Introduction. Lead dust/air mixture has an ignition temperature of 710 °C and an estimated maximum explosion pressure of 400 kPa. At the same time, the lead dust/air mixture does not explode in a 20-litre chamber with
an ignition source having energy of 2.5 kJ. These circumstances make it difficult to answer the question about the explosiveness of lead dust under normal handling conditions. In this paper, arguments in favour of explosion safety of this dust at a temperature of 25 °C are obtained.

Lead dust and method of its study. Lead concentrate dust (d50 = 8.5 microns, d90 = 36.6 microns) with lead content of at least 99 % (wt.) was studied in a 20-liter Sivek explosion chamber with an ignition source of increased energy (10 kJ).

Results. The explosion hazard of lead dust was manifested in the range of dust concentrations from the lower limit (500 g/m3) to the upper limit (1,500 g/m3). In the whole specified range, the occurrence of lead dust explosion from experiment to experiment was random. The maximum explosion pressure was 150 kPa, the explosion index Kst was 2 bar ∙ m/s. The explosion pressure dependence on time P(t) had two inflection points, in the first of which the minimum dP/dt was reached, and in the second point the maximum dP/dt was reached.

Discussion and conclusions. The results of the study of lead dust have features characteristic of a dispersed material that is explosion-proof under normal handling conditions: Kst < 45 bar ∙ m/s (Proust, Accorsi, Dupont, 2007); the random nature of the explosion in a wide range of dust concentrations and the two-stage explosion (Poletaev, Sazonov, Koptev, 2024). Thus, it is most likely that the investigated lead dust is explosion-proof. The cases of its explosion are due to the “overdrive” effect — airborne dust preheating in experiments using an energy-intensive ignition source.

Introduction. When solving the problem of ensuring fire safety at large industrial facilities, it is important to ensure the highest speed of response to emerging threats. This paper discusses a new method of detecting and determining the exact location of the fire centre in real time, based on modern methods of image processing and artificial intelligence.

Aims and Objectives. The aim of the work is to create a system capable of detecting fire in a panoramic image and, based on a 3D model, determining the coordinates of the detected threat.

Objectives of the work:

• CNN training and its adaptation to work in a panoramic image;
• development of an algorithm for determining the spatial coordinates of an object found in the image.

Methods. The paper describes the scheme of the proposed system. Methods for detecting fires in the image are discussed. The choice of the approach using a convolutional neural network is justified. The application of a neural network in a panoramic image is considered and an approach to straightening distortions in the image is described in order to improve the accuracy of the network. A method for combining a 3D model with a panoramic image and determining the spatial coordinates of found fires is described.

Results and Discussion. The work shows the results of the system in a virtual environment where fires were generated. The environment emulates all key components of the system, such as a panoramic camera and a 3D model of the object. In the experiments carried out, the error in determining the coordinates of the fire was about 20 cm.

Conclusions. The work examined a new approach to detecting fires using computer vision. A neural network of the YOLOv5 architecture was trained, which is capable of recognizing fire and smoke. To reduce distortion, stereographic projection was used. A method was developed and applied to determine the coordinates of fire in space by combining a 3D model and a panoramic image.

Introduction. Justification of safety of operation of an underground research laboratory for the final isolation of radioactive waste requires, among other things, an assessment of the fire resistance of the rock in which it is constructed. In this case, the choice of the main parameters of the corresponding fire tests is determined by the temperature regime, as well as the duration of heating of the rock during the fire. One of the effective ways to assess these factors, in conditions where there is no possibility of conducting a full-scale experiment or creating a full-scale physical model of the designed object, is computer modelling of fire dynamics.

Aims and objectives. The aim of the work is to assess the temperature regime of the fire in an underground research laboratory, taking into account the influence of geometric parameters and the depth of horizontal mine opening, the characteristics of the ventilation system used, the combustible load, and the thermophysical properties of the minerals enclosing the free space.

Methods. To simulate fire dynamics, the work uses the FDS software platform, designed to carry out the corresponding calculations. The study of the influence of various factors on the results is carried out by modifying the basic model, the rationale and main tuning parameters of which are presented in the corresponding section.

Results and discussion. Based on a series of computer experiments with various tuning parameters of the model, it was found that the calculation results are significantly influenced by: the depth of the horizontal excavation, the energy consumption for heating the rock, the parameters of the ventilation system used, and also, in some cases, the dimensions of the calculation grid cell.

Conclusions. Based on the analysis of the modelling results, a number of features of the research object were identified that should be taken into account when conducting appropriate computer experiments and full-scale tests. The developed computer model can be used to assess the effectiveness of fire protection systems at the facility and study the heating of enclosures under various fire scenarios. The parameters of the temperature regime during the fire obtained from the modelling results can be used to conduct fire tests of rock samples that make up the enclosures of the underground complex structures.

Introduction. Russian standards provide deterministic indicators of the required fire resistance of load-bearing structures of industrial facilities. Changes in CP 4.13130 are based on the American standard API 2218, where a probabilistic approach is assumed for determining fire exposure zones and required fire resistance limits. However, this approach is not used at oil industry facilities due to the lack of a methodology for determining the impact zones for hydrocarbon combustion.

Aims and objectives. The aim of this study is to determine the actual fire resistance limits of steel overpasses executing indicated scenarios in order to obtain the dependence of fire resistance of structures on the distance to the source of fire. Objectives of the study also include developing field fire models according to the design documentation; determination of the zones exposed to critical temperature; identifying the fire resistance of structures under different fire regimes.

Methods. The initial data was the design documentation of three oil fields with cluster arrangement of wells. The most dangerous and probable oil or gas spill fire scenarios were modelled for each field. Models of raised oil and gas pipelines were developed using Revit software. Fire hazard spreading was modelled by the method of field fire simulation using PyroSim.

Results. The study found actual fire resistance limits of pipelines of three fields, along with the sizes of fire impact zones, where fire protection of structures is required. Fire protection to ensure fire resistance R60 is required at less than 10.7 m at a source of fire of 305.24 MW; at 38.6 MW the critical temperature is reached in the radius of as low as 3 m.

Conclusions. In a “real” fire regime, structures may have higher fire resistance limits than required in the regulations. Modelling and calculation of fire resistance allows to determine the need for fire protection for each zone of fire exposure, not only within a radius of up to 12 meters. Scientific research in this area will make it possible to develop new normative documents for determining the fire exposure zones and fire resistance limits of exterior structures.

Introduction. Fires at disposal and accumulation sites of municipal solid waste (MSW) during their disposal and transportation occur with sufficient regularity. At present, they are practically not predicted. Their detection in many cases occurs when the burning has spread over significant areas.

Aims and objectives. The aim of the work is to develop a system of monitoring and forecasting of conditions of places of disposal and accumulation of MSW that enables to detect burning areas, to forecast the dynamics of changes in key parameters and to assess fire danger of the objects in question.

Materials and methods. A comparative analysis of monitoring systems for places of disposal and accumulation of MSW was made. It is proved that forecasting methods based on artificial neural networks and machine learning are the most promising for preventing fire-hazardous situations at the examined objects. The stages of the working process in the implementation of machine learning technology are defined.

Results. A system of indicators for assessing the fire hazardous conditions of waste disposal and accumulation sites is developed. A model allowing to forecast the dynamics of change of key parameters and to give an assessment of fire hazard of waste disposal and accumulation sites taking into account the chosen planning horizon on the basis of the data received from sensors is created. The requirements for the model, the tasks to be performed were determined, data gathering and cleaning, labelling, design of attributes were performed. The model was trained and evaluated. A method of anomaly detection based on teacherless learning was justified.

A model was developed that allows detecting combustion spots, including hidden ones, with indication of their location and boundaries, based on the data received from sensors. Characteristics of the main scenarios determining the structure and use of the Smart Site service are presented. Its architecture is described. Benefits of its usage are proved. The developed models are tested.

Conclusion. The application of the “Smart Polygon” service will enable visualization of information about the state of waste disposal sites and forecasting results; generate a report for the polygon for a selected period; provide timely notification and transfer necessary information about the possibility or occurrence of fires; select the best solutions aimed at minimizing fire risk and monitor their effectiveness.

The results of the study will be included as a module in an integrated platform for risk-oriented forecasting, reduction of environmental and fire hazard of disposal sites and accumulation of solid waste.

Introduction. This paper examines the tactical and technical characteristics of various breathing apparatuses in service with the gas and smoke protection service in the fire protection units of the Russian Federation — compressed air breathing apparatus, compressed oxygen breathing apparatus, and also substantiates the need for the development of domestic breathing apparatuses on chemically bound oxygen. The relevance of this paper is the lack of modern domestic breathing apparatus with a long period of protective action for effective fire extinguishing.

Aims and Objectives. The aim of this paper is to improve the equipment of the gas and smoke protection service of fire protection units with the most effective and suitable breathing apparatus for extinguishing fires at metro stations, harbour yards and ships, underground car parks and high-rise buildings.

Materials and methods. An analytical approach is used to consider personal respiratory protection equipment, which are in service in all types of fire protection in our country, the characteristics of various types of chemically bonded oxygen breathing apparatus are analyzed in detail and their comparative analysis is carried out.

Results and their discussion. As a result of the study, recommendations were made to improve the equipment of fire departments with breathing apparatus. The authors gave recommendations for some changes in the re­gulatory legal acts of the Russian Federation.

Conclusions. A reasonable conclusion was obtained about the effectiveness and necessity of introducing breathing apparatus based on chemically bound oxygen and supplementing them with gas and smoke protection service of fire and rescue units. Also, in the absence of breathing apparatus of this type at the moment, the authors of the paper presented proposals that should be taken as a basis for the production of completely new breathing apparatus and sets of front parts with adapters for attachment to a fire helmet, as well as proposals for amendments to the regulatory legal documents of the Russian Federation and the necessary abbreviation for their designation are given.

Introduction. Forecasting the number of involved forces for elimination and localization of forest fires is an important and urgent task that affects the efficiency of the work carried out. However, the use of traditional methods of statistical forecasting does not allow to obtain a reliable assessment of the target indicator, due to the lack of a number of features in the analysis, the consequence of which is a decrease in the effectiveness of decisions.

Objective. Investigation of the possibility of applying the logistic regression model to make decisions on the number of forces to be used for localization and suppression of forest fires at the initial stage of the fire.

Research methods. The application of the logistic regression method was evaluated on the basis of a database of forest fires in the territory of the Leningrad region in the period from 2015 to 2023, in which 16 features were identified. The logistic regression model allows training on data with different types of distribution, including binomial, Poisson, Bernoulli and other types of distribution. The mathematical apparatus used in the model allows us to estimate the posterior probabilities for assigning training objects to the appropriate classes.

Results. The results of the model training evaluation in the form of error matrices and classification reports are presented as results, and visualization of the decision boundaries for the cases of using two and three features is performed. The results show that the best accuracy was achieved using all available features.

Conclusion. The research of forest fires data in the Leningrad region has shown that there are factors that are not taken into account when making plans for the involvement of forces and resources. The use of machine learning models and, in particular, logistic regression, proposed in this study, can improve the validity and efficiency of decisions to determine the number of forces to be involved in forest fires.

Introduction. One of the main problems of the fire safety system of energy facilities is the prevention of combustible gas fires. An analysis of existing fire prevention systems showed low efficiency of their operation. In order to prevent combustible gas fires, the use of an aqueous medium in a metastable phase state is proposed in this work.

Purpose. Investigation of the characteristics of an aqueous medium in a metastable phase state to prevent combustible gas fires in closed volumes.

Objectives. An analysis of existing means of the gas fire prevention system. The calculations substantiate the possibility of using an aqueous medium in a metastable phase state to prevent fires of flammable gases in closed volumes. Modelling the process of phlegmatization of methane in a closed volume by an aqueous medium in a metastable phase state and determining the optimal parameters of its supply.

Materials and methods. The determination of the need to use a new means of preventing gas fires at energy facilities was justified using the method of analysis and synthesis. To substantiate the possibility of preventing methane fires in a closed volume, mathematical modelling based on the Pyrosim hardware and software complex was applied.

Theoretical bases. To calculate the minimum phlegmatizing concentration, Hess’s law and the theory of branched-chain combustion processes were applied.

Results and discussions. Based on the calculations performed, the number of technical means of supply for different degrees of room leakage was established. The required number of barrels depends linearly on the volume of the room. It is worth noting that when a certain leakage coefficient is reached, which will correspond to the supply of an aqueous medium in a metastable phase state to an open space, the number of barrels will take the maximum value for a given volume. Mathematical modelling has established that it is advisable to install devices for feeding an aqueous medium in a metastable phase state on the side surfaces, and the achievement of phlegmatizing concentrations occurs within 10 seconds from the moment of feeding.

Conclusions. The analysis method has established that the existing fire prevention systems are not effective enough, since in some cases they can cause a fire. A method for preventing fires of combustible gases by aqueous medium in a metastable phase state in closed volumes at energy facilities is proposed and theoretically substantiated. The calculation of the required number of technical means of supplying an aqueous medium in a metastable phase state, depending on the volume of the room and the leak coefficient, is performed. The use of the Pyrosim software and hardware complex confirmed the correctness of the calculations performed and allowed to establish the optimal method of supplying an aqueous medium in a metastable phase state to the volume of the engine room of the thermal power plant.

Statistical data on fires caused by electrical equipment are presented. The current requirements of regulatory documents on cleaning and methods of protecting electrical installations from the negative effects of dust and other contaminants are considered. Explanations on the frequency of maintenance of electrical equipment according to Russian and foreign standards are given. The possibility of using more flexible organizational and technical solutions for scheduling preventive maintenance is shown. The importance of regular inspections and maintenance of electrical equipment for increasing the efficiency of the fire prevention system is noted.