Automatic Pipeline Inspection

TNT members involved in this project:
Dipl.-Inf. Daniel Gritzner
Prof. Dr.-Ing. Jörn Ostermann
Dr.-Ing. Karsten Vogt
Show active Staff only

Undetected corrosion damage can lead to incalculable economic and environmental costs during the operation of industrial pipelines. For cost reasons, the early detection of such damage (predictive maintenance) is usually performed by passively operated robots, which are routed through the pipeline system during its normal operation. Such robots, however, record huge amounts of data. In this project, methods of machine learning and signal processing, among others, were adapted to achieve the fully automatic analysis of this sensor data.

Corrosion damage can be effectively detected by measuring the magnetic flux leakage (MFL) at the inner wall of a pipe. However, features observed in the MFL signal may also be attributed to uncritical events, such as the occurrence of welds and valves. Such events must therefore first be distinguished from potential pipe damage by employing modern methods of signal processing and machine learning.

Processing Chain
Figure: Processing chain for the automatic analysis of magnetic flux leakage signals for the detection of corrosion damage in pipelines

 

Within this project, various methods have been applied and developed, including:

  • Edge-preserving signal denoising
  • Object detection
  • Segmentation
  • Model-free outlier detection
  • Nonlinear optimization