SLIDE 1
1
IoT
- T and
and Big ig Data
BNS NSF F Railw ailway ay
Sunny Bajaj
2
IoT oT and and Big ig Data BNS NSF F Railw ailway ay Sunny - - PowerPoint PPT Presentation
IoT oT and and Big ig Data BNS NSF F Railw ailway ay Sunny - - PowerPoint PPT Presentation
IoT oT and and Big ig Data BNS NSF F Railw ailway ay Sunny Bajaj 1 BNS NSF F at a a Glance Glance 32,500 mi of track 28 States/ 3 Canadian Provinces 1600 trains/ day 8000 Locomo>ves 13,000 Bridges 89 Tunnels 25,700 Grade
SLIDE 2
SLIDE 3
Internet of Things
3
Way ayside ide Det etect ector
- rs
SLIDE 4
4
Why hy Way ayside ide Det etect ection? ion?
- Improve Safety, Availability, Reliability and Velocity of rolling stock
- Augment manual inspec>ons
- Reduce train delays associated with setouts
- Proac>vely iden>fy “Bad Actors”
SLIDE 5
Det etect ector
- r Types
pes
5
Infrared T echnology
Excessive friction in wheels and bearings generates elevated temperatures that indicate a defect that, if not addressed, can result in catastrophic failure.
Force Detectors
It is normal for railcars to impart stable and balanced forces to the rail, but excessive impact forces or imbalanced forces in curves or straightaways indicate issues that may result in component damage or derailment.
Vision Cameras
Recording images of components operating at track speed is proving an effective and modern way to spot defects that are hard to identify while a car is sitting in a yard.
Acoustic Sensors
Harnessing sounds of a target component as it operates under load and speed can provide early warnings about defects in a component that may not be visible, like a crack or an internal defect.
Laser T echnology
Measuring position of components can provide useful information. Most recently, this information is being used to plan maintenance for locomotive wheels that require attention and to monitor freight-car braking capabilities.
5 Types of Technologies
13 Types of Detector Systems 2000+ Individual Detectors
SLIDE 6
Det etect ector
- r Examples
xamples
11/4/15 6
- Acoustic Bearing Detector (ABD)
– acoustic systems used to evaluate sounds generated by specific bearing component defects
- Hot Box Detector (HBD) –
evaluates bearing temperature history for statistical outliers; brake issues, burned off journals
- Cracked Wheel/Axle Detector
(CWAD) – Rail mounted sensors capable of detecting the difference between tones generated by normal
- vs. flawed wheels and
axles
Known Standard Cracked Wheel
SLIDE 7
The he Res esult ults
11/4/15 7
SLIDE 8
Internet of Things
8
The he Connect
- nnectiv
ivit ity
SLIDE 9
The he Connect
- nnectiv
ivit ity
11/4/15 9
SLIDE 10
Establis blishing hing a a Big ig Data a Pla latfor
- rm…
m… and and Explor xploring ing the he Pos
- ssibilit
ibilities ies… …
10
SLIDE 11
Big ig Data a Pla latfor
- rm
m – – Any ny Data, a, Any ny Wher here, e, Any ny Time ime
11
Mechanical Detectors
- Engr. Geo Cars
Weather Drones
Sources Analytics Data WEKA, R, etc.
Industry Data Asset Mgmt
Op>mized for Analy>cs Op>mized for Opera>ons
Video & Audio Structured Data Internet & Log Data Real-Time Streams Standard Reporting Discovery Predictive & Prescriptive Analytics Visualization
SLIDE 12
Pot
- tent
ential ial Bus usines iness Applica pplications ions… …
12
What is the impact of weather on Detector readings? Map weather paXers and history to BNSF Network. Use Detector data to run predic>ve models. Hadoop IOC DB2 SAS/R/SPSS What is the correla>on between Track Quality and Truck/wheel condi>on? Use Geo/Detector Car &
- Mech. Sensor data to
determine correla>ons Hadoop IOC DB2 SAP SAS/R/SPSS
Business Case Analysis PlaJorm
Can we predict engineering track defects in advance? Combine Geo-Car EAM and drones data to predict engineering track defects in advance Hadoop GIS Teradata SAS/R/SPSS