Abstract
AbstractEngineered timber is increasingly in demand for tall buildings due to its positive impact on building sustainability. However, quick adoption raises fire engineering questions regarding flammability and structural performance. Understanding the behaviour of timber in fire is crucial, particularly for structural calculations of tall buildings. The charring rate of timber plays a significant role in its structural performance because the loss of cross section reduces the load bearing capacity of the element. Eurocode-5 (EC5) provides a simple method to calculate the charring rate and it is widely adopted for design in many countries while more complex physics-based models exist but are rarely used for design. For example, we want to know when EC5 underpredicts or overpredicts and by how much. This paper compares different data-driven methods, including statistical and artificial intelligence algorithms, for predicting the average charring rate of timber in fire. A new database of charring rates, VAQT, was created comprised of 231 furnace tests of timber products found in the scientific and technical literature. Statistical methods such as ridge regression (λ = 0.001) predict the charring rate with a minimum 11% error whilst EC5 predicts with 27% error. A trained neural network predicts the charring rate with minimum 9% error. This paper presents a novel database of timber charring experiments and provides a set of data-driven predictive models, all of which calculate the average charring rate with a significantly higher accuracy than EC5 for a wide range of mass timber products.
Funder
Engineering and Physical Sciences Research Council
Publisher
Springer Science and Business Media LLC