Search

Aim: This article focuses on the use of artificial neural networks to mathematically describe the parameters that determine the size of a jet fire flame. To teach the neural network, the results of a horizontal propane jet fire, carried out experimentally and using CFD mathematical modelling, were used. Project and methods: The main part of the work consisted of developing an artificial neural network to describe the flame length and propane-air mixing path lengths with good accuracy, depending on the relevant process parameters. Two types of data series were used to meet the stated objective. The first series of data came from field tests carried out by CNBOP-PIB and from research contained in scientific articles. The second type of data was provided by numerical calculations made by the authors. The methods of computational fluid mechanics were used to develop the numerical simulations. The ANSYS Fluent package was used for this purpose. Matlab 2022a was used to develop the artificial neural network and to verify it. Results: Using the nftool function included in Matlab 2022a, an artificial neural network was developed to determine the flame length Lflame and the length of the Slift-off mixing path as a function of the diameter of the dnozzle and the mass flux of gas leaving the nozzle. Using Pearson’s correlation coefficient, a selection was made of the best number of neurons in the hidden layer to describe the process parameters. The neural network developed allows Lflame and Slift-off values to be calculated with good accuracy. Conclusions: Artificial neural networks allow a function to be developed to describe the parameters that determine flame sizes in relation to process parameters. For this purpose, the results of the CFD simulations and the results of the jet fire experiments were combined to create a single neural network. The result is a ready-made function that can be used in programmes for the rapid determination of flame sizes. Such a function can support the process of creating scenarios in the event of an emergency. A correctly developed neural network provides opportunities for the mathematical description of jet fires wherever experimental measurements are not possible. Solution proposed by the authors does not require a large investment in ongoing calculations, as the network can be implemented in any programming language. Keywords: computational fluid mechanics, artificial neural networks, jet fire

Aim: The aim of this article is to determine the characteristics of a pool fire, including the temperatures and thermal radiation densities caused by it. Mappings of pool fires occurring in actual emergency events were conducted by performing large-scale polygon tests. Project and methods: Experimental study of pool fire of technical ethanol was carried out on a specially built test stand in the training area of the Training Centre in Pionki of the Regional Headquarters of the State Fire Service in Warsaw. The pool fire test stand consisted of a test tray, with a test chamber with the diameter of 300 cm, founded on a reinforced concrete slab. Using a developed measurement system with data acquisition that included measurement sensors mounted at defined locations relative to the fire, temperatures and thermal radiation densities were measured at various distances/locations relative to the fire. Metrological data such as air temperature, atmospheric pressure, humidity, wind direction and speed were monitored and recorded using the weather station. The height of the fire flame was measured by comparing it to racks set up nearby with marked scales of specific lengths. Results: A polygon stand that was built to study pool fires, equipped with a temperature and thermal radiation density measuring system with measuring sensors distributed in defined locations, is discussed. A study of a pool fire resulting from the combustion of dehydrated, fully contaminated ethanol was conducted. The study measured emperatures, thermal radiation densities, and flame heights. The average and maximum values of temperatures and thermal radiation densities during the steady-state combustion stage (i.e., phase II of the fire) were determined. Conclusions: Based on the presented results of temperature and thermal radiation density measurements at various distances/locations relative to the pool fire site, there was a significant effect of wind direction and speed on these values. Higher temperature and heat radiation density were recorded at the sensors on the leeward side than on the windward side. As the wind speed decreased, there was an increase in the temperature values recorded on the thermocouples located above the centre of the bottom of the tray test chamber due to the flame, which, when not blown away, was allowed to rise vertically upward and fully sweep the temperature sensors.