An intelligent situation awareness support system for safety-critical environments

• A situation awareness support system for managing abnormal situations is introduced.
• Both hardware failure and human failure are considered in this study.
• A situational network modeling process based on Bayesian networks is proposed.
• A situation assessment model based on fuzzy logic and risk indicators is developed.
• The proposed system provides adequate evidence of conformity with ALARP.

Operators handling abnormal situations in safety-critical environments need to be supported from a cognitive perspective to reduce their workload, stress, and consequent error rate. Of the various cognitive activities, a correct understanding of the situation, i.e. situation awareness (SA), is a crucial factor in improving performance and reducing error. However, existing system safety researches focus mainly on technical issues and often neglect SA. This study presents an innovative cognition-driven decision support system called the situation awareness support system (SASS) to manage abnormal situations in safety-critical environments in which the effect of situational complexity on human decision-makers is a concern. To achieve this objective, a situational network modeling process and a situation assessment model that exploits the specific capabilities of dynamic Bayesian networks and risk indicators are first proposed. The SASS is then developed and consists of four major elements: 1) a situation data collection component that provides the current state of the observable variables based on online conditions and monitoring systems, 2) a situation assessment component based on dynamic Bayesian networks (DBN) to model the hazardous situations in a situational network and a fuzzy risk estimation method to generate the assessment result, 3) a situation recovery component that provides a basis for decision-making to reduce the risk level of situations to an acceptable level, and 4) a human-computer interface. The SASS is partially evaluated by a sensitivity analysis, which is carried out to validate DBN-based situational networks, and SA measurements are suggested for a full evaluation of the proposed system. The performance of the SASS is demonstrated by a case taken from US Chemical Safety Board reports, and the results demonstrate that the SASS provides a useful graphical, mathematically consistent system for dealing with incomplete and uncertain information to help operators maintain the risk of dynamic situations at an acceptable level.