Predictive Maintenance A smarter way to manage assets Tim Ricketts Smarter Infrastructure Team September 2014
Traditional Way of Doing Asset Management IBM Software Group Challenges Assets are managed and maintained according to a fixed schedule Unplanned issues with assets are manually reported, delaying the response time. Responses are reactive, typically only after a failure has occurred. Question How can we use data from networked assets to reduce the response time, and enable proactive action rather than waiting for failures? Solution Use the real-time metric and event data coming from instrumented and networked assets to automatically create tickets to address issues or respond to failure warnings.
Predictive Maintenance is the next step towards Maintenance Excellence Maintenance Maturity Model Managing budget costs while improving reliability and safety Reactive Maintenance (machine fails, then fix) Preventive Maintenance (based on manufacturers schedules, time, or operational observations) Conditionbased Maintenance (based on monitoring to assess condition of assets) Predictive Maintenance (based on models of evolution of the condition of assets) Predictive Maintenance uses analytics to model foreseeable evolutions of the characteristics of individual systems or assets Source: Gartner 3
IBM Predictive Maintenance and Quality Reduce operational costs Improve asset productivity Increase process efficiency July 23, 2013! Accelerate Time-to-Value 2012 Singular software capabilities (Maximo, Cognos) Q1 2013 Customizable, cross-ibm, software and services solution (Analytics with real-time data integration) Packaged, cross-ibm, software product (Analytics with real-time data integration) Real-time capabilities Big data, predictive, and advanced analytics Quick and accurate decisioning Maximo integration Open architecture Business intelligence 4
A proven architecture based on best practices underlies Predictive Maintenance and Quality End User Reports, Dashboards, Drill Downs Predictive Analytics Telematics, Manufacturing Execution Systems, Legacy Databases, Distributed Control Systems Decision Management Analytic Datastore Integration Bus (Message Broker) High volume streaming data Business Intelligence (Pre-built data schema for storing quality, select machine and prod data, configuration) Enterprise Asset Management Systems IBM Software Group Advanced analytics powered by IBM SPSS and Cognos Data integration provided by Websphere Message Broker and Infosphere Master Data Management Collaborative Edition, which feeds a pre-built, DB2-based data schema Process Integration with Maximo automatic work order generation Includes data models, message flows, reports, dashboards, business rules, adapters, and KPIs 5
Predictive Maintenance and Quality generates significant business value for organizations Business Use Case Business Value Predict Asset Failure/Extend Life Determine failure based on usage and wear characteristics Utilize individual component and/or environmental information Identify conditions that lead to high failure è Estimate and extend component life è Increase return on assets è Optimize maintenance, inventory and resource schedules Predict Part Quality Detect anomalies within process Compare parts against master Conduct in-depth root cause analysis è Improve quality and reduce recalls è Reduce time to identify issues è Improve customer service
Predictive Maintenance and Quality converges Enterprise Asset Management (EAM) and Analytics capabilities Enterprise Asset Management Predictive Maintenance and Quality + = Better Outcomes Asset maintenance history Condition monitoring and historical meter readings Inventory and purchasing transactions Labor, craft, skills, certifications and calendars Supply Chain Processes Asset Lifecycle Mgmt Analytical insights Facilities Operation Optimized maintenance windows to reduce operating expense Efficient assignment of labor resources Enhanced capital forecasting plans Optimized spare parts inventory Safety and regulatory Requirements Staff Planning Automated analytical techniques, including anomaly detection for assets and sensors Improved reliability and uptime of assets
Predictive Maintenance and Quality provides several key features Real-time capabilities Big Data, Predictive and Advanced Analytics Quick and Accurate Decisioning Maximo integration Open Architecture Business Intelligence Accelerated Time-to-Value
Integration Overview IBM PMQ contains adapters for IBM Maximo, which allow data integration IBM PMQ uses existing Maximo infrastructure for data integration Maximo Upstream Module (Master Data Loading) IBM PMQ can consume master data residing in IBM Maximo IBM PMQ mirrors the asset data that is managed in IBM Maximo. An automated process can be designed to synchronize data between IBM PMQ and IBM Maximo Data that comes from IBM Maximo must be updated and maintained in IBM Maximo. It is not possible for changes that are made in IBM PMQ to be propagated back to IBM Maximo Maximo Downstream Module (Work Order Creation) IBM PMQ generates recommended actions which can be passed to IBM Maximo IBM PMQ can be customized to import IBM Maximo work orders as events to record activities such as inspections and repairs.
Questions Tim Ricketts Cloud & Smarter Infrastructure Team IBMSoftware Group Dubai Phone: 971-4-3907067 Mobile: 971-(50)1881945 E-mail: timricketts@ae.ibm.com IBM Corporation 2011