- February 10, 2017
- Sightline Systems
February 10, 2017 – Sightline Systems announced the release of its EDM for Manufacturing. The predictive analytics software is designed specifically to help manufacturers take advantage of IIoT system and device data streams, enabling them to proactively address challenges that can develop throughout the production process.
EDM for Manufacturing assists process and quality engineers by correlating thousands of data points collected in real time from sensors, SCADA systems, historians, PLCs and more. EDM for Manufacturing displays the information on a dashboard, providing a picture of the entire manufacturing operation, enabling floor personnel to identify trends and patterns that affect output quality. Additionally, manufacturers will be able to leverage the data to better forecast demand, automate manual processes and perform preventive maintenance.
The software uses advanced machine learning techniques to simplify predicting future operational performance. By reviewing historical data which has been collected, EDM for Manufacturing learns the best statistical model to provide a forecast of future behavior. Forecasts are automatically generated on dashboards. Alerts can also be created, giving process and quality engineers early warning to problems. Behavioral alerts can also be generated if real time data does not conform to predictions, adding another layer of alerts to a system or process.
EDM correlates vast amounts of data in microsecond intervals and provides actionable intelligence on a dashboard, enabling manufacturers to remedy issues managing risk and ensuring safety and compliance.
EDM for Manufacturing also recognizes anomalies that could indicate that a machine is likely to break down in the near future providing the manufacturer with an opportunity to perform the needed maintenance in non-emergency conditions without shutting down production, saving valuable production time and resources. EDM looks at the history of machine failures and compares those instances to the sensor data the machine is sending to identify trends and patterns that could signal a problem before the breakdown.