Lloyd F. Colegrove Mary Beth Seasholtz Bryant LaFreniere 1
Run Design - Mountains of Data Planning Wisdom Improvement Marketing Trailer
Current Data Use Poor coordination, no obvious plan. We work, data sits. Manufacturing Products Data Data Data Process Control Monitor Safety Product Release
Future Data Use: Data will work for us! Manufacturing Products Data Data Data Run Design!
Motivation Use DATA to Justify* actions to FIX Guide* actions to IMPROVE Prescribe* actions to make BREAKTHROUGH CHANGES Largest impediment to becoming more data-driven is lack of understanding of how to use analytics* *Analytics: The New Path to Value, MIT Sloan Management Review, October 2010 What this means to us is We must learn how to better listen to the signals that our plants are sending us and how to respond to them.
Establish new rules as to how the data lives Guiding Principles (1) Data lives in one spot only (2) Every piece of data is owned by one entity and uniquely identifiable.
What will Run Design! look like? How will we know we re there? Examples: Rethink the concept of the COA (and all that entails) and make it work for us, rather than getting lost in file cabinet. Our customers will receive products based on data provided to them representing the normal operation of the plant within Multivariate control limits. Our suppliers will do the same. Design the Infrastructure and establish new rules as to how the data lives. Our data systems will be smart enough to decide whether data is good, bad or missing. All data systems within a plant (analytical in LIMS, engineering process data, other) are integrated across a portfolio of appropriate manufacturing Future technological developments in data analysis and process control can be implemented in the architecture without crisis. Learn how to better listen to the signals that our plants are sending us and respond to them. Our Plants will instantly know when continuous processes are trending out of normal, and our batch processes are not progressing properly in batch normal We will not just detect faults, our systems will identify their source. Our Technology Centers will know which plants are in trouble based on control observations from all the plant data, not just GPI, and this information will be accessible. Our Sr. Leadership within each business will have realtime metrics reporting on how well their operations are running, from Raw Materials to Supply Chain across the enterprise. Our Plant operators and Engineers will have meaningful signals and understand what action(s) to take when plant is trending into the weeds. The System will instruct. The system will learn. The system will keep and share its knowledge.
Rethink the CoA
Reveal Data and New Relationships Why was this graph so hard to make?
D from 100% is good product being flushed away
Looking At More Than Control Charts Control Charts Many Control Charts Good info, useful but Only answers questions about individual variables Need next step of what all of this data means in the bigger context More than linear grabbing of data It is the relationship/interaction of the data among the business information, collaborative troubleshooting, and other important aspects in the plant/process. Clay Shirky: It s not information overload. It s filter failure Need to cull out the relationships
Future Workflow as dreamed up on a paper napkin What the User Sees: A Workflow Implementation Tool Retrieve Data Join Data Analyze Data Services Layer This services Layer will know how to interact with all the different databases (1) Discover what is available & show it to the user (2) Retrieve data once user says what s/he wants Manually or unattended. A Wonderful tool Join data depending on goals: Continuous Batch Multiple plants Quality Analyst SIMCA-P Matlab Pirouette Etc.
Where to Start? Our First Hurdles: Accessing and Joining Data Data available in instrument software Lab information systems process historians SAP-like product systems Data collected at different time intervals Indexed differently; some in time, some in batchid Data integrity impacted by e.g. Natural plant variation Inappropriate plant operation Vagaries of chemical processes (reaction kinetics, etc.) Once we create an appropriate play space for our data, what will we achieve?
Analytic Complexity Journey to the SOLUTION COMPLEX Enterprise Quality Analyst Knowledge Automated Actionable Analytics Information SIMPLE Data Organized Data Dashboards for Improvements Value Delivery RUN $ Alarms DESIGN! $$$$
From Very BIG Data to Knowledge Automated Analyze V A L U E Analyze Report Prepare/ Distribute Report Capture Capture Data Aggregation Manual Data + Analytics = Intelligence Collaboration + Intelligence = Knowledge
Solution of Choice NWA Focus EMI Core EMI Services Direct data-source connectivity Real-time data aggregation Comprehensive analytics Real-time, role-based dashboards Alarm & notification services Accelerating Services KnowledgeBase Key-word searchable enterprise-wide, collective knowledge store Collaboration Center Fully-integrated, role-based, problemsolving workspace (with rich-content visual communications capabilities)
Manufacturing Intelligence NWA Collaboration Center NWA Focus EMI Rolespecific clients/content ERP Intelligence Executive Management SCM NWA KnowledgeBase Business Unit Management Process MES Intelligence NWA Focus EMI Data Integration & Analytics NWA Focus EMI Corporate Engineering/Quality Plant Management Plant Quality Historian Historian Quality System LIMS Process Engineers DCS Instrumentation / Devices HMI/SCADA Instrumentation / Devices QC Test Stations Laboratory Operators Machine #1 Machine #2 Machine #1 Machine #2 Process #1 Process #2
Scope Initiative #1 Implementing Core EMI Implementing across enterprise Currently 12 plants across multiple Business Units Initiative #2 Testing Accelerating Service Presently implementing accelerating services KnowledgeBase Collaboration Center Started September 2012 2 of 3 plants across single BU (separate countries)
Initial Results, ROI Dashboards for similar plants in two countries Contains analytical & process data Calculations of relevant metrics Teaching SPC/SQC vs. specification cutoffs for plant monitoring Research and Manufacturing are engaged! Detected numerous plant drifts which have initiated conversations and actions Developing a collaborative culture of proactive intervention Situations being fixed before they become a concerns Proactive rather than Reactive!
Next Steps Accelerate NWA Focus EMI implementations across company Continue to build out KnowledgeBase Expand Collaboration Center usage Plot next steps to Run Design! Analytics
Run Design - The Journey Out of Darkness Planning Wisdom Improvement Marketing Trailer
Thank you for your attention. Lloyd Colegrove, Director, The Dow Chemical Company lfcolegrove@dow.com; 979.238.9948 Louis Halvorsen, CTO, Northwest Analytics, Inc. lhalvorsen@nwasoft.com; 503.224.7727