Affiliation:
1. HX5, LLC, Moffett Field, CA 94035
2. NASA Ames Research Center Intelligent Systems Division, , Moffett Field, CA 94035
Abstract
Abstract
Methodologies for failure assessment frequently rely on historical failure modes, causes, and recommendations for prevention. Meanwhile, there are growing databases of narrative-based lessons that are under-utilized due to their size. Advances in natural language processing (NLP) enable unsupervised extraction of this knowledge. We present a methodology for (1) identifying relevant information using a term frequency inverse document frequency (TF-IDF) classifier and (2) extracting knowledge for failure assessment using a hierarchical topic modeling approach, hierarchical latent Dirichlet allocation (LDA). To interpret the extracted topics, we apply an automatic topic labeling technique using pointwise mutual information (PMI) extraction. The methodology is applied to NASA’s Lessons Learned Information System (LLIS), which is publicly available. Partitioned topics enable the extraction of three aspects: cause, failure, and recommendation, while a hierarchy enables organization into a taxonomy. The methodology is generalizable to databases containing narrative-style documents, while the results from the LLIS represent a summary of themes in the dataset, expressed in a format that can be linked to early design failure analyses.
Subject
Industrial and Manufacturing Engineering,Computer Graphics and Computer-Aided Design,Computer Science Applications,Software
Reference59 articles.
1. A Failure Modes and Mechanisms Naming Taxonomy;O’Halloran,2012
2. A Rule Level Knowledge Management System for Knowledge Based Engineering Applications;Fan,2002
3. A Model-Based Approach to Identify Barriers in Design Knowledge Reuse;Jordan,2019
4. Development of a Hypersonic Vehicle Configuration Compendium;Simon
5. Design Principles for Effective Knowledge Discovery From Big Data;Begoli,2012
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献