Distributed Intelligence Architecture for Real-Time Control, Protection and Instrumentation Systems

Web Published:
7/25/2016
Description:

Princeton Docket # 16-3182-1

 

Researchers at Princeton Plasma Physics Laboratory have combined concepts of data flow prioritization management, cognitive neuroscience, and smart sensing to create a distributed intelligence network.

 

Architecture of complex, high-speed, real-time Instrumentation, Acquisition, Control and Protection systems are typically centralized with a single computer. As the size of the system grows, or the complexity of the sensors and the amount of data increases, this single computer must be scaled accordingly.  It complicates hardware selection and software development and ensuing testing and tuning. Critical sensors that require fail-safe redundancy adds another level of complexity and cost to hardware and software.

 

This invention describes a distributed intelligence network which combines innovative bus architecture, smart sensors, and a system controller configured to generate, transmit, and learn from the nature and sequence of evolving data streams. The network uses machine learning algorithms to improve situational awareness over time at the Sensor and System level. The system can also group, prioritize, and control the movement and rate of transmission of various data streams in order to act on specific event triggers that are sensed by the sensing elements.

 

This Distributed Intelligence Architecture is unique in its ability to provide a high level of fault tolerant performance when sensors fail.

 

Applications       

•       Real Time and Non-real time Sensing and Control Systems

•       Ground Fault Monitoring

•       Power Transmission and Distribution

•       Automotive and Vehicle Sensing Systems

•       Unmanned aerial (drone)

•       Computer vision systems

•       Virtual reality

 

Advantages       

•       Resilient and adaptive system

•       High functionality with reduced number of sensing devices

•       Dynamic bandwidth control

•       Fault tolerant

•       Scalable

•       Cost reduction in overall system level

 

Princeton Plasma Physics Laboratory (PPPL)  

The U.S. Department of Energy’s Princeton Plasma Physics Laboratory (PPPL) is a collaborative national center for fusion energy research. The Laboratory advances the coupled fields of fusion energy and plasma physics research, and, with collaborators, is developing the scientific understanding and key innovations needed to realize fusion as an energy source for the world. An associated mission is providing the highest quality of scientific education.

 

Inventors

 

Hans Schneider is an Electrical Engineer at Princeton University’s Plasma Physics Laboratory. His work focuses on circuit level to system level design and implementation of cost effective personal computer based systems. These systems include a wide variety of analog, digital, radio frequency and power components. At Lockheed Martin, he conceptualized and demonstrated Automated System Level Testing of the AEGIS Weapon System, and introduced re-configurable, reusable, automated control and data acquisition for flight hardware and systems testing. He received a BS in Electrical Engineering and Associate’s Degree in Communications Arts from Villanova University in 1985.

 

Greg Tchilinguirian is a system and software engineer at the Princeton Plasma Physics Laboratory (PPPL). His focus is on experimental data acquisition and control systems for both real-time and non real-time applications. He is responsible for the design and implementation of the NSTX-U core data system architecture, its integration and many software and hardware systems used for the experiment. Prior to PPPL, Greg worked at AT&T labs, helping to build their software development management processes as well as starting a small business designing and manufacturing parts for antique automobiles. His education encompasses both Computer Science and Cognitive Neuroscience which has given rise to his interest in the practical application of Artificial Intelligence for control system and real-time applications.

 

Intellectual Property & Development status

Patent protection is pending.

Princeton is currently seeking commercial partners for the further development and commercialization of this opportunity.

 

Contact:

 

Michael R. Tyerech

Princeton University Office of Technology Licensing

• (609) 258-6762• tyerech@princeton.edu

Xin (Shane) Peng

Princeton University Office of Technology Licensing

• (609) 258-5579• xinp@princeton.edu

 

Patent Information:
For Information, Contact:
Michael Tyerech
former Princeton Sr. Licensing Associate
Princeton University
mtyerech@rd.us.loreal.com
Inventors:
Hans Schneider
Greg Tchilinguirian
Keywords: