by Haley Cowans
Artificial intelligence is already a part of our everyday lives, working behind the scenes when you type a query into a search engine or get a recommendation from your favorite streaming service. In the latest episode of Chat NDT with ASNT, host Debbie Segor, CAE, talks with Raj Venkatachalam about the potential for artificial intelligence/machine learning (AI/ML) applications in NDT. Raj has been involved in the field of nondestructive evaluation for over 18 years and is currently the Systems Engineering Manager at VMI – A Varex Imaging Company. At VMI, Raj is working on developing engineered solutions using robotics and analytical tools to enable next generation tools for radiography. Raj is also the Chair of ASNT’s Ad Hoc Committee for Artificial Intelligence and Machine Learning.
In the episode, Raj explains that AI/ML refers to processes or algorithms that are able to simulate human intelligence by performing tasks like problem solving, perception, and learning. As he noted, this is already in play in the examples illustrated above of search engines and targeted recommendations. As Raj explains, the NDT field has a lot of potential for adoption of AI/ML tools due to the large number of data inspections generate. Currently, inspectors have to examine high volumes of parts, the majority of which do not have defects. As Raj explains, this creates a higher potential for inspector fatigue and opportunities for error. With mature AI/ML programs that are able to help sort this vast amount of data, inspectors could be able to evaluate parts with potential defects more efficiently.
Many worry that the evolution of this technology means that inspectors will be replaced, but Raj elaborates on the important role that inspectors will play in working with AI/ML tools in NDT.
“In a sense, they’re going to have much cooler toys in their hands,” he said.
He notes that in the early stages of development of these tools, it will be important for the NDT technician to not merely “accept” what the machine says, but rather to understand how the data is being collected and be able to evaluate the performance of the system. It will be important to have technicians who are eager to adopt new technologies as well as technicians who are skeptical of their use; as Raj notes, both groups will have an important role to play as this field develops.
In the episode, Raj and Debbie also discuss the steps needed to progress AI/ML use in the NDT industry, the importance of data-sharing to the development of these tools, and examples of AI/ML applications currently in use in the NDT industry.
Listen to the full conversation with Raj Venkatachalambelow or search for Chat NDT with ASNT in your favorite podcast platform.
_______
Learn more about ASNT’s Ad Hoc Committee for Artificial Intelligence and Machine Learning.
The purpose of the committee is to investigate how AI/ML is presently affecting or will affect the NDT industry. For more information or to join the committee please email volunteer@asnt.org.
For more information about AI/ML
Materials Evaluation
Xiaodong, S., A. Olvera, C. Hamilton, E. Gao, J. Li, L. Utke, A. Petruska, Z. Yu, L. Udpa, Y. Deng, H. Zhang, “AI-Enabled Robotic NDE for Structural Damage Assessment and Repair,” DOI: https://doi.org/10.32548/2021.me-04214
Aldrin, J.C., “Intelligence Augmentation and Human-Machine Interface Best Practices for NDT 4.0 Reliability,” DOI: https://doi.org/10.32548/2020.me-04133
Research in Nondestructive Testing
Shafiei Alavijeh, M., R. Scott, F. Seviaryn, R.Gr. Maev, “NDE 4.0 compatible ultrasound inspection of butt-fused joints of medium-density polyethylene gas pipes, using chord-type transducers supported by customized deep learning models,” DOI: https://doi.org/10.1080/09349847.2020.1841864
_______
Haley Cowans is the Content Strategist at ASNT, hcowans@asnt.org.
Debbie Segor, CAE, is the Marketing and Communications Manager at ASNT, and the host of Chat NDT with ASNT. To be a guest on the podcast, contact desgor@asnt.org.
Raj Venkatachalam is Systems Engineering Manager at VMI – A Varex Imaging Company.
Nice Blog, thanks for sharing !!!