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

Method for identifying wheel state of railway vehicle based on axle box vibration

A rail vehicle and state recognition technology, which is applied in the direction of railway vehicle testing, character and pattern recognition, wheel rim measurement/measurement, etc., can solve the problems of train overall stability reduction, vibration acquisition, peeling, etc., achieve remarkable recognition effect, eliminate random Effects of noise disturbance and impact mitigation

Inactive Publication Date: 2019-11-26
广州运达智能科技有限公司
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the rigid contact between the wheel and the track, under the long-term interaction between the wheel and the rail, the wheels are prone to defects such as tread abrasion, peeling, cracks, polygonization, etc., resulting in increased wheel-rail vibration and reduced overall train stability.
Studies have shown that wheel-rail vibration can effectively reflect the running state of the wheel on the track, but the vibration cannot be directly obtained at the vibration source, and the axlebox is the most effective place to obtain wheel-rail vibration
Although most of the vibration signals of the axlebox come from the vibration of the wheel and rail, there are also a lot of noise and vibration caused by other components
Most of the existing wheel fault identification methods do not consider the noise reduction problem, and a few methods use mean noise reduction and wavelet noise reduction, but the noise reduction effect is not ideal
In addition, the influence of train speed on the spectrum characteristics of vibration signals cannot be ignored when extracting fault features. Currently, fault identification methods based on frequency domain features do not consider the important factor of speed, or select data under uniform speed conditions for analysis. Data at speed is not adaptive
Moreover, the existing wheel fault identification methods basically only perform feature recognition for a single fault type, and do not evaluate the overall health status of the wheel.

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
  • Method for identifying wheel state of railway vehicle based on axle box vibration
  • Method for identifying wheel state of railway vehicle based on axle box vibration
  • Method for identifying wheel state of railway vehicle based on axle box vibration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] This embodiment proposes a method for identifying the state of rail vehicle wheels based on axlebox vibration, such as figure 1 As shown, the method includes the following steps:

[0054] Step S1, collecting the vibration signal of the axle box during the running of the train in real time.

[0055] In this embodiment, a three-way vibration acceleration sensor is installed on the axle box to collect vibration acceleration signals of the axle box during the train running (different speeds).

[0056] Step S2, resampling the vibration signal collected in step S1, so that the vibration signal in each speed state has consistent frequency domain characteristics.

[0057] In this embodiment, the speed-adaptive signal processing method is adopted to satisfy that the data in each speed state has consistent frequency domain characteristics, that is, among the signals with different speeds at one end selected, the signal with the highest speed is used as the reference. The other ...

Embodiment 2

[0083] In this embodiment 2, the method proposed in the above-mentioned embodiment 1 is applied to the specific process of the state identification of rail transit train wheels as follows:

[0084] 1. The present invention collects wheel vibration signals at corresponding positions by installing a three-way vibration acceleration sensor on the bogie axle box. The specific sensor arrangement position is as follows: figure 2 As shown, ZZC01~ZZC04 represent the sensors on the four axle boxes corresponding to the bogie respectively. In this way, the on-site test is carried out when the train is running, and the vibration signal x(t) is collected, such as image 3 shown.

[0085] 2. The sampling frequency of the vibration signal is set to f t (4kHz in this example), the sampling rate of the train speed value is 1Hz, that is, each speed value corresponds to 4k vibration acceleration values. When the speed range is between 20km / h and 70km / h, take ν max The vibration value corres...

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 method for identifying the wheel state of a railway vehicle based on axle box vibration. The method comprises the steps of S1, acquiring axle box vibration signals in the running process of the train in real time; S2, resampling the vibration signals acquired in the step S1 so as to enable the vibration signals in each speed state to have consistent frequency domain characteristics; S3, noise carrying out noise reduction processing on the vibration signals obtained after resampling in the step S2; S4, extracting wheel state characteristic indexes of the vibration signals subjected to noise reduction processing in the step S3; and S5, training and classifying the wheel state characteristic indexes obtained in the step S4, and identifying the wheel state. The methodis applied to the field of rail transit, has speed adaptability, can effectively eliminate random noise interference, and can effectively reduce the influence of coherent noise related to speed on effective signals for signals with different speeds.

Description

technical field [0001] The invention relates to the technical field of wheel detection, in particular to a method for identifying the state of rail vehicle wheels based on axlebox vibration. Background technique [0002] As a key component of rail vehicles, wheels play an important role in supporting the car body structure and driving the car body to move. Its health directly affects the safety and stability of driving. Due to the rigid contact between the wheel and the track, under the long-term interaction between the wheel and the rail, the wheels are prone to defects such as tread scratches, peeling, cracks, polygons, etc., resulting in increased wheel-rail vibration and reduced overall train stability. The research shows that the wheel-rail vibration can effectively reflect the running state of the wheel on the track, but the vibration cannot be obtained directly at the vibration source, and the axlebox is the most effective place to obtain the wheel-rail vibration. Al...

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): G01M17/10G01M17/08G01H17/00B61K9/12G06F17/14G06F17/16G06K9/62G06Q10/06G06Q50/30
CPCG01M17/10G01M17/08G01H17/00B61K9/12G06F17/142G06F17/16G06Q10/06393G06F18/2411G06Q50/40
Inventor 陈博邹梦卜显利胡林桥王志云
Owner 广州运达智能科技有限公司