Understanding importance of positive and negative signs of optimized weights used in the sum of weighted normalized Fourier spectrum/envelope spectrum for machine condition monitoring

Review Engineering, Mechanical

A review on the application of blind deconvolution in machinery fault diagnosis

Yonghao Miao et al.

Summary: Fault diagnosis is crucial for the safe operation of machinery equipment. Signal processing techniques, especially blind deconvolution methods, play a significant role in feature extraction, signal denoising, and fault identification. The use of blind deconvolution methods in machinery fault diagnosis has been extensively studied and applied, with a focus on historical background, principles, merits, limitations, performance analysis, research, and applications.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

添加到收藏夹

Article Engineering, Mechanical

Fully interpretable neural network for locating resonance frequency bands for machine condition monitoring

Dong Wang et al.

Summary: This paper presents a fully interpretable neural network for machine condition monitoring, which combines signal processing and physical feature extraction to automatically localize informative frequency bands.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

添加到收藏夹

Article Engineering, Mechanical

Interpretable online updated weights: Optimized square envelope spectrum for machine condition monitoring and fault diagnosis

Bingchang Hou et al.

Summary: This paper studies the integration of online monitoring data with cyclostationarity of fault transients to construct a fault cyclostationarity-based convex optimization model. An online weight updating algorithm is developed to make the weight updating of the proposed optimization model adaptive to online monitoring data. Interpretable online updated weights are proposed as an optimized square envelope spectrum (OSES) to enhance the identification of fault characteristic frequency (FCF) and its harmonics. A three-dimensional (3D) OSES and a detector with an alarming threshold are designed to achieve incipient fault time detection, fault type diagnosis, and online fault evolution monitoring. The effectiveness and superiority of this approach are validated using practical bearing datasets and experimental run-to-failure datasets.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

添加到收藏夹

Article Automation & Control Systems

WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis

Tianfu Li et al.

Summary: The article introduces a novel wavelet-driven deep neural network, WaveletKernelNet (WKN), for mechanical fault diagnosis, which is more effective than traditional CNN in terms of accuracy and convergence speed. The network is designed with a continuous wavelet convolutional layer to discover more meaningful kernels and provides a customized kernel bank for extracting defect-related impact components.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2022)

添加到收藏夹

Article Engineering, Mechanical

The sum of weighted normalized square envelope: A unified framework for kurtosis, negative entropy, Gini index and smoothness index for machine health monitoring

Dong Wang et al.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2020)

添加到收藏夹

Review Engineering, Mechanical

Machinery health prognostics: A systematic review from data acquisition to RUL prediction

Yaguo Lei et al.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2018)

添加到收藏夹

Article Engineering, Mechanical

Fast computation of the kurtogram for the detection of transient faults

Jerome Antoni

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2007)

添加到收藏夹

Understanding importance of positive and negative signs of optimized weights used in the sum of weighted normalized Fourier spectrum/envelope spectrum for machine condition monitoring

相关参考文献

A review on the application of blind deconvolution in machinery fault diagnosis

Fully interpretable neural network for locating resonance frequency bands for machine condition monitoring

Interpretable online updated weights: Optimized square envelope spectrum for machine condition monitoring and fault diagnosis

WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis

The sum of weighted normalized square envelope: A unified framework for kurtosis, negative entropy, Gini index and smoothness index for machine health monitoring

Machinery health prognostics: A systematic review from data acquisition to RUL prediction

Fast computation of the kurtogram for the detection of transient faults

导出引文

分享论文