## Lucent

Single alkali halide crystals (boules) are indispensable in a number of a very demanding applications in high energy, nuclear, space and medical physics. Growing large crystals is an expensive and complex process with strict requirements placed on their physical properties. We used AI to improve crystallisation process quality control.

## The Problem

Physical properties of the crystals are subject to strict requirements. Boule’s diameter has to be constant and activator impurities – trace elements added to induce luminescence – have to be distributed through the body of the crystal evenly. An overhaul of the process control system was desired to increase the production yield – the percentage of marketable boules.

## Our Solution

To improve the production yield we suggested a cognitive IoT solution. Our intelligent decision support system was based on an original information-extreme classifier and its metaheuristic training algorithm developed by our researchers. Housed in a single-board computer directly at the production site, it automated the simple decisions without the need for human intervention. Notably, the system could also automatically forecast the point when its efficiency would begin to decrease to signal the need for preventive maintenance and system retraining.

## The Outcome

Cognitive manufacturing approach generated tangible results. Timely autonomous correction of the manufacturing parameters improved the distribution of the activator and reduced the deviations in boule’s diameter **2X**, increasing the yield. a great example of Industry 4.0 approach delivering an improvement to the bottom line!