Kaspersky - Kaspersky Machine Learning for Anomaly Detection
With Kaspersky Machine Learning for Anomaly Detection, deviations in production processes can be detected at an early stage and downtimes reduced. The solution's neural network analyzes the telemetry of various sensors used in the production process in real time. The system detects even minor deviations, such as a change in signal dynamics or signal correlations, and notifies users before the values reach their limits and affect performance.
In order to detect anomalies, the neural network learns the normal behavior of the machine from historical telemetry data. Should a parameter of the production process change, for example because a new type of raw material is introduced or a part of the machine is replaced, an operator can re-run the machine learning training to update the neural network. In addition to a machine learning-based detector, individual diagnostic rules can be added for specific cases.