Expansive Inferential Sensing
Our deep learning technology dramatically expands your real-time capability to autonomously sense and respond to physical system and environmental changes, including degradations and failures.
​
Reduce opportunities for:
-
Delays
-
Accidents
-
Degradations
-
Failures
R
Our technology utilizes the readily available sparse outputs of your time-varying system or environment to perform accurate real-time inferential sensing of 100's of physical attributes that are otherwise impractical or impossible to measure.
​
Advanced Process Control and Degradation Management
Track a phlethora of specific degradations by type and location in complex processes without adding additional sensors.
​
-
​Improve product yield
-
Reduce delays and shutdowns
-
Increase safety
-
Maintain GHG compliance
-
Reduce emissions
-
Increase revenue
​
Comprehensive Inferential Sensing
Our technology provides to control and monitoring systems extraordinary adaptive, expansive, and comprehensive coverage of physical attributes, disturbances, and situations concerning time-varying systems and environments.
Applications for expanded capabilities include:
​​
-
Complex Dynamical Threat Environment Situational Awareness for Satellites and Submarines
-
Failure Avoidance and Fault-Tolerance Capabilities in Aircraft and Spacecraft
-
Auto-Tuning Control Systems Concerning Manufacturing Tolerances and System Maintenance
-
Life-Cycle Management of Distributed Machines and Robots
-
Robot Swarm Management and Autonomous Planning and Reconfiguration
-
High Fidelity Performance Digital Twinning
-
Autonomous Process Control
Relative to the State of The Art
There are many inferential sensing methods in practice, including frequent innovations in the literature.
However, all such methods are limited by a maximum number of parameter estimates (not including state estimates) that is roughly equal to the number of independent output signals used to derive the estimates.
That's -- so last-century.
Our technology overcomes such limit to accurately infer essentially any number of time-varying physical parameters from scarce output signal resources, e.g., by a factor of 100. Further, our technology adapts to manufacturing tolerances, wear, degradations, and failures, eliminating the need for inferential system updates over the life of the machine or process.