| Author: | Lee, Tak-shing |
| Title: | Automatic brake pad gauging by machine vision |
| Degree: | M.Sc. |
| Year: | 1997 |
| Subject: | Railroads -- Trains -- Brakes -- Maintenance and repair Computer vision -- Industrial applications Hong Kong Polytechnic University -- Dissertations |
| Department: | Multi-disciplinary Studies Department of Electrical Engineering |
| Pages: | [132] leaves : ill. ; 31 cm |
| Language: | English |
| Abstract: | The maintenance schedules for all types of rail vehicles call for frequent inspections of underside components and systems. For many such examinations, the inspection is largely visual. Inspection of brake pad condition is a major requirement, and is often cited as the primary reason for the most frequent examination interval. Brake pads are a high cost consumable item so maximizing pad life is an important consideration. At present, brake pad maintenance is based upon setting a lower limit for pad thickness and changing any pads below this limit when the unit is in the depot examination. The limit used has to be based upon the worst set of possible wear conditions in order to prevent pads wearing through to the back plate, contacting the disc and causing expensive damage. Individual pads do not wear at the same rate, even on the same unit or vehicle. There are many reasons for this, some due to design of the unit {load regulation, different vehicle mass etc.} and others to variations in performance of the brake system (rough discs, sticking calipers, faulty pneumatic actuators etc.). The worst case wear rate is typically 3 times higher than the average, resulting in conservative gauging limits and significant wastage of friction material life for the majority of pads, particularly as longer maintenance intervals are employed. For many fleets this high cost of pad material wastage is the main factor preventing an extension in maintenance intervals. This paper describes an automatic system for the measurement of brake pad thickness. This system called Automatic Brake Pad Measuring System, determines the wear rate and thickness of all pads in the fleet and makes automatic predictions of life of each pad. Using this information allows a new approach to pad maintenance resulting in significant cost savings. The whole process for developing the Automatic Brake Pad Gauging System involves concept developing, image processing algorithum implementation, system fine tune and real system installation. Based on the experience of developing and of the image processing algorithum, we found that the most important thing are the methodology for extracting the area of interest and determine the critical parameters in a reliable way. In this project, we choose a simple image processing algorithum to perform the operation. Reliable measurement and acceptable processing speed can be achieved and verified through the testing process. The image analysis process is summarized as the following stages:- (i) In order to increase processing speed, the image would pre-process through histogram equalization and thresholding (ii) The hole of pad holder would be identified as a centre reference point of image (iii) The scaling factor would be determined by calculating the distance / no. of pixel between two reference point on the holder (iv) The distance between holder and disc would be determined by counting the distance between the lines of holder/pad interface and pad/disc interface (v) The Pad thickness can then be found through transformation of the distance in Step iv by a constant offset factor (gap between holder and pad) and a ratio factor (scaling factor determined in step iii). |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b1471954x.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.84 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/4317