[Back]

F. Ansari:
"Cost-Based Text Understanding to Improve Maintenance Knowledge Intelligence in Manufacturing Enterprises, Computers and Industrial Engineering, Elsevier";
Computers & Industrial Engineering, 141 (2020), 106319.

Improving maintenance knowledge intelligence using text data has not been largely explored in the literature of production and engineering management. The state-of-the-art approaches and solutions mainly focus on either clustering and classification of maintenance logs, or extracting additional (meta-)data e.g. failure time data from maintenance text reports, operators´ workbooks and digital logbook. Knowledge Discovery from Text (KDT) enables finding undetected causalities, hidden patterns, frequencies, associative relations, and sentiments in maintenance text repositories. Applying KDT may enhance understanding the content of text data syntactically and semantically. However, advanced KDT approaches do not significantly provide meaningful and explainable outcomes, due to certain barriers in manufacturing enterprises, namely availability and quality of (longitudinal) maintenance text data.

To overcome these barriers in real world industrial maintenance, generate added value in industrial maintenance, and lay the ground for autonomous maintenance decision-support in the context of Industry 4.0, the first step is to adopt KDT methods and accordingly provide maintenance-specific solutions considering practical challenges and possibilities.

This paper discusses the lack of understanding maintenance text data and examines its effect on maintenance knowledge intelligence in manufacturing enterprises. A compositional framework for text understanding (TextPlan) is introduced. TextPlan explores quantification of text data in both syntax and semantic levels, i.e. how to vectorize an annotated maintenance report into numeric values, which represent cost data, hidden associations and sentiments. A prominent feature of TextPlan is cost-based text analysis, which decomposes a maintenance text report into separate cost items, and then (re-)composes the findings to estimate the total maintenance cost associated with the given report. Finally yet importantly, TextPlan consolidates the findings into a Text Understanding Map for assisting maintenance planner, based on three proposed measures of text comprehension, namely Association Measuring Index (AMI), Opinion Index (OI) and Cost Vector (CV).

Maintenance, Cost, Understanding, Knowledge discovery, NLP, Associative measuring, Sentiment analysis

http://dx.doi.org/10.1016/j.cie.2020.106319