Artificial intelligence based smoke flow mechanism analysis and prediction patterns of fire for large space building

Abstract

The deposition and dynamics of smoke layers in large-space building fires are governed by a complex interplay of factors, making the prediction of such dynamics using traditional mathematical models challenging. In response, this study introduces a Back Propagation (BP) neural network model, devised from field simulation data, to efficiently forecast the temporal progression of smoke layers. It was observed that the model exhibits minimal training errors and high processing speeds, thereby fulfilling the stringent accuracy demands of fire engineering. Specifically, the model achieved a minimum relative error of 0.0005 and a maximum of 0.0845 across various prediction points, underscoring its reliability and precision. The ability of this BP neural network model to predict smoke layer changes significantly enhances the design optimization of smoke control systems swiftly and accurately in large buildings and supports rapid, informed decision-making during fire emergencies. Moreover, the model facilitates the development of engineering calculation models tailored for the quick prediction of fire smoke dynamics, which are essential for both theoretical research and practical applications. This approach not only conserves experimental resources but also advances the implementation of scientific, effective rescue operations in the event of large space building fires.