Tianyu Zhang
University of Iowa, IA·Engineering
Modern factories rely on networks that link robots, sensors and controllers, and these links must deliver data on time, every time. Factory floors are full of moving machines, radio interference and equipment faults, and today's network fixes mostly react after something goes wrong.
- Fields
Engineering
Computer Science
- Topics
smart manufacturing
industrial networks
Time-Sensitive Networking
- Grants
- 1 known grant, through Sep 2029
What they work on
- Develop machine-learning methods that predict wireless channel conditions and interference on the factory floor, so 5G/6G radio resources can adapt in real time.
- Combine integrated sensing and communication with scheduling aligned to machine cycles, so wireless traffic matches the timing of industrial control loops.
- Strengthen Time-Sensitive Networking (TSN) wired cores with predictive fault detection, precomputed backup 'shadow' schedules and zero-touch failover, keeping delay and jitter bounded during faults.
- Design a framework that jointly partitions, reserves and schedules wireless and wired network resources for industrial applications with differing timing, throughput and computing needs.
- Release software platforms, network data traces, simulation tools and testbed designs that academia and industry can use to evaluate resilient manufacturing networks.
More about the research
Each part of the network is also usually managed separately. This collaborative project, shared with the University of Connecticut and Mid Sweden University, aims to build factory networks that predict problems and adjust before they cause delays or downtime.
Why it matters
Network failures and interference can halt production lines. More resilient, predictable factory networks could reduce downtime and help industrial systems meet strict timing requirements. Because the approach avoids highly customized infrastructure, it could lower the barrier for small and medium-sized manufacturers seeking automation. The methods may also carry over to other real-time systems in healthcare, energy, transportation, logistics and aerospace.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Behnam Dezfouli
Santa Clara University, CA·Computer Science
Build a scalable, programmable software framework for monitoring the WiFi (802.11) stack, along with a reference testbed and traffic generation methods that mimic real-world deployments.
Guangjing Wang
University of South Florida, FL·Computer Science
Design a secure authentication framework to verify transmitters and receivers in integrated sensing and communication (ISAC) systems, where a single radio signal both senses and carries data, under zero-trust assumptions.
Taejoon Kim
Arizona State University Campus Immersion, AZ·Engineering
Develop Zero Trust Chain security software that lets military squads share situational awareness over untrusted 5G networks, using O-RAN Intelligent Controllers on the OAIC platform to detect and block threats in near-real time.
The school
University of Iowa: 32 labs on PI Pages, $703M a year on research, 418 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.