Using Optimization Algorithms-Based ANN to Determine the Temperatures in Timber Exposed to Fire for a Long Duration

The article investigates the temperature prediction in rectangular timber cross-sections exposed to fire. Timber density, exposure time, and point coordinates within cross-section are treated as inputs determine temperatures. A total of 54,776 samples wood with a variety characteristics were considered this study. Of sample data, 70% was dedicated training networks, while remaining 30% used for testing networks. Feed-forward networks various topologies employed examine temperatures fire more than 1500 s. weight artificial neural network optimized using bat genetic algorithms. results conclude that both algorithms efficient accurate tools determining temperatures, algorithm being marginally superior accuracy algorithm.