moneo SmartLimitWatcher (SLW) is an AI-based software product from the moneo DataScience Toolbox. It is used to dynamically monitor complex machine and production processes in companies.
The underlying technology enables the automatic and early detection of anomalies in critical process variables based on dependent sensor data, values, information and other process parameters. moneo SmartLimitWatcher continuously monitors the target variable with regard to the production quality, efficiency or plant condition (e.g. temperature, flow, vibration or current consumption).
An algorithm trains a mathematical model based on historical data that continuously compares measured values with predicted target values, thus providing a continuous target/actual comparison. It also calculates dynamic expectation ranges (confidence bands) for the target variable in order to automatically detect and signal deviations.
moneo SmartLimitWatcher is an intelligent AI monitoring tool that is easy to handle and can be operated without data science expertise. It makes data conveniently and automatically accessible, monitoring it autonomously on the basis of “machine learning”.
The AI software is custom-configurable and allows user-friendly sensitivity adjustment for anomaly detection. Warning and alarm thresholds can be customised to allow you to respond quickly to deviations in your production process. You can choose from “inactive”, “low”, “medium”, “high” and “custom”.
The moneo SmartLimitWatcher software solution can be used both for monitoring comparable machine components and for the detailed monitoring of individual components using multiple parameters for condition monitoring.
moneo SmartLimitWatcher offers a setup wizard that makes the software easy to use. In just five steps, the intelligent monitoring tool can be activated without expert assistance.
The SmartLimitWatcher’s AI can be used in different ways for process monitoring within the context of condition monitoring: to monitor comparable machine components or to monitor individual add-on parts or parameters.
Requirement:
The connected machine components are integrated in a process or in the same plant and a physical dependency exists. The advantage is that only a few sensors or parameters are needed to detect anomalies.
Requirement:
In order to detect deviations, a sufficient number of parameters of the component to be monitored must be recorded.This generalist approach is very well suited to a wide range of monitoring problems.