Fault detection separation sparse representation method and fault period detection method
A sparse representation and fault detection technology, applied in the fields of instruments, character and pattern recognition, computer parts, etc., which can solve the problems of difficulty in accurately extracting fault cycles, instability, etc.
Inactive Publication Date: 2018-08-07
JIANGSU UNIV
View PDF4 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the bearing fault vibration signal always contains periodic transients and strong background noise, which is unstable, which makes it difficult to accurately extract the fault period only by frequency domain analysis
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0052] The purpose of the present invention is to provide a fault cycle detection method based on a sparse model, which is used for detecting and extracting fault cycles in vibration signals. A disjoint sparse representation model is constructed in which the disjunction time parameter can be tuned. The method uses B-spline basis functions to construct a dictionary representing sparse signals. The augmented Lagrangian shrinkage algorithm is applied to efficien...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a fault detection separation sparse representation method and a fault period detection method. The method comprises the steps of providing a new fault detection technology by utilizing the sparsity of transient components; constructing a separation sparse representation model with an adjustable separation time parameter; in the implementation process of the model, adoptingthe B-spline dictionary to represent the transient process due to the inherent model sparsity and the impressive flexibility, solving the model by utilizing the split augmented Lagrangian shirkage algorithm; and providing the fault period detection standard based on that the power value calculated by the reconstructed signal reaches the maximum value when the separation time parameter is the sameas the real fault period. The effectiveness of the method is verified through simulation and actual rolling bearing fault vibration signals. The result shows that the method is superior to fault period detection methods of wavelet transformation and empirical mode decomposition.
Description
technical field [0001] The invention relates to the field of signal analysis and detection, in particular to a detection method for sparse representation of transient components in a signal and a fault cycle detection method, which can be used to extract vibration signals of multiple cycles in compound fault extraction for other mechanical applications. Background technique [0002] At a constant speed, when a local defect occurs on the bearing, the vibration signal measured due to the transfer of the defect always contains periodic transients. The most relevant information for detecting the type of fault is the time interval between transients, the fault period. However, faulty cycle information is usually severely masked by background noise, so advanced signal processing techniques need to be developed to remove noise and detect faulty cycles. [0003] There are usually three signal processing methods to detect the fault cycle of the signal under test, real-time domain an...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/00G06K9/62
CPCG06F2218/00G06F18/2136
Inventor 许桢英万东燕洪红
Owner JIANGSU UNIV