Artificial Intelligence (AI) has rapidly become a part of our everyday lives at home and at work. Be it a recognition of a song playing nearby, hiding pimples from your face in a photo or detection of spam calls and e-mails – these are just a few examples of a wide range of AI applications.
Fire Safety Engineering is not standing apart from this progress. The benefits of Machine Learning (ML) includes cost and time which could assist with lifesaving applications when utilised by industry professionals.
- Cost is saved when a material’s resistance and behaviour in fire is being predicted with ML as opposed to expensive fire testing and long modelling.
- AI can save an engineer’s time, helping with calibrating input parameters and predicting simulation results based on the array of results from hundreds of previous long-run simulations.
- The method has potential in saving human lives too. For example, research has been done in analysing conditions within a fire compartment to predict flashover conditions for future smart firefighting.
However, it should be said that AI-predicted results can only be as good as the input data for ML. It is susceptible to the same limitations as the underlying methods and should play only a supportive role in decision making in conjunction with fundamental knowledge and experience.
Our engineers would be pleased to assist you and can work on projects of all sizes. Please get in touch with our team if you have any questions, we are keen to help.
References
Tianhang Zhang, Zilong Wang, Ho Yin Wong, Wai Cheong Tam, Xinyan Huang, Fu Xiao, Real-time forecast of compartment fire and flashover based on deep learning, Fire Safety Journal, Volume 130, 2022, 103579, ISSN 0379-7112, https://doi.org/10.1016/j.firesaf.2022.103579.
D. Norsk, A. Sauca, K. Livkiss, Fire resistance evaluation of gypsum plasterboard walls using machine learning method, Fire Safety Journal, Volume 130, 2022, 103597, ISSN 0379-7112, https://doi.org/10.1016/j.firesaf.2022.103597.
Hoang T. Nguyen, Yousef Abu-Zidan, Guomin Zhang, Kate T.Q. Nguyen, Machine learning-based surrogate model for calibrating fire source properties in FDS models of façade fire tests, Fire Safety Journal, Volume 130, 2022, 103591, ISSN 0379-7112, https://doi.org/10.1016/j.firesaf.2022.103591.
Bin Sun, Xiaojiang Liu, Zhao-Dong Xu, Dajun Xu, BP neural network-based adaptive spatial-temporal data generation technology for predicting ceiling temperature in tunnel fire and full-scale experimental verification, Fire Safety Journal, Volume 130, 2022, 103577, ISSN 0379-7112, https://doi.org/10.1016/j.firesaf.2022.103577.
Su, Lingchu & Xiqiang, Wu & Zhang, Xiaoning & Huang, Xinyan. (2021). Smart Performance-Based Design for Building Fire Safety: Prediction of Smoke Motion via AI. Journal of Building Engineering. 43. 10.1016/j.jobe.2021.102529.