Hui Ma

Hui Ma

Auto-generated profile, based on publicly available information

Hui Ma

Suzhou Polytechnic University

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
28 November 2024 in IEEE Access
Verified
Journal Article
Open access
CYchao yuan
chao yuan
YLYunhan Ling
Yunhan Ling
NZNan Zhang
Nan Zhang
YYYong Yang
Yong Yang
LPLidong Pan
Lidong Pan
HMHui Ma
Hui Ma
The forging press plays a crucial and indispensable role in industries such as metallurgy, automotive, and aerospace. Its stable and efficient operation directly impacts the productivity and product quality of the entire production line. Therefore, it is particularly important to carry out efficient fault diagnosis for forging presses. In this paper, a method combining Convolutional Neural Network (CNN), Principal Component Analysis (PCA) and Transmission Support Vector Machine (TSVM) is proposed, which is called Multi-modal Attention-based CNN with PCA and TSVM (MACNN-PTSVM). This method effectively integrates multi-sensor information fusion technology, attention mechanism, CNN, PCA technology and TSVM, fully utilizing data collected from various sensors of the forging press. The constructed network model takes smooth monitoring signal data from the die forging press as input samples. Fault features are extracted through CNN, and PCA is utilized for feature fusion. Applications of this model in forging press fault diagnosis demonstrate significant advantages in fault classification performance. Specifically, its semi-supervised learning technology exhibits higher generalization ability and diagnostic accuracy when dealing with unlabeled data.

22 June 2026 in Multidiscipline Modeling in Materials and Structures
Verified
Journal Article
Closed access
HMHui Ma
Hui Ma
YGYi Gao
Yi Gao
WLWei Li
Wei Li
Purpose: Metaheuristic algorithms often suffer from premature convergence and poor population diversity when solving complex optimization issues. This study aims to develop an improved hybrid algorithm to balance global exploration and local exploitation, and adapt it to multi-objective constrained engineering optimization. Design/methodology/approach: A Marsh Wren-Cuckoo Search algorithm is proposed by combining marsh wren decoy nest mechanism and cuckoo Levy flight strategy. Non-dominated sorting and crowding distance are adopted to construct its multi-objective version. Comparative experiments are carried out on standard benchmark functions and CEC-2022 test functions, with mainstream intelligent algorithms chosen as contrast models. Multiple indexes and statistical tests are used for performance assessment, and an I-beam design case is applied for practical verification. Findings: The presented algorithm greatly restrains premature convergence and acquires superior convergence precision and stability. Statistical results prove its competitive performance. The multi-objective variant performs well on constraint engineering optimization tasks. Originality/value: This work innovatively fuses two biological behaviors to maintain population diversity without losing convergence speed. It provides a reliable optimization tool for practical complex engineering design problems.