Fuzzy clustering of infrared images applied in air leak localization

Nan Ge; Guang-zheng Peng; Mu-zhou Jiang

doi:10.1117/12.836623

4 August 2009 Fuzzy clustering of infrared images applied in air leak localization

Nan Ge, Guang-zheng Peng, Mu-zhou Jiang

Proceedings Volume 7383, International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications; 73830U (2009) https://doi.org/10.1117/12.836623
Event: International Symposium on Photoelectronic Detection and Imaging 2009, 2009, Beijing, China

Abstract

Most current research into the localization of leaks is focused on leaks of petroleum and natural gas pipelines, while there is very little new work being done on the leakage of vessels. A novel air-leak diagnosis and localization method based on infrared thermography is described in this paper, which is developed in an attempt to overcome the disadvantages of low efficiency and poor anti-jamming ability associated with the traditional approaches to localization of leaks from a vessel. The method achieves leak positioning through a factor θ based kernelized fuzzy clustering segmentation done to weighted differential thermal images of the test objects. The temperature difference factor θ is inventively built as a parameter changed with temperature range of the target region, in order to enhance the robustness and the interference proof ability of the algorithm. Heat transfer simulation with air-leak flow is addressed by the finite element analysis. The experimental results indicate that the method proposed is effective and sensitive. The purpose of air-leak localization has been reached.

Citation Download Citation

Nan Ge, Guang-zheng Peng, and Mu-zhou Jiang "Fuzzy clustering of infrared images applied in air leak localization", Proc. SPIE 7383, International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications, 73830U (4 August 2009); https://doi.org/10.1117/12.836623

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available