Machine learning methods can establish complex nonlinear relationships between input and response variables for stadium fire risk assessment. However, the output of machine learning models is considered very difficult due to their complex “black box” structure, which hinders their application in stadium fire risk assessment. The SHapley Additive exPlanations (SHAP) method makes a local approximation to the predictions of any regression or classification model so as to be faithful and interpretable, and assigns significant values (SHAP value) to each input variable for a given prediction. In this study, we designed an indicator attribute threshold interval to classify and quantify different fire risk category data, and then used a random forest model combined with SHAP strategy in order to establish a stadium fire risk assessment model. The main objective is to analyze the impact analysis of each risk characteristic on four different risk assessment models, so as to find the complex nonlinear relationship between risk characteristics and stadium fire risk. This helps managers to be able to make appropriate fire safety management and smart decisions before an incident occurs and in a targeted manner to reduce the incidence of fires. The experimental results show that the established interpretable random forest model provides 83% accuracy, 86% precision, and 85% recall for the stadium fire risk test dataset. The study also shows that the low level of data makes it difficult to identify the range of decision boundaries for Critical mode and Hazardous mode.

In England, there are no fixed requirements on the parameters adopted when considering residential design fires, and analyses undertaken are often deterministic with limited consideration given to probabilistic assessments and the sensitivity of parameters. The Home Office dwelling fires dataset has been analysed, considering the fire damage area and the time from ignition to fire and rescue service arrival. From this, lognormal distributions for the maximum heat release rate (HRR) and fire growth rate of residential fires have been approximated. The mean maximum HRR ranges from 900 kW to 1900 kW, with a standard deviation ranging from 2000 kW to 3700 kW, depending on property type and room of fire origin. The mean growth rate, assuming a t² relationship, ranges from 0.0022 kW/s² to 0.0034 kW/s², with a standard deviation ranging from 0.0071 kW/s² to 0.0132 kW/s². When considering incidents which result in immediate fire and rescue service call out following ignition, the mean growth rate increases to a range of 0.0058 kW/s² to 0.0088 kW/s². As a result of the analyses, design fire distributions are provided which can be adopted for probabilistic assessments. For deterministic analyses, it is proposed that an approximate 95th percentile fire may be adopted, aligning with a medium growth rate of 0.0117 kW/s² and a maximum fuel-limited HRR in the region of 3800 kW to 4400 kW, depending on whether the dwelling is a house or an apartment. A 95th percentile design fire broadly aligns with values already specified in guidance, helping to substantiate the existing recommendations.

9,10‐Dihydro‐9‐oxa‐10‐phosphaphenanthrene‐10‐oxide (DOPO) and its derivatives have been widely used as effective flame retardants. In this study, 6‐((bis(2‐hydroxyethyl) amino) methyl)‐6H‐dibe‐nzo[c,e][1,2]oxaphosphinine‐6‐oxide (DHDOPO) was synthesized from DOPO, paraformaldehyde, and diethanolamine, and subsequently used as a reactant for synthesis of flame retarded alkyd resin (FR‐ALK). Thermogravimetric analysis (TGA) showed that DHDOPO had relatively high thermal stability and would not decompose at synthesis temperature of ALK. The thermal stability and flame retardancy of ALKs were improved by introduction of DHDOPO. As the mass fraction of phosphorus in FR‐ALK increased the decomposition temperature, the char yield in TGA experiments, the fire residue, and time to ignition in cone calorimeter tests increased, and peak heat release rate (PHRR) and total heat release (THR) decreased. Compared with the non‐flame retarded ALK the PHRR and THR values of FR‐ALK containing 2.5 wt % phosphorus decreased, respectively, by 43.1% and 58.5%. © 2017 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2018, 135, 45643.