Wednesday, July 3, 2013

The Mystery of Enterprise Manufacturing Intelligence

Enterprise Manufacturing Intelligence, or EMI, has been around for over 15 years.  It was created as a way to put more context and meaning around data that was created in oil and gas refining plants--information such as throughput, yields, bottlenecks, and quality.  The value of these reports, to the outside world, wasn't apparent, and even the users themselves referred to the application as "MES" (or, Manufacturing Execution Systems).  But it's not--it's different, it's special, and they are both needed:  MES to govern the transformation of raw materials through finished goods, and EMI to provide meaning and relationships, acting as a Decision Support System for the organization.
We're going to focus on EMI.  AMR, in 2008, defined 5 properties of EMI:
  • Aggregation: Making available data from many sources, most often databases
  • Contextualization: Providing a structure, or model, for the data that will help users find what they need.
  • Analysis: Enabling users to analyze data across sources and especially across production sites.
  • Visualization: Providing tools to create visual summaries of the data to alert decision makers and call attention to the most important information of the moment. The most common visualization tool is the dashboard
  • Propagation: Automating the transfer of data from the plant floor up to enterprise-level systems such as an ERP, or vice versa
And although the market may have advanced, from more players, market consolidation, and expansion of the definition, these core features still remain. EMI is often confused with BI (Business Intelligence) but there's a key difference: BI's context and world surpasses manufacturing (or industry), it brings in more "ERP" or "business" context, such as HR, Finance, sales, etc. and is used as a business portal.  EMI is used for bringing context and relationships around events occuring that are near-real time.  This aspect differs from BI, which can use batched data from days, or even weeks.  EMI is about real time, providing responsiveness to an organization, transcending applications such as historians, MES systems, alarm databases, quality systems.  Typical plant applications that store execution information.

With EMI, companies can understand the "big picture" when it comes to multi-dimensional activities or problems, such as energy usage by shift, by location.  Or compare site performance on one or two different measures.  EMI is used in any type of industry--oil and gas, food and beverage, automotive.  We've even sold into non-manufacturing industries, providing a tool for energy management and resource allocation.  Avantis DSS (Decision Support System) uses Wonderware's  EMI to drive asset management optimization.

If you aren't looking at an EMI, perhaps you should.  It adds additional capabilities to your decision making, it links your plant and business databases to give you information, versus data, and it can grow in capabilities to make you more response to changes and events in your business.

No comments:

Post a Comment