Show simple item record

dc.contributor.advisorRoy E. Welsch and Natasha Markuzon.en_US
dc.contributor.authorJeong, Hyunsooen_US
dc.contributor.otherMassachusetts Institute of Technology. Engineering Systems Division.en_US
dc.date.accessioned2017-01-06T16:13:55Z
dc.date.available2017-01-06T16:13:55Z
dc.date.copyright2016en_US
dc.date.issued2016en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/106252
dc.descriptionThesis: S.M. in Engineering and Management, Massachusetts Institute of Technology, School of Engineering, System Design and Management Program, Engineering and Management Program, 2016.en_US
dc.descriptionCataloged from PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 115-122).en_US
dc.description.abstractThe manufacturing industry has, recently, been facing tremendous challenges, including cost efficiency, system safety, and process automation, and manufacturing companies are required to adopt new technologies to keep themselves sustainable in the fast-changing world of technology. This research focuses, in particular, on how to prevent cutting tool failures and catastrophic accidents in Computerized Numerically Controlled (CNC) machining processes by using a predictive model based on the cutting sound data. With advances in machine learning algorithms and predictive analytics techniques, it becomes possible to create a noise-robust predictive model from an unstructured dataset of sound data. It is an obviously desirable decision to make use of every technology as required and benefit from it. The predictive model introduced in this research uses cutting sound data rather than acoustic emission or force/torque sensor data, which have been widely used for machine failure detection but have shown some limitations. The model is an important stepping stone for realizing an unmanned and fully automated manufacturing system, the so-called "smart factory," and it would be a meaningful movement for the government side as well, taking into account government's responsibility to keep people safe in the workplace. In this research, several experiments were carried out to collect sound data in the CNC machining center in Korea, and particular features were extracted from the analog waveform signals, using the unstructured data to make the predictive model using various advanced data analytics techniques and cutting-edge machine learning algorithms. Then, several analysis methods with systems thinking were used to explore potential impacts of the predictive model on the manufacturing system because the systems thinking approach is the most effective way to analyze a wide range of potential impacts from a holistic perspective. Specifically, the impact analysis was successfully conducted by using a "Causal Analysis based on STAMP (CAST)," which is a system safety analysis method. Also used was "system dynamics modeling," which is generally employed to identify dynamic behaviors in a complex system. Finally, a "complete value template" was constructed to portray how the new system delivers value to its stakeholders from a system architecture perspective.en_US
dc.description.statementofresponsibilityby Hyunsoo Jeong.en_US
dc.format.extent122 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsM.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectEngineering and Management Program.en_US
dc.subjectSystem Design and Management Program.en_US
dc.subjectEngineering Systems Division.en_US
dc.titlePredictive analytics for smart manufacturing : use and impact from a systems thinking perspectiveen_US
dc.typeThesisen_US
dc.description.degreeS.M. in Engineering and Managementen_US
dc.contributor.departmentMassachusetts Institute of Technology. Engineering and Management Program.en_US
dc.contributor.departmentSystem Design and Management Program.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Engineering Systems Division.en_US
dc.identifier.oclc961940194en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record