Anda di halaman 1dari 28

DESIGN OF RAIL TRACK FLAW DETECTION

SYSTEM USING MATLAB

Presented by

ESHU SHARMA
M.Tech(MEC)

14SCME202001

Under the Supervision of


SWET CHANDAN
Assistant Professor
School of Mechanical Engineering

CONTENT
Introduction
Case Studies
Literature Review
Objectives
Vision inspection system
Work done so far

Data

collection
Method selection
Coding

Further Work
References

INTRODUCTION

Rail track inspection is a necessary task in railway


maintenance and is required to periodically inspect the
rail track by trained human operator, who is walking along
the track & searching for defects .
The detection of cracks in rails is a challenging problem,
and much research effort has been spent in the
development of reliable, repeatable crack detection
methods for use on in service rails.
Rail inspection methods include destructive techniques
and non-destructive techniques, such as hammer
sounding. But these methods just cover limited space and
3
have limited effectiveness in identifying the faults.Contd.

Non-destructive evaluation techniques for rail track


inspection had developed. These technologies include
ultrasonic
and eddy current methods,neither
technique is particularly effective for the detection of
cracks in the rail foot. The results of these studies
confirm the ability of the proposed method to locate
and quantify surface-connected notches and cracks
Visual inspection has been developed in recent years
with the great progress of computer vision
techniques. In a visual inspection system (VIS), a
high speed digital camera, which is installed under a
test train, is used to capture images of a rail track as
the train moves over the track, and then, the
obtained images are analyzed automatically using a
customized image processing software.

CASE STUDIES
In indian railway 80% accidents were caused by
human failure.
Here we have the summary of rail accidents due to
derailment causes from year 2009 to 2014.
YEAR
ACCIDENTS
2009-10
80
2010-11
78
2011-12
55
2012-13
48
2013-14
52

Contd.

LITERATURE REVIEW
Esther

resendiz and narendra ahuja [1] were proposed


Automated visual inspection of rail road tracks in june ,2013
A computer vision system, consisting of field-acquired video
and subsequent analysis, could improve the efficiency of the
current methods. Such a system is prototyped, and the
following
challenges
are
addressed:
the
detection,
segmentation, and defect assessment of track components
whose appearance vary across different tracks and the
identification and inspection of special track areas. An
algorithm that utilizes the periodic manner in which track
components repeat in an inspection video is developed. Results
are demonstrated on field acquired images and video
7

Contd.

LITERATURE REVIEW
Gimy

joy and Jyothi R L [2] were proposed A Real Time VIS


for Rail Flaw Detection in august ,2014
This paper presents a real-time VIS for discrete surface defects
of rail heads. VIS comprises the Image Acquisition Subsystem
(IAS) and the image analysis subsystem. IAS acquires gray rail
images for the surface of a rail head, and the latter processes
rail images and detects possible defects. This paper propose the
Local Normalization(LN) method to enhance the distinction
between defects and background in a rail image. VIS first
acquires a rail image by the image acquisition system, and then,
it cuts the sub image of rail. Track by the track extraction
algorithm. Then, VIS enhances the contrast of the rail image .At
last, VIS detects defects using the defect localization based on
projection profile (DLBP), which identifies possible defects using
the projection profile of the mean intensity over each
8
longitudinal (or transversal) line. This is robust to noise and
Contd.
very fast.

LITERATURE REVIEW
Ashwini belkhade and Snehal kathale [3] were
proposed Automatic vision based inspection of railway
track-a review in Indian journal of research in
engineering and technology.
This paper proposes a system to inspect the rail track
component such as missing bolts, tie plates, anchors etc by
using vision based method and simultaneously do the
calibration of railway track by using vibration based
method. The system provides real-time monitoring and
structural condition for railway track using vision based
method and calibration to search the fault location on the
track. Inspections include detecting defects on tracks,
missing bolts, anchor, tie plate and clips etc. In vision based
method camera we will use to capture the images or videos.
In vibration based method some sensors we will use to
9
detect the vibrations on the railway track.We will extract
Contd.
the signal from 2-D.

LITERATURE REVIEW

Mohd. Karukh Hashmi and Avinash G Keskar [5]


were proposed Computer-Vision Based Visual
Inspection And Crack Detection Of Rail Road Tracks
in Recent Advances in Electrical and Computer
Engineering.
This paper proposes a rail surface defects inspection
method based
on computer vision system. Various
algorithm related denoising, filtering, thresholding;
segmentation and feature extraction are applied for
processing the images of Railroad surface defect and
cracks. It has mostly been implemented on computers.
For better speed and complexity, the algorithms need
to be implemented on embedded platforms.

10

METHODS USED IN PAST


EDDY

CURRENT CRACK DETECTION METHOD:

It is used to detect discontinuities and defects in conductive


materials. Eddy current inspection system of rail flaws used in this
study included a detection coil and an excitation coil, which formed
an eddy current sensor probe. Two eddy current sensor probes
were used. One was for detecting the signal from a rail. It was
positioned on a tested sample and scanned along the rail length.
Another was for reference. It was positioned in air far from a
sample. The controller supplied an excitation current to a series
connection of two excitation coils and amplified a signal from the
detection coils. The width of the railhead was 65 mm; thus, the
detection coil in the sensor probe could not effectively evaluate the
entire plane of the rail top. Therefore, the position of the sensor
probe was varied in five different positions along the width. The
scan speed of the sensor probe was 2.5 mm/s and the data
acquisition rate was 8 point/s (3.2 point/mm). The frequency ofthe
exciting magnetic field was 5 kHz.

11

ULTRASONIC

CRACK DETECTION METHOD:

Rails are systematically inspected for internal and surface defects


using various Non-Destructive Evaluation (NDE) techniques.
During the manufacturing process rails are examined visually for
any surface damage, while the presence of any internaldefects is
assessed mainly through ultrasonic inspection.Ultrasonic testing
(UT) is a non-destructive inspection method that uses high
frequency sound waves (ultrasound) that are above the range of
human hearing, to measure geometric and physical properties in
materials. To perform UT, electrical energy is converted to
mechanical energy, in the form of sound waves, by a transducer. The
transducer accomplishes this energy conversion due to a
phenomenon referred to as the piezoelectric effect. This occurs in
several materials, both naturally-occurring and manmade. Quartz is
a naturally occurring piezoelectric material. A piezoelectric material
will produce a mechanical change in dimension when excited with
an electronic pulse. Similarly, this same material will also produce
an electric pulse when acted upon mechanically.

12

OBJECTIVE:

Reduce rail accidents caused by surface cracks.


1)Proper maintenance of rail tracks.
2)Identify the crack geometry.
o

13

VISION INSPECTION SYSTEM

14

VISION INSPECTION SYSTEM

In vision based method our device will capture videos of


railway track component using vehicle-mounted Camera,
image enhancement using image processing and assisted
automation using a real time tracking algorithms.
In a visual inspection system (VIS), a high speed digital
camera, which is installed under a test train, is used to
capture images of a rail track as the train moves over the
track, and then, the obtained images are analyzed
automatically using a customized image processing programe.
15

Contd.

ISITION

Digital cameras are used to capture the images or


videos of rail track
Surf View comes with on board computer, data
acquisition and software along with six cameras
scanners and cables .A calibrated CCTV camera is
used to capture the image frame at resolution 640x480
at 30 frames per second which was mounted on the rail
track
Different types of cameras are used for data
acquisition purpose in different vision based system.

16

Contd.

DATA ACQUISITION SYSTEM

17

IMAGE ANALYSIS
The frames of image are proceeds by using algorithm
to identify the defected component and assess the
stipulation of railway tracks.
In vision based system image processing is used to
recognize of clips, smoothing and edge detection.
The captured data send to PC .
Matlab coding program is used for defect analysis and
it provide a comprehensive result evaluation

18

Contd.

WORK DONE SO FAR


Data collection

19

METHOD SELECTION
Here we have so many methods for rail track
fault detection,like music algorithm,neural
networks,pixelation and wavelets etc.
We use matlab coding method due to certain
causes like easy to understand,fault detection is
easy,coding is easy.

20

CODING
First give the image to the system.
Adjust the image.
Convert the image from RGB to Gray.
We done thresolding operation on image.
Then we apply several morphological operation on
image like
1. Cleaning of image
2. Thinning of image
3. Filled image
. Then we apply image tool for crack detection.
. At last we give command for crack length detection.

21

CODE
load image
I=imread('two.jpg');
figure,imshow(I)
title('Original image')
Image adjust
Istrech = imadjust(I,stretchlim(I));
figure,imshow(Istrech)
title('Contrast stretched image')
Convert RGB image to gray
Igray_s = rgb2gray(Istrech);
figure,imshow(Igray_s,[])
title('RGB to gray (contrast stretched) ')

22

o Image segmentation by thresholding

use incremental value to run this selection till required


threshold 'level' is achieved
level = 0.08;
Ithres = im2bw(Igray_h,level);
figure,imshow(Ithres)
title('Segmented cracks')
Image morphological operation
BW = bwmorph(gradmag,'clean',10);
figure,imshow(BW)
title('Cleaned image')
BW = bwmorph(gradmag,'thin', inf);
figure,imshow(BW)
title('Thinned image')
BW = imfill(gradmag, 'holes')
figure,imshow(BW)
title('Filled image')

23

Image tool
figure,imtool(BW1)
figure,imtool(I)
Calaculate crack length
calibration_length=0.001;
calibration_pixels=1000;
crack_pixel=35;
crack_length=(crack_pixel
*calibration_length)/calibration_pixels;

24

FURTHER WORK
Another parameter of crack width yet to be
calculated.
The image tool work has to be completed yet.
Real time implemention is also in process.

25

REFERENCES
1-Esther Resendiz,Member, IEEE, John M. Hart, and Narendra
Ahuja, Felllow IEEEAutomated Visual Inspection of Railroad
Tracks IEEE transaction on intelligent transportation systems,
vol.14, no.2, June 2013
2-Jyothi R L ,Gimy joy A Real Time VIS For Rail Track Flaw
Detection
International Journal of Scientific and
Research Publications, August 8,2014
3-Ashwini Belkhade and Snehal Kathale, Automatic Vision Based
Inspection Of Railway Track A Review International Journal Of
Research In Engineering and Technology .
4-Luis Fernando, Condition Monitoring Of Railway Turnouts And
Other Track Components Using Machine Vision November 2010
5-Mohd. Karukh Hashmi and Avinash G. Keskar, Computer
Vision Based Visual Inspection And Crack Detection Of Rail Road
Tracks Recent Advances in Electrical and Computer Engineering .

26

REFERENCES
6-Abhisekh Jain, Arvind, Balaji, Ram Viyas N.P. Onboard dynamic
rail track safety monitoring system International conference on
advanced communication systems, January 10 - 12, 2007
7-. Beena vision Automated Rail Surface and Track Inspection.
8-Isabelle Tang and Toby P. Breckon, Automatic road environment
classification IEEE transaction on intelligent transportation systems,
vol.12, no.2, June 2011.
9-Hoang Trinh Norman Haas Ying Li Charles Otto Sharath Pankanti
Enhanced rail component detection and consolidation for rail track
inspection Ibm T. J. watson research center 19 skylikne dr,
hawthorne, ny 10532.
10-Maneesha Singh, Sameer Singh, Autonomous rail track inspection
using vision based system IEEE international conference on
computational intelligence for homeland security and personal safety
alexandria, va, usa 16-17 october 2006.

27

THANK YOU

28

Anda mungkin juga menyukai