The Role of Semantic Models in Smarter Industrial Operations
CHANDLER, ARIZ., May 14, 2013 - The paper investiages the application of semantic model design and technology in industrial operations integration and the evolving role of Semantic Computing in operations management. Semantic (data) modeling as a core component of application architecture is compared to more familiar architectural integration patterns. As operations functions are described, the value of semantic models is illustrated through a series of examples that should be familiar to the reader.
Manufacturing best practices only match what is driven by competition; so to compete by differentiating its performance, each company must judiciously apply leading practices. Semantic Computing now has sufficient industrial application to be considered a leading practice. As such, various ways in which Semantic Computing supplements legacy technologies and possible longer term enhancements are suggested to facilitate operations safety and data integrity.
Three critical elements are often described in discussions around smarter plant solutions, of which semantic concepts are a key element. These three critical elements, the three “I”s as they are sometimes labeled, are “Instrumented,” “Intelligent” and “Interconnected.” These elements support the idea that much data are collected from the world around us and if we use the three “I”s to federate the data, operations intelligence is derived and with that we drive timely communication, response, and optimization around critical business tasks.
Important in this approach is the ability to interpret data for timely analysis and to derive understanding from a wide variety of sources in a wide range of formats and contexts. With Semantic Computing, the calculations and analysis are generalized to apply them to all instances of similar objects.
Data in the real world are subject to constant change. Therefore, structures need to be self-adapting and not rigidly predefined. This difference is referred to as the “Open World” versus the “Closed World.” Semantic modeling and its technology identify changes in underlying data and the potential interactions of those changes.
However, for the most part, the role of semantics is to alert a human promptly and in the appropriate context so that responses to those changes can be identified and appropriately acted upon.
Implemented semantic models can federate data from any connected data store into an agile, adaptive, fit-for-purpose model that leverages and extends industry standards and ontologies. When semantic models are coupled with applications that perform analysis, logic, reports, views, etc., which are easily and consistently applied and adapted, manufacturers are truly evolving to an global environment in which business and operations personnel are directly in control of their data, business and operations rules, and business and operations processes.This evolution is refered to as the “evolving ubiquitous computing model,” since computing power has become highly distributed and pervasive.
Industrial architectures must be designed to handle ever-changing, disparate data and implied, actual relationships between the data. Data sources include structured and unstructured data, sensor data (current value and historical), images, audio, and video. In addition, interactions of proposed data changes must be identified so that coordinated change is the rule and discovery is minimized. Not only does current data handling not fit well into standard relational persistence structures, but there is also the challenge to make sense of this data in context and adapt to additions, deletions, and changes with validation but without undue complexity.
This paper was produced as part of the MESA/ISA-95 Best Practices Working Group through an international peer review process involving 5 or more subject matter reviewers. This MESA White Paper is also be published in the methodology best practices collection, The MOM Chronicles: ISA-95 Best Practices Book 3.0 (Published by ISA, February 2013)
This white paper is available at: https://services.mesa.org/ResourceLibrary/ShowResource/cd41c356-ca0d-4128-93eb-25471b8c7508
All of MESA's white papers are available at www.mesa.org for MESA premium members, who have complimentary access to over 250 white papers, presentations, MOM/MES guidebooks, industry studies and web casts.
Dave Noller, IBM
Tim Hanis, IBM
Michael Feldman, Savigent Software
Charlie Gifford, 21st Century Manufacturing Solutions LLC
Jimmy Asher, Savigent Software
Bill Bosler, P.E., Texas Consultants, Inc.
Eyad A. Buhulaiga, Saudi Aramco
About MESA International
MESA International (Manufacturing Enterprise Solutions Association) is a global not-for-profit industry association dedicated to improving outcomes for businesses and their people through the use of manufacturing information. MESA is comprised of manufacturers, producers, solution providers, and industry thought leaders collaborating to formulate practical strategies to turn plant-floor data into valuable knowledge for enterprise success. We do this by:
- Collecting, sharing, and publishing best practices to help drive greater productivity and the overall profitability of the manufacturing enterprise. Over 800 webcasts, guidebooks, whitepapers, studies, and surveys are available for download in our Resource Library.
- Educating professionals through our IACET-accredited MESA Global Education Program (GEP).
- Facilitating collaboration among members in over 40 countries who connect, contribute, cultivate understanding, and exchange strategies to drive business results through real-time enterprise and Plant to Enterprise (P2E) integration.
Creating partnerships with other industry associations and experts like the World Batch Forum (WBF). Our 2012 merger broadens our knowledge of ISA-95 related standards like B2MML, and ISA-88 related standards like BatchML.