• No results found

Deploying Predictive Analytics Solutions in the Rail Industry and Seeing a Return on Investment

N/A
N/A
Protected

Academic year: 2021

Share "Deploying Predictive Analytics Solutions in the Rail Industry and Seeing a Return on Investment"

Copied!
15
0
0

Loading.... (view fulltext now)

Full text

(1)

D e p l o y i n g P r e d i c t i v e A n a l y t i c s S o l u t i o n s

i n t h e R a i l I n d u s t r y a n d S e e i n g a R e t u r n

o n I n v e s t m e n t

R o b e r t M o r r i s , P h . D .

C o - F o u n d e r & C h i e f S c i e n c e O f f i c e r

P r e d i k t o , I n c .

(2)

S H O W I N G B U S I N E S S V A L U E F R O M

D E P L O Y E D P R E D I C T I V E A N A T Y I C S I S

(3)

I N D U S T R I A L B U S I N E S S E S H A V E B I G D A T A B U T

S T R U G G L E T O S E E V A L U E F R O M I T .

(4)

S O M E C H A L L E N G E S

1 )

I D E N T I F Y I N G T H E L O W E S T H A N G I N G F R U I T

2 )

M A X I M I Z E T H E U S E O F D E S P E R A T E D A T A

S O U R C E S

3 )

N E E D F O R A D A P T A T I O N T O T E M P O R A L A N D

S P A T I A L C O N T E X T C H A N G E S O N T H E F L Y

4 )

S C A L E A C R O S S A T R E M E N D O U S V O L U M E O F

U S E - C A S E S A N D B E I N G A C C U R A T E

5 )

S H O W I N G T H E V A L U E T O B U S I N E S S

6 )

C O M M U N I C A T I N G T H E V A L U E O F R E S U L T S

(5)

B U S I N E S S E S T E N D N O T T O K N O W W H A T

T H E Y W A N T O R C A N U S E

P R E D I C T F U T U R E E V E N T S ?

F O R E C A S T R E L I A B I L I T Y ?

I N S I G H T T O O E P R A T I O N A L D A T A ?

T R I A G E D M A I N T E N A C E ?

I T ’ S N O T J U S T A N A N A L Y S I S … I T ’ S A S O L U T I O N

(6)

A C C U R A C Y V S . U T I L I T Y

W E R E Y O U R I G H T O R W R O N G ?

H O W R I G H T I S R I G H T ?

H O W A C C U R A T E M U S T W E B E T O S H O W

V A L U E ?

(7)

H O W D O E S P R E D I K T O S C A L E ?

A U T O - D Y N A M I C

P R E D I C T I V E A N A L Y T I C S S O F T W A R E

G E T T I N G T O V A L U E W I T H T H E

(8)

8

H O W P R E D I K T O S O F T W A R E D E L I V E R S

A C T I O N A B L E R E S U L T S

SENSORS INTELLITRAIN GE RM&D EMD NYAB LEADER MOTIVEPOWER WABTEC EAM SAP INFOR ORACLE MAXIMO OTHER BEACONS WILD WEATHER TCIS CUSTOM APPS UMLER ACTIONABLE PREDICTIONS

PREDIKTO ENTERPRISE PLATFORM

PREDIKTO INPUT API’S AUTO-DYNAMIC DATA TRANSFORM. ENGINE AUTO-DYNAMIC MACHINE LEARNING ENGINE PREDIKTO OUTPUT APIS & BI VIZ.

(9)

9

A R C H I T E C T U R E D I A G R A M

Standard JSON

AutoDynamic

Feature Engineering

AutoDynamic

Feature Selection

ETL

Data Cleaning

Dimension

Reduction

AutoDynamic

Machine Learning

Ensemble

Post-Processing

and Calibration

Email

SMS

WebHook

UI Data Store

P

redi

k

to dat

a P

ipel

ine

“MA

X

O

per

at

ion

al

I

nt

eg

rat

ion

Apache Spark

(10)

10

(11)

11

R E D U C I N G B A D S T O P S

I N F R E I G H T R A I L R O A D

B U S I N E S S C H A L L E N G E

Class 1 railroad experiencing unscheduled train stops

due to false warnings from wheel monitoring sensors

(HBDs)

800 HBDs installed throughout 22,000 miles of track

Unscheduled railroad stops due to HBD failures costing

over $10M annually

S O L U T I O N

Use the Predikto platform to improve reliability, reduce

train delays and reduce maintenance costs

Automatically predict which HBDs are expected to fail

within the next 7 days. Allows maintenance teams to be

proactive and focus on the right equipment and tools

Dashboard with GIS maps showing bad actors

Asset health score to show worst performing HBDs

R E S U L T S

• Solution entered production June 2014 • 12.7% reduction in the number of bad stops • $1.5M impact in Year 1

• Predikto identifying 37% of all bad stops with 7 day advanced

(12)

12

P R E D I C T I N G F A I L U R E S

I N C O M M U T E R T R A I N D O O R S

B U S I N E S S C H A L L E N G E

• Malfunctioning doors on commuter trains is a costly

problem for manufacturers, service providers, and passengers

• Manufacturers have Service License Agreements (SLAs) that

result in fines for service delays due to failed equipment

• When a door on a commuter train does not open properly,

passengers take longer to exit and board, resulting in delays, increased safety incidents, and potential for loss of revenue

S O L U T I O N

• Actionable and tailored prediction of whether a specific train

door will malfunction at some point in the future and allowed for enough time so that an actionable response to the problem could happen, but before delays occurred

• Malfunctions over the next 7 days delivered via the “Cloud” • The output from the Predikto’s automated solution were to

be interfaced with the customer’s existing data management to take action on immediately

R E S U L T S

• Predictions of whether and when a specific door in a “door set”

on a specific car on a specific train will fail, providing for a 7 day window.

• The precision (accuracy) of the “warnings” produced by

Predikto is in excess of 84 percent.

• The solution reduces delays caused by door failures, enhances

train travel velocity, expedites repair time, and most importantly, saves time and money.

(13)

13

P R E D I C T I N G F A I L U R E S

I N R A I L R O A D T R A C K

B U S I N E S S C H A L L E N G E

Cracks or breakages in segments of track significantly

increases the likelihood for derailment.

Need for better methodology to prioritize track inspection.

Narrowing inspection to a small track segment.

S O L U T I O N

Analysis of historical track data, usage and weather to

identify risk track segments

Provide granular predictions to quarter mile segments.

Provide a lead-time to allow the customer to properly

schedule and procure for predicted failures, thus reducing

operational costs.

Algorithms focused on accurate detection.

R E S U L T S

• Actionable predictions on which half-mile segments of track

are most likely to experience a defect well in advance of it actually occurring at some point during the following 3 months with a 63% accuracy.

• Predictions on defects were based on data provided by the

customer including: ultrasonic readings, historical defects and track details, Class I Railroad company (train movements, tonnage, etc.), and data built in by Predikto (e.g., weather).

(14)

14

P R E D I C T I N G D E L A Y S

I N B U L L E T T R A I N S

B U S I N E S S C H A L L E N G E

European railroad experiencing stops/delays due to

mechanical failure

Delays greater than 20 minutes including breakdowns

Cost to pull engine out of service very high

S O L U T I O N

Predikto providing alerts at train, car, component, and

sub-component levels

Provide top most likely error codes associated with failure

Algorithms configured for low false positive rate

Daily notification to operations team

T A R G E T R E S U L T S

• 100% Precision in Identifying 10% of Control Unit Delays • Identification of failures and delays greater than 20 minutes

1-4 days in advance.

(15)

References

Related documents

I We also consider a noisy variant with results concerning the asymptotic behaviour of the MLE. Ajay Jasra Estimation of

This incl udes not only volca nic eruptions but a lso the deep-seated intrusion of granites a nd other rocks ( p. These three processes act so that at any time the form

This listing is provided to assist wing plans officers and applicable HQ AETC staff OPRs with plan development and management.. The listing may be accessed via the HQ

Although environmental benefits have traditionally been in the center of attention for collaborative agri-environ- mental management, there is recognition of benefits to the

It then discusses the impact of the market crisis beginning in 2007 on short sale regulation, the current debate over the Securities and Exchange Commission’s (“SEC”) revisions

(Medicare, for example, has canceled its DM demonstration programs, and more commercial payors are bringing the DM function in-house.) Once again, the pharmacy is well

In-Breast Recurrence Breast conservation therapy Mastectomy Risk 10 to 15% 1 to 3%.. TRAM

So the total energy flux carried off by the perturbation electric and magnetic fields we have generated is exactly equal to the rate of work per unit area to pull the charged sheet