Millions of miles of pipelines in the United States transport natural gas, crude oil, and refined fuels essential to daily life. However, as this infrastructure ages, incidents involving cracks, leaks, and ruptures have become more frequent. Between 2002 and 2021, pipeline accidents led to 276 deaths, over 1,100 injuries, and $10 billion in damages. The nation currently averages about 650 serious pipeline incidents each year.
Many sections of these pipelines remain uninspected for long periods due to their complex layouts. These “unpiggable” pipelines contain sharp turns and outdated valves that traditional inspection tools cannot navigate.
Researchers at Arizona State University (ASU) are working on new technology to address these challenges. Supported by the U.S. National Science Foundation, the team is developing advanced robotic systems and artificial intelligence (AI) models aimed at making pipeline inspections faster and safer.
Wenlong Zhang, associate professor of manufacturing engineering in ASU’s School of Manufacturing Systems and Networks, leads the project. Zhang’s group is designing autonomous soft robots inspired by inchworms. Made with inflatable fabric actuators, these robots can grip and move through narrow or twisting pipes while carrying sensors to detect cracks or corrosion.
“Pipelines can be inspected using in-line tools with magnetic flux leakage and ultrasonic waves,” Zhang says. “However, due to the complex geometries of pipelines, over- or undersized valves, small-radius bends and other challenges, many critical segments of the 2.6 million miles of pipeline in the U.S. are uninspected.”
“This project will allow us to significantly improve the efficiency, endurance and autonomy level of future in-pipe robots,” Zhang adds.
Another aspect of the research focuses on predicting failures before they occur. Yongming Liu, professor of mechanical and aerospace engineering at ASU’s School for Engineering of Matter, Transport and Energy, uses machine learning to estimate how pipelines deteriorate under real-world conditions such as fluctuating pressure or environmental changes.
“Energy infrastructure safety is fundamental to both the economy and public well-being,” Liu says. “Many of these systems are aging, and understanding how to extend their lives safely is a grand scientific and societal challenge.”
Hao Yan, associate professor of industrial engineering in ASU’s School of Computing and Augmented Intelligence, leads development on an AI system that not only predicts failures but also explains its reasoning. The system integrates real-time sensor data from inside pipes with physics simulations and historical accident reports to identify subtle risk patterns.
“By teaching AI to read and learn from decades of pipeline accident reports, we can uncover recurring human, environmental and mechanical risk factors that traditional models overlook,” Yan says. “These insights can give utilities early warnings about potential failures, protecting people’s safety and minimizing costly service disruptions.”
To ensure practical adoption outside the lab environment, Hanna Breetz—associate professor at ASU’s School of Sustainability—is guiding stakeholder engagement and policy analysis for the project. Her team consults policymakers as well as industry leaders to align new technologies with evolving safety codes.
The project also involves collaboration with Michigan State University and GTI Energy; field demonstrations will take place at GTI Energy’s Illinois test site so industry experts can provide feedback on real-world performance.
This interdisciplinary approach combines expertise from robotics engineering through policy studies—a model consistent with ASU’s recognition for innovation over several years by U.S. News & World Report (https://news.asu.edu/20220911-university-news-asu-no-1-innovation-us-news-world-report-eighth-year?utm_source=twitter&utm_medium=asu&utm_campaign=ASURankings&utm_term=USNWR).
ASU has previously worked on technology partnerships within Arizona communities as well; for example collaborating with Argos Vision on smart traffic cameras for improving local street safety (https://www.phoenix.gov/newsroom/street-transportation/2420).
The researchers believe their work could set a standard for intelligent infrastructure monitoring nationwide.
As Liu notes: “This project will demonstrate that proactive, data-informed safety management is possible on a national scale.”
