一种基于IGRO-LSSVM的轴承故障诊断方法
By combining SVD noise reduction and information entropy feature extraction with IGRO-LSSVM-based method, and optimizing LSSVM parameters, the difficulties of traditional bearing fault diagnosis in low-speed and noisy environments are solved, and higher fault type identification accuracy and diagnostic efficiency are achieved.
CN119377833BActive Publication Date: 2026-07-17NANJING UNIV OF POSTS & TELECOMM
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANJING UNIV OF POSTS & TELECOMM
- Filing Date
- 2024-09-23
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Traditional bearing fault diagnosis methods struggle to accurately identify fault types when fault signals are weak at low speeds and environmental noise is severe, leading to diagnostic difficulties.
Method used
A bearing fault diagnosis model is constructed by using an IGRO-LSSVM-based method, combined with SVD noise reduction and information entropy feature extraction. Significant features are selected through feature evaluation, and the kernel function parameters and penalty factor of LSSVM are optimized.
Benefits of technology
It improves the accuracy of bearing fault type identification, enhances diagnostic efficiency and precision, especially in low signal-to-noise ratio and noisy environments.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN119377833B_ABST
Abstract
本发明公开了一种基于IGRO‑LSSVM的轴承故障诊断方法。首先，提取原始信号时频域特征及SVD降噪信号基于信息熵的特征构建原始特征集。针对原始特征集会存在无关或冗余特征，提出一种特征评估方法进行特征选择，得到敏感性好且稳定性高的特征子集。其次，对于淘金优化器(GRO)全局和局部搜索能力不足且易陷入局部最优，引入精英反向学习策略、余弦控制因子的动态边界策略和自适应t分布变异，组成多策略增强淘金优化器(IGRO)。最后，鉴于LSSVM的参数选取会影响分类效果，采用IGRO对参数进行寻优，构建基于IGRO‑LSSVM的故障诊断模型实现故障诊断。实验表明该方法的故障诊断准确性高，能够对不同类型、不同损伤直径的轴承故障进行精确分类。
Need to check novelty before this filing date? Find Prior Art