An Assessment of Machine Learning Applied to Ultrasonic Nondestructive Evaluation

Technical Report · Fri Dec 01 04:00:00 EST 2023

DOI:https://doi.org/10.2172/2320378· OSTI ID:2320378

Sun, Hongbin ^[1]; Ramuhalli, Pradeep ^[1]; Meyer, Ryan ^[1]

---

1. Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

In the United States, the nuclear industry performs inservice inspection (ISI) through nondestructive examination (NDE) methods in accordance with guidelines specified in the American Society of Mechanical Engineers (ASME) Boiler and Pressure Vessel Code (BPVC), Section XI, Rules for Inservice Inspection of Nuclear Power Plant Components. Ultrasonic nondestructive testing and evaluation (NDT&E) is one of the more commonly used techniques for inspecting Class 1 structural components in nuclear power systems. As the number of qualified NDE inspectors declines, the nuclear industry is looking to take advantage of advances in automation to enhance inspection capabilities. Advances in computational power, cloud-based computing, and machine learning algorithms make automated data analysis possible. Machine learning (ML) has shown huge potential in automated data analyses for ultrasonic NDE in the context of weld inspections.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 2320378
• Report Number(s): ORNL/SPR--2023/3245
• Country of Publication: United States
• Language: English

Related Subjects

22 GENERAL STUDIES OF NUCLEAR REACTORS