BGSU Researchers Lead Ohio-Backed Effort to Apply AI in Glass Manufacturing

The research initiative, part of the Northwest Ohio Glass Innovation Hub, is a three-year study into how AI could improve process controls and energy efficiency in glass melting. Photo: Igor Omilaev/Unsplash.

Bowling Green State University (BGSU) has launched a new Ohio-backed research initiative that places Artificial Intelligence (AI) at the center of next-generation glass manufacturing. The three-year project is part of the Northwest Ohio Glass Innovation Hub and is supported by a $652,000 grant from the Northwest Ohio Innovation Consortium. The goal is to improve process control and energy efficiency in glass melting, one of the most energy-intensive and technically challenging operations in the industry.

The research is led by Mohammed Abouheaf, Ph.D., Associate Professor in the BGSU College of Engineering and Innovation. According to the team, energy efficiency has become a key focus for glass producers, but the furnace environment creates an immediate limitation: the extreme temperatures and corrosive conditions inside the melt area make it impractical to install enough sensors for full measurement and real-time monitoring.

To overcome this gap, the BGSU team plans to develop advanced AI and machine learning algorithms capable of estimating “unmeasured variables” using the sensor data that furnaces already generate. In practice, this means creating a digital intelligence layer that can predict conditions inside areas where direct measurement is difficult or impossible, supporting smarter control decisions without relying on additional hardware.

A central technical challenge is the need for multi-objective optimization. Traditional furnace control strategies typically focus on one main target, such as maintaining a set temperature. BGSU’s approach aims to optimize several competing factors simultaneously, developing a data-driven tool designed to balance energy efficiency, nitrous oxide emissions, control input constraints, and robustness under changing boundary conditions.

While the research is centered on glass manufacturing, the team believes the same methodology could benefit other industries where harsh environments limit sensor placement and where performance depends on managing multiple trade-offs. The initiative includes collaboration with the University of Toledo, several global industrial organizations, and Actual Reality Technologies, a Toledo-based company specializing in augmented intelligence and data modeling.

Source: USGlassMag with additional information added by Glass Balkan

Keep Up to Date with the Most Important News

By pressing the Subscribe button, you confirm that you have read and are agreeing to our Privacy Policy and Terms of Use
Stay Ahead in the Glass Industry

Get exclusive insights, global trends, and business opportunities from the glass industry, delivered directly to your inbox.
Join professionals, manufacturers, and innovators across the Balkans and beyond.