Outstanding Master’s Thesis Award

Ramin Sabbagh, an INFONEER alumni, has won the 2018–2019 Graduate College Outstanding Master’s Thesis Award in the Mathematics, Physical Sciences, and Engineering. His thesis, “Semantic Text Analytics Technique for Classification of Manufacturing Suppliers“, was directed by Dr. Farhad Ameri, Associate Professor in the Department of Engineering Technology. Ramin is currently a Ph.D. student in the Mechanical Engineering Department at University of Texas at Austin.

This is the first time in the history of the Department of Engineering Technology that a graduate student in the Technology Management program has received such a prestigeous award.

The Outstanding Master’s Thesis award is in alignment with the Conference of Southern Graduate School’s (CSGS) regional competition. By winning this award, Ramin has earn the chance to win additional funding and to attend the organization’s annual conference.

read more

APMS 2018 Presentation

The paper titled “Skill Modeling for Digital Factories” was presented in the Industry 4.0- Digital Twin session at APMS conference in Seoul, South Korea in August 2018. The presenter was Damiano Arena from EPFL, Switzerland, who was also the lead author on this paper.

IMG_4393

IMG_4392

Abstract: 

In the past two decades, the use of ontologies has been proven to be an effective tool for enriching existing information systems in the digital data modelling domain and exploiting those assets for semantic interoperability. Despite the presence of many databases for industrial skills and professions, a formal representation, namely, an ontology, which meets the requirements of an existing tool for skill and capability analysis called CaMDiF is missing. In this research, the MSDL ontology used by the former tool in its initial version is extended by importing modules of two well-known ontologies (BFO and Agent Ontology) and by developing a new ontology for industry skills and profession based on an existing non-ontological resource (O*NET). As a result, an overview of the enriched data structure in provided along with some discussions on two use cases related to skill analysis enabled by the new CaMDiF’s modelling features

CIE 2018- Quebec City

idetc2018

The paper titled “Supplier Clustering Based on Unstructured Manufacturing Capability Data” was presented at ASME IDETC/CIE 2018 conference in Quebec City on August 28th. Ramin Sabbagh was the primary author on this paper.  In this research, we successfully demonstrated how a hybrid approach based on document cluttering (K-means method) and topic modeling  (supported by LDA) can be used for automated extension of a SKOS thesaurus. Our longterm objective is to improve the performance of supervised machine learning techniques, such as document classification, with the aid of semantic models such as formal thesauri and ontologies. After including the new research findings, the journal version of the paper will be submitted to JCISE in near future.

This paper was one of the papers presented at Smart Manufacturing Informatics symposium. Dr. Ameri was the chair and symposium organizer.

Abstract: 

The descriptions of capabilities of manufacturing companies can be found in multiple locations including company websites, legacy system databases, and ad hoc documents and spreadsheets. The capability descriptions are often represented using natural language. To unlock the value of unstructured capability information and learn from it, there is a need for developing advanced quantitative methods supported by machine learning and natural language processing techniques. This research proposes a multi-step unsupervised learning methodology using K-means clustering and topic modeling techniques in order to build clusters of suppliers based on their capabilities, extract and organize the manufacturing capability terminology, and discover nontrivial patterns in manufacturing capability corpora. The capability data is extracted either directly from the website of manufacturing firms or from their profiles in e-sourcing portals and directories. Feature extraction and dimensionality reduction process in this work in supported by N-gram extraction and Latent Semantic Analysis (LSA) methods. The proposed clustering method is validated experimentally based a dataset composed of 150 capability descriptions collected from web-based sourcing directories such as the Thomas Net directory for manufacturing companies. The results of the experiment show that the proposed method creates supplier cluster with high accuracy.

IOF Workshop in Buffalo

The first IOF (Industrial Ontology Foundry) )working group workshop was held in Buffalo in July 2018. The objective was to develop a tentative roadmap for the next few months. Below is the summary of the developed roadmap:

September 2018
– create mobi repository for IOF ontologies in OWL,
and use COLORE as home for Common Logic IOF ontologies (Stephen, Michael)
– distribute WG procedures document, including
         – guide for using repositories in the context of IOF (Michael)
         – draft of ontology review criteria (Michael)
– finalize Technical Principles document (Todd)
– Project Management Issues
         – establish website for IOF (instead of GoogleDocs) (Melinda)
         – coordination of WGs (including creation of new WGs) (Chris)
         – mailing lists (Serm)
 
October 2018
– finalize current set of use cases from WGs
– initial set of proposed terms extracted from use cases
– competency questions for WG ontologies
– identification of overlapping terminology among initial WG ontologies
 
November 2018
– initial ontologies from WGs
Farhad Ameri chairs the Supply Chain working group.

Workshop agenda 

Keynote lecture: Capability Workshop

Farhad Ameri, an associate professor of manufacturing engineering and technology at Texas State University and an expert in design theory and ontology engineering, will deliver the keynote address for a UB workshop that seeks to advance the understanding of capabilities within information systems.

“Capabilities: Human and Machine” will take place at 12:45 p.m. April 20 in 126 Bonner Hall, North Campus, University at Buffalo School of Engineering and Applied Sciences, Buffalo, NY

workshop website

University of Buffalo News 

CIE/SEIKM Best Paper

Our paper, titled ”  A Thesaurus-guided Text Analytics Technique for Capability-based Classification of Manufacturing Suppliers” received the the  2017 SEIKM/CIE Best Paper award. The CIE conference was held is Cleveland, OH in August 2017.

cie-cleveland

Paper Abstract: 

Capability analysis is a necessary step in the early stages of supply chain formation. Most existing approaches to manufacturing capability evaluation and analysis use structured and formal capability models as input. However, manufacturing suppliers often publish their capability data in an unstructured format. The unstructured capability data usually portrays a more realistic view of the services a supplier can offer. If parsed and analyzed properly, unstructured capability data can be used effectively for initial screening and characterization of manufacturing suppliers specially when dealing with a large pool of prospective suppliers. This work proposes a novel framework for capability-based supplier classification that relies on the unstructured capability narratives available on the suppliers’ websites. Naïve Bayes is used as the text classification technique. One of the innovative aspects of this work is incorporating a thesaurus-guided method for feature selection and tokenization of capability data. The thesaurus contains the informal vocabulary used in the contract machining industry for advertising manufacturing capabilities. An Entity Extractor Tool (EET) is developed for the generation of the concept vector model associated with each capability narrative. The proposed supplier classification framework is validated experimentally through forming two capability classes, namely, heavy component machining and difficult and complex machining, based on real capability data.

 

CaMDiF Project Kickoff

Texas State’s first Digital Manufacturing and Design Innovation Institute ( DMDII ) project was kicked off in the UI LABS headquarter in downtown Chicago on February 10th 2017.Dr. Farhad Ameri is the PI from Texas State on this project. The project is titled “Capability Modeling for Digital Factory (CaMDiF)”.

The objective this project is to enhance the intelligence and effectiveness of various supply chain decisions through providing real-time, dynamic insight into the technological capabilities, capacities, and quality history of manufacturing suppliers. This project will result in creation of a cloud-based software solution for manufacturing capability modeling and sharing supported by a formal ontology.  This project is conducted in collaboration with the Applied Research Institute (ARI) at the University of Illinois at Urbana- Champaign (UIUC), Indiana Technology and Manufacturing Companies (ITAMCO), and the Innovation Machines. Texas State leads this project technically.

Screen Shot 2017-04-08 at 3.20.00 PM

NIST IOF Workshop

Dr. Ameri Attended the first workshop on Industrial Ontology Foundry (IOF) at NIST, Gaithersburg, MD. The objective of this first workshop was to identify industry needs and research issues that will lead to a roadmap for development of such IOF. Academic and industrial representatives (including representatives form Dassault Systems, JPL,  and Autodesk) participated in this workshop to identify the major challenges and develop a roadmap. .

Ontologies and semantic technologies have seen increasing uses in engineering applications; and most recently they have gained traction in the context of advanced manufacturing. Nearly all projects in the EU H2020 FoF project have adopted ontology as a component. Similarly, NIST’s smart manufacturing projects also have an ontology as a component. In addition, over the last two decades, NIST has developed several ontologies in the manufacturing and other engineering domains. These ontologies served various, overlapping objectives and related yet disparate. The goal of the IOF is to bring together ontologies in the industrial domain so that they can together provide more industrial value.