EOT’s AI Edge Controller enables the use of trained machine learning models to perform real-time predictions and anomaly detection at the edge of operation centers and uses closed-loop, event-response operational action to instantly avoid expensive downtime and increase production output.
EOT’s Intelligent Operational Data Platform
Twin Talk and AI Edge Controller work together to extract, filter, enrich, transform and deliver operational time-series data from industrial plants to the cloud and operationalize AI at the edge.
During the training phase of machine learning (ML) models, large data sets of sensors are needed to optimize their prediction quality. This requires significant compute and storage power which is only available in the cloud. However, the need for anomaly detection and self-optimization occurs at the operational edge where there is no compute, storage, or internet connection. EOT’s AI Edge Controller serves as a bridge by delivering the rather small, trained ML models from the cloud to the edge. This is where EOT’s Twin Talk’s Operational Insight Engine streams real-time operational data through the trained ML models to detect equipment abnormalities, diagnose issues, reduce false alerts, self-optimize production, and avoid expensive downtime by acting before machine failures occur.
Making Self-Optimizing Industrial Plants a Reality
AI Edge Controller enables the use of trained AI models in closed-loop environments without access to the internet. EOT’s approach of “Analyzing in the Cloud – Operationalizing at the Edge” is leveraging the power of the cloud to train machine learning models, and utilizing the predictions of the trained models to optimize assets from inside the operation center environments.
AI Edge Controller and Twin Talk connecting industrial plants with the AWS Cloud.