4 August 2009 Fuzzy clustering of infrared images applied in air leak localization
Author Affiliations +
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.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Nan Ge, Nan Ge, Guang-zheng Peng, Guang-zheng Peng, Mu-zhou Jiang, 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); doi: 10.1117/12.836623; https://doi.org/10.1117/12.836623
PROCEEDINGS
8 PAGES


SHARE
Back to Top