Human error is responsible for 23% of manufacturing downtime. One possible solution to this problem is AI-powered detection and robotic vision systems that can analyze real-time visual data to detect anomalies and enhance efficiency. These systems can operate continuously with high accuracy, reducing reliance on manual inspections. As a result, manufacturers can minimize costly disruptions and improve overall product quality.
Operational downtime and quality issues cost manufacturers billions of euros in losses, and human error is a major culprit, accounting for roughly 23% of production defects and stoppages. But tests show that the number doesn’t have to stay so high. Integrating AI-powered vision systems into day-to-day operations can sharply reduce both errors and delays on the production line.
One example is the field of wood processing, where AI can be used for proactive maintenance that results in a 30-50% reduction in downtime, lower maintenance costs, and increased overall equipment effectiveness. AI can also be effectively used for quality control purposes. As such, manufacturers are turning to AI technologies to combat the rising costs, gaining a competitive edge by reducing associated costs.
“The human factor accounts for a significant portion of all production errors. For instance, in one of our factories, we sorted wooden parts according to certain parameters. A human performs this task subjectively, adapting to the situation. On the other hand, AI performs everything consistently, without any deviations, reducing the risk of downtime,” says Augustas Urbonas, Head of Computer Vision Group at VMG Technics, a part of VMG Group, a global investment company currently operating 20 wood processing and furniture manufacturing companies in Europe.
How AI Can Help Reduce Downtime
Financial losses are often unavoidable in areas of production traditionally managed by humans. Repetitive tasks demand sustained attention, something people naturally struggle to maintain over time. AI, however, excels at exactly that, performing these tasks with consistent precision.
According to Urbonas, the decision to implement AI tools came down to their strength in handling tasks that demand consistency and repetition. At Klaipėdos mediena, a woodworking facility within the VMG Group, AI is used for segmenting and identifying individual pieces based on specific criteria. By combining AI-driven detection systems with robotic vision, the plant saw a 33% boost in productivity, increasing from 16.3 to 21.76 square meters per hour. Packaging speeds also rose from 9 to 12 units per minute.
“We have been working on implementing these systems for about 2-3 years. The implementation itself is the easy part of the process. It takes longer to refine and adjust them, as numerous small details emerge that require consideration,” Urbonas says.
VMG Group estimates that its production lines lose 2–3 hours each week to unnoticed issues. At Sakuona, a subsidiary specializing in curved plywood, the company tackled this with a deep learning model, the Siemens SIMATIC S7-1500 TM NPU. Trained on historical data and anomaly detection algorithms, the system identifies irregularities in real time. It does this by capturing thousands of images per item using dozens of cameras embedded along the production line, feeding them into the model for continuous analysis.
“In this case, AI is tasked with anomaly detection and preventing production jams. This is achieved through specialized algorithms and by utilizing existing operational data,” explains Urbonas.
His team is already planning to roll out additional AI-powered tools, with a particular focus on identifying potential issues early and preventing costly production line stoppages before they occur.
Urbonas says, “I think we have learned a great deal throughout this process. The systems we use have only improved and become more complex. We envision a chatbot application enabling workers to communicate directly with machines, making the working process even more efficient.”
