An intelligent situation awareness support system for safety-critical environments

Mohsen Naderpour, Jie Lu, Guangquan Zhang
2014 Decision Support Systems  
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
more » ... riven 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 decisionmaking 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. 1 Corresponding author, Tel: +61 2 9514 4520 [34] . In abnormal situations, a well-trained operator should comprehend a malfunction in real time by analyzing alarms, assessing values, and recognizing unusual trends associated with multiple instruments. When confronted with a complex abnormal situation, many alarms from different systems may sound at the same time, making it difficult for operators to judge within a short period of time which situation should be given priority. To return operational units to normal conditions, operators must respond quickly and make rapid decisions, but the mental workload of operators under these circumstances rises sharply, and a mental workload that is too high may increase the rate of error [17] . Paradoxically, several researches show that the focus of most human-system studies is on the technical elements, and human factors are often neglected [39] . This is due to well understood hardware reliability techniques, whereas the handling of human factors, by contrast, is difficult. These problems highlight the urgent need to discover cognitive decision support systems to manage abnormal situations that will lower operator workload and stress and consequently reduce the rate of errors made by operators. Decision support systems (DSSs) are envisioned as "executive mind-support systems" that are expected to support decision-making from a human cognition perspective [4] . Over the years, some types of DSS, such as model-driven and data-driven DSSs, have achieved increased popularity in various domains. Model-driven DSSs emphasize the creation and manipulation of statistical, financial, optimization, or simulation models that require decision makers to specify model parameters according to their decision problems. The functionality of data-driven DSSs results from access to, and manipulation of, a large database of structured data, and their outputs are based on perceiving and comprehending the integrated information [41] . Unlike model-driven and data-driven DSSs, cognitive DSSs have not been researched, albeit they have long been recognized as being worthy of consideration [4] . Just as a cognitive process refers to an act of human information processing, so a cognition-driven decision support system refers to assisting operators in their decision-making from a human cognition perspective, using such attributes as sensing, comprehending and projecting [39] . Of these cognitive aspects, an operator"s situation awareness (SA) is considered to be the most important prerequisite for decision-making. Situation awareness comprises the perception of elements in the environment, the understanding of their meaning, and the projection of the status of that environment in the near future [10] . Situation awareness is likely to be at the root of many accidents in safety-
doi:10.1016/j.dss.2014.01.004 fatcat:qixmjzg46fbfzbp3bxvwbch2eq