Variation in Magnetic Memory Testing Signals and Their Relationship with Stress Concentration Factors During Fatigue Tests Based on Back-Propagation Neural Networks

被引：0

作者：

Wang, Huipeng ^{[1
]}

Wang, Qiaogen ^{[1
]}

Liu, Huizhong ^{[1
]}

机构：

[1] Jiangxi Univ Sci & Technol, Sch Mech & Elect Engn, Ganzhou 341000, Peoples R China

来源：

MATERIALS | 2025年 / 18卷 / 05期

基金：

中国国家自然科学基金;

关键词：

magnetic memory testing signal; stress concentration factor; tension-tension fatigue test; characteristic extraction; back-propagation neural network;

D O I：

10.3390/ma18051008

中图分类号：

O64 [物理化学（理论化学）、化学物理学];

学科分类号：

070304 ; 081704 ;

摘要：

To investigate the relationship between metal magnetic memory testing (MMMT) signals and stress concentration factors (SCFs), four-level sinusoidal constant-amplitude load tension-tension fatigue tests were carried out on 45CrNiMoVA steel specimens with different SCFs. The normal component of MMMT signals, Hp(y), was collected during the fatigue tests, and three characteristics were extracted and analyzed during the tests, including the peak-to-peak value of abnormal peaks (Delta Hp(y)), the slope coefficient of the fitting line of Hp(y) (K1), and the slope coefficient of the fitting line of Hp(y) between abnormal peaks (K2), and a back-propagation (BP) neural network was developed to differentiate the SCF of the specimens. The results showed that both fatigue load and fatigue cycle number influenced MMMT signals, and the characteristics remained stable as the fatigue cycle number increased for the same fatigue load but increased significantly as fatigue load increased. In addition, all the characteristics increased as the distance between the scan line and the center line increased, but none of them could be used to differentiate the SCF of the specimens. With properly selected input vector and hidden nodes, the established BP neural network can quantitatively recognize the SCF of specimens.

引用

页数：10