从信封光谱到承载剩余的有用生命:一个基于振动的智能预测模型,具有量化不确定性
Haobin Wen1, Long Zhang2, Jyoti K Sinha1
1Dynamics Laboratory, The Department of Mechanical and Aerospace Engineering, The University of Manchester, Manchester M13 9PL, UK.
Sensors (Basel, Switzerland)
|November 27, 2024
概括
预测轴承的剩余使用寿命 (RUL) 对于机器维护至关重要. 这项研究使用变异神经网络和增强的平均包膜光谱来准确地估计RUL与信心指标.
科学领域:
- 机械工程 机械工程
- 机器学习 机器学习
- 可靠性工程可靠性工程
背景情况:
- 轴承在旋转机械中至关重要,它们的故障可能会导致系统性问题.
- 准确的剩余使用寿命 (RUL) 预测对于有效的预测性维护策略至关重要.
- 现有的数据驱动的RUL方法缺乏物理解释性和可靠的不确定性量化.
研究的目的:
- 开发一种可靠和可解释的方法来预测轴承RUL.
- 量化RUL预测中的不确定性,以改善维护规划.
- 为了利用轴承退化的物理见解来提高RUL估计.
主要方法:
- 使用一个卷积变量自编码器回归 (CVAER) 模型.
- 使用增强的平均封面光谱 (AES) 作为改进故障检测和物理强度的输入.
- 制定了一个概率回归器和潜在生成器,用于不确定性量化和有意义的潜在空间学习.
主要成果:
- 该CVAER模型概率地预测了RUL分布与相关的信心指标.
- 使用AES隔离带有特定信息,提高RUL预测的准确性.
- 实验验证证证实了与基准方法相比,该模型的有效性.
结论:
- 拟议的CVAER方法提供了一个物理上可解释和可靠的方法来进行轴承RUL预测.
- 将信封光谱与深度学习相结合,提高了预测性维护的可靠性.
- 这项工作推进了轴承状况监测和RUL估计的最新技术.
相关概念视频
Bearings: Problem Solving
272
Understanding the calculations and concepts related to double-collar bearings is essential for engineers and designers to optimize the performance of these components in various applications. By analyzing the bearing under different conditions, one can ensure that it can withstand the forces and moments experienced during operation. This knowledge enables better decision-making when designing and selecting bearings for specific purposes and configurations. Consider a double-collar bearing with...
272
Journal Bearings
637
Journal bearings are mechanical components that support and provide lateral stability to rotating shafts and axles. They are crucial in reducing friction, wear, and vibration in machinery such as engines, turbines, and pumps. The principle behind journal bearings is forming a thin lubricant film between the bearing surface and the rotating shaft, which minimizes direct contact and reduces frictional forces.
To better understand the concept of journal bearings, consider a rope winch with dry or...
To better understand the concept of journal bearings, consider a rope winch with dry or...
637
Bearing Stress
743
Bearing stress refers to the contact pressure between two separate bodies. To visualize this, imagine a bolt thrust through a plate. The bolt applies a force to the plate, which exerts an equal but opposite force back onto the bolt. This force isn't just a singular entity but a compilation of numerous smaller forces distributed across the contact surface between the bolt and the plate.
Due to the intricacy of these microforces, an average value, known as bearing stress, is often used by...
Due to the intricacy of these microforces, an average value, known as bearing stress, is often used by...
743
Pivot Bearings
1.2K
In mechanical systems, bearings are crucial in facilitating relative motion between two components while minimizing friction and wear. They help distribute various loads (radial, axial or a combination of both loads) across machinery parts, ensuring smooth and efficient operation.
A pivot bearing is a specialized type of bearing designed to support axial loads on a rotating shaft. The bearing surface, or the pivot, is positioned at the end of a shaft to support the axial thrust. The pivot may...
A pivot bearing is a specialized type of bearing designed to support axial loads on a rotating shaft. The bearing surface, or the pivot, is positioned at the end of a shaft to support the axial thrust. The pivot may...
1.2K
Residual Stresses in Circular Shafts
161
In materials that exhibit elastic and plastic behavior, known as elastoplastic materials, residual stresses can accumulate when these materials experience plastic deformation. This deformation arises from either high levels of shearing stress or significant strains. Residual stresses are internal stresses that persist within a material after removing the external force causing deformation. This phenomenon is demonstrated when observing the behavior of a shaft under torque; notably, the...
161
Uncertainty: Confidence Intervals
3.1K
The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor...
3.1K


