BEiT deep learning-aided investigation on the creep-fatigue fracture mechanisms of variously heat-treated FB2 steel

IF 6.8 2区材料科学 Q1 ENGINEERING, MECHANICAL

International Journal of Fatigue Pub Date : 2025-09-10 DOI:10.1016/j.ijfatigue.2025.109281

Chipeng Zhang , Wei Li , Shunpeng Zhu , Shengnan Hu , Dapeng Jiang , Jian Chen , Guowei Bo

{"title":"BEiT deep learning-aided investigation on the creep-fatigue fracture mechanisms of variously heat-treated FB2 steel","authors":"Chipeng Zhang , Wei Li , Shunpeng Zhu , Shengnan Hu , Dapeng Jiang , Jian Chen , Guowei Bo","doi":"10.1016/j.ijfatigue.2025.109281","DOIUrl":null,"url":null,"abstract":"<div><div>The service life of FB2 steel, a boron-modified 9 % Cr martensitic stainless steel for high-temperature applications, is predominantly governed by its creep-fatigue resistance. Therefore, the stress-controlled cycling loading tests with different dwell time (5, 15, 30 s) at 620 ℃ were employed to study the creep-fatigue behavior of FB2 steel. Meanwhile, two martensitic lath widths of 286 nm (H-FB2 steel) and 568 nm (L-FB2 steel) were tailored for FB2 steel by different heat treatment. Both FB2 variants exhibited pronounced cyclic softening behavior. However, H-FB2 steel showed significantly lower performance than L-FB2 steel, with the latter exhibiting a 64.7 % greater elongation and superior creep-fatigue life improvements of 21.9 %, 14.2 %, and 8.5 % at holding durations of 5 s, 15 s, and 30 s respectively. Further, the BEiT deep learning method achieved an accuracy of 94.4 % for fractographic analysis, by which the fracture mode was identified as brittle and ductile fracture for H-FB2 and L-FB2 steel, respectively. This difference is attributed to the lower initial dislocation density and fine spherical carbides (M<sub>23</sub>C<sub>6</sub> and MX types) in L-FB2 steel, which could accommodate more dislocation and restrict dislocation movement at martensite lath boundaries. This effectively delays both crack initiation and propagation processes, and consequently improves the creep-fatigue resistance.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"203 ","pages":"Article 109281"},"PeriodicalIF":6.8000,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Fatigue","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0142112325004785","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}

引用次数: 0

Abstract

The service life of FB2 steel, a boron-modified 9 % Cr martensitic stainless steel for high-temperature applications, is predominantly governed by its creep-fatigue resistance. Therefore, the stress-controlled cycling loading tests with different dwell time (5, 15, 30 s) at 620 ℃ were employed to study the creep-fatigue behavior of FB2 steel. Meanwhile, two martensitic lath widths of 286 nm (H-FB2 steel) and 568 nm (L-FB2 steel) were tailored for FB2 steel by different heat treatment. Both FB2 variants exhibited pronounced cyclic softening behavior. However, H-FB2 steel showed significantly lower performance than L-FB2 steel, with the latter exhibiting a 64.7 % greater elongation and superior creep-fatigue life improvements of 21.9 %, 14.2 %, and 8.5 % at holding durations of 5 s, 15 s, and 30 s respectively. Further, the BEiT deep learning method achieved an accuracy of 94.4 % for fractographic analysis, by which the fracture mode was identified as brittle and ductile fracture for H-FB2 and L-FB2 steel, respectively. This difference is attributed to the lower initial dislocation density and fine spherical carbides (M₂₃C₆ and MX types) in L-FB2 steel, which could accommodate more dislocation and restrict dislocation movement at martensite lath boundaries. This effectively delays both crack initiation and propagation processes, and consequently improves the creep-fatigue resistance.

Abstract Image

查看原文本刊更多论文

基于深度学习的不同热处理FB2钢蠕变疲劳断裂机制研究

FB2钢是一种用于高温应用的硼改性9% Cr马氏体不锈钢，其使用寿命主要取决于其抗蠕变疲劳性能。为此，采用620℃下不同停留时间（5、15、30 s）的应力控制循环加载试验，研究了FB2钢的蠕变疲劳行为。同时，通过不同的热处理，为FB2钢定制了286 nm （H-FB2钢）和568 nm （L-FB2钢）两种马氏体板条宽度。两种FB2变体都表现出明显的循环软化行为。然而，H-FB2钢的性能明显低于L-FB2钢，L-FB2钢在保温5秒、15秒和30秒时，伸长率提高了64.7%，蠕变疲劳寿命分别提高了21.9%、14.2%和8.5%。此外，BEiT深度学习方法的断口分析准确率达到94.4%，将H-FB2和L-FB2钢的断裂模式分别确定为脆性断裂和韧性断裂。这种差异是由于L-FB2钢中较低的初始位错密度和细小的球形碳化物（M23C6和MX型），可以容纳更多的位错并限制位错在马氏体板条边界的移动。这有效地延缓了裂纹的萌生和扩展过程，从而提高了抗蠕变疲劳性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Fatigue 工程技术-材料科学：综合

CiteScore

10.70

自引率

21.70%

发文量

619

审稿时长

58 days

期刊介绍： Typical subjects discussed in International Journal of Fatigue address: Novel fatigue testing and characterization methods (new kinds of fatigue tests, critical evaluation of existing methods, in situ measurement of fatigue degradation, non-contact field measurements) Multiaxial fatigue and complex loading effects of materials and structures, exploring state-of-the-art concepts in degradation under cyclic loading Fatigue in the very high cycle regime, including failure mode transitions from surface to subsurface, effects of surface treatment, processing, and loading conditions Modeling (including degradation processes and related driving forces, multiscale/multi-resolution methods, computational hierarchical and concurrent methods for coupled component and material responses, novel methods for notch root analysis, fracture mechanics, damage mechanics, crack growth kinetics, life prediction and durability, and prediction of stochastic fatigue behavior reflecting microstructure and service conditions) Models for early stages of fatigue crack formation and growth that explicitly consider microstructure and relevant materials science aspects Understanding the influence or manufacturing and processing route on fatigue degradation, and embedding this understanding in more predictive schemes for mitigation and design against fatigue Prognosis and damage state awareness (including sensors, monitoring, methodology, interactive control, accelerated methods, data interpretation) Applications of technologies associated with fatigue and their implications for structural integrity and reliability. This includes issues related to design, operation and maintenance, i.e., life cycle engineering Smart materials and structures that can sense and mitigate fatigue degradation Fatigue of devices and structures at small scales, including effects of process route and surfaces/interfaces.