国外文献 > 1.轴承 > 2. 轴承类型与部件 > 核心部件
关键词搜索：
| 标 题： |
An Enhanced Modeling Framework for Bearing Fault Simulation and Machine Learning-Based Identification With Bayesian-Optimized Hyperparameter Tuning
基于贝叶斯优化的超参数调优的轴承故障仿真与机器学习识别增强建模框架 |
| 作 者： |
Ortiz, Ricardo
Miranda-Chiquito, Piedad
Encalada-Davila, Angel
Marquez, Luis E.
Tutiven, Christian
Chatzi, Eleni
Silva, Christian E. |
| 关键词： |
artificial intelligence [人工智能]
machine learning for engineering applications [ 工程应用中的机器学习]
multiphysics modeling and simulation [ 多物理场建模与仿真]
physics-based simulations [ 基于物理的模拟]
BALL-BEARINGS [ 滚珠轴承]
RANDOM SEARCH [ 随机搜索]
VIBRATION [ 振动]
PROGNOSTICS [ 预后：蜕变]
TRANSFORM [ 诊断]
DIAGNOSIS [ 系统]
SYSTEM [ 齿轮] |
| 出版年： |
2024 |
| 期刊名： |
Journal of Computing and Information Science in Engineering
计算与信息科学工程杂志 |
| 年卷期： |
2024, vol.24, no.9 |
| 摘 要： |
Monitoring the condition of rotating machinery offers a salient tool for predictive maintenance of rolling elements subjected to continuous working loads, wear, fatigue, and degradation. In this study, an enhanced computational tool for bearing fault simulation and feature extraction is proposed. A subsequent identification scheme is realized, through Bayesian optimization of hyperparameters, including support vector classifier (SVC), gradient boosting (GBoost), random forest (RF), extreme gradient boosting (XBoost), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost). The proposed hyperparameter optimization technique stands out from traditional methods by offering a more informed and efficient pathway to optimal performance in predictive maintenance. By using Bayesian optimization for hyperparameter tuning of machine learning models, which has not been extensively explored in this field, our approach shows significant advancements. Typical instances of bearing faults like inner race, outer race, and ball faults are considered. The analysis relies on the extraction of statistical and engineering characteristics from the collected response signals, including kurtosis, root mean square, peak, and ridge factor. Highly influential variables are highlighted on the basis of feature selection and importance algorithms, allowing bearing fault classification. We demonstrate that SVC and LightGBM produce over 97% of accuracy at low computational cost. This approach constitutes a robust and scalable framework for similar applications in engineering diagnostics.
监测旋转机械的状态，为承受持续工作载荷、磨损、疲劳和劣化的滚动元件提供了一种有效的预测性维护工具。本研究提出了一种增强型计算工具，用于轴承故障的仿真与特征提取。随后通过贝叶斯优化超参数，实现了一种识别方案，包括支持向量分类器（SVC）、梯度提升（GBoost）、随机森林（RF）、极端梯度提升（XBoost）、轻量级梯度提升机器（LightGBM）以及类别增强（CatBoost）。所提出的超参数优化方法相较于传统方法具有显著优势，能够更有效地实现预测性维护中的最优性能。由于在该领域尚未广泛采用贝叶斯优化技术对机器学习模型进行超参数调优，因此我们的方法取得了重要进展。本文考虑了内圈、外圈及滚珠等典型轴承故障情况。该分析基于从采集的响应信号中提取统计和工程特征，包括峰度、均方根值、峰值和脊因子。通过特征选择和重要性算法，突出显示了具有高度影响力的变量，从而实现轴承故障分类。我们证明，SVC和LightGBM在低计算成本下可达到超过97%的准确率。该方法为工程诊断中的类似应用提供了一个稳健且可扩展的框架。 |
| 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