Developing a firewater deluge monitoring and forecasting system based on GA-ARMA model

Abstract

Purpose The firewater deluge system (FDS) can provide water automatically through a deluge valve when a fire breaks out. However, there are many fire hazards caused by the abnormal operating state of the FDS. To monitor and predict the working state of the FDS, this paper aims to propose a firewater deluge monitoring and forecasting system using the Internet of Things (IoT) technology. Design/methodology/approach The firewater deluge monitoring and forecasting system consists of three layers: the sensing layer, network layer and application layer. The firewater pressure obtained by the monitoring nodes was transmitted to the local gateway and then to the remote monitoring center. In the application layer, an autoregressive moving average (ARMA) model was put forward to forecast the firewater pressure. Furthermore, a genetic algorithm (GA) was proposed to perfect the order determination method of the ARMA model. Finally, a Web application was developed to display the real time and predicted working status of the FDS. Findings The predicted results show that the ARMA model improved by the GA (GA-ARMA) is significantly better than traditional ARMA models in terms of mean relative error, mean absolute error and mean square error. Moreover, the proposed system is demonstrated to be effective, and an early warning can be alerted to remind users of repairing abnormal FDS equipment ahead of fire dangers. Originality/value The proposed system cannot only be applied to the FDS of all buildings to avoid fire hazards by monitoring and predicting the working state of the FDS, but can also be widely used in other fields, such as environmental monitoring, intelligent logistics and intelligent transportation.