Unlock instant, AI-driven research and patent intelligence for your innovation.

Vertical ladder excessive vibration fault diagnosis method based on wavelet packet decomposition and neural network

A technology of wavelet packet decomposition and neural network, which is applied in the field of fault diagnosis based on wavelet packet decomposition and fully connected neural network, can solve the problems of responding to equipment fault information, difficulty, etc., achieve good diagnostic results, ensure safety, and reduce accidents Effect

Active Publication Date: 2019-11-19
ZHEJIANG UNIV
View PDF12 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

After the signal is preprocessed, since there are many sub-signals obtained by decomposition, and there are many time-frequency domain features of the signal, it is difficult to effectively reflect the fault information of the equipment by extracting a single statistical feature

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Vertical ladder excessive vibration fault diagnosis method based on wavelet packet decomposition and neural network
  • Vertical ladder excessive vibration fault diagnosis method based on wavelet packet decomposition and neural network
  • Vertical ladder excessive vibration fault diagnosis method based on wavelet packet decomposition and neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific examples.

[0036] For mechanical equipment, its vibration signals contain a lot of effective information, which can reflect the operation of the mechanical equipment at this time. The characteristics of the signal in the time domain can reflect the characteristic information of the signal more intuitively, and the characteristics of the signal in the frequency domain can reflect the characteristic information contained in the signal from another angle. However, the original acceleration signal when the elevator is running contains a lot of noise, and the calculation of time domain features and frequency domain features directly based on the original signal cannot accurately reflect the characteristic information contained in the signal. Therefore, the present invention first uses wavelet packet decomposition to perform three-level decomposition on th...

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

No PUM Login to View More

Abstract

The invention discloses a vertical ladder excessive vibration fault diagnosis method based on wavelet packet decomposition and a neural network. Aiming at a vertical elevator, a wavelet packet decomposition method and a full-connection neural network are comprehensively applied, and the fault of excessive elevator vibration is diagnosed based on an elevator acceleration signal. According to the invention, considering the non-stationarity of the elevator acceleration signal in the actual environment; decomposing the acceleration signal into sub-signals by wavelet packet decomposition; extracting time-frequency domain features of the sub-signals, combining the time-frequency domain features into a feature vector, performing binary classification processing on the positive sample and the negative sample according to the feature vector of the acceleration signal by using a fully connected neural network, and establishing a model capable of identifying the positive sample and the negative sample for online fault diagnosis. By means of the method, effective real-time diagnosis of the faults caused by excessive vibration of the vertical elevator is achieved, a good diagnosis effect is achieved, the safety of the manned elevator in the running process is guaranteed, and accidents are reduced.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of acceleration signals, in particular to a fault diagnosis method based on wavelet packet decomposition and fully connected neural network for excessive vibration of straight elevators. Background technique [0002] Straight ladder is a kind of special equipment widely used in urban buildings, and its safety and reliability are directly related to the personal safety of residents. According to the "Notice of the State Administration of Market Supervision and Administration on the National Special Equipment Safety Situation in 2017" issued by the General Administration of Quality Supervision, Inspection and Quarantine, as of the end of 2017, the total number of special equipment in the country reached 12.9652 million units, an increase of 8.31% compared with the end of 2016. The number of elevators 5.627 million units. In 2017, there were 238 special equipment accidents and related accide...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/06G06F2218/08G06F2218/12
Inventor 赵春晖郑琪李泽华
Owner ZHEJIANG UNIV