A Proposal of NFA Model for Anomaly Detection of Potable Water Management Process

It is very important to protect water management systems, which are one of the critical infrastructures, from intentional or accidental pollution events. Detecting possible anomalies in water processes in a short time and with high accuracy increases the emergency response capacity. For this purpose, NFAs, which are known to provide very successful results especially in network security, data processing and pattern matching, play an important role in detecting anomalies in the operation of critical infrastructure systems. In this context, the NFA-based model designed for the early detection of possible anomalies in water management processes in this study defined different states regarding the normal operations of the system and determined the transitions between these states. It was observed that this model, which was tested on real-time data collected from the water process in the Center Water infrastructure, detected anomalies with high accuracy.