In biologics upstream manufacturing, bioreactor leaks remain a persistent and costly threat. Whether caused by handling errors, faulty connections, or worn seals, even a small leak can compromise an entire batch—leading to contamination, production losses, and expensive downtime.
DEEPEYES Leak Detection offers a game-changing approach. Using advanced computer vision technology, it provides continuous, real-time monitoring of client fermentor systems—detecting the earliest signs of leaks before they escalate. Unlike traditional inspection methods, this solution runs 24/7 during operation, providing the visibility and responsiveness needed to protect production.
This article describes a project carried out with the goal of instantly detecting leaks, droplets, liquid streams, or puddles in and around bioreactors during upstream processing. The objective was clear: enable immediate countermeasures to prevent batch loss, reduce downtime, and safeguard product quality.
DEEPEYES’ AI-based solution delivered significant time and cost savings while meeting the highest standards of safety and operational efficiency. The system was developed to be ready for rapid deployment—ensuring continuous protection of critical manufacturing processes.
Even in highly automated, IoT-enabled production environments, blind spots remain—especially when it comes to human error. Leaking bioreactors are often the result of improper handling, making the human factor one of the most persistent risks. Such leaks can lead to contamination, unplanned downtime, and substantial financial losses.
To address these challenges, DEEPEYES was invited by one of the world’s top 10 pharmaceutical manufacturers to develop a real-time computer vision module for leak detection.
We took on the challenge and put our technology to the test—demonstrating how AI-powered visual monitoring can close critical gaps in process oversight and enhance reliability across the board.
PROJECT OVERVIEW: AI POWERED REAL-TIME LEAK DETECTION
The project focused on detecting colourless liquid leaks in the form of tiny drops, streams or puddles on the surface of single-use bioreactors of a specified brand. We used standard, off the shelf 4k NDI cameras. Here’ s a detailed look at the project
Assignment - Goals
Objective: Detect colorless liquids on a transparent plastic or metal surface of single-use bioreactors, or on tubes and/or connectors, valves or water in the form of puddles on the floor in real-time.
Setup: Installed four 4K, NDI cameras along with flicker-free LED illuminators under the ceiling.
Training Data: Six hours of video recording served as the training sample.
Processing Resources: An on-premise video server with specific resources allocated per camera (1 i) 7900X 3.3 GHz, 8 GB DDR4 RAM, 120 Pbps LAN).
Development: Real-time AI video-based leak detection developed on pre-produced 4K video footage.
Test Phase: Demonstrated ability on live streams.
Team: Composed of AI developers, computer vision experts, statisticians, metrologists, electronics and sensor specialists, and backend developers.
Results: Achieved a 100% recognition rate from 400 control events.
Challenges: Addressed false positives caused by minute vibrations and human presence.
Privacy Compliance: Implemented blurring to meet GDPR requirements.
Timeline: Completed in 7 months, including camera installation, video production, algorithm development, and documentation.
Solution Readiness: The DEEPEYES leak detection solution is ready for deployment, potentially requiring an initial adaptation phase of 2-4 months.
Conclusion
The integration of advanced technologies such as computer vision is becoming a key driver of operational excellence and competitive advantage in the biopharmaceutical industry. In this project, real-time leak detection powered by the DEEPEYES leak detection module proved to be a powerful enabler for safeguarding production processes, enhancing product quality, and supporting the long-term sustainability of manufacturing operations.
The DEEPEYES leak detection module delivered precisely on these goals—providing reliable, non-invasive monitoring that seamlessly integrated into existing systems. Ready for deployment and highly scalable, the solution demonstrated substantial time and cost savings while upholding the industry’s highest standards of safety and efficiency. The results underscored the transformative potential of AI in critical production environments—both as a protective measure and as a strategic investment in quality and resilience.
Join The Conversation
How is your organization leveraging AI and computer vision to enhance manufacturing processes and prevent contamination? Share your experiences and insights in the comments below. Connect with us to stay updated on the latest trends in biopharmaceutical manufacturing and AI-driven innovations.
