Utilizing fuzzy-CBR methodology as an artificial intelligent engine in generating scenario case for plant virtual reality risk simulation

Process Hazards Analysis (PHA) is a systematic identification, evaluation and mitigation of potential process hazards, which could endanger the health and safety of humans and cause serious economic losses. PHA is often solely relied on expert imaginative thinking in simulating hazard conditions. Especially in Hazard and operability study (HAZOP), where intensive human resources involving time and high cost required. A risk managing virtual reality simulation supported by automated HAZOP proposed to eliminate analysis redundancies and bring static 'paper-base' analysis to more dynamic and interactive virtual analysis simulation. However, the efficiency of VR simulator depends on the scenario accuracy to the real world that can be simulated. In this paper, we introduce the system's artificial intelligent engine responsible for generating the most accurate and highest possibility to happen scenario case. A fuzzy - CBR method enables the engine to classify and used real past scenario combining with suitable parameters to create a defined scenario. This method resolves issues in balancing between computational complexity and knowledge elicitation. A reactor section of a VGO hydrodesulphurization process is used to illustrate proposed method.