Situation Awareness (SA) in maintenance intervention

Published: 14 August 2017

The overall goal of this project is to explore and describe the importance of SA in maintenance and to recommend how to develop and provide better SA for intelligent maintenance systems.

Sponsors: Trafikverket/JVTC

Researchers: Prasanna Illankoon (PhD candidate), Uday Kumar, Phillip Tretten (PL)

Duration: 2016-2020

Goal: The overall goal of this project is to explore and describe the importance of SA in maintenance and to recommend how to develop and provide better SA for intelligent maintenance systems. Project answers three questions: Why is SA important in maintenance? Why will developing SA be more challenging in future maintenance systems How can SA requirements be met to facilitate maintenance actions in the future? The main methodology used in the project is Cognitive Task Analysis. It involves
Semi structured interviews, participatory observations, focus groups and case studies.

Project Status and Results: Answering the first research question, four studies identify provisions for subtle and overt cues for anomaly detection; comprehension and projection challenges of energy isolation (Lockout-tag out); SA for maintenance compliance; and SA for judgmental accuracy. Second research question was partially answered by above four studies and a 5th study on the different cognition modes and cognition continuum in maintenance. Third question was answered by developing a collaborative framework and modeling decision support based on collaborative distributed awareness (CDA). Based on these models, two use cases are presented, in connection to decision support. One use case presents how SA interventions can help overcoming the upcoming challenges in railway maintenance such as making sense of heterogeneous data, increasing need for context awareness, and retaining the experts’ domain knowledge (figure showing a part of these interventions). The second case study recommends technological improvements needed in the Augmented Reality based maintenance decision support.
Conclusions: 1). SA interventions can help leverage the accuracy of expert judgements in maintenance. Main contribution of SA here is that it can employ more reflexive thinking. 2). SA interventions can help overcome the limited implicit learning opportunities in future maintenance systems. Although SA research has largely focused on employing explicit awareness,
this study suggested novel ways to promote implicit awareness. 3). SA interventions can help collaboration of the human awareness with intelligent systems.