Text Analysis of Assembly Work Instructions

Abstract

The objective of this research is to investigate the requirements and performance of parts-of-speech tagging of assembly work instructions. Natural Language Processing of assembly work instructions is required to perform data mining with the objective of knowledge reuse. Assembly work instructions are key process engineering elements that allow for predictable assembly quality of products and predictable assembly lead times. Authoring of assembly work instructions is a subjective process. It has been observed that most assembly work instructions are not grammatically complete sentences. It is hypothesized that this can lead to false parts-of-speech tagging (by Natural Language Processing tools). To test this hypothesis, two parts-of-speech taggers are used to tag 500 assembly work instructions (obtained from the automotive industry). The first parts-of-speech tagger is obtained from Natural Language Processing Toolkit (nltk.org) and the second parts-of-speech tagger is obtained from Stanford Natural Language Processing Group (nlp.stanford.edu). For each of these taggers, two experiments are conducted. In the first experiment, the assembly work instructions are input to the each tagger in raw form. In the second experiment, the assembly work instructions are preprocessed to make them grammatically complete, and then input to the tagger. It is found that the Stanford Natural Language Processing tagger with the preprocessed assembly work instructions produced the least number of false parts-of-speech tags.

A multimedia case-based reasoning framework for assembly sequence planning

“…More recently, Ou and Xu (2013) presented a system that can analyze and use assembly data available from a CAD model to generate assembly sequences. Renu and Mocko (2015) investigated the requirements and performance of Natural Language Processing of assembly work instructions.…”

“…Intelligent techniques, such as NLP, are already able to extract assembly information from text and make it available for further using. For example, Renu and Mocko (2015) used NLP and belief networks to analyze and represent design documents. Although formats of text and tables are different, the analysis method for text and tables are the same in nature.…”

Understanding Human Decision-making during Production Ramp-up using Natural Language Processing

“…Nowadays, NLP is widely used in social media [18], but other applications can also be found in the manufacturing domain. These include areas such as work instructions [19] and automated requirements specification analysis [20] or product quality and reliability improvements based on customer data [21]. Although the use of natural language is intuitive for the human, this usually causes problems to a machine and can complicate further analysis.…”

Automated Extraction of System Structure Knowledge From Text

“…In biomimetic design, Cheong and Shu [28] used syntactic rules to retrieve causally related functions from biology texts, to support analogical reasoning. Recently, Kang et al [29] attempted to extract manufacturing rules in the form of Semantic Application Design Language from text and Renu and Mocko [30] investigated potentially extracting assembly planning knowledge from assembly work instructions. While all of the above mentioned work used off-the-shelf parsers, Zeng [31] used the author's own recursive object model to translate requirements text into UML diagrams.…”