Research on Rolling Bearing Fault Diagnosis Based on Distributed Fuzzy Broad Learning System under Imbalanced Data
ID:20 Submission ID:21 View Protection:ATTENDEE Updated Time:2024-10-23 10:40:54 Hits:51 Oral Presentation

Start Time:2024-11-02 09:50 (Asia/Shanghai)

Duration:20min

Session:[P1] Parallel Session 1 » [P1-2] Parallel Session 1(November 2 AM)

No files

Abstract
广义学习系统 (BLS) 作为一种新颖的快速有效的智能算法,在数据分类领域得到了广泛的应用。然而,真实数据往往是不平衡的,这使得 BLS 在处理不平衡数据时性能有限,无法获得良好的分类结果。有鉴于此,该文提出了一种基于不平衡数据下的分布式模糊广泛学习系统(DFBLS)的方法。该模型为每个训练点分配一个模糊从属值,减少了不平衡样本对模型的影响,DFBLS 并行执行模糊函数,从而提高了计算效率和处理速度。此外,DFBLS 通过映射特征和增强特征来学习输入数据中的特征,解决了模糊化导致数据样本丢失或混淆的不足。最后,通过两个滚动轴承实验数据集进行了验证,结果表明,所提方法在不同指标上均表现出优异的性能,为不平衡数据故障诊断提供了有效的解决方案。
Keywords
Broad Learning System (BLS); Distributed Fuzzy Broad Learning System; fuzzy function; fault diagnosis
Speaker
LiuHaoran
Mr Anhui University of Technology

Submission Author
PanHaiyang Anhui University of Technology
LiuHaoran Anhui University of Technology
ZhengJinde Anhui University of Technology
TongJinyu Anhui University of Technology
ChengJian Anhui University of Technology
Comment submit
Verification code Change another
All comments

Important Dates

15th August 2024   31st August 2024- Manuscript Submission

15th September 2024 - Acceptance Notification

1st October 2024 - Camera Ready Submission

1st October 2024  – Early Bird Registration

 

Contact Us

Website:

https://icsmd2024.aconf.org/

Email:
icsmd2024@163.com