Predictive Maintenance with R Oliver Bracht – CEO info@eoda.de Agenda • About eoda • Predictive Maintenance • Predictive Maintenance with R • Best practice Oliver Bracht – CEO info@eoda.de About eoda • an interdisciplinary team of data scientists, engineers, economists and social scientists, • founded 2010 in Kassel (Germany), • specialized in analyzing structured and unstructured data, • integrated portfolio for solving analytical problems, • with a focus on „R“. Oliver Bracht – CEO info@eoda.de eoda portfolio Consulting Software Solution Training Oliver Bracht – CEO info@eoda.de Predictive Maintenance Oliver Bracht – CEO info@eoda.de The past of maintenance Reactive or Breakdown Maintenance Preventive or Periodic Maintenance Condition-based Maintenance Oliver Bracht – CEO info@eoda.de The past of maintenance Unplanned Reactive or production Breakdownshutdowns Maintenance Inefficient Preventiveuse or Periodic of resources Maintenance High Condition-based monitoring costs Maintenance Oliver Bracht – CEO info@eoda.de The requirements on maintenance International competition Shorter product life cycles New business processes Faster technological leaps The future of maintenance Predictive Maintenance Oliver Bracht – CEO info@eoda.de Predictive Maintenance Definition Predictive Maintenance as an extension of condition-based maintenance represents the informatization of production processes. With intelligent IT-based production systems Predictive Maintenance represents one important step on the path towards the development of a Smart Factory in industrial production. Oliver Bracht – CEO info@eoda.de Predictive Maintenance Potential Analytic know-how Domain Expertise Requirements of the market Oliver Bracht – CEO info@eoda.de Predictive Maintenance Workflow Business Value Maintenance Planning of maintenance Data analysis Data management Data collection Time Oliver Bracht – CEO info@eoda.de Predictive Maintenance Production indicators Data Collection and Management Big Data Environmental Data Sensor-based Machine Data Oliver Bracht – CEO info@eoda.de Predictive Maintenance Data analysis Data Scientists Power User Administrative User Consumer Source: David Smith Oliver Bracht – CEO info@eoda.de Predictive Maintenance Example – Gearbox Bearing damage in wind farm • Reactive Maintenance • Cost for a replacement of the bearing $ 250.000 • Cran costs $ 150.000 • Power generation / Revenue losses $ 26.000 $ 426.000 Source: http://www.wwindea.org/ Oliver Bracht – CEO info@eoda.de Predictive Maintenance Example – Gearbox Bearing damage in wind farm • Predictive Maintenance Use of acceleration sensors, oil particle counters and weather forecast modules, plus reliable evaluation of the data Early detection of the damage at the gearbox bearing • Repair instead of exchange of the bearing $ 30.000 < $ 250.000 • Lower cran costs $ 75.000 < $ 150.000 • Power generation / Revenue losses $ 2.000 $ 26.000 < $ 107.000 < $ 426.000 Source: http://www.wwindea.org/ Oliver Bracht – CEO info@eoda.de Predictive Maintenance Potential factors 50 % Reduction of maintenance costs 50 % Reduction of machine damage 50 % Reduction of machine downtime 20 % Increase in machine lifetime 20 % Increase in productivity 25 % - 60% Profit growth Source: Barber, Steve & Goldbeck, P.: “Die Vorteile einer vorwärtsgerichteten Handlungsweise mit vorbeugenden und vorausschauenden Wartungstools und –strategien – konkrete Beispiele und Fallstudien.” Oliver Bracht – CEO info@eoda.de Predictive Maintenance w Oliver Bracht – CEO info@eoda.de Predictive Maintenance with R Advantages • Features • • The features that come with R (without additional investment) are incomparable R in the software stack Oliver Bracht – CEO info@eoda.de Predictive Maintenance with R Advantages • Features • • The features that come with R (without additional investment) are incomparable R in the analytic stack • R can be integrated into all the layers of an analysis or reporting architecture Integration into an existing IT environment Forecast on the machine Prototyping C Implementation R directly on the machine Oliver Bracht – CEO info@eoda.de Predictive Maintenance with R Advantages • Features • • R in the analytic stack • • The involvement of the scientific community and large companies support the development and acceptance of R Quality • • R can be integrated into all the layers of an analysis or reporting architecture Investment protection • • The features that come with R (without additional investment) are incomparable R offers high reliability and uses the latest statistical methods Costs • R is Open Source and there are no license costs Oliver Bracht – CEO info@eoda.de Predictive Maintenance with R Data Collection and Management Production indicators Big Data Environmental Data Sensor-based Machine Data Oliver Bracht – CEO info@eoda.de Predictive Maintenance with R Data Collection and Management Different types of data at different times Production indicators Big Data Environmental Data Time Pressure Time Density 7:00 235 7:30 15,3 8:00 239 8:30 16,1 9:00 240 10:00 228 9:30 15,7 Sensor-based Machine Data 10:30 15,5 11:00 231 11:30 16,0 12:00 233 12:30 15,9 Oliver Bracht – CEO info@eoda.de Predictive Maintenance with R Data Collection and Management Different types of data at different times Environmental Data Big ModelData based interpolation Production indicators Time Pressure Density 7:00 235 8:00 9:00 Time Density 15,4 7:30 15,3 239 16,0 8:30 16,1 240 15,7 10:00 228 15,4 9:30 15,7 Sensor-based Machine Data 10:30 15,5 11:00 231 15,8 12:00 233 16,1 Smart Data 11:30 16,0 12:30 15,9 Oliver Bracht – CEO info@eoda.de Predictive Maintenance with R Data analysis Data Scientists Power User User Consumer Source: David Smith Oliver Bracht – CEO info@eoda.de Predictive Maintenance with R Best Practice Oliver Bracht – CEO info@eoda.de Predictive Maintenance with R Best practice Web based Front End API Authentication (LDAP) Administration RScripts Analysis Internal data Java Script User-, RoleManagement … … Data Public data sources Interactive Web App Machine data Oliver Bracht – CEO info@eoda.de Session Management Thank you for your attention For more information Whitepaper: Predictive Maintenance with R www.eoda.de eoda GmbH Ludwig-Erhard-Straße 8 34131 Kassel Germany +49 (0) 561/202724-40 Results as a Service eoda Service Platform www.eoda.de http://blog.eoda.de https://service.eoda.de/ http://twitter.com/datennutzen https://www.facebook.com/datenwissennutzen https://service.eoda.de/ info@eoda.de Oliver Bracht – CEO info@eoda.de