Automatic recommendation of prognosis measures for mechanical components based on massive text mining (extended version)

• Jorge Martinez-Gil
• Bernhard Freudenthaler
• Thomas Natschläger

Purpose – The purpose of this study is to automatically provide suggestions for predicting the likely status of a mechanical component is a key challenge in a wide variety of industrial domains.

Design/methodology/approach – Existing solutions based on ontological models have proven to be appropriate for fault diagnosis, but they fail when suggesting activities leading to a successful

prognosis of mechanical components. The major reason is that fault prognosis is an activity that, unlike fault diagnosis, involves a lot of uncertainty and it is not always possible to envision a model for predicting possible faults.

Findings – This work proposes a solution based on massive text mining for automatically suggesting prognosis activities concerning mechanical components.

Originality/value – The great advantage of text mining is that makes possible to automatically analyze vast amounts of unstructured information to find corrective strategies that have been successfully exploited, and formally or informally documented, in the past in any part of the world.