P-Flash - A Machine Learning-based Model for Flashover Prediction using Recovered Temperature Data.

Research was conducted to examine the use of Support Vector Regression (SVR) to build a model to forecast the potential occurrence of flashover in a single-floor, multi-room compartment fire. Synthetic temperature data for heat detectors in different rooms were generated, 1000 simulation cases are considered, and a total of 8 million data points are utilized for model development. An operating temperature limitation is placed on heat detectors where they fail at a fixed exposure temperature of 150 °C and no longer provide data to more closely follow actual performance. The forecast model P-Flash (Prediction model for Flashover occurrence) is developed to use an array of heat detector temperature data, including in adjacent spaces, to recover temperature data from the room of fire origin and predict potential for flashover. Two special treatments, sequence segmentation and learning from fitting, are proposed to overcome the temperature limitation of heat detectors in real-life fire scenarios and to enhance prediction capabilities to determine if the flashover condition is met even with situations where there is no temperature data from all detectors. Experimental evaluation shows that P-Flash offers reliable prediction. The model performance is approximately 83 % and 81 %, respectively, for current and future flashover occurrence, considering heat detector failure at 150 °C. Results demonstrate that P-Flash, a new data-driven model, has potential to provide fire fighters real-time, trustworthy, and actionable information to enhance situational awareness, operational effectiveness, and safety for firefighting.

Generating Synthetic Sensor Data to Facilitate Machine Learning Paradigm for Prediction of Building Fire Hazard.

Using the zone fire model CFAST as the simulation engine, time series data for building sensors, such as heat detectors, smoke detectors, and other targets at any arbitrary locations in multi-room compartments with different geometric configurations, can be obtained. An automated process for creating inputs files and summarizing model results, CData, is being developed as a companion to CFAST. An example case is presented to demonstrate the use of CData where synthetic data is generated for a wide range of fire scenarios. Three machine learning algorithms: support vector machine (SVM), decision tree (DT), and random forest (RF), are used to develop classification models that can predict the location of a fire based on temperature data within a compartment. Results show that DT and RF have excellent performance on the prediction of fire location and achieve model accuracy in between 93 % and 96 %. For SVM, model performance is sensitive to the size of training data. Additional study shows that results obtained from DT and RT can be used to examine the importance of each input feature. This paper contributes a learning-by-synthesis approach to facilitate the utilization of a machine learning paradigm to enhance situational awareness for fire fighting in buildings.

Risk perception in fire evacuation behavior revisited: definitions, related concepts, and empirical evidence.

Risk perception (RP) is studied in many research disciplines (e.g., safety engineering, psychology, and sociology). Definitions of RP can be broadly divided into expectancy-value and risk-as-feeling approaches. In the present review, RP is seen as the personalization of the risk related to a current event, such as an ongoing fire emergency; it is influenced by emotions and prone to cognitive biases. We differentiate RP from other related concepts (e.g., situation awareness) and introduce theoretical frameworks relevant to RP in fire evacuation (e.g., Protective Action Decision Model and Heuristic-Systematic approaches). Furthermore, we review studies on RP during evacuation with a focus on the World Trade Center evacuation on September 11, 2001 and present factors modulating RP as well as the relation between perceived risk and protective actions. We summarize the factors that influence perception risk and discuss the direction of these relationships (i.e., positive or negative influence, or inconsequential) and conclude with presenting limitations of this review and an outlook on future research.