36
Hadoop Summit 2016 Preventive maintenance of Robots in Automotive industry Ari Flink, Amit Kumar

Preventative Maintenance of Robots in Automotive Industry

Embed Size (px)

Citation preview

Page 1: Preventative Maintenance of Robots in Automotive Industry

Hadoop Summit 2016 Preventive maintenance of Robots

in Automotive industry

Ari Flink, Amit Kumar

Page 2: Preventative Maintenance of Robots in Automotive Industry

2© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

• Intro • IoT evolution, Big Data in IoT• Cisco Cloud Platform

• Case Study• Preventive maintenance of Robots in Automotive industry• Adaptive, self-learning next-gen Predictive maintenance platform

Agenda

Page 3: Preventative Maintenance of Robots in Automotive Industry

3© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Ari fun fact: Kemi, Finland

Page 4: Preventative Maintenance of Robots in Automotive Industry

4© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

About Ari

Solutions Architect at Cisco Cloud • Architect service deployments on Cisco’s cloud platform (BDaaS,

DBaaS, BSS)

Previously Operations Architect at WebEx, eBay, Excite@Home• Ensure operational readiness for complex distributed services• HA, DR,, config, deployment, monitoring, event correlation

Page 5: Preventative Maintenance of Robots in Automotive Industry

5© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

What I love doing: Bikram Yoga @ 105 F

Page 6: Preventative Maintenance of Robots in Automotive Industry

6© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Amit: my other passion

Big Data Architect at Cisco Cloud Platform & Services Group• Big Data Solutions for clients and infra needs using Hadoop, Cassandra• Analytics platform design• Data Center infra software abstraction : Firewall as a Service, Networking as a

Service.

Previously Symantec/Verisign, HCL-US, BoA• Distributed Systems design and implementation• Hadoop based solutions for large data sets

Page 7: Preventative Maintenance of Robots in Automotive Industry

7© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Cisco Cloud Platform

Global platform deployed across

Cisco and SP Partners

API-driven, elastic experience for

developers,based on open

standards

Cisco-architected and operated for rapid application development and

deployment

Page 8: Preventative Maintenance of Robots in Automotive Industry

8© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Audience?

• Big Data ?• Robotics / car manufacturer?• IoT ?

Page 9: Preventative Maintenance of Robots in Automotive Industry

9© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

IoT evolution

Page 10: Preventative Maintenance of Robots in Automotive Industry

10© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

The Four Eras of Compute

1960 1980 2005 2015

Mainframe

x86 Linux Web VMs iPhone

PC + Web Cloud + MobileIoT + Analytics + Automation (ML)

Cloud Containers

Enterprise Consumer IoT ( Machines )

Page 11: Preventative Maintenance of Robots in Automotive Industry

11© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Why preventative maintenance for robots

Page 12: Preventative Maintenance of Robots in Automotive Industry

12© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

How much does unplanned downtime cost a car manufacturer?

$20k per minute

How much can a single incident can cost?

$2 million

Page 13: Preventative Maintenance of Robots in Automotive Industry

13© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Million dollar question

Which robot will fail next?

How can we predict robot failure?

Page 14: Preventative Maintenance of Robots in Automotive Industry

14© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Keep the assembly line moving

Page 15: Preventative Maintenance of Robots in Automotive Industry

15© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Why does a single robot failure matter?

Page 16: Preventative Maintenance of Robots in Automotive Industry

16© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Zero Downtime• Cisco and Fanuc have created a Zero Downtime Solution (ZDT)

that analyzes data from robots to detect potential problems that could lead to a failure.

• ZDT is currently used in production with over 6,000 robots at automotive plants globally. GM alone has deployed ZDT in 27 factories in 5 countries analyzing over 5,000 of robots

• ZDT has successfully detected over 45 cases of potential failure across 26 production plants over the past year and saved already customers  $40 million

Page 17: Preventative Maintenance of Robots in Automotive Industry

18© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Platform for Preventative Maintenance

Page 18: Preventative Maintenance of Robots in Automotive Industry

19© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Overview

$2 million outage avoided !

Telemetrycollected

Notify robot manufacturer

and plant

PlantDataCollector

Cisco Cloud

Partswarehouse

Car plant

Scheduledmaintenance

Page 19: Preventative Maintenance of Robots in Automotive Industry

20© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Cisco Cloud

Automotive manufacturer APlant 2

Plant 1

Plant Data Collector

Case study: Data Flow

Cisco IoT Platform

Plant 3

Cisco IoT Platform

Cisco BDaaS

ZDT application

Reporting

Analytics

Car manufacturers

Robot manufacturer

Automotive manufacturer BPlant 2

Plant 1

ZDT Data Collector

Cisco IoT Platform

Plant 3

Notifications

Page 20: Preventative Maintenance of Robots in Automotive Industry

21© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Cisco Cloud

Car PlantCar Plant

Batch Layer

Cisco Cloud: High Level Arch Framework

Speed Layer

Serving LayerMasterdataset Batch

view Batch view

Real-time view

App

Car Plants

Batchprocessing

Real-timeview

Real-timeprocessing

DataIngestLayer

Datastream

Page 21: Preventative Maintenance of Robots in Automotive Industry

22© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Cisco Cloud

Batch

Case study: ZDT Cisco Cloud Pilot details

Real-time

Serving

Masterdata

Computeddata

HBase

Ingest

Cisco IoT

Kafka

Flume

Spark Streaming

Batch processing:Pig, Hive

Impala

Impa

la S

QL

schema

Data

API

Page 22: Preventative Maintenance of Robots in Automotive Industry

23© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

UI

Hadoop

Multi-tenancy

User Interfaces

API

SQL(Impala)

HDFS

Customer Portals

Mobile Devices PD BI

Page 23: Preventative Maintenance of Robots in Automotive Industry

24© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Next Gen Platform: “Predictive” Maintenance

Page 24: Preventative Maintenance of Robots in Automotive Industry

25© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Why Predictive? Car Production facilities operate at high volume

Unexpected downtime creates considerable losses There is a need to be informed of a potential robot, controller or process problem

before unexpected downtime occurs

Early detection is key in the following scenarios Mechanical failures Process control failures System issues: Controller Maintenance reminders

Not-too-early and not-too-late detection is “key” Too early is expensive in the long run Too late is detrimental as well Finding the sweet spot is key to the most “optimal solution”

Page 25: Preventative Maintenance of Robots in Automotive Industry

26© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Sweet Spot: “Not-too-early” and “not-too-late” either

Time

Met

ric

Sweet spot

Too early Too late

Page 26: Preventative Maintenance of Robots in Automotive Industry

27© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Preventative Maintenance

Unscheduled outage avoided

Torque out of range

Notify robot manufacturer

and plant

Page 27: Preventative Maintenance of Robots in Automotive Industry

28© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Predictive analytics: Increased ROI

Repor

t• What

happened

Analyze

• Why did it happen

Monitor

• What is happening now

Predict• What

might happen

Increasing ROI and Complexity

Page 28: Preventative Maintenance of Robots in Automotive Industry

29© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Data Modeling details

Initial Dataset

Run/Evaluate Models

Gather Data

Define Problem

Validation Dataset

Test Model

Select Model

Test Dataset

Apply Model Run Prediction

Page 29: Preventative Maintenance of Robots in Automotive Industry

30© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Stream Processing Layer

HDFS

Data Ingest Layer

Predictive Analytics: High level architecture

Learning Layer

Action Layer

Rawdataset

Processeddataset

KafkaCisco

IoTPlatform

Near “real-time” (micro-batch) processing

( Spark )

Machine Learning ( Spark ML )

HDFSKnowledge

Base

Operational Dashboard platform

( custom built / Sensu

customized )

Page 30: Preventative Maintenance of Robots in Automotive Industry

31© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Stream Processing Layer

HDFS

Data Ingest Layer

Predictive Analytics: High level architecture

Learning Layer

Action Layer

Rawdataset

Processeddataset

Near “real-time” (micro-batch) processing

( Spark )

Machine Learning ( Spark ML )

HDFS

Knowledge Base

Page 31: Preventative Maintenance of Robots in Automotive Industry

32© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

File Formats: Avro vs Parquet vs ORC Avro is row-based

storage format, optimized for scans of all fields in a row for each query

Parquet is column-based, best used when dataset has many columns and only a few columns are worked on

ORC is column-based as well

Page 32: Preventative Maintenance of Robots in Automotive Industry

33© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Spark based Predictive platform on Hadoop

Data Integration ( Kafka, Sqoop, Flume )

Storage for any type of data

Filesystem(HDFS)

Online NoSQL(HBase)

Workload Management ( YARN )

Machine Learning(Spark, Mahout)

Stream Processing(Spark)

Page 33: Preventative Maintenance of Robots in Automotive Industry

34© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Stream Processing LayerData Ingest Layer

Predictive Analytics: High level architecture

Learning Layer

Action Layer

Operational Dashboard platform

( custom built / Sensu

customized )

Page 34: Preventative Maintenance of Robots in Automotive Industry

35© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Action Layer

Predictive Analytics: Action layer

Event store

Event consumer API based event Topic

Consumer for email

Events from the

Predictive platform

Dashboard middle-tier

API for Ad-hoc queries

Consumer for PagerDuty

Custom built / Sensu

customized

Page 35: Preventative Maintenance of Robots in Automotive Industry

36© 2015 Cisco and/or its affiliates. All rights reserved. Cisco Confidential

Recap

Unscheduled outage avoided: Savings $40 million

Page 36: Preventative Maintenance of Robots in Automotive Industry

PRESENTATIONEND