System Invariant Analysis Technology

Automatic modeling of correlations between sensors to enable early detection of 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.

Related solutions

Plant Failure Sign Detection Solution––detects signs of failure in a plant before an incident occurs.

Related cases

NEC Corporation's AI-powered monitoring system will perform intricate checks to ensure the spacecraft is tested and operating properly during the production phase.

Potential applications

Preventive maintenance of transportation equipment, production quality control, anomaly detection in buildings and other infrastructure