demo day iot driven engineering - aalto · 2019. 1. 22. · 7 21/01/2019 iot driven engineering /...

IOT DRIVEN ENGINEERING

18.1.2019Matti LehtoValtteri Peltoranta

ENGINEERING ASSUMPTIONS CHALLENGED BY IOT DATA

Crane engineering

Analytics IoT data

Digital Twin

Assumptions from standards, books, …

21/01/2019 IoT driven Engineering / Matti Lehto, Valtteri Peltoranta2

Physical crane

DIGITAL TWIN IN PLM AS A NEW APPROACH

21/01/2019 IoT driven Engineering / Matti Lehto, Valtteri Peltoranta3

21/01/2019 IoT driven Engineering / Matti Lehto, Valtteri Peltoranta4

PLM EXTENDED TOWARDS REAL WORLD

Analyzed component information from Service and Engineering viewpoints

IoT data:Usage & condition monitoring

Analyses:EngineeringcriteriaVs.Usage & service history

Service data:Faults & repairs of components

21/01/2019 IoT driven Engineering / Matti Lehto, Valtteri Peltoranta5

ANALYZED COMPONENT INFORMATION

Service view

• Maintenance tasks & inspections based on Twin analyses

• Lifetime estimations for components

• “Digital Twin based maintenance”

Engineering view

• Comparison of design calculations and realized use

• Information about weak points of products

• Optimized dimensioning & selection of componentsà

à

21/01/2019 IoT driven Engineering / Matti Lehto, Valtteri Peltoranta6

STATISTICAL VIEW TO SIMILAR COMPONENTS

100%

0%

• Find similar parts in cranes on field• Equalize data from different cranes• Analyse statistically

Average

21/01/2019 IoT driven Engineering / Matti Lehto, Valtteri Peltoranta7

USE CASE

Z Ve

rtic

al p

ositi

onLoad forces

FL

Fr1Fr2 Fr3

Rope forcesFr4

R1 Bear

ing

rota

tions

Bearin

g typ

e and

capa

city i

nfo

Algorithms analyzing and reporting bearing status & estimation

Sensored raw dataProcessed info from raw data

a=b*c < E

R2 Bear

ing

rota

tions

21/01/2019 IoT driven Engineering / Matti Lehto, Valtteri Peltoranta8

CONCLUSIONS

• IoT and Digital Twins give a chance to make a cultural revolution in engineering

– From assumptions to real world information – design to fit purpose – no over or under engineering

– Connects engineering and service more tightly together (real usage and condition based service)

– Collected facts from field to support discussion between machine manufacturer and customer

– Continuous learning by utilizing field data in every day engineering and service work

• Challenges

– Raw data varies from asset to another and is not always similarly formalized

– Currently available data does not fit directly to existing engineering formulas as such

– Customers are used to refer to international standards

• Machine manufacturer needs to have a lot of analyzed knowledge from the field to renew approach