- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Fault Classification in Electrofusion Polyethylene Joints by Combined Machine Learning, Thermal Pulsing and IR Thermography Methods - A Comparative Study
摘要： The capability of conveniently classifying the fault types in the electrofusion joints can certainly increase the security of polyethylene gas pipelines. Therefore in the current study, we use machine learning to push the horizons of our recent thermal pulsing and IR thermography method, to identify ovality versus unalignment faults. To do so, we extend our experimental IR-thermography data bank and then apply k-means, Random Forests and GLMNet algorithms in a two stage approach. The overall classification accuracy for k-means and Random Forests were 70.37% and 84.21% respectively; GLMNet could successfully outperform the others with a classification accuracy of 93.75%.
关键词： Machine Learning,Electrofusion Polyethylene Joint,IR Thermography,Fault Classification,Thermal Pulsing NDT
更新于2025-09-23 15:21:21
-
A novel computational supplement to an IR-thermography based non-destructive test of electrofusion polyethylene joints
摘要： Electrofusion Polyethylene (PE) joints are important elements of the gas distribution networks. Unfortunately they are prone to leakage if not tested thoroughly. Our team has recently proposed a novel noncontact and IR thermal non-destructive test for these PE joints. That is, to induce a controlled heat pulse within the joint via its internal wire, and compare its thermal response with other experimental reference cases. Two gaps exist in this method due to the lack of access to a mathematical model. Firstly the pulsing duration at different initial temperatures are only determined by trial and errors. Secondly, preparing experimental reference thermal images at different joint conditions is considerably costly. Therefore, here we rigorously simulate this pulsing process to tackle both abovementioned shortcomings. We experimentally validate our simulation and report the appropriate pulsing durations between 300 K and 320 K initial temperatures. Moreover, we successfully screen a contaminated joint nondestructively.
关键词： Non destructive testing,Dynamic heat transfer,Non-contact IR test,Electrofusion polyethylene joint,IR thermal imaging
更新于2025-09-23 15:21:01