Wallboard manufacturers are increasingly adopting an AI-powered void detection system to improve quality and throughput on their lines. The system, delivered by Gyptech and powered by Eigen's Thermal AI, gives operators real-time alerts and provides visibility of quality trends to plant leadership.
Void problems driving scrap and slowing production lines
Voids have been a persistent challenge in the wallboard industry for decades. As product formulations have evolved and production line speeds have increased, void formation within the board core has intensified, forcing manufacturers to rely more heavily on manual inspections
Legacy void detection systems don't understand context
Legacy detection systems — typically rules-based, positioned further downstream — catch voids but don’t provide context to operators:
Is the void small, medium, or large for this particular SKU?
Is the void a one-off or an escalating issue?
Has void density changed in the last 30 days?
The result: legacy detection systems send countless alerts but don’t provide meaningful data to improve the operation.
How AI thermal vision solves the void problem
Gyptech's solution, powered by Eigen's Thermal AI, uses thermal cameras mounted over an existing roller conveyor, positioned post-slurry and pre-knife, where voids are still forming and correctable.
Two to three cameras span the full board width. An edge device processes the thermal data using Eigen's machine learning models, trained at the product SKU level. The system pulls part width and product type data directly from the PLC, so it automatically adapts when operators switch SKUs without manual reconfiguration.
AI classifies voids and alerts only for severe issues
The AI classifies voids by size (small, medium, large) and triggers warning or critical alerts based on configurable thresholds. These alerts are programmed into the local PLC. Operators see results on an interactive HMI near the knife, with a live thermal stream of the board as it moves down the line.
Daily email reports show quality trends
Beyond the factory floor, quality and operations teams get daily reports showing void frequency broken down by size and severity.
Critical events link directly to Eigen's OneView cloud platform, where teams can drill into specific inspection records, filter by product type, and review trend data over time.
Faster lines, less scrap, fewer complaints
With the system running, plant teams know exactly what's happening on the line. Quality leads get daily trending instead of periodic spot checks. Operators can see when voids spike and correlate that with process changes upstream.
Instant visibility from 100% continuous inspection gives plant operations teams immediate insight into product quality. Reject rates are reduced, and issues are isolated quickly, enabling operations to run at peak performance.
The outcome is twofold: lower cost of quality from fewer claims and rejects, and higher yield from a more stable, optimized process.
See the system work on your line
Reach out to our team to learn more and to schedule an on-site demo. During the demo, our engineers set up the system on your line so you can see the results in real time.
