MANUFACTURING community of practice

Open Knowledge Networks (OKN 3rd Workshop))

NITRD

What is the state-of-the-art for open knowledge networks in manufacturing?

What are some driving research questions that will benefit from manufacturing OKN?

What are some driving commercial or consumer questions that will benefit from manufacturing OKN?

What are the gaps, why do they exist, and how do we address them?

See under use cases

How is manufacturing different from other practices (biomedical, health, GEO, finance, self-driving vehicles, etc)?

The manufacturing industry uses sophisticated CAD software, but the model-based design paradigm has not yet been successfully extended to other areas, such as materials, supply chain management, product life cycle, and so forth. See on this:

DMDII-15-11 Completing the Model-Based Definition

What do we share with other domains? How can we benefit from this synergy?

The Industry Ontologies Foundry (see below) is an initiative to replicate in the manufacturing context some of the successes of ontology in the bioinformatics domain

Manufacturing Community of Practice

Barry Smith (Lead), National Center for Ontological Research

Slides 1

Slides 2

John Milinovich, Pinterest

Alessandro Oltramari, Bosch

William Regli, DARPA

Ram Sriram, NIST

Sudarsan Rachuri, DOE

Related initiatives in the manufacturing domain

---

Use cases

Use cases span the following broad areas:

Smart Manufacturing

Large and small companies are creating or buying software tools to support different aspects of model-based development in addition to CAD

The problem is that these software tools are rarely interoperable, and so digital workflows break where communication is needed with vendors or suppliers, or even across distinct divisions within a single enterprise

The Industry Ontologies Foundry (IOF) is a consortium of government (NIST, Air Force Research Lab), commercial and academic groups interested in addressing this problem by developing a suite of small modular ontologies constructed by analogy with the OBO Foundry in the field of biomedicine. Ontologies proposed for inclusion in the suite include:

MatOnto (Materials Ontology)

On-going AFRL work (Clare Paul, Wright-Patt) to create a MatOnto, a large materials science ontology growing out of the Materials Genome Initiative

Product Life Cycle Ontology

Manufacturing Capabilities (of companies, of manufacturing equipment, of sensors, of persons ...)

Use case: classification of suppliers, screening to select suitable suppliers (risk mitigation in supply-chain management -- for example when accepted bidder might drop out)

In progress: scraping information on the webpages of manufacturing companies and mapping terms identified to ontologies to enable reasoning (Farhad Ameri, Collaborative agreement between NIST and Texas State)

Can we create wikipedia-like pages for each company from this activity?

Manufacturing Readiness Levels (MRL) of interest also to DOD

Manufacturing Processes

Manufactured Products

So far what exists are primarily NLP-based attempts to identify emerging trends in customer needs or markets for example from the study of Amazon reviews of products

Standard for the Exchange of Product Model Data (STEP)

OntoSTEP

Can we convert this activity into an ontology-based OKN?

Workforce development

Here again a treatment of relevant capabilities data would potentially bring benefits

(from OKN Finance CoP) Creating many economic datasets based on social media, e.g., “i lost my job” to approximate something about the labor market.

Patents

Use case: to enable enhanced patent search resolving terminological inconsistencies

Focus on the patent system

Retrieval of patent information

Comparison of International Patent Classification (IPC) with MeSH

Robots

Probably not enough data in the public domain to enable a useful OKN for robot use in manufacturing at this stage

Examples of questions the OKN methods might be able to answer

One goal is to develop automatically short reports / wikipedia article specific to the question being queried

What open data already exist?

What are the questions that are being asked to the data? How is the answer currently discovered? Which datasets are consulted to find the answer?