Enabling Proactive Quality in Commercial Airplanes using Natural Language Processing
Quality management systems traditionally draw insight from structured, often numerical, sources of data; unstructured, free-text representations of quality data are less frequently employed despite having high informational value, and often require additional human effort to prepare their contents f...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2022
|
| Online Access: | https://hdl.handle.net/1721.1/146644 https://orcid.org/0000-0003-2487-6448 |
| _version_ | 1826189279575932928 |
|---|---|
| author | Allinson, Christian |
| author2 | Boning, Duane |
| author_facet | Boning, Duane Allinson, Christian |
| author_sort | Allinson, Christian |
| collection | MIT |
| description | Quality management systems traditionally draw insight from structured, often numerical, sources of data; unstructured, free-text representations of quality data are less frequently employed despite having high informational value, and often require additional human effort to prepare their contents for use. An ability to extract and proactively employ this information enables a richer analysis of quality performance.
The primarily free-text reports generated by Boeing Commercial Airplane's "in-service investigation" (ISI) process are taken as an example of such quality data. We investigate both an unsupervised clustering method and a supervised classification method to group these reports by the broader "quality topic" they pertain to, using semantic relationship-maintaining text "embeddings" as features. We find success in supervised classification, and describe a method to relate ISI records with quality records from other parts of the commercial airplane value stream via standardized "code" metadata.
We extend the use of similarity techniques to investigation execution and propose a "helper" tool that automates parts of the manual data collection and relationship-finding process. The benefits of using such a tool over traditional keyword searches are described through an illustrated example. |
| first_indexed | 2024-09-23T08:12:38Z |
| format | Thesis |
| id | mit-1721.1/146644 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T08:12:38Z |
| publishDate | 2022 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1466442022-12-01T03:48:53Z Enabling Proactive Quality in Commercial Airplanes using Natural Language Processing Allinson, Christian Boning, Duane Spear, Steven Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Sloan School of Management Quality management systems traditionally draw insight from structured, often numerical, sources of data; unstructured, free-text representations of quality data are less frequently employed despite having high informational value, and often require additional human effort to prepare their contents for use. An ability to extract and proactively employ this information enables a richer analysis of quality performance. The primarily free-text reports generated by Boeing Commercial Airplane's "in-service investigation" (ISI) process are taken as an example of such quality data. We investigate both an unsupervised clustering method and a supervised classification method to group these reports by the broader "quality topic" they pertain to, using semantic relationship-maintaining text "embeddings" as features. We find success in supervised classification, and describe a method to relate ISI records with quality records from other parts of the commercial airplane value stream via standardized "code" metadata. We extend the use of similarity techniques to investigation execution and propose a "helper" tool that automates parts of the manual data collection and relationship-finding process. The benefits of using such a tool over traditional keyword searches are described through an illustrated example. S.M. M.B.A. 2022-11-30T19:38:40Z 2022-11-30T19:38:40Z 2022-05 2022-08-25T19:15:16.228Z Thesis https://hdl.handle.net/1721.1/146644 https://orcid.org/0000-0003-2487-6448 In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Allinson, Christian Enabling Proactive Quality in Commercial Airplanes using Natural Language Processing |
| title | Enabling Proactive Quality in Commercial Airplanes using Natural Language Processing |
| title_full | Enabling Proactive Quality in Commercial Airplanes using Natural Language Processing |
| title_fullStr | Enabling Proactive Quality in Commercial Airplanes using Natural Language Processing |
| title_full_unstemmed | Enabling Proactive Quality in Commercial Airplanes using Natural Language Processing |
| title_short | Enabling Proactive Quality in Commercial Airplanes using Natural Language Processing |
| title_sort | enabling proactive quality in commercial airplanes using natural language processing |
| url | https://hdl.handle.net/1721.1/146644 https://orcid.org/0000-0003-2487-6448 |
| work_keys_str_mv | AT allinsonchristian enablingproactivequalityincommercialairplanesusingnaturallanguageprocessing |