Avionics Sensor Health Assessment is a sub-discipline of Integrated Vehicle Health Management (IVHM), which relates to the collection of sensor data, distributing it to diagnostics/prognostics algorithms, detecting run-time anomalies, and scheduling maintenance procedures. Real-time availability of the sensor health diagnostics for aircraft (manned or unmanned) subsystems allows pilots and operators to improve operational decisions. Therefore, avionics sensor health assessments are used extensively in the mil-aero domain. As avionics platforms consist of a variety of hardware and software components, standards such as Open System Architecture for Condition-Based Maintenance (OSA-CBM) have emerged to facilitate integration and interoperability. However, OSA-CBM is a platform-independent standard that provides little guidance for avionics sensor health monitoring, which requires onboard health assessment of airborne sensors in real-time. In this paper, we present a distributed architecture for avionics sensor health assessment using the Data Distribution Service (DDS), an Object Management Group (OMG) standard for developing loosely coupled high-performance real-time distributed systems. We use the data-centric publish/subscribe model supported by DDS for data acquisition, distribution, health monitoring, and presentation of diagnostics. We developed a normalized data model for exchanging the sensor and diagnostics information in a global data space in the system. Moreover, Extensible and Dynamic Topic Types (XTypes) specification allows incremental evolution of any subset of system components without disrupting the overall health monitoring system. We believe, the DDS standard and in particular RTI Connext DDS, is a viable technology for implementing OSA-CBM for avionics systems due to its real-time characteristics and extremely low resource requirements. RTI Connext DDS is being used in other major avionics programs, such as FACE™ and UCS. We evaluated our approach to sensor health assessment in a hardware-in-the-loop simulation of an Inertial Measurement Unit (IMU) onboard a simulated General Atomics MQ-9 Reaper UAV. Our proof-of-concept effectively demonstrates real-time health monitoring of avionics sensors using a Bayesian Network –based analysis running on an extremely low-power and lightweight processing unit.

1. Infotech@Aerospace
19 - 22 August 2013
Boston, Massachusetts
Your systems. Working as one.
An Extensible Architecture for Avionics
Sensor Health Assessment Using DDS
Sumant Tambe, Ph.D.
Senior Software Research Engineer
Real-Time Innovations, Inc.
12/3/2013
Acknowledgement: This research is funded by the Air Force Research Laboratory, WPAFB, Dayton, OH under Small Business Innovation
Research (SBIR) contract # FA8650-11-C-1054. Manuscript approved for publication by WPAFB: PA Approval Number: 88ABW-2013-3209.

2. 12/3/2013
NASA K10 Rover:
Surface Telerobotics
Uses RTI Connext DDS
© 2012 RTI • COMPANY CONFIDENTIAL
2

3. Why NASA Uses RTI Connext DDS
• NASA was looking for a software architecture and
communications infrastructure that enabled reliable,
standards-based messaging between the
International Space Station and Earth.
• NASA relied on the RTI Connext DDS solution because
of its ability to tolerate time delay and loss of signal.
• A common, flexible, interoperable data
communications interface that would readily
integrate across each robot’s disparate applications
and operating systems.
12/3/2013
© 2013 Real-time Innovations, Inc.
3

4. Data-Centric Architecture of DDS
Sensor Health
Assessment
Airborne
Sensor
DataWriter
publish
DDS Global Data Space
Sensor ID
Airborne
Sensor
12.35
35.45
0x2
1.34
6.78
ID
Roll
10
35.5
35.5
DataReader
-45
10.1
subscribe
Yaw
0x4
Airborne
Sensor
Pitch
0x3
DataWriter
DataReader
Velocity Y
0x1
publish
Velocity X
subscribe
-30
subscribe
publish
DataReader
DataWriter
12/3/2013
© 2013 Real-time Innovations, Inc.
4

5. Research: Cyber Situational Awareness
• Research is funded by the Air Force Research
Laboratory, WPAFB, Dayton, OH
12/3/2013
© 2013 Real-time Innovations, Inc.
5

6. Context: Cyber Situational Awareness
• Enterprise Security Situational Awareness
• Sensor Health Management
Security Situational
Awareness
Sensor Health Management
Goal
Situation (Attack) recognition, comprehension,
projection
Fault Detection, Isolation, Mitigation
Sensors
E.g., Host-based and network intrusion detection
systems (OSSEC, Snort, Ganglia), malware
detectors, firewalls, operating system, etc.
E.g., Accelerometer, fuel-flow sensors, altimeter,
speedometer, etc.
Input to
Analysis
Events and Alerts: log analysis, file integrity
checking, policy monitoring, rootkit detection, realtime alerting and active response
Sensor readings, software status signals, software
quality signals, operating system information
Analysis
Techniques
Complex Event Processing, Classification (Naïve
Bayes, SVM, linear classifiers), clustering (Kmeans), pattern matching etc.
Bayesian Networks, Hybrid Bayesian, Timed Fault
Propagation Graphs (TFPG),
Tools/Librari
es
R, Weka
Smile and Genie
Visualization
Histograms, heat maps, time series
Time series
12/3/2013
© 2013 Real-time Innovations, Inc.
6

7. Sensor Health Management
12/3/2013
© 2013 Real-time Innovations, Inc.
7

8. Cyber Health Analysis of Airborne Sensors
Propulsion
Comms
Engine
Electrical
Navigation
(formerly Predator B)
Mechanical
Payload
STANAG 4586 Message #1101: Subsystem Status Report
0 = No Status; 1 = Nominal; 2 = Caution; 3 = Warning; 4 = Emergency; 5 = Failed

9. Hardware-in-the-loop Simulation
Visualization
Sensor Health
Estimates
BeagleBone
Bayesian Network
Orientation
Sensor
(IMU)
Sensor Health
Analysis using
Bayesian Network
Pitch/Roll/Yaw
updates over TTL UART1
EngineOperatingStates
Smile library
Simulated UAV
Engine Data
(STANAG 4586)
DDS
Simulated MQ-9 Reaper UAV
12/3/2013
© 2013 Real-time Innovations, Inc.
9

10. Flight Simulator
• Flight Simulator
– E.g., Flight-Sim , X-Plane
– Realistic aerodynamic simulation
– Large number of model planes
including UAVs
• E.g., GD MQ-9 Reaper
– Simulates sensor failures
•
E.g., Engine fire
• Using Simulator data
– Publish using DDS
– Drive the Bayesian Network
– Inject artificial failure to evaluate
BaysNet
12/3/2013
© 2012 RTI • COMPANY CONFIDENTIAL
10

11. Hardware-in-the-loop Simulation using
Orientation Sensors
• Hardware Description
– Beaglebone Rev A5 (700 MHz,
256 MB RAM)
– CHR-6dm AHRS Orientation
Sensor
– Communication over TTL (3.3V)
UART at 115200 Baud
– Onboard Extended Kalman Filter
(EKF) produces yaw, pitch, and
roll angle estimates
12/3/2013
BeagleBone with CHR-6dm (above)
CHR-6dm orientation Sensor (below)
© 2013 Real-time Innovations, Inc.
11

12. Sensor Health Analysis Using Bayesian
Networks
• Bayesian Network based on STANAG 4586
• Sensor dependencies are modeled as an acyclic
graphs
• Can learn the structure and parameters from
raw data
• Each node has a probability distribution
function with respect to its parents
• Raw values of sensor readings are discretized
and plugged in
• Health nodes (H_*) give instantaneous
probability of sensor being faulty
–
–
Health Nodes
Sensor Nodes
A real value between 0 to 1
A value above or below a threshold trigger an alert
12/3/2013
© 2013 Real-time Innovations, Inc.
12

13. IMU-in-the-loop Simulation (Failure Scenarios)
1
Sub-Scenario #1
High Engine Thrust
Replay
Starts
[0:00]
Replay
Ends
[5:00]
(Change Pitch and Roll Physically)
2
Replay
Starts [0:00]
Sub-Scenario #2
Very Low Engine Thrust @ [1:30]
(Change Pitch and Roll Physically)
Engine
Catches Fire
[0:57]
12/3/2013
Very Low Engine
Thrust [1:30]
© 2013 Real-time Innovations, Inc.
Replay Ends [5:00]
13

14. Extensibility Facilitates System Evolution
• Evolution
– Hardware evolves  Software evolves  Data-types evolve
– Evolved system components must continue to communicate with
unevolved components
– E.g., 2d point (X, Y) evolves to 3d point (X, Y, Z)
– New radar that produces 3d points must work with old display that
expects 2d
• Solution: OMG Extensible and Dynamic Topic Types
Specification
struct EngineOperatingStates {
double timestamp;
string vehicleId; //@key
long
engineStatus;
double engineSpeed;
double enginePower;
double exhaustGasTemperature;
double engineBodyTemperature;
double outputPower;
long
fireDetectionSensor;
};// Extensibility(EXTENSIBLE)
12/3/2013
struct EngineOperatingStatesSensorsHealth {
double p_engineSpeedSensor_good;
double p_engineSpeedSensor_bad;
double p_exhaustGasTempSensor_good;
double p_exhaustGasTempSensor_bad;
double p_fireDetectionSensor_good;
double p_fireDetectionSensor_bad;
. . .
};// Extensibility(EXTENSIBLE)
© 2013 Real-time Innovations, Inc.
14

15. Take Home Points
• Bayesian Networks
– A flexible and capable platform for fault
detection and diagnosis
– Fine-grain fault detection within a
subsystem and across subsystems
– Large number of COTS tools
• RTI Connext DDS
– Has small footprint
• Runs on a ARM processors (700 MHz,
256MB RAM)
– Has low latency
• Supports hardware-in-the-loop simulation
as well as Smart Systems
– Standards-based support for system
evolution
12/3/2013
© 2013 Real-time Innovations, Inc.
15

16. Future Work
1. Expanded Cyber Situational
Awareness
–
Using independent ground-based
sensors
2. Integrate portable and truly
interoperable airborne software
components
–
Use RTI Transport Services Segment
(TSS) implementation
3. Semantic Interoperability
–
–
12/3/2013
Use UAS Control Segment (UCS)
Protocol Interoperability using DDS
(RTPS)
© 2013 Real-time Innovations, Inc.
16

17. Thank You!
12/3/2013
© 2013 Real-time Innovations, Inc.
17