Aviation Safety Program Integrated Vehicle Health Management (Srivastava).pdf · Section D5:...

National Aeronautics and Space Administration

www.nasa.gov

National Research CouncilAssessment of NASA’s Aeronautics Research

Program

Aviation Safety ProgramIntegrated Vehicle Health Management

Principal Investigator: Ashok N. Srivastava, Ph.D.Project Manager: Joseph E. Grady, Ph.D.

Associate Project Manager: Susan Johnson

1


www.nasa.gov

AgendaProject Goals and Objectives

Project Structure and Milestones

Program Coordination and Partnership

NASA IVHM Relationship to the Decadal Survey

Future Work

The IVHM Data Mining Lab


www.nasa.gov

Project Goals and Objectives

Aviation Safety Program GoalsDevelop technologies, tools, and methods to:

- Improve aircraft safety for current and future aircraft

- Overcome safety technology barriers that would otherwise constrain full realization of the Next Generation Air Transportation System

- Concurrently, leverage these technologies to support space exploration activities, such as enabling self-reliant and intelligent systems necessary for the long-duration travel requirements of future space vehicles.

IVHM Project GoalsDevelop technologies to determine system/component degradation and damage early enough to prevent or gracefully recover from in-flight failures in both the near-future and next-generation air transportation systems, and to provide enabling technology for space exploration.

3

http://www.nasa.gov/pdf/168652main_NASA_FY08_Budget_Request.pdf (ARMD-12)


www.nasa.gov

IVHM Project Goals


www.nasa.gov

Project Goals and Objectives




Future Work



www.nasa.gov


www.nasa.gov

Selected IVHM Milestones


www.nasa.gov





Future Work



www.nasa.gov

Cross-Project and Program Coordination

Project or Program Activity

IRAC C-17, F/A-18, Airstar shared testbedSystems Analysis

IIFD Architecture analysisData mining for cockpit switching

AAD Crack propagation, aging and durability tools, providing SHM data

Space Operations Mission Directorate Virtual Sensors and anomaly detection methods for ISS and Shuttle

Science Mission Directorate Virtual Sensors for anomaly detection

Exploration Systems Anomaly detection algorithms for Ares

Air Force NASA-AF Executive Research Committee


www.nasa.gov

New Space Act Agreements: • FLX Micro: to develop a high temperature, wireless pressure sensor • Moog: to develop prognostic technologies for electromechanical actuators • Boeing: to develop data mining technologies for anomaly detection

Developing Space Act and Other Partnership Agreements: • Sun Microsystems: Sunspot wireless sensors for prognostics • Sikorsky: Testing and integration of Sunspot wireless sensors• Lockheed Martin: Data mining anomaly detection methods on an F-16.

Partnership Status IVHM4Info%

10


www.nasa.gov

Moog SAA• Prognostics for Electro Mechanical Actuator (EMA) Systems• Moog Activities

– Moog has a set of 40+ EMAs dedicated for this work (power rating in aircraft actuator range)

– Provide guidance on developing new and/or simplified models for EMAs– Assist in the EMA prognostic algorithm verification and validation via tests with seeded

faults– Data will be shared with NASA

• NASA Activities– Develop physics-based models for actuator damage propagation

11

Design OutFail / OperateJam

Wall Thickness / Structural

Screw Fracture

Core Ductility

Load Distribution

Thread Shear

Contact Fatigue

Brinelling

False Brinelling

Lubrication

Misalignment

Classical Brg Race Failures

Screw

Circuit Orientation

Wall Thickness / Structural

Nut Fracture

Core Ductility

Load Distribution

Thread Shear

Contact Fatigue

Brinelling

False Brinelling

Lubrication

Misalignment

Classical Brg Race Failures

Nut

Great Circle Generation

Ball Fracture

Dimpling

Wear

Classical Brg Ball Failures

Ball

Fatigue Damage

Wear Damage

Misaligment

Rupture

Return Failure

Ice Damming

External

Internal

Contamination

Screw / Nut Seperation

Return

Circuit

Ball Screw Failures


www.nasa.gov

IVHM4Info%





Future Work



www.nasa.gov

Section D5: Fault-tolerant and Integrated Vehicle Health Management systems

“Fault-tolerant aircraft systems, coupled with CBM, may improve aircraft safety and reduce aircraft life-cycle maintenance and ownership costs. Critical research tasks include developing:

1. Robust and reliable hardware and software tools for monitoring components, detecting faults, and identifying anomalies;

2. Prognosis analysis tools for predicting the remaining life of key components;

3. Approaches for recovering from detected faults, including reconfiguration of the flight control system for in-flight failures of manned and unmanned aircraft; and

4. Low-cost, lightweight, wireless, self-powered sensors with greater memory and processing capability.”

From the Decadal Survey of Civil Aeronautics.


www.nasa.gov

Rotordynamic AnalysisNASA Decadal Survey: D5 and C1

• Development of a physics based diagnostic system

• Disk imbalance causes synchronous whirl

• Current model accounts for shifting eccentricity as function of crack characteristics and speed

• Notch used to emulate crack for global, vibration response

x

y

z

T

Machined flaw

Milestone 1.3.1


www.nasa.gov

Modeling Approach

Equations of motion Solution for undamaged case (fixed imbalance)

( )θω −= tXx cos

( )θω −= tYy sin

( ) ( )222

2

21 rr

erYXξ+−

==

⎟⎠⎞

⎜⎝⎛

−= −

21

12tan

rrξθ

r = ω/ωn

{

These terms define the synchronous whirl amplitude.

texxx nn ωωωξω cos2 22 =++ &&&

teyyy nn ωωωξω sin2 22 =++ &&&

x

y

O

C

Me

θU

V

6/4/2007

Modeling Approach

Modeling the crack dependenceTotal eccentricity is a function of crack characteristics and speedSum of initial imbalance vector and imbalance due to crack

e0

eecr

x

y

ecr sin ββα

e0 +ecr cos β

βcos2 022

0 crcr eeeee ++=

ββ

αcos

sintan

0

1

cr

cr

eee

e+

==∠ −

Crack dependent solution

( ) ( )( )( )αθω

ξ

β+−

+−

++= t

rr

eeeerx crcr cos

21

cos2222

022

02

( ) ( )( )( )αθω

ξ

β+−

+−

++= t

rr

eeeery crcr sin

21

cos2222

022

02

( ) ⎟⎟⎠

⎞⎜⎜⎝

⎛+

+⎟⎠⎞

⎜⎝⎛−

=+ −−

ββξαθ

cossin

tan1

2tan0

12

1

cr

cr

eee

rr

Phase angle has new term due to the introduction of a crackAmplitude of ecr is defined by numerical analysis


www.nasa.gov

ResultsNo notch

1.2 in notch at 0 degrees




0

50

100

150

200

250

0 5000 10000 15000Shaft speed, rpm

Phas

e, d

egre

es

0

0.0005

0.001

0.0015

0.002

0.0025

0 5000 10000 15000Shaft speed, rpm

Sync

hron

ous

whi

rl am

plitu

de, i

n


www.nasa.gov

ADAPT Advanced Diagnostics and Prognostics Testbed

18

• Provide development platform with real, representative Electrical Power System (EPS) components for: – Diagnostic and prognostic models and algorithms– Advanced caution and warning methods

• Allow performance assessment of these algorithms– Standardized testbed– Repeatable failure scenarios


www.nasa.gov

19

Preliminary Characterization of Sensor Placement Methodology

Iterative Down-Select ProcessIterative Down-Select Process

Knowledge BaseKnowledge Base

Final SelectionFinal Selection

HealthRelated

Information

HealthRelated

Information

SystemSimulation

SystemSimulation

Down-SelectAlgorithm

(Genetic Algorithm)

Down-SelectAlgorithm

(Genetic Algorithm)

SystemDiagnostic

Model

SystemDiagnostic

Model

Sensor SuiteMerit

Algorithm

Sensor SuiteMerit

Algorithm

OptimalSensorSuite

OptimalSensorSuite

Candidate Sensor Suites

i=0 i>0

Candidate SelectionComplete

YesNo

Collection of NearlyOptimalSensorSuites

StatisticalEvaluationAlgorithm

StatisticalEvaluationAlgorithm

CombustorFan

LPC HPC LPTHPT

Blue = typical sensors

Green = optional sensors

Red = advanced sensors

FADECControl Sensors

T2AP2A

T25 T3PS3 WF36 XN2 XN25T49

OptionalSensors

P17T17

P25

AdvancedSensors

T5P5

T41P41 P48W17 W25 W3 W49 W5W41

Large Commercial Turbofan Engine – Problem Characterization

Systematic Sensor Selection Strategy (S4) ArchitectureNASA Decadal Survey: D5 and B3

The overall fitness of different sensor suites selected by the S4 algorithm

Sensor Selection Results:

Target Num

Target Wt. XN2 XN25 P2A T2A P17 T17 P25 T25 PS3 T3 T49 P5 T5 WF36 Fitness

Num Sensors

9 0.000 X X X X X X X X X X X X 27.708 129 0.010 X X X X X X X X X X X X 26.901 129 0.100 X X X X X X X X X X 23.161 109 0.500 X X X X X X X X X 20.857 910 0.001 X X X X X X X X X X X X 27.653 12


www.nasa.gov

Comparison of Unsupervised Anomaly Detection Methods, JANNAF ’07Outstanding Achievement in Liquid Propulsion Award in the Operational Systems category at the JANNAF 3rd LPS Meeting in May, 2007

NASA/Decadal Survey D5 and B3

N/A130.54553.05277.84295.8467.04130Turbine Blade Failure

A10853

N/A156.64N/A183.4431.4420.66119Knife Edge Seal CrackA20619

11.8417.4423.4423.44176.2423.4411.62

Fuel Leak and

Controller Failure

STS-93 (#3)

12.64N/A25.0425.0415.4425.0411.38Controller Failure

STS-93 (#1)

N/AN/AN/AN/AN/A77.8232.76Sensor Failure

STS-91 (#1)

N/AN/AN/AN/AN/AN/A74.42

Anomalous Spike in Sensor

Reading

STS-77 (#2)

GMMLDSIMSSVMGritBotOrcaActual

Time of failure (in seconds) as recorded by each methodFailure Type

Failure Data

Milestone 1.6.1Blue: Fastest response times. Red: Highest accuracy. 20


www.nasa.gov

Section D5 cont’d: Fault-tolerant and Integrated Vehicle Health Management systems

“Evaluate component capability in a simulated environment(ground test and hardware in the loop). That is, take a particular subsystem, such as a real landing gearsystem that has been represented by an appropriate behavioral model as specified and insert simulated faults to test for proper operation of the health monitoring system.”



www.nasa.gov

727 Landing Gear Test Preparations in ALDF

Description: The Aircraft Landing Dynamics Facility (ALDF) is capable of exercising a landing gear, for a brief extent, through the touchdown, rollout, and braking phase of aircraft landings at operational load and speed conditions while injecting subsystem faults. Data collected during the tests can be used to develop and verify diagnosis andprognosis algorithms. Preparations are underway for a series of 727 main landing gear tests in the ALDF. Over ten test runs are planned, including fault injections in the hydraulic system, anti-skid valves, brakes, and wheel speed sensors.


www.nasa.gov

Section C1: Integrated Vehicle Health Management“IVHM holds the promise of reducing vehicle cost,weight, and maintenance downtime, as well as speeding theintroduction of new material systems and structural concepts.Real-time onboard sensor systems that monitor the actualstate of materials and structural components enable moreefficient use of material, including novel concepts…”

“With a better model of itself, the aircraft can trace back system anomalies through the multitude of discrete state and mode changes to isolate aberrant behavior. Fault-tolerant systems combine simple rule-based reasoning, state charts, model-free monitoring of cross-correlations among state variables, and model-based representations of aircraft subsystems.”



www.nasa.gov

Classification of Damage Signatures in Composite Plates Using One-Class SVMs, submitted to AIAA Journal

a

b

c 0.4

0.5

0.6

0.7

0.8

0.9

1

30 40 50 60 70 80 90

100

Torque

Cla

ssifi

catio

n R

ate

Milestone 1.6.1


www.nasa.gov





Future Work



www.nasa.gov

• Research and development of diagnostic and prognostic methods across structures, propulsion, and aircraft systems.

• Release of NASA Research Announcement.

• Fostering cross agency technology advancements to benefit IVHM.

• Data Mining in Aeronautics Science and Exploration Systems conference

• Building an IVHM Data Mining Lab

• Developing publicly available IVHM data.

Future Work

26


www.nasa.gov





Future Work



www.nasa.gov

Mission of the IVHM Data Mining Lab

The lab enables the dissemination of Integrated Vehicle Health Management data, algorithms, and results to the public. It will serve as a national asset for research and development of discovery algorithms for detection, diagnosis, prognosis, and prediction for NASA missions.

Serves several High Priority R&T Challenges including C1, D5, E8B, and E8C.


www.nasa.gov

Features of the IVHM Data Mining Lab

Datasets• Propulsion, structures, simulation

and modeling• ADAPT Lab • Icing• Electrical Power Systems• Systems Analysis • Flight and subscale systems• Fleet-wide data• Multi-carrier data

Open Source• Code• Papers• Generation of an IVHM community

Selected Discovery Tools• Inductive Monitoring System

(IMS) – cluster-based anomaly detection

• Mariana – Text classification algorithm

• Orca – Distance-based outlier detection

• ReADS – Recurring anomaly detection system for text

• sequenceMiner – anomaly detection for discrete state and mode changes in massive data sets.


www.nasa.gov

Key Research Issues Addressed in the IVHM Data Mining Lab

• Real-time anomaly detection • Model-free prediction methods• Hybrid methods that combine discrete and continuous data• Distributed and privacy-preserving data mining• Analysis of integrated systems


www.nasa.gov

Appendix


www.nasa.gov


www.nasa.gov

DATA

IVHM Data Mining LabThere is a suite of tools already available for analysis, so researchers will not only be able to help analyze the data now, but the additional data will allow for continued R&D to develop algorithms and tools to answer evolving and complex questions (such as system-level questions).

IVHM elements create large amounts of data

The results of the data mining analysis, simulated data sets and new tools could be returned to the other research areas as well as disseminated to other NASA directorates, academia etc.., creating a mutually beneficial relationship of enhanced data analysis.


www.nasa.gov

From the Decadal Survey….Section B9

“The growth of new MEA loads is being driven byadvances in the capabilities of electric actuators and controls,and it is being enabled by the development of moreflexible and reliable aircraft generators.”

“Intelligent power management and distribution (PMAD)using advanced system models and wireless sensors orSensor-less control technologies for graceful degradationand failsafe operation.”



www.nasa.gov

Diagnosing Electrical Power Systems Using Bayesian NetworksNASA/Decadal Survey: B9 and D5

BN Inference

Command nodes

Health nodes

Sensor nodes

INPUT: OUTPUT:

Description:Bayesian networks offer an effective way to distinguish sensor faults or noise from component or system faults. They can model probabilistic, uncertain behavior but also exploit determinism in the system. For example, in circuit analysis, deterministic behavior takes the form of Ohm's law and Kirchhoff's laws. The goal of this effort is to develop a sensor validation approach that is powerful in domains with a combination of probabilistic and deterministic behavior; an example is the ADAPT lab.

To Battery

To Load

Outcome/Results:Professor Darwiche and students from UCLA visited the ADAPT lab to continue collaborations with NASA researchers on the development of an approach for modeling both probabilistic and deterministic behavior by means of Bayesian networks. The approach involves the generation of a Bayesian network with the following types of nodes: • Health nodes

– System health: represent health of system – Sensor health: represent health of sensors

• Command nodes: commands from a testbed user • Sensor nodes: read from ADAPT or from vehicle • Push nodes: mediate flow being pushed from battery to load• Pull nodes: mediate flow being pulled by load from battery

35

Aviation Safety Program Integrated Vehicle Health Management (Srivastava).pdf · Section D5:...

Documents

Transcript of Aviation Safety Program Integrated Vehicle Health Management (Srivastava).pdf · Section D5:...