This thesis presents a development of Structural Health Monitoring (SHM) and Fault Diagnosis based on Artificial Immune System (AIS), a biology-inspired method motivated from the Biological Immune System (BIS). Using the antigen to model structural health or damage condition of specific characteristics and the antibody to represent an information system or a database that can identify the specific damage pattern, the AIS can detect structural damage and then take action to ensure the structural integrity. In this study the antibodies for SHM were first trained and then tested. The feature space in training includes the natural frequencies and the modal shapes extracted from the simulated structural response data including both free-vibration and seismic response data. The concepts were illustrated for a 2-DOF linear mass-spring-damper system and promising results were obtained. It has shown that the methodology can be effectively used to detect, locate, and assess damage if it occurred. Consistently good results were obtained for both feature spaces of the natural frequencies and the modal shapes extracted from both response data sets. As the only exception, some significant errors were observed in the result for the seismic response data when the second modal shape was used as the feature space. The study has shown great promises of the methodology for structural health monitoring, especially in the case when the measurement data are not sufficient. The work lays a solid foundation for future investigations on the AIS application for large-scale complex structures.
Identifer | oai:union.ndltd.org:wpi.edu/oai:digitalcommons.wpi.edu:etd-theses-1168 |
Date | 29 February 2012 |
Creators | Xiao, Wenchang |
Contributors | Zhikun Hou, Advisor, Mikhail F. Dimentberg, Committee Member, Yeesock Kim, Committee Member, Stephen S. Nestinger, Committee Member |
Publisher | Digital WPI |
Source Sets | Worcester Polytechnic Institute |
Detected Language | English |
Type | text |
Format | application/pdf |
Source | Masters Theses (All Theses, All Years) |
Page generated in 0.0019 seconds