Fire Resistance Rating Research Articles

Cost-oriented fire safety design of urban structures

Providing adequate fire safety for urban buildings is a life-saving goal, and can be addressed in different ways. Reported studies integrating fire safety and life cycle cost (LCC) of conventional urban structures are rare. To address this gap, a cost–performance framework was developed. Four- and seven-storey steel (with and without fireproofing coatings) and reinforced concrete (RC) structures were designed, first for conventional loads and then fireproofed to meet their required fire-resistance rating. A range of sprinkler spacings, from 3200 mm (based on NFPA 13) to 12 000 mm, was configured. Fire was simulated using a fire dynamic simulation tool and the results were used to monitor evacuation plans and structural responses. The steel structures were additionally analysed under the assumption that they were not fireproofed. Human and financial damage costs were then estimated and the LCC for every case/scenario was determined. Interestingly, the results showed that the optimum LCC was not achieved for cases designed based on NFPA 13; instead, a sprinkler spacing of 6000 mm led to the optimum LCC. It was also found that steel structures without fireproofing do not have a higher LCC if the sprinklers are placed over a shorter distance. This result could be particularly beneficial for existing structures that are not fireproofed.

Impact of waste rockwool on the performance of LC3-based lightweight mortar: A promising solution for greener construction

The objective of this study is to explore the influence of waste rockwool (RW) on the mechanical strength and fire resistance performance of high-volume expanded vermiculite (EVM) lightweight mortar made with limestone-calcined clay cement (LC3). LC3 binder was prepared by blending ordinary Portland cement (OPC), metakaolin (MK), and limestone (LS) powder at weight percentages of 40, 40, and 20 wt%, respectively. LC3-based lightweight mortar with a binder-to-aggregate ratio of 1:3 was prepared by replacing 50 vol% of the sand with EVM aggregate. The waste RW was added to the EVM-blended LC3 mortar with different percentages of 1, 3, and 5 % by weight of binder. The compressive strength, flexural strength, drying shrinkage, bulk density, thermal conductivity, fire resistance, and microstructural properties of the hardened LC3-lightweight mortars were determined in accordance with ASTM standards after 28 days of water curing. The results revealed remarkable enhancements in both mechanical and fire resistance performances with RW addition. The addition of 3 wt% RW into the EVM-blended LC3 mortar provided the appropriate enhancement ratios of 56.55 % and 52.83 % in compressive and flexural strengths respectively and increased the fire resistance rating by 25 %. A residual compressive strength of 76.19 % has been maintained after exposure to standard fire for an hour (1 h). The doping of RW into the EVM-blended LC3 mortars led to significant reduction in drying shrinkage rate. A slight, insignificant variation in the thermal conductivity of EVM-blended LC3 lightweight mortar incorporated with RW has been obtained. RW addition resulted in improved microstructure in terms of compactness.

Performance-based fire protection of clustered individual members within a steel frame structure

Fire resistance rating (FRR) in the existing codes and literature sets an overall criterion for buildings by different fire resistance levels with undifferentiated fire protection. However, the performance diversity of individual members within a building is not considered. Therefore, a performance-based fire protection method for clustered individual members within a steel frame structure is established. First, parametric models of a steel frame structure exposed to two typical fires are built for data acquisition. Three features considering the mechanical properties of steel members and their impact on the entire structure are selected. Then, K-means clustering is adopted for the classification and ranking of individual members to assign fire resistance ratings and conduct clustered fire protection design. A comparison between the undifferentiated fire protection strategy and the clustered fire protection strategy is conducted. The quantitative evaluation results indicate the feasibility of the proposed method for clustered fire protection design, with the consideration of the performance diversity of individual members within the steel structure.

Numerical analysis of fire-exposed reinforced concrete sections for assessing post-heating axial and flexural capacity

PurposeThis study investigates the impact of the fire decay phase on structural damage using the sectional analysis method. The primary objective of this work is to forecast the non-dimensional capacity parameters for the axial and flexural load-carrying capacity of reinforced concrete (RC) sections for heating and the subsequent post-heating phase (decay phase) of the fire.Design/methodology/approachThe sectional analysis method is used to determine the moment and axial capacities. The findings of sectional analysis and heat transfer for the heating stage are initially validated, and the analysis subsequently proceeds to determine the load capacity during the fire’s heating and decay phases by appropriately incorporating non-dimensional sectional and material parameters. The numerical analysis includes four fire curves with different cooling rates and steel percentages.FindingsThe study’s findings indicate that the rate at which the cooling process occurs after undergoing heating substantially impacts the axial and flexural capacity. The maximum degradation in axial and flexural capacity occurred in the range of 15–20% for cooling rates of 3 °C/min and 5 °C/min as compared to the capacity obtained at 120 min of heating for all steel percentages. As the fire cooling rate reduced to 1 °C/min, the highest deterioration in axial and flexural capacity reached 48–50% and 42–46%, respectively, in the post-heating stage.Research limitations/implicationsThe established non-dimensional parameters for axial and flexural capacity are limited to the analysed section in the study owing to the thermal profile, however, this can be modified depending on the section geometry and fire scenario.Practical implicationsThe study primarily focusses on the degradation of axial and flexural capacity at various time intervals during the entire fire exposure, including heating and cooling. The findings obtained showed that following the completion of the fire’s heating phase, the structural capacity continued to decrease over the subsequent post-heating period. It is recommended that structural members' fire resistance designs encompass both the heating and cooling phases of a fire. Since the capacity degradation varies with fire duration, the conventional method is inadequate to design the load capacity for appropriate fire safety. Therefore, it is essential to adopt a performance-based approach while designing structural elements' capacity for the desired fire resistance rating. The proposed technique of using non-dimensional parameters will effectively support predicting the load capacity for required fire resistance.Originality/valueThe fire-resistant requirements for reinforced concrete structures are generally established based on standard fire exposure conditions, which account for the fire growth phase. However, it is important to note that concrete structures can experience internal damage over time during the decay phase of fires, which can be quantitatively determined using the proposed non-dimensional parameter approach.

Fire resistance of axially loaded semi-precast composite columns

Recently, semi-precast composite (SPC) columns have been newly developed using steel angles and internal molds. Although the manufacturability, constructability, and seismic performance of SPC columns have been proven to meet design requirements, their structural responses under fire conditions (or fire resistance) have not yet been reasonably examined. Thus, in the present study, an experimental study was conducted for five full-scale SPC columns under standard fire conditions. The test parameters included the joint detail, axial load ratio, thickness of the precast section, and slenderness ratio. The test results show that the fire resistance rating was relatively low due to the high moisture contents and relatively high axial load ratio, and concrete spalling controlled the fire resistance of the columns. The concrete spalling was affected by the concrete moisture contents and permeability, the consequent moisture clog phenomenon, the relatively high axial load ratio, and the longitudinal weak planes between the concrete cover and confined concrete created by longitudinal and transverse bars. Addressing these effects, a finite element analysis (FEA) model was developed for SPC columns using ABAQUS. Although there were some discrepancies between the test and analysis results, the FEA model gave a conservative prediction, which is reasonable for design purpose considering the complexity of nonlinear thermal-stress analysis.

Solving Separation Distances from Flammable Surfaces of Exterior Walls by Central-European Standards

The paper deals with the topic of determining the density of heat flow from combustible surface treatments of exterior walls, such as combustible insulation systems, combustible cladding of facades and from all-wood constructions of exterior walls. Heat flow density is an important indicator in determining the fire resistance rating of exterior walls and in determining safe separation distances. The article describes the ways in which exterior walls can be classified in terms of fire resistance. One of these methods is a numerical calculation (of the surface amount of released heat and heat flow density), which will be applied to various types of combustible surfaces of the perimeter walls of wooden buildings. The results showed that the numerical calculation is a suitable method for determining the classification of fire resistance rating of exterior walls with combustible coating. The Czech legislation defines the criteria for this classification better.

Fire Resistance of Fire-Protected Reinforced Concrete Beams Strengthened with Externally Bonded Reinforcement Carbon Fibre-Reinforced Polymers at the Full Utilisation Degree.

The fire resistance of reinforced concrete (RC) beams strengthened with externally bonded reinforcement carbon fibre-reinforced polymers (EBR CFRP) depends on the load level and degree of strengthening. Design guides for this type of structure recommend strengthening limits to prevent collapse of the structure due to vandalism, damage or fire. In practice, however, it is not uncommon to exceed the proposed limits. This necessitates protection of the CFRP adhesive against high temperatures, namely glass transition temperature levels. This paper presents the results of 10 full-scale experimental fire resistance tests of reinforced concrete beams with EBR CFRP strengthening, with and without fire protection and under various load levels including full utilisation. It was demonstrated that in cases where CFRP strengthening was not needed to carry load in an accidental fire scenario, test specimens with and without it achieved the same fire resistance. It was also proven that in cases where CFRP failure influenced the failure of the entire beam, fire protection was crucial for maintaining the beam's load-bearing capacity and its thickness had to be substantial. A fire resistance rating of over 4 h was achieved, nevertheless.

Numerical analysis of the effects of fire with cooling phase on reinforced concrete members

Fire exposed structures may collapse during or after the fire decay phase, with risks for building occupants and firefighters; yet, understanding of the effects of the fire decay phase on structural loadbearing capacity remains limited. This paper describes a numerical investigation on the behavior of reinforced concrete columns, beams, and walls under natural fires including cooling down phases. Finite element models are benchmarked against experiments capturing the behavior during heating. The models are then used to simulate the structural response of the concrete members under fires with various cooling rates and load ratios. The analyses capture the irreversibility of material properties through tracing of the temperature history in the structure. The results show that temperatures and deformations continue increasing after the end of the fire heating phase. As a result, concrete columns, beams, and walls may fail during the cooling phase. Faster cooling rates reduce the likelihood of failure in cooling. For beams, failure can be inferred from the maximum reinforcement temperature reached throughout the fire, but for columns and walls a thermal–mechanical analysis of the member throughout the fire history is needed. A relationship is proposed to evaluate the burnout resistance from the fire resistance rating and cooling rate. The presented numerical method allows assessing the structural stability throughout a fire event, an important requirement for designing a fire resilient built environment.

Aluminium Bridges under Fire Conditions: Structural Behaviour

Due to a number of advantages, aluminium is used in the attachment units of mullion and transom systems for decorative panels and translucent fillings, as well as for bridge structures. Despite its advantages, aluminium has a low melting point and does not have fire resistance performances required by regulatory documents under fire conditions. Therefore, this article is aimed at studying the behaviour of aluminium structures under high temperatures. To achieve this objective, we have analysed the aluminium structures most commonly used in construction—the attachment units of mullion and transom systems, with different protections against fire, columns and orthotropic decks used in bridge construction. In order to assess the behaviour of selected structures under fire conditions, we have developed methods for studying temperature distributions in structures in detail. Using the developed methods, tests have been carried out. Based on the received experimental data, we analysed the behaviour of aluminium structures in fire conditions and developed measures to increase the fire resistance of aluminium structures. Such measures include using hollow profiles to ensure air exchange with the cold sections of the structure, applying dedicated cooling agents to cool the structure and removing heat to the atmosphere and thermal barriers so as to protect aluminium structures. We found that fire resistance measures enhance the fire resistance of aluminium attachment units of mullion and transom systems by 1.5 times. The use of hollow air-permeable profiles and cooling agents in orthotropic decks increases fire resistance by 3 times by removing heat from the structures. The fire resistance rating of hollow profile aluminium columns is 1.5 times higher than that of structures without air-permeable profiles. The obtained results can be used as the most effective basis for the design of aluminium structures. The principles of increasing fire resistance given in this article are applicable to other types of structures, and can also be used with other methods of fire protection. Increasing the fire resistance of aluminium structures enables the expansion of the scope of their applications.

Behavior of a Composite Steel Decking and Boarding System in Fire Based on Large-Scale Experimental Testing and Numerical Modelling

This paper presents experimental and numerical results of an investigation into the thermal and structural behaviour of an innovative modular structural steel system, which includes cellular beams, that was tested in a 1-h standard fire scenario while loaded. The modular system consists of a 5.66 × 3.8 m rectangular steel frame, with a profiled steel sandwich decking (SD) system attached, which comprises of (a) profiled steel decking, (b) fibre cement, and (c) calcium silicate boards and strips. The SD system is suspended from the underside of the horizontal structural members to provide inherent fire protection to the steel beams from the bottom and acts as the load-bearing component of the flooring. The purpose of the experiment was to determine the fire resistance of the structural system, whilst under load, which is primarily based on the fire resistance of the SD system. Temperature data for the SD system was collected during the experiment and used to validate a numerical finite element analysis model. This study shows that the SD system was able to achieve a fire resistance rating of 57 min in the experiment which was governed by insulation resistance. A lower fire resistance rating is estimated based on numerical models. Structural resistance was maintained throughout the test. During preliminary testing structural collapse was observed in a separate experiment which highlights how the system is sensitive to damage to the ceiling boards. Numerical results highlight that thermal bowing and movement may result in changes in thermal interactions between adjacent elements. This paper provides novel large-scale experimental data on a loaded flooring system in fire.

Comparative response of tiled finishes and bonded fire resistive coatings for normal weight concrete tunnel liners under high-intensity one-sided heating

Experimental tests were performed to examine the relative fire resistance provided by several bonded coatings for normal weight concrete (NWC) panels that emulate a tunnel liner: ceramic tiling on mortar, spray-applied fire resistive material (SFRM), and intumescent paint (IP). Sixteen panel specimens (150-mm [6-in.] thick, 457-mm [18-in.] wide, and 610-mm [24-in.] tall) were subjected to one-sided heating using a gas-fired radiant panel, which can apply heat flux at intensities similar to hydrocarbon fuel fire. All specimens were cast from a single batch of NWC (approx. 40 MPa compressive strength) with a single curtain of steel reinforcing bars at 38-mm (1.5-in.) cover to the heated face. All specimens were vertically loaded to a service level of compressive uniaxial stress (approx. 14% of ambient specified compressive strength), which remained relatively constant during each test. Four bare concrete panel specimens were tested as a control group, and a ceramic tile finish was installed on six specimens in accordance with a current state department of transportation specification. The other six specimens were coated with fire resistive material (three each with SFRM and IP) at thicknesses corresponding to a 1-hr fire resistance rating per manufacturer specifications. Thermally-induced explosive concrete spalling was observed in 3 of 4 control specimens, 4 of 6 tiled specimens, and none of the 6 SFRM/IP coated specimens. The tiled finishes delaminated and eventually became fully detached from the concrete surface, thus providing negligible fire resistance compared to that provided by the SFRM or IP. Temperature time histories recorded within the outer 25-mm (1.0-in.) thickness of the heated concrete were used to evaluate the relative thermal resistance of each surface finish, as well as to validate a simplified thermal numerical model used for a brief parametric study. Post-fire removal of the surface finishes is also demonstrated.

Performance of steel beam with welded top-seat angle connections at elevated temperatures

PurposeTop-seat angle connection is known as one of the usual uncomplicated beam-to-column joints used in steel structures. This article investigates the fire performance of welded top-seat angle connections.Design/methodology/approachA finite element (FE) model, including nonlinear contact interactions, high-temperature properties of steel, and material and geometric nonlinearities was created for accomplishing the fire performance analysis. The FE model was verified by comparing its simulation results with test data. Using the verified model, 24 steel-framed top-seat angle connection assemblies are modeled. Parametric studies were performed employing the verified FE model to study the influence of critical factors on the performance of steel beams and their welded angle joints.FindingsThe results obtained from the parametric studies illustrate that decreasing the gap size and the top angle size and increasing the top angles thickness affect fire behavior of top-seat angle joints and decrease the beam deflection by about 16% at temperatures beyond 570 °C. Also, the fire-resistance rating of the beam with seat angle stiffener increases about 15%, compared to those with and without the web stiffener. The failure of the beam happens when the deflections become more than span/30 at temperatures beyond 576 °C. Results also show that load type, load ratio and axial stiffness levels significantly control the fire performance of the beam with top-seat angle connections in semi-rigid steel frames.Originality/valueDevelopment of design methodologies for these joints and connected beam in fire conditions is delayed by current building codes due to the lack of adequate understanding of fire behavior of steel beams with welded top-seat angle connections.

Spalling mitigation techniques for high-performance concrete at elevated temperature

High-performance concrete (HPC) is highly susceptible to temperature-induced spalling, which unveils severe damage of HPC structural members. Therefore, this research work is aimed at developing spalling mitigation techniques for HPC and experimentally assessing spalling behaviour at transient heating conditions up to 1000 °C for a 4-hour fire resistance rating. A total of four HPC mixes were comprised for spalling behaviour evaluation, in which Mix H1 was designed only using main binder ordinary Portland cement (OPC), whereas Mix-H2, Mix-H3, and Mix-H4 were designed by partial replacement of OPC with three different supplementary cementitious materials (SCMs), i.e., fly ash (FA), silica fume (SF), ground granulated blast furnace slag (GGBS) one at a time as a binary composite system. Polypropylene (PP) fibres and steel (ST) fibres one at a time from a range of 0.00, 0.62, 1.24, 1.86, and 2.48 kg/m3 and ST fibres range of 0.00,12.43, 24.87, 37.30, and 49.74 kg/m3 were incorporated into HPC mixes for evaluating spalling mitigation behaviour at elevated temperature. For each HPC mix, a total of three standard cylindrical specimens (100 mm diameter × 200 mm height) were exposed to transit temperature 1000 °C for up to 4 h to assess spalling behaviour. It is observed that Mix-H1 content only OPC does not reveal any severe damage and spalling behaviour, whereas Mix-H2, Mix-H3, and Mix-H4 comprising SCMs revealed very severe damage and spalling behaviour. This result indicates that the highly dense microstructure with a highly durable HPC matrix using SCMs does not allow any moisture movement/migration from the inherent concrete binding matrix to the outer exposed surface of cylinder specimens and resulting in explosive-type spalling of HPC. However, using 1.86 kg/m3 of PP fibres and 37.30 kg/m3 of ST fibres in HPC binary systems has a positive impact on mitigating spalling of HPC at elevated temperatures.

Numerical analysis on mechanical behavior of steel‐concrete composite beams under fire

SummaryThis paper investigated the fire behavior of steel‐concrete composite beams (SCB) and partially encased steel‐concrete composite beams (PEB) through numerical analysis. The numerical models established by the software ABAQUS were verified against experimental results. Parametric studies were performed to study the influences of load ratio, strength of concrete and steel, width of concrete slab, size of steel beam, fire protection layer, and degree of shear connection on the fire behavior of SCB and PEB. The analysis results show that the deformation stages of SCB and PEB under fire both go through four stages: elastic, elastic–plastic, plastic small deformation, and plastic large deformation. The web of SCB experiences a tension–compression–tension process under fire, and the bottom flange of PEB may even change from tension to compression at a lower load ratio. The failure mode of PEB, whether the concrete is crushed, depends on the load ratio. When SCB fails, the concrete is crushed and only the bottom flange of the steel beam yields. Under various parameters, the fire resistance of SCB is about 22 min, while the fire resistance of PEB is 82–93 min under a load of 0.4. When the load ratio increases from 0.2 to 0.6, the fire resistance of SCB decreases by 8 min, while that of PEB decreases by 110 min. To meet class I fire resistance rating under a normal service load ratio of 0.4, additional measures for PEB are still required, and at least 15 mm of fire protection layer is required for the steel beam of SCB. Finally, considering the temperature internal fore, a coefficient related to the fire time was introduced to modify the formula of ultimate flexural capacity of SCB and PEB, which showed good accuracy.

Parametric Framework for Early Evaluation of Prescriptive Fire Design and Structural Feasibility in Tall Timber

This paper describes a computational framework that performs automated structural design of tall timber buildings at the resolution of conceptual design while considering typical loads and load combinations, material properties, and a set of architectural requirements. The framework is used to assess a range of tall timber geometries in terms of feasibility for different fire design approaches and structural systems. Based on constructed precedents, two structural systems are considered: a post–beam–panel system and a post-and-platform system. For these systems, a set of geometric parameters and variables are established to create a parametric design space, after which each geometry is subjected to structural analysis and structural design. The resulting design space contains significant diversity and can be used to assess the feasibility of the two considered structural systems for a range of geometries. The results show clear relationships between building height and the feasibility of using wood sections for lateral elements, as well as a positive relationship between the amount of structural material required and higher fire-resistance ratings, which can be interpreted in light of concern for embodied carbon.

Fire Resistance Evaluation of Concrete Beams and Slabs Incorporating Natural Fiber-Reinforced Polymers.

This paper presents a numerical study to evaluate the fire resistance of concrete beams and slabs incorporating natural fiber-reinforced polymers (FRP). A validated finite element model was applied to carry out a series of numerical studies on fire-exposed reinforced concrete (RC) beams and slabs strengthened with conventional and bio-based FRP composites. The model calculates the temperature-dependent moment-curvature relationship for various segments of the member at each time step, which are then used to calculate the moment capacity and deflection of the member. The variables in the beams and slabs include different strengthening techniques (externally bonded FRP and near-surface mounted FRP), different fiber composites, and fire insulation schemes (uninsulated and insulated). The results from the study indicate that the bio-based FRP-strengthened RC members undergo a faster degradation in moment capacity and also experience higher deflections under fire exposure. This leads to a lower fire resistance in RC members with bio-based FRP composites compared to beams and slabs with conventional FRP-strengthened concrete members. The addition of fire insulation to the bio-based FRP-strengthened members can enhance their fire performance and help achieve the required fire resistance ratings for use in building applications. In this study, the NSM CFRP-strengthened RC beams were found to have a fire resistance of 3 h without any fire insulation; however, the bio-based FRP-strengthened beams required a layer of vermiculite-gypsum-based fire insulation material (of about 25 mm) to achieve similar fire resistance.

Reliability-Based Fire Resistance Periods for Buildings in England

The traditional route to achieving adequate structural performance in the event of fire is through ensuring that structural elements attain fire resistance ratings. The magnitude of these ratings typically varies in function of the building use, size, and height. In their genesis, fire resistance ratings were a proxy for the specification required of elements such that they had a reasonable likelihood of surviving the full duration of a fire, i.e., burn-out. As such, fire resistance periods were specified in the function of fire load, which, over time, progressively increased in consideration of the consequences of fire induced structural failure. This ratcheting of fire resistance periods was seemingly done so based on the collective experience of the profession, in response to observations from real fires and, where applicable, resulting disasters. That is, the safety levels associated with current fire resistance recommendations in most global codes and guidance documents are not determined. Therefore, this paper presents a review of reliability-based acceptance criteria for structures, ahead of their application, to determine fire resistance recommendations for buildings in England based on both codified reliability indices and the principle of relative (marginal) lifesaving costs. The study applies a novel form of probabilistic time equivalence, which is augmented by fire occurrence related statistics/parameters, to arrive at risk-informed fire resistance ratings that directly relate to the life safety consequences of fire induced structural failure (i.e., fatalities) to adequate fire resistance ratings. In determining these building fire resistance periods, it is observed that safety targets which implicitly include material damage and building reconstruction costs result in fire resistance recommendations that are well-aligned with National codes and standards. That is, to some extent, the ratcheting of fire resistance periods with time has resulted in some potential resilience to fire. Where safety targets are rationalised in consideration of life safety only, i.e., through the principle of relative (marginal) lifesaving costs, it is shown that fire resistance periods can be optimised, particularly in sprinkler protected buildings. However, this has the potential to introduce vulnerabilities to common mode failures.

Vigas de concreto armado com aberturas retangulares em situação de incêndio

Abstract Openings in reinforced concrete (RC) beams may be required due to building installations (electrical, water, etc.). They weaken its cross-sectional area and, in case of fire, can increase the thermal field of the structure. NBR 15200 does not consider this. The paper evaluated the influence of rectangular openings on the Fire Resistance Rating (FRR) of RC beams by the Simplified Method of NBR 15200. This method combines a non-linear thermal analysis (isotherms) with the evaluation of the flexural strength of the beams using a manual design calculation method. The thermal field were obtained by a thermal model solved by finite element analysis (FEA) with Abaqus software. Thermal parameters of NBR 15200 were used. This FRR was compared with equivalent beams without openings solved by the Tabular Method of NBR 15200. Twelve 60 cm high beams with different widths and dimensions of openings were studied. Beams with openings had a FRR up to 60 min lower than the equivalent beam without openings. The larger the size of the rectangular opening, the greater the mechanical degradation of the beam in fire. NBR 15200 Tabular Method proved to be unsafe in this case. Prescriptions for beams with openings must be shown in NBR 15200.

Теплофизические характеристики стали и огнезащитных покрытий при нормированных температурных режимах пожара

PURPOSE. The article is devoted to the experimental study of thermophysical characteristics of steel on an experimental model – a metal plate of 600×600×5 mm, and to determining effective thermophysical characteristics of a fireproof coating made of a two-component epoxy composition under standardized temperature conditions. METHODS. In this work the finite element method implemented in the Ansys Mechanical software complex was applied for numerical thermotechnical calculation. The inverse heat conduction problem method was also applied for determining thermophysical characteristics of fireproof coatings. FINDINGS. As a result of the study the temperature fields were obtained in the cross section of steel structures with a fireproof coating under various fire temperature conditions. The conducted analysis showed that the discrepancies between numerical modeling and experimental data were satisfactory. RESEARCH APPLICATION FIELD. The results obtained can be applied for designing passive fire protection systems for building structures at construction facilities. As a result of the calculations, a number of values of fire resistance limits of structures with a fireproof coating from a two-component epoxy composition were obtained, taking into account the influence of standardized temperature fire regimes. All these data are put down in the tables of structures fire resistance ratings for three critical temperatures values based on which the corresponding nomograms were built. CONCLUSIONS. The study confirms the effectiveness of epoxy-based fireproof coatings to improve fire resistance of steel structures. Thermotechnical calculation and experimental modeling make it possible to determine the effectiveness of fireproof materials and justify their application in buildings and structures designed in accordance with standardized temperature fire modes requirements.

Application of neural networks for light gauge steel fire walls

This research study evaluates the applicability of neural networks to determine the fire-resistance rating of Light gauge Steel Frame walls, made of cold-formed steel studs and lined with gypsum plasterboard.Many full-scale tests and numerical studies were conducted to determine the fire-performance of LSF walls, but these studies were expensive and time consuming. Therefore, an alternative option of using machine learning to predict the fire performance was proposed. The actual fire performance data from FEA and full-scale tests of previous research studies were used as inputs in the machine learning. Separate sets of training and test data were used; thus, test data is not used to calibrate the machine learning-based analysis. Here LSF walls made of different wall configurations and different steel profiles were considered. Training and testing of the artificial neural network are performed by combining different parameters such as loss function, keep probability factor, learning rate, the number of layers, and neurons to determine the optimal and accurate solution. The structural fire capacity of LSF walls obtained from machine learning was compared against the test data to evaluate its accuracy. Based on the findings, suitable neural network models with two hidden layers and suitable loss functions were recommended.