Engler and Prantl system of classification in plant taxonomy
Rita Gaibadullina - Automatic defect recognition in corrosion logging using magnetic imaging defectoscopy data
1. Automatic Defect Recognition in
Corrosion Logging using Magnetic
Imaging Defectoscopy data
Rita Gaibadullina, Bulat Zagidullin, Vladimir Bochkarev
Kazan Federal University, Kazan, Russia
2. Objective: To automate the search for
corrosions in oil wells according to MID
data
batteries
short sensor
(120 mm)
long sensor
(320 mm)
memory
The Magnetic Imaging Defectoscope (MID)
1 10 100
0
500
1000
1500
2000
Time, ms
Response,mV
short sensor
long sensor
Responses of the short and long MID sensors.
3. Casing and tubing corrosions
Algorithm of automatic corrosion
recognition:
2. Construction of binary
maps according to Drift
panels
1. Construction of Drift
panels according to MID
data
3. Making a decision on
significant deviation on
binary maps
4. Summary
1. The automatic defect recognition algorithm based on maximum
likelihood criterion accurately separates the defects of the 1st and
2nd barriers;
2. When configuring the algorithm to search for small intervals of
corrosion (metal loss less than 10%), lots of false defects are
present, which complicates data processing. With such
configuration, the algorithm detects 89% of the first barrier corrosions
and 93% of the second barrier corrosions.
3. The algorithm is designed to find major defects (metal loss greater
than 10%). When setting the appropriate algorithm parameters, all
defects, including a small number of false defects, are detected.