The value of AI in manufacturing lies in reducing product defects, automating quality control, increasing capacity and streamlining maintenance. Highly automated manufactures are ideal candidates for sophisticated analytics as they are already well-instrumented with sensors and controllers. However, less automated manufactures can also beneficially utilize robotics and AI by eliminating inefficient manual processes.
Solar Panel Defect Detection
Solar panels during production can have a variety of defects like scratches, cracks and many others. Our algorithm provided the possibility to autonomously detect such defects during the production. Deep Learning solutions are able to detect 95% of the defects during production line.
Anomaly Detection System
Anomaly detection system for a chemical factory was developed by our team and was able to prevent and detect possible failures during the factory process. Historic data from 21 sensors were processed and used to train the AI model System became able to predict future failures 39-44 hours in advance 99.782 % accuracy achieved as tested. Future development of a system allowed us to develop a fully autonomous anomaly detection system where user can train on any new data a new model for the same anomaly detection and prediction.