diagnosis methods under variable working conditions. Unsupervised domain adaptation (UDA)-based methods can effectively alleviate this problem by decreasing the distribution discrepancy between two dataset. However, most current UDA-based methods focus only on minimizing the marginal distribution. The influence of misclassification of samples near the classification boundaries is ignored. This may lead to the result that even though the marginal distributions are aligned well, the diagnosis accuracy is not ideal enough. On account of this, an unsupervised contrastive domain adaptation network (UCDAN) for bearing fault diagnosis under variable working conditions is proposed. A deep convolution feature extractor is constructed to extract high-level features. At the same time, a domain-adversarial total loss function based on the strategy of minimizing the domain distribution discrepancy is designed to obtain domain-shared discriminant features for aligning the marginal distribution. Moreover, a contrastive estimation term is designed to quantize the similarity of data distribution and maximize the consistency between the samples from the same health conditions. Thereby reducing the probability of samples being misclassified near or on the boundary and improving diagnosis performance. And information entropy is used to avoid most samples are assigned to the same cluster. The effectiveness of UCDAN is confirmed by examining various fault diagnosis situations with domain discrepancies across the source and target conditions, using experimental data from two bearing systems.

24 November 2023
Verified
Conference Paper
Closed access
YFYuanliang Fan
Yuanliang Fan
XHXinghua Huang
Xinghua Huang
HWHan Wu
Han Wu
JCJinyu Chen
Jinyu Chen
ZLZewen Li
Zewen Li
JWJianhua Wang
Jianhua Wang
A LVDC distribution network pole-to-pole short-circuit fault model is established within this paper, with the aim to derive the pole-to-pole short-circuit fault characteristics of the LVDC distribution network through theoretical means. Detailed analysis reveals that the inter-pole short circuit fault can be partitioned into three distinct stages, each of which is meticulously elucidated while providing the corresponding response equations for voltage and current at every stage subsequent to the occurrence of the fault. At the same time, the impact of this fault on the AC current is analyzed. On the basis of the above, the characteristics of the fault current differential initial value are determined, a fault location method using current differential initial value characteristics is proposed, and a detailed fault location process is given. Finally, the MTLAB/Simulink simulation model was established. After simulation verification, it was confirmed that this method can accurately identify the fault location.

15 September 2024
Verified
Conference Paper
Open access
YLYuanyuan Li
Yuanyuan Li
XYXiaoyan Yin
Xiaoyan Yin
SZShenhai Zheng
Shenhai Zheng
PHPeng Han
Peng Han
Private set intersection cardinality (PSI-CA) is a derivative of Private set intersection (PSI). It is designed to securely compute the intersection size of two sets, with one party obtaining the result without revealing anything. Optimizing the communication of encrypted sets and reducing privacy leaks at lower costs remains a challenge. This paper presents an efficient unbalanced PSI-CA protocol based on the Diffie-Hellman oblivious pseudorandom function (DH-OPRF). The protocol combines slicing for filtering with polynomial linking (PoL) to maintain connections between sliced data. This approach reduces computational and communication overhead without compromising privacy. The proposed protocol is 29.71 times more efficient in computation and 3.98 times more efficient in communication compared to existing unbalanced PSI-CA protocols, breaking the communication bottleneck and speeding up receiver query time. The protocol's viability for private common contact counting is demonstrated using sets with significant size differences.