强大的稀有非负矩阵因子化用于识别在轴承故障检测中感兴趣的信号
1Tony Davies High Voltage Laboratory, School of Electronics and Computer Science, Faculty of Engineering and Physical Sciences, University of Southampton, Southampton SO17 1BJ, UK.
Sensors (Basel, Switzerland)
|November 27, 2025
概括
本研究引入了一种强大的稀疏非负矩阵因子化 (NMF) 方法,用于在旋转系统中早期检测故障. 这种方法有效地识别了轴承故障,即使有沉重的尾声噪声,也优于传统方法.
科学领域:
- 机械工程 机械工程
- 信号处理 信号处理
- 机器学习 机器学习
背景情况:
- 轴承是旋转系统中的关键部件,它们的早期故障检测对于工业应用至关重要.
- 经典的故障检测方法与重尾或非周期性冲动噪声作斗争.
- 深度学习方法通常需要大型标记数据集,并假定高斯噪声,这并不总是实用的.
研究的目的:
- 为可处理重尾噪声的旋转机械开发强大的故障检测方法.
- 为了提高轴承信号中故障频段识别的准确性.
- 在杂的工业环境中解决现有的经典和深度学习方法的局限性.
主要方法:
- 开发了一种稀疏的非负矩阵因子化 (NMF) 方法,使用最大电流的标准来确定对重尾噪声的稳定性.
- 拟议的NMF方法用于识别信号光谱图中的故障频段.
- 使用蒙特卡洛模拟和统计效率分析来验证该方法在各种噪声条件下的性能.
主要成果:
- 拟议的方法证明了在模拟信号中识别故障频段的有效性,这些信号具有高斯式和重尾噪声.
- 统计分析证实了该方法对随机扰动的稳定性.
- 在三个现实世界数据集上的评估表明了该方法的实际适用性和有效性.
结论:
- 基于最大流标准的强大的稀疏NMF方法为旋转系统的早期故障检测提供了有前途的解决方案,特别是在具有挑战性的噪声条件的情况下.
- 该方法为传统技术和深度学习方法提供了可靠的替代方案,这些方法对噪音和数据可用性敏感.
- 这些发现突显了在工业环境中改进机械诊断和预测性维护的潜力.
相关概念视频
01:30Classification of Signals
1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K
01:15Discrete Fourier Transform
831
The Discrete Fourier Transform (DFT) is a fundamental tool in signal processing, extending the discrete-time Fourier transform by evaluating discrete signals at uniformly spaced frequency intervals. This transformation converts a finite sequence of time-domain samples into frequency components, each representing complex sinusoids ordered by frequency. The DFT translates these sequences into the frequency domain, effectively indicating the magnitude and phase of each frequency component present...
831
01:07Basic signals of Fourier Transform
867
The Fourier Transform is a pivotal mathematical tool in signal processing, enabling the transformation of time-domain signals into their frequency-domain representations. Among the numerous elements within this domain, certain functions like the sinc function, delta function, and exponential signals hold significant importance due to their unique properties and implications.
The sinc function, defined as sinc(x) = sin(πx)/(πx), is particularly notable for its symmetry and behavior at...
The sinc function, defined as sinc(x) = sin(πx)/(πx), is particularly notable for its symmetry and behavior at...
867
01:22Bearing Stress
1.9K
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...
1.9K
01:24Bearings: Problem Solving
466
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...
466
01:08IR Spectrum Peak Splitting: Symmetric vs Asymmetric Vibrations
1.7K
Identical bonds within a polyatomic group can stretch symmetrically (in-phase) or asymmetrically (out-of-phase). Similar to hydrogen bonding, these vibrations also influence the shape of the IR peak. Generally, asymmetric stretching frequencies are higher than symmetric stretching frequencies. For example, primary amines exhibit two distinct IR peaks between 3300–3500 cm−1 corresponding to the symmetric and asymmetric N-H stretching, while secondary amines exhibit a single...
1.7K