Fault diagnosis system for an electronically controlled hydraulic crawler crane

Pao Yue-kong Library Electronic Theses Database

Fault diagnosis system for an electronically controlled hydraulic crawler crane

 

Author: Ho, Kim-lai Antony
Title: Fault diagnosis system for an electronically controlled hydraulic crawler crane
Year: 1999
Subject: Hydraulic machinery -- Data processing
Expert systems (Computer science)
Fault location (Engineering) -- Data processing
Hong Kong Polytechnic University -- Dissertations
Department: Multi-disciplinary Studies
Dept. of Manufacturing Engineering
Pages: viii, 101 leaves : ill. ; 30 cm
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b1492570
URI: http://theses.lib.polyu.edu.hk/handle/200/2689
Abstract: At the construction site, crawler crane is one of the major plants for material handling and earth moving. Therefore, efficient and accurate trouble shooting is critical to minimize the down time of it. The goal of this project is to construct a fault diagnosis system using an expert system approach. Firstly, the operation principle of the studied crane is analysed to obtain the full functional picture of the components, performance parameters, malfunction patterns and data flow in the system. On the other hand, the personnels performing the trouble shooting are interviewed to gather their expert knowledge, experience on problems and suggestions on the diagnosis procedure. This conducts the knowledge acquisition for the expert system. Based on the information collected from the analysis and interview, a symptom to fault knowledge base is formed. To represent the knowledge base, rule representation formalism is selected. For manipulation of the rules in the inference engine, backward chaining is considered as it is a sound diagnostic reasoning algorithms. Turbo PROLOG is chosen for programming because it is a symbolic language and suited for backward chaining. To test the diagnostic expert system, trial run was carried out at the construction site. A signal-sampling monitor collected a set of data in normal working condition. Then by readjusting the control system, simulated symptoms and the data of the abnormal condition were obtained. The results are discussed to evaluate the performance of the system. The developed expert system was well functioning in the simulated single-fault condition and capable to shorten the trouble shooting and the machinery down time. The results also reflected the significance of human domain expertise in the formation of the knowledge base. However, the weakness of the developed expert system in multi fault diagnosis was disclosed and it provided hints that for further modification and application development, weighting mechanism and rules for handling uncertainty must be introduced in the expert system.

Files in this item

Files Size Format
b14925709.pdf 4.305Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. 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.
  3. 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.

     

Quick Search

Browse

More Information