A Gearbox Vibration Signal Compressed Sensing Method Based on the Improved GLOW Flow Model
Journal Title: Precision Mechanics & Digital Fabrication - Year 2024, Vol 1, Issue 4
Abstract
In response to the complex characteristics of gearbox vibration signals, including high frequency, high dimensionality, non-stationarity, non-linearity, and noise interference, this paper proposes a data processing method based on improved compressed sensing. First, the K-means Singular Value Decomposition (K-SVD) dictionary is used for sparse representation, ensuring good sparsity in the frequency domain. Next, a random convolution kernel measurement matrix is employed in place of the traditional Gaussian random matrix, satisfying the equidistant constraint while enhancing both computational and hardware implementation efficiency. Finally, the Generative Flow (GLOW) model is introduced, incorporating the measurement matrix, dictionary matrix, and sparse coefficient matrix into a unified optimization framework for joint solving. Through reversible mapping and probabilistic distribution modeling, the method effectively addresses noise interference and the challenges posed by complex signal distributions. Experimental results show that, compared with traditional compressed sensing methods, the proposed method offers superior signal reconstruction quality and better noise robustness.
Authors and Affiliations
Tichun Wang, Tian Xia
Keywords
Related Articles
- EP ID EP755411
- DOI https://doi.org/10.56578/pmdf010402
- Views 44
- Downloads 0
Formulation of Stiffness and Strength Characteristics of Flexible Wire Ropes and Their Application in Photovoltaic Support Structures
The safety and functionality of flexible photovoltaic (PV) racking systems critically depend on understanding the force and deformation behavior of wire ropes. This study establishes mechanical equilibrium equations to d...
Digitalization of Strategic Decision-Making in Manufacturing SMEs: A Quantitative SWOT-TOWS Analysis
The transition of contemporary manufacturing processes from digital to post-digital paradigms within the framework of Industry 5.0 necessitates the integration of both technological advancements and human-centered perspe...
Identification of the Conduit Water Starting Time Constant in Hydropower Plants Using LSTM and MLP Machine Learning Algorithms
The accurate determination of the conduit water starting time constant (Tw) is critical for optimizing hydro turbine performance and dynamic control in hydropower plants. Instead of relying on conventional calculation me...
Reliability Analysis of Complex Repairable Systems Using Artificial Neural Networks: A Case Study on Underground Mining Machinery
The effective utilisation of equipment is essential for achieving the operational goals within production sectors, particularly in industries involving heavy machinery. Throughout its lifecycle, equipment is exposed to d...
Forward Kinematics Solution for Cable-Driven Hyper-Redundant Manipulators Based on BiLSTM
This paper investigates the kinematic solution of cable-driven hyper-redundant manipulators, focusing on the transformation from the cable-driven space to the joint space. Two forward kinematics solution networks based o...