Autonomous industrial operations are becoming the norm due to advancements in technology, which has led to both advantages and disadvantages for the organisations involved. The use of intelligent systems has resulted in higher system reliability, a higher quality product, and reduced risk for human error. These systems collect large amounts of information, analyse them, make predictions, and take decisions, of which humans cannot do in the same capacity, have led to new and expanded levels of interactions. One key aspect concerns the fact that human interaction has decreased although has become more critical than before. Even if the systems are advanced and automated, human intervention is still necessary: such as maintenance actions, selection of data to train the system, and advanced decision making. Human intervention is especially crucial when dealing with complex and safety critical systems, where and when immediate interventions are required. Moreover, an expert human can improvise and make novel decisions in a capacity that present intelligent systems cannot. The problem is that both humans and machines need assistance to perform well. Autonomous operation is not perfect and when problems arise, humans must react. Although it is common that humans when not actively interacting with the system tend to lose perspective and find it difficult to quickly analyse a situation when it arises. Which means that they “fall out of the loop”. Their ability to gain a good understanding of the situation and make good decisions when the system suddenly needs their interaction is lost. In other words, humans have lost their situation awareness (SA) and a good SA it is needed in dynamic environments if they are to intervene quickly and successfully. If, and when a system can assist a human to quickly assess the situation and get back “into the loop” then the human can make educated decisions in a much quicker fashion. The purpose of this research was to explore and describe the importance of SA in maintenance and to recommend how to develop and provide better SA for intelligent maintenance systems (IMS).

This thesis consists of a literature study conducted to develop the theoretical framework and two case studies were used to test the theoretical concepts. The thesis work tested five systematic methodologies to find suitable interventions to fulfil the SA requirements. The first case study focused on SA requirements during maintenance execution in a manufacturing organisation; there a quick return to production was the focus. The second case study was SA requirements in maintenance in the aviation domain, where safety is a top priority. The case study data were collected using interviews, observations, focus groups, and archival records. These qualitative data were analysed using qualitative content analysis, cognitive task analysis, and case taxonomic analysis.

This work resulted in the identification of seven key SA requirements for maintenance: consisting of detection of abnormalities; diagnosing and predicting their behaviour; making changes in system configuration; compliance with maintenance standards; conducting effective maintenance judgements; maintenance teams; and for safe maintenance work. Five strategies to maintain SA were identified: explicit knowledge status, sense making, recognition primed decision making, skilled intuition, and heuristics. We also argue why IMS will make it difficult for humans to use most of these strategies to maintain SA in future. Finally, a new theoretical model for decision support (Distributed Collaborative Awareness Model) was developed. The study also shows how to apply these interventions in the railway maintenance sector. In conclusion, this study shows that in the maintenance domain, keeping humans in the loop requires a novel collaborative approach where the integration of the strengths of intelligent systems and human cognition is necessary. We also argue that a better understanding of SA strategies will lead to the further development of SA support for the human operator and maintenance technician.