FM-LLM: A Lightweight Multimodal LLM with Simulation-Augmented Data for Mechanical Fault Diagnosis

断层(地质) 计算机科学 可靠性工程 实时计算 故障检测与隔离 工程类 人工智能 嵌入式系统 控制工程 工程制图
作者
Youpeng Gao,Bohui Ding,Gengfu Zhang,Zhuyun Chen,Hongqi Lin,Weihua Li,Qiang Liu
出处
期刊:Chinese journal of mechanical engineering [China Machine Press]
卷期号:: 100333-100333 被引量:1
标识
DOI:10.1016/j.cjme.2026.100333
摘要

Industrial fault diagnosis is a key component of intelligent manufacturing systems. Diagnostic accuracy directly influences the safety of production systems and the efficiency of equipment operation and maintenance. However, traditional bearing fault diagnosis methods are limited by three critical constraints. First, single-modal sensor data are relied upon, which fails to comprehensively characterize the complex operational states of equipment. Second, raw fault samples are scarce, resulting in poor model adaptability in small-sample scenarios. Third, generalization performance is significantly degraded during cross-operating-condition and cross-equipment transfer, with multimodal information being insufficiently integrated. Moreover, in the application of large language models (LLMs) to fault diagnosis, challenges such as insufficient data volume, modal gaps, and high fine-tuning costs remain unresolved. To address these challenges, this study proposes FM-LLM, a bearing fault diagnosis method that integrates simulation-based data augmentation with lightweight multimodal fine-tuning of LLMs. The implementation of the method is described as follows. First, a large number of simulated bearing fault datasets are generated through simulation technology. These datasets are fused with original measured datasets, effectively mitigating the limitation of scarce fault samples in industrial scenarios. Second, the fused data are processed via envelope analysis to suppress noise interference and enhance fault feature signals. Third, time-frequency images are extracted from the processed data as the visual modality. Concurrently, text-modal data are constructed by integrating core bearing information, such as model specifications, operating parameters, and fault type descriptions. This process produces a multimodal fine-tuning dataset composed of time-frequency images and text. Finally, parameter-efficient fine-tuning techniques, namely Low-Rank Adaptation (LoRA) and Quantized Low-Rank Adaptation (QLoRA), are adopted. These techniques facilitate accurate learning and classification of bearing fault features by the LLM. Additionally, computational costs are significantly reduced, and the forgetting of pre-trained knowledge is prevented.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
星空发布了新的文献求助10
刚刚
水煮电吹风的应助被HANA采纳,获得10
刚刚
秋风的应助被科研通管家采纳,获得10
刚刚
方超发布了新的文献求助10
刚刚
chaow完成签到,获得积分10
刚刚
研友_VZG7GZ的应助被科研通管家采纳,获得10
刚刚
ZX612完成签到,获得积分10
刚刚
刚刚
沥练的应助被yhwang_smu采纳,获得10
刚刚
GHX_1195979443完成签到,获得积分10
1秒前
whyritoday完成签到,获得积分10
1秒前
1秒前
慕青的应助被小低调采纳,获得10
1秒前
等待香薇完成签到,获得积分10
1秒前
快毕业吧完成签到 ,获得积分10
1秒前
土豆煲洋芋完成签到,获得积分10
1秒前
2秒前
碧蓝的睫毛完成签到,获得积分10
2秒前
Phil丶完成签到,获得积分10
2秒前
文艺的文龙完成签到,获得积分10
3秒前
july7292发布了新的文献求助10
3秒前
夏日的羊屁屁完成签到,获得积分10
3秒前
albbxmy完成签到,获得积分10
3秒前
CipherSage的应助被Caicai采纳,获得10
3秒前
bkagyin的应助被yaya采纳,获得10
3秒前
星星完成签到 ,获得积分10
3秒前
Www完成签到,获得积分10
4秒前
Orange的应助被dzh采纳,获得10
4秒前
学术牛马完成签到,获得积分10
4秒前
小马甲的应助被mkl采纳,获得10
4秒前
美好眼神完成签到,获得积分10
4秒前
4秒前
obito发布了新的文献求助10
4秒前
动听无声完成签到,获得积分10
4秒前
5秒前
5秒前
tyx发布了新的文献求助10
5秒前
宫冷雁完成签到 ,获得积分10
5秒前
叨叨小夫夫完成签到,获得积分10
5秒前
踏实采波完成签到,获得积分10
5秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180531
求助须知:如何正确求助?哪些是违规求助? 9570507
关于积分的说明 21812974
捐赠科研通 7776619
什么是DOI,文献DOI怎么找? 3433286
关于科研通互助平台的介绍 2557539
邀请新用户注册赠送积分活动 2479185