Development of Consequent Models for Three Categories of Fire through Artificial Neural Networks

Abstract

This paper demonstrates the successful implementation of an artificial neural network to accurately predict the designated thermal radiation distance for jet fire, early pool fire, and late pool fire hazard consequence analysis. Specifically, integrated feedforward neural network models employing the backpropagation Levenberg–Marquardt algorithm were trained using data sets obtained through separate PHAST software simulations of 450 leak scenarios of 35 common flammable chemicals. For each fire model (jet, early, late pool), there are 11 input parameters spanning both chemical parameters and release conditions. Simulation data was randomly divided into 70% training, 15% validation, and 15% test sets to conduct cross-validation and provide an independent measure of predictive accuracy for the neural network models. Statistical values, namely, coefficient of determination (R 2) and mean-square error (MSE), are calculated to evaluate model regression performance. All three neural network predictive models achieved considerably accurate predictions of the logarithm format of the designated radiation effect distance. The models give an overall R 2 of 0.9930 and an MSE of 0.0022 for jet fire, an overall R 2 of 0.9909 and an MSE of 0.0016 for early pool fire, and an overall R 2 of 0.9899 and an MSE of 0.0015 for late pool fire.

Analysis of deep learning neural network combined with experiments to develop predictive models for a propane vertical jet fire

“…Shultz and Fischbeck (1999) prepared the risk assessment of accidents, occurred in offshore platforms during 1986 and 1995, using ANN models. Sun et al (2019) developed an ANN approach to accurate predict the thermal radiation consequences of jet fire and pool fire scenarios occurred in process industries. Lattimer et al (2020) Table 1.…”

“…The experimental models need open field and/or laboratories with instrumental facilities, and the CFD studies require the processor system and computational time, depending on the size of the analyzed physical geometry. Machine learning has been shown to be one promising tool to develop a predictive approach ( Franke et al., 2017 ; Sun et al., 2019 ; Lattimer et al., 2020 ). Machine learning can be used to predict jet flame's shape and behavior.…”

“…(2020b) 12.75 Propane and hydrogen Vertical Jet flame length and radiation simulated by a CFD approach. Sun et al. (2019) - 35 flammable chemicals - Jet flame radiation distance predicted by an ANN approach.…”

Intelligent voltage regulator for distributed generation-based network

“…Consequently, to offer a proper voltage regulation in the DN, we employ an ANN technique. An ANN is a biologically motivated computational related model [23]. It comprises neurons that are processing elements.…”

“…Also, the input as well as output 104 layer dimensions are alike to the input and target parameter numbers. On the other hand, dimensions of the hidden layer are adapted manually with respect to the model performance [23]. The network model weights and associated biases are initialized by means of the MATLAB ® Neural Network Toolbox.…”