How to use AI to speed up your valve inspection process

Studies show that 5-10% of valves in industrial plants are leaking internally which can lead to economic losses, health and safety issues or potentially to environmental pollution. The reason for this is the lack of simple tools and the difficulty for companies to build up expert knowledge internally due to the lack of skilled labour in industry. As a result, valve leaks often remain unrecognised for a long time until they cause major damage to systems. We will demonstrate based on a real customer example how Valve Sense – a smart and mobile inspection system can help to tackle these challenges. By developing a software-guided inspection process and using algorithms and artificial intelligence to analyse measurement data, valves can now be inspected quickly and easily by maintenance teams. Inspection results become reproducible, data is automatically analyzed and stored in a way that companies can further use it for preventive and predictive maintenance strategies.

1. Current challenges industrial companies face with valve inspection
2. How algorithms and AI can speed up the inspection process
3. Real-life case study to improve valve inspection processes, increase efficiency and reduce costs due to leaking valves

Acoustic emission technology is a relatively modern but already well-established technology for leak detection in valves, however existing solutions show some limitations. These are among others e.g., their complexity of use, they need trained and experienced personnel, the time required to perform analyses and the use of solely proprietary and closed devices. Interviews with experts performing inspections in the field have shown that they are facing challenges such as using the right measuring points, finding the right duration of measurement, applying the right pressure when placing the sensor and finally transferring data and interpreting the results.