Indoor Occupant Locating and Motionless Alarm System Based on BP Neural Network and DS-TWR Technology

To address the critical demand for real-time dynamic tracking of personnel in complex buildings during emergency rescue operations, an indoor locating and motionless alarm system has been proposed, integrating BP (Back Propagation) neural networks with DS-TWR (Double-Sided Two-Way Ranging) technology. The system was composed of hardware and software. The hardware included positioning base stations (arranged in advance within the target area), positioning tags (with personnel), POE switches, routers and a computer. The software was developed based on the LabVIEW platform that coupled the BP neural network with the DS-TWR ranging technology to identify and locate the position of personnel more accurately. Thresholds of time period and movement distance were set to determine whether the occupant was trapped. System testing results showed that the system had good stability and high positioning accuracy, up to the order for centimeter level. Furthermore, the system could re-al-time monitor and display the movement trajectory of each person, and automatically alarm when anyone was trapped in a fire scene. Hence, once someone is trapped or in danger, rescue measures can be taken timely ac-cording to the alarm information provided by the system, effectively ensuring the safety of personnel and improving the efficiency of fire rescue work.