AI Anomaly Detection –
System Invariant Analysis Technology (SIAT)
NEC’s AI utilization in the IoT field does offer manufacturers a certain level of assurance in failure detection with an automatic modelling of correlations between sensors to enable early detection of anomalies.
Usually you would use sensors to detect anomalies. There are a variety of different types, such as those that pick up vibrations, and those that check pressure or temperature, and you monitor the site by looking at observation data from these sensors.
Normally, anomaly detection rules are set for each sensor, with "threshold values" used to determine the presence of an anomaly when data values go above or below a certain level. However, the more complex a system gets, the more complicated the points to monitor and rules become.
SIAT makes it possible for factories and industries to operate more efficiently than ever before that is AI based analytics technology that analyses vast quantities of sensor data to find anomalies.
This technology automatically extracts and creates invariant relationships that represent the characteristics of facilities or systems based on massive quantities of sensor data. By comparing the values predicted by the invariant model with real-time data, "not usual" behaviors can be detected.
Since the relationships among the sensor data can be extracted and profiled automatically by machine learning, this technology can identify relationships that cannot be discovered even by experts. All invariant relationship formulas are simplified so that they can be calculated at high speed. In addition, all relationships among the sensors can be visualized comprehensively, allowing facilities and systems to be monitored without any oversights.