国外文献 > 1.轴承 > 6. 信号处理与特征分析 > 信号处理
关键词搜索：
| 标 题： |
A multi-stage diagnosis method using CEEMD, ABC, and ANN for identifying compound gear-bearing faults
基于CEEMD、ABC和ANN的多阶段诊断方法用于识别复合齿轮轴承故障 |
| 作 者： |
Athisayam, Andrews
Kondal, Manisekar |
| 关键词： |
Compound gear-bearing faults [复合齿轮轴承故障]
fault diagnosis [ 故障诊断]
CEEMD [ CEEMD]
ABC [ ABC]
ANN [ 公告]
EMPIRICAL MODE DECOMPOSITION [ 经验性分解模式]
ARTIFICIAL BEE COLONY [ 人工蜂群]
ROTATING MACHINERY [ 旋转机械]
FEATURE-SELECTION [ 特征选择]
FEATURE-EXTRACTION [ 特征提取]
ALGORITHM [ 算法]
CLASSIFICATION [ 分类]
IDENTIFICATION [ 身份识别]
OPTIMIZATION [ 优化]
PARAMETERS [ 参数] |
| 出版年： |
2023 |
| 期刊名： |
Proceedings of the Institution of Mechanical Engineers, Part C. Journal of mechanical engineering science
机械工程师学会会刊，C部分。机械工程科学杂志 |
| 年卷期： |
2023, vol.237, no.8 |
| 摘 要： |
Compound gear-bearing faults that occur in real-time conditions lead components to fail prematurely. Despite their significance in system failure, these compound faults are rarely studied since extracting accurate information from vibration signals is challenging. Therefore, it is necessary to develop reliable denoising, feature selection, and fault classification technique for forecasting compound faults in a rotor system to assure its durability. This research proposes a multi-stage diagnosis method for the identification of compound gear-bearing failures based on complementary ensemble empirical mode decomposition (CEEMD) based denoising, Artificial Bee Colony (ABC) based feature selection, and Artificial Neural Networks (ANN) based classification. The proposed method is validated through a case study, and the integrated method achieves a classification rate of 95.95%. Furthermore, the proposed method is compared with other denoising, feature selection and classification methods. All the other methods are outperformed by the proposed CEEMD-ABC-ANN method.
在实时工况下发生的复合齿轮轴承故障会导致部件提前失效。尽管这类复合故障对系统故障具有重要意义，但由于从振动信号中提取准确信息较为困难，因此很少被研究。为此，有必要开发出可靠的去噪、特征选择和故障分类技术，以预测转子系统的复合故障，从而确保其可靠性。本研究提出一种多阶段诊断方法，基于互补集合经验模态分解（CEEMD）去噪、人工蜂群算法（ABC）特征选择以及人工神经网络（ANN）分类，用于识别复合齿轮轴承故障。该方法通过一个实际案例进行验证，综合方法的分类准确率达到95.95%。此外，该方法还与其他去噪、特征选择和分类方法进行了比较，结果表明，所提出的CEEMD-ABC-ANN方法优于其他所有方法。 |
| 中文内容为网络AI翻译，专业术语未必准确，仅供参考。 |
京公网安备 11010202009788