 |
Rotorcraft
CBM |
Structural
Health Monitoring |
Engine
Health Monitoring and CBM |
| SYSTEM
MODEL |
• Fatigue Model Analysis
for Critical Components
• Prognostics based on Complex System Modeling
• Diagnostics with High Performance Real Time Artificial
Neural Networks (ONGFE and Collaborative Learning Engine).
• Noise Measurement and Modeling
• Incremental Learning based on Collaborative Learning
Engine and Artificial Neural Networks |
• Aluminum and Composite
Structural Specimens
• Fatigue Model Analysis
• Observer Model for Sensor and System Failure Detection
• State-Chi-Square Test
• Robust Kalman filter.
• Prognostics based on Complex System Modeling
• Diagnostics with High Performance Real Time Artificial
Neural Networks (ONGFE and Collaborative Learning Engine) |
• State-Chi-Square Test
• Robust Kalman filter.
• Residual Analysis
• Prognostics based on Complex System Modeling
• Diagnostics with High Performance
Real Time Artificial Neural Networks (ONGFE and Collaborative
Learning Engine).
• Incremental Learning based on Collaborative Learning
Engine and Artificial Neural Networks |
| RELATED
TECHNOLOGIES |
• Autonomous Learning
• Sensor and System Design for Optimized Size, Weight,
and Power
• Regression by ANNs
• Distributed Processing
• Pattern Recognition by supervised, unsupervised, and
hybrid schemes
•Bayesian Learning
•Stochastic Expert Systems
• Fast Embedded Learning
• Automated Feature Selection
• Man Machine Interfaces and Visualization
• Real Time Processing
• FMEA |
• Incremental Learning
• Sensor and System Design for Optimized Size, Weight,
and Power
• Regression by ANNs
• Distributed Processing
• Pattern Recognition by supervised, unsupervised, and
hybrid schemes
•Bayesian Learning
•Stochastic Expert Systems
• Fast Embedded Learning
• Automated Feature Selection
• Man Machine Interfaces and Visualization
• Real Time Processing
• FMEA |
• Autonomous Learning
• Sensor and System Design for Optimized Size, Weight,
and Power
• Regression by ANNs
• Distributed Processing
• Pattern Recognition by supervised, unsupervised, and
hybrid schemes
•Bayesian Learning
•Stochastic Expert Systems
• Fast Embedded Learning
• Automated Feature Selection
• Man Machine Interfaces and Visualization
• Real Time Processing
• FMEA |
| PATENTS |
•ONGFE: US Patent
2011/0167024 A1
•eCLE: US Provisional Application #61/633,374
•CRE-SSN: U.S. Provisional Application |
•ONGFE: US Patent 2011/0167024
A1
•eCLE: US Provisional Application #61/633,374
•CRE-SSN: U.S. Provisional Application |
•ONGFE: US Patent 2011/0167024
A1
•eCLE: US Provisional Application #61/633,374
•CRE-SSN: U.S. Provisional Application |
| COMMUNICATIONS |
•Zigbee (IEEE 802.15.4)
•Bluetooth
•Cellular Networks
•High Speed Wireless Data Links
• Sensor Management by the IEEE 1451.0 Software Stack
|
•Zigbee (IEEE 802.15.4)
•Bluetooth
•Cellular Networks
•High Speed Wireless Data Links
•Client-Server Enterprise Technologies
•Smart Mobile Devices (smart phones, tablets)
• Sensor Management by the IEEE 1451.0 Software Stack
|
•Zigbee (IEEE 802.15.4)
•Bluetooth
•Cellular Networks
•High Speed Wireless Data Links
• Sensor Management by the IEEE 1451.0 Software Stack
|
| HARDWARE |
• CRE-SSN (Smart Sensor
Node)
•MicroElectroMechanical Systems
•Ultra-low power processors (microcontroller, microprocessors,
and DSP)
•PC104, PC104-Plus, Single Board Computer, Smart Devices
(android, iPhone, and tablets), Power PC, ruggedized mobile
computers
•ASIC-Analog/Mixed-mode
•Electromechanical Design
•CNC Machines
•PCB Layout
•Circuit Simulation/ Analysis
•EMI
•Firmware (FPGA) Development |
• CRE-SSN (Smart Sensor
Node)
•CSWN-SFDI (Smart Sensor Network)
•MicroElectroMechanical Systems
•Ultra-low power processors (microcontroller, microprocessors,
and DSP)
•PC104, PC104-Plus, Single Board Computer, Smart Devices
(android, iPhone, and tablets), Power PC, ruggedized mobile
computers
•ASIC-Analog/Mixed-mode
•Electromechanical Design
•CNC Machines
•PCB Layout
•Circuit Simulation/ Analysis
•EMI
•Firmware (FPGA) Development |
• CRE-SSN (Smart Sensor
Node)
•CSWN-SFDI (Smart Sensor Network)
•MicroElectroMechanical Systems
•Ultra-low power processors (microcontroller, microprocessors,
and DSP)
•PC104, PC104-Plus, Single Board Computer, Smart Devices
(android, iPhone, and tablets), Power PC, ruggedized mobile
computers
•ASIC-Analog/Mixed-mode
•Electromechanical Design
•CNC Machines
•PCB Layout
•Circuit Simulation/ Analysis
•EMI
•Firmware (FPGA) Development |
| SOFTWARE |
• coremicro® Real-Time
Structure Health Monitoring Kernel (RTSHM-Kernel)
•Optimized Neuro Genetic Fast Estimator (ONGFE)
• Machine Evolutionary Behavior by Embedded Collaborative
Learning Engine (eCLE)
• Distributed Intelligent Health Monitoring (DIHM)
• Automated Feature Selection Toolbox
•Unsupervised clustering toolbox
•Proprietary Collaborative Learning Toolbox
•Real Time Interface Software
•Windows CE
•Unix
•Embedded OS |
•
coremicro® Real-Time Structure Health Monitoring Kernel
(RTSHM-Kernel)
•Optimized Neuro Genetic Fast Estimator (ONGFE)
• Machine Evolutionary Behavior by Embedded Collaborative
Learning Engine (eCLE)
• Distributed Intelligent Health Monitoring (DIHM)
• Automated Feature Selection Toolbox
•Unsupervised clustering toolbox
•Proprietary Collaborative Learning Toolbox
•Real Time Interface Software
•Windows CE
•Unix
•Embedded OS |
•
Optimized Neuro Genetic Fast Estimator (ONGFE)
• coremicro® Real-Time Structure Health Monitoring
Kernel (RTSHM-Kernel)
• Machine Evolutionary Behavior by Embedded Collaborative
Learning Engine (eCLE)
• Distributed Intelligent Health Monitoring (DIHM)
• Automated Feature Selection Toolbox
•Unsupervised clustering toolbox
•Proprietary Collaborative Learning Toolbox
•Real Time Interface Software
•Windows CE
•Unix
•Embedded OS |
| SENSOR
SUITE |
•Strain Gages
•PZT sensors
•Accelerometers
•Inertial Measurement Unit
•MEMS Sensors
•GPS |
•Strain Gages
•PZT sensors
•Accelerometers
•MEMS sensors |
•Pressure
•Flow
•Accelerometers
•PZT sensors
•Temperature
•MEMS sensors |
