Search

The modern composite cable-stayed bridge always has a wider deck, and the slab has an obvious shear lag effect. At the operation stage, internal forces distribution of the composite girder under live loads differs from that under dead loads only. It is essential to investigate the shear lag of the main beam under dead and live loads. Then, in-situ tests under truck loads were carried out on Xia Zhang Bridge. Considering the superposition of axial forces, a simplified method is proposed to evaluate the effective width. The finite element models (FEMs) of the full bridge using solid shell elements under dead and live loads were established. The longitudinal distribution of the effective widths for concrete slabs under different loading positions and loading forms was obtained. Furthermore, the full-scale variable parameter analysis considering the effects of span lengths and deck widths was conducted by FEMs. The numerical results show that the composite girder segments at the location of the bridge tower and the loading position need to be concerned for shear lag analysis. A generalised verification for a cable-stayed bridge was made, and compared results show that simplified methods can calculate the normal stresses in slabs more accurately than Eurocode 4. [ABSTRACT FROM AUTHOR]

The flexural performance of concrete beams incorporating glass fiber–reinforced polymer (GFRP) bars and further strengthened by a prefabricated permanent ultrahigh-performance concrete (UHPC) formwork is investigated in this study. A total of eight beams, including seven composite beams with a UHPC formwork and one reference beam without a UHPC formwork, were tested under four-point bending. The parameters evaluated included the interface treatment method, the existence of a prefabricated permanent UHPC formwork, the presence of a top UHPC layer, and the GFRP reinforcement ratio. Experimental results revealed that the flexural capacity of beams with the UHPC formwork significantly improved relative to the reference beam. The maximum crack width of the composite beam was smaller than that of the reference beam under the same load. The addition of the top UHPC layer significantly increased the ultimate load of the composite beam, and the high tensile strength of the GFRP bar was effectively utilized. Moreover, characterization results revealed that interface treatment, specifically the addition of a linear low-density polyethylene bubble wrap interface, prevented debonding of the UHPC formwork from the concrete. A calculation model for flexural stiffness was also developed, which provided high predictive accuracy as verified by the close agreement of its results with experimental measurements. [ABSTRACT FROM AUTHOR]

The bending stiffness of beams represents a pivotal parameter influencing both the dimensions of the elements during their design and their subsequent utilisation. It is evident that excessive deflections can cause discomfort to users and contribute to further structural degradation. The objective of this study was to enhance the bending stiffness of timber beams by bonding a composite sheet to their external surfaces. A carbon sheet exhibiting an ultra-high modulus of elasticity and low elongation at rupture was employed. Two variables of analysis can be distinguished including whether the reinforcement was applied or not and the number of reinforcement layers. The beams, with nominal dimensions of 80 × 80 × 1600 mm, were subjected to a four-point bending test in order to ascertain their mechanical properties. In total, 15 beams were tested (5 unreinforced and 10 reinforced). The reinforcement had no appreciable impact on the increase in flexural load capacity, with the maximum average increase recorded at 9%. Nevertheless, an increase in stiffness of 34% was observed. Additionally, significant increases were observed in ductility up to 248%. However, the ductile behaviour of the beam occurred after the rupture of the reinforcement. In all instances, the failure was attributed to the fracturing of the wooden components or the UHM CFRP (ultra-high-modulus-carbon-fibre-reinforced polymer) sheet. The numerical analysis proved to be a valuable tool for predicting the stiffness of the wood–composite system, with a relatively low error margin of a few percentage points. The modified approach, based on the equivalent cross-section method, permits the determination of a bilinear load deflection relationship for reinforced beams. The aforementioned curve is indicative of the actual behaviour. Given the propensity for the sudden rupture of reinforcement, the described method of reinforcement is recommended for beams subjected to lower levels of stress. [ABSTRACT FROM AUTHOR]

This study investigates the toughness and load capacity of various innovative beam configurations of cold-formed steel beams (CFSB) using both ordinary concrete slabs and engineered cementitious composite (ECC) slabs. A finite element analysis with ABAQUS 20 was conducted on double-channel, sigma, G, and omega sections, both with and without inverted lips, as well as the effects of L, channel, and trapezoidal stiffeners and length-to-depth ratios. The double-omega section with ordinary concrete achieved the highest first peak load of 365.2 kN and a toughness increase of 181.1%. Inverted lips enhanced toughness in the double-G and sigma sections, with increases of 156.9% and 158.3%, respectively. Among ECC configurations, the double-omega section with ECC3 slab reached 387.4 kN and a toughness increase of 199.5%. Thinner ordinary concrete sections (70 mm and 90 mm) negatively impacted toughness, emphasizing the need for adequate thickness. Trapezoidal stiffeners also improved toughness. These findings highlight the importance of geometrical design and material selection in optimizing CFSB performance, offering valuable insights for future design practices. [ABSTRACT FROM AUTHOR]

This research addresses the phenomena of thermoelastic damping (TED) and frequency shift (FS) of a thin flexible piezoelectro-magneto-thermoelastic (PEMT) composite beam. Its motion is constrained by two linear flexible springs attached to both ends. The novelty behind the proposed study is to mimic the uncertainties during the fabrication of the beam. Therefore, the equation of motion was derived utilizing the linear Euler–Bernoulli theory accounting for the flexible boundary conditions. The beam's eigenvalues, mode shapes, and the effects of the thermal relaxation time ( t 1 ), the dimensions of the beam, the linear spring coefficients ( K L 0 and K L L ), and the critical thickness ( C T ) on both TED and FS of the PEMT beam were investigated numerically employing the Newton–Raphson method. The results show that the peak value of thermoelastic damping ( Q p e a k − 1 ) and the frequency shift (Ω) of the beam increase as t 1 escalates. Another observation was made for the primary fundamental mode, where an increase in the spring coefficient K L L leads to a further increase in Ω. On the other hand, the opposite trend is noted for the higher modes. Indeed, the results show the possibility of using the proposed design in a variety of applications that involve damping dissipation. [ABSTRACT FROM AUTHOR]

This study conducted experiments to investigate the flexural behavior of steel–concrete composite beams with U-shaped sections, utilizing cold-formed lipped channels as web components. To enhance both flexural and shear performance, trapezoidal plates were added to the lower sides of the composite beams. A total of ten specimens were fabricated, with variables defined according to the following criteria: presence of bottom tension reinforcement and bottom studs, thickness of the trapezoidal side plates (6 mm and 8 mm), and the welding method. Four-point bending tests were conducted, and all specimens exhibited typical flexural failure at the ultimate state. Specimens with bottom tension reinforcement, specifically those in the H5-T6 and H5-T8 series, demonstrated increases in ultimate load of 28.8% and 33.5%, respectively, compared to specimens without tension reinforcement. The use of lipped channels enabled full composite action between the concrete and the steel web components, eliminating the need for stud anchors. Additionally, it was confirmed that the plastic neutral axis, reflecting the material test strengths, was located within the concrete slab as intended. This study also compared the design flexural strengths, calculated using the yield stress distribution method from structural steel design standards such as AISC 360 and KDS 14, with the experimental flexural strengths. The comparison was used to evaluate the applicability of current design standards. [ABSTRACT FROM AUTHOR]

Dynamic analysis of structures is a key challenge in structural engineering, especially in choosing effective and accurate numerical methods. Steel–concrete composite structures, commonly used in bridges and floors, require calculations of dynamic parameters to ensure safety and comfort. Few studies compare the effectiveness of the finite element method (FEM) and the rigid finite element method (RFEM) in the dynamic analysis of such structures. This study fills this gap by comparing the methods using experimental results. FEM and RFEM models were developed using Abaqus, Python, and Matlab. The main parameters were identified, i.e., the Young's modulus of the concrete slab (EC) and the stiffness of the connection (Kx, KRX, Kv, Kh). Both methods closely matched the experimental results. The RFEM matched natural frequencies with 2–3% deviations, while the FEM showed 3–4% deviations for the torsional, axial, and first three flexural frequencies. The RFEM reduced the computation time by about 65%, making it suitable for large-scale applications. The FEM provided a finer resolution of local effects due to its higher element density. The results can be applied to the design of bridges, floors, and other structures under dynamic loads. It will also provide the authors with a basis for developing structural health monitoring (SHM). [ABSTRACT FROM AUTHOR]

The effects of single and multiple transverse open cracks on the dynamic properties of woven fibre laminated composite beam (LCB) under free vibration by experimental and numerical approaches are explored in this research work. The experimental modal testing is performed n laminated glass/epoxy composite beams using vibration Fast Fourier Transformation (FFT) analyser system. The finite element simulation software ABAQUS is used as the platform for numerical modal analysis to arrive at the natural frequencies. Within the test domain of modal analysis, the simulated results are finely agreed with the empirical test results. The effects of crack location, relative crack depth, boundary conditions and fibre orientations on the modal frequency of the cracked LCB are explored under free vibration. The results of the study conclude that the maximum decrease in frequencies is observed for 0° ply oriented single and multi-cracked LCB. Furthermore, the results elicit that the presence of crack positioned nearer to the restrained end exhibits more reduction in vibration frequencies for any particular crack depth. Within the frequency domain, the present research approach can be employed as an effective tool for the detection and analysis of crack or crack-like defects in LCB structures in any applied field of engineering. [ABSTRACT FROM AUTHOR]

Basalt fiber (BF) is known for its high tensile strength, low elastic modulus, and environmental friendliness. To investigate the influence of basalt fiber reinforced concrete (BFRC) lamination heights on the beams' shear performance, four basalt fiber reinforced concrete and reinforced concrete (BFRC‐RC) beams featuring diverse laminated heights were fabricated and underwent bending tests. To further investigate the impact of stirrup and shear span ratios on the shear performance of BFRC‐RC beams, finite element models (FEMs) were established based on the experiments. The results indicated that four test beams experienced diagonal shear failure. Compared to RC beams, BFRC‐RC beams exhibited heightened ductility and stiffness. Additionally, as the BFRC laminated height rose, both cracking and peak loads increased. Compared to BFRC‐RC beams without stirrups, stirrups in those beams transitioned the diagonal shear failure to flexural failure. Stirrups in BFRC‐RC beams increased both the yield and peak loads, thereby enhancing their ductility. With a reduction in the shear span ratio, BFRC‐RC beams increased in both yield and peak loads, accompanied by a simultaneous decrease in yield and peak displacement. Finally, a model incorporating the influence of laminated height on BFRC‐RC beams' behavior was introduced to predict their bearing capacity. The theoretical values aligned well with the experimental results. [ABSTRACT FROM AUTHOR]

This paper presents a new mixed finite element model for material and geometric non-linear analysis of composite beams in partial interaction taking into account the non-penetration condition between layers. The Hu–Washizu functional with three independent fields is chosen for the developed mixed formulation. The force fields in the connection are chosen as the redundant forces and approximated using interpolation functions. The remaining force fields are obtained from solving equilibrium equations so that the element equlibrium is verified. Nevertheless, the compatibility as well as the constitutive law is satisfied only in a weak sense. The geometric non-linearity is taken into account by adopting the co-rotational approach. In this paper, the contact condition is imposed at the element level. Augmented Lagrangian method with Uzawa iteration algorithm is used to solve the contact problem. It has been shown that the proposed mixed formulation gives a more accurate result with less elements comparing to classical displacement based model. Besides, the buckling behaviour of delaminated two-layered composite columns has been studied by using the developed mixed formulation model. It has been observed that the buckling strength of the composite column can be overestimated if the uplift is not considered in the model. [ABSTRACT FROM AUTHOR]

Currently, due to the simplifications imposed on continuous models, there is an absence of a generalized approximate solution to investigate all possible dynamic behaviors of a tall building. In an attempt to address this deficiency, this paper proposes a new generalized continuous model and its solution methods to generalize all types of behavior that may be encountered in structural systems and tall buildings. The continuous model results from a composite beam that serially couples the classical sandwich beam and a pure shear beam. Unlike existing continuous models, the serial coupling, inclusion of new kinematic fields, and inclusion of rotational inertia allow for the resolution of complex interaction among different types of bending and shear behaviors. Specifically, it is shown how local shear behavior simultaneously interacts with global bending behavior, global shear, and local bending. Two solutions to the dynamic problem are presented: a closed-form analytical solution method for structures with uniformity along their height, and a numerical method that combines the advantages of the continuous method and the transfer matrix method to resolve structural and geometric variability in height. The transfer matrix is analytically solved by maintaining a fixed 6 × 6 matrix range that is independent of the number of levels of the structure, drastically reducing computational cost by eliminating the classical need to calculate the inverse of the zero matrix. Numerical applications investigate the effect of rotational inertia and local shear on the accuracy of the proposed results compared to results from the finite element method. To this end, a parametric analysis of 1560 different cases covering a wide range of typical behaviors in individual structural systems and tall buildings is conducted. The results exhibit promising accuracy, showing that the qualities of the proposed continuous model significantly improve precision compared to classical continuous models and therefore justify its practical application by academics and practicing engineers. Furthermore, the proposed mathematical approach is easily applicable in various domains of composite materials engineering. [ABSTRACT FROM AUTHOR]

The present study dealt with a comprehensive mathematical model to explore the nonlinear forced vibration of a magnetostrictive laminated beam. This system was subjected to mechanical impact, a nonlinear Winkler–Pasternak foundation, and an electromagnetic actuator considering the thickness effect. The expressions of the nonlinear differential equations were obtained for the pinned–pinned boundary conditions with the help of the Galerkin–Bubnov procedure and Hamiltonian approach. The nonlinear differential equations were studied using an original, explicit, and very efficient technique, namely the optimal auxiliary functions method (OAFM). It should be emphasized that our procedure assures a rapid convergence of the approximate analytical solutions after only one iteration, without the presence of a small parameter in the governing equations or boundary conditions. Detailed results are presented on the effects of some parameters, among them being analyzed were the damping, frequency, electromagnetic, and nonlinear elastic foundation coefficients. The local stability of the equilibrium points was performed by introducing two variable expansion method, the homotopy perturbation method, and then applying the Routh–Hurwitz criteria and eigenvalues of the Jacobian matrix. [ABSTRACT FROM AUTHOR]

Composite girder bridges with Corrugated Steel Webs (CSWs) have won increasing popularity among bridge designers owing to its exceptional mechanical properties. The extant literature focuses on the static and dynamic performance of girder bridges with CSWs, there is limited research on the mechanical performance of such structures under high temperature. The mechanical performance of composite beams with CSWs undergoes degradation under the influence of high temperatures during a fire. By conducting local fire simulation in Fire Dynamics Simulator (FDS) and finite element (FE) thermal-mechanical coupling analysis, this study examined the differences in shear performance between the three-span continuous and continuous rigid-frame beams with CSWs, under exposure to fire at the side span and middle span, respectively. This study discovers that the shear stress on the continuous and rigid-frame beam is disorderly distributed in the fire-exposed region, and the shear stress on the CSWs is no longer uniformly distributed but exhibits violent fluctuations. Additionally, at the fire-unexposed spans, the shear stress on the continuous beam increases by several multiples, whereas the shear stress on the rigid-frame beam experiences minimal change. This study provides a reference for further optimizing the fire performance design of composite beams with CSWs. [ABSTRACT FROM AUTHOR]

This paper proposes a method for modifying brick masonry walls using ultra-high-performance concrete (UHPC) to effectively reduce the beam section width in composite members. First, a detailed finite element model of UHPC–brick masonry composite beams was established using the finite element software ABAQUS 2022 and validated through comparison with the existing literature. Then, the effects of factors such as the tensile reinforcement ratio, UHPC layer thickness, and UHPC strength grade on the load–midspan deflection curve of composite members were analyzed, along with a study of the bending performance under vertical loads. Based on the results of the finite element analysis, a calculation formula for the positive section bending capacity of UHPC–brick masonry composite beams was proposed. The study found that longitudinal tensile reinforcement yielded first, followed by the crushing of the compressive region of UHPC and brick masonry, resulting in overall bending failure. With the increase in the tensile reinforcement ratio and UHPC layer thickness, both the yield load and peak load significantly increased, while the UHPC layer thickness had a notable impact on the cracking load of the composite member. When the UHPC strength grade ranged from 150 MPa to 180 MPa, the bearing capacity of the composite member changed little. The proposed calculation method for bearing capacity correlated well with the finite element results, providing a theoretical basis for the design and analysis of UHPC–brick masonry composite beams. [ABSTRACT FROM AUTHOR]

Pultruded glass fiber-reinforced polymer (GFRP) materials are increasingly recognized in civil engineering for their exceptional properties, including a high strength-to-weight ratio, corrosion resistance, and ease of fabrication, making them ideal for composite structural applications. The use of concrete infill enhances the structural integrity of thin-walled GFRP sections and compensates for the low elastic modulus of hollow profiles. Despite the widespread adoption of concrete-filled pultruded GFRP tubes in composite beams, critical gaps remain in understanding their flexural behavior and failure mechanisms, particularly concerning design optimization and manufacturing strategies to mitigate failure modes. This paper provides a comprehensive review of experimental and numerical studies that investigate the impact of key parameters, such as concrete infill types, reinforcement strategies, bonding levels, and GFRP tube geometries, on the flexural performance and failure behavior of concrete-filled pultruded GFRP tubular members in composite beam applications. The analysis includes full-scale GFRP beam studies, offering a thorough comparison of documented flexural responses, failure modes, and structural performance outcomes. The findings are synthesized to highlight current trends, identify research gaps, and propose strategies to advance the understanding and application of these composite systems. The paper concludes with actionable recommendations for future research, emphasizing the development of innovative material combinations, optimization of structural designs, and refinement of numerical modeling techniques. [ABSTRACT FROM AUTHOR]

Highlights Proper design and accurate mechanical assessment of composite C‐beam after opening are of great importance in structure engineering. This paper aims to experimentally and analytically investigate the postbuckling response of large‐size C‐beam with web opening under bending‐shear coupling load. New specimen with four different open shapes were designed and tested. Strain gauges and displacement measurements were applied to monitor its buckling behavior, strain field distribution and critical failure load. Four specimens with various openings were loaded until catastrophic failure occurred. Additionally, an analytical model was introduced to predict the residual strength of circular opening. The results indicate that while the presence of an opening significantly decreases the load carrying capacity, it has minimal effect on the bending stiffness. Compared with intact specimen, the initial delamination, buckling and ultimate strength of the circular opening decreases less than those of the rectangular opening. By altering the position of the rectangular opening, improvements can be made in terms of initial delamination resistance and buckling load; however, ultimate strength remains largely unaffected. Reinforcing the edge of an opening further reduces resistance to initial delamination but other two indicators are improved. Overall, from buckling to failure stages, post‐buckling bearing capacity after opening decreases by 40%. Moreover, the shear failure mode is observed during catastrophic failures. And the analysis method employed is relatively conservative. Ten large size composite C beams are conducted under coupling loads. Deformation, strain distribution and failure mode are presented. Influence of openings on postbuckling behavior of beam is analyzed. An analysis method is employed to predict the residual strength of beam. It could provide valuable insights for assisting in designing beam openings. [ABSTRACT FROM AUTHOR]

The steel-wood composite beam with I-section is made of laminated veneer lumber (LVL) and cold-formed thin-wall steel by structural adhesive. The flexural properties of nine composite beams are tested with parameters such as LVL plate thickness, section height, thin wall steel thickness and flange LVL width. The failure forms, deflection development, strain distribution and bearing capacity of specimen are observed, the influence factors of flexural property are analyzed, and a formula for calculating midspan deflection considering the slip effect is proposed. The results show that steel-LVL composite beams have good overall working performance. The composite beam has a high deformation ability before failure, and the most typical failure mode is the lower flange LVL fracture. The material properties are fully utilized, showing good ductility. The flexural bearing capacity of composite beams can be improved by increasing the ratio of section height to width and web height to thickness and reducing the ratio of flange width to thick‐ ness. The slip between the LVL and the section steel reduces the stiffness of the composite beam. Compared with the results without taking slip into account, the theoretical calculation results of mid-span deflection of composite beam with interface slip effect are closer to the real deformation, and the calculation accuracy is improved by 2. 38%. [ABSTRACT FROM AUTHOR]

In this research, the equations governing the vibrations of a composite curved beam reinforced with graphene platelets have been solved using a quasi-3D model of the beam. The investigated composite beam is multi-layered, each layer can be reinforced by different amount of graphene platelets, which leads to a functionally-graded distribution of reinforcements. According to the quasi-three-dimensional theory of beams, the effect of thickness stretching and shear strains is included and does not require a shear correction factor. It should be noted that according to the geometry of the assumed beam, deformations and strains are considered small and the structural relations of the material are linear. The governing equations of the curved beam are derived based on Hamilton’s principle after calculating the kinetic and strain energies. The boundary conditions of the beam are assumed to be simply supported on both ends. Therefore, the displacement parameters of the problem have been explained with Navier’s solution method and with the use of Fourier expansions, closed form expressions are obtained as elements of mass and stiffness matrices. The elasticity modulus of the beam is rewritten using the Halpin–Tsai model and Poisson’s ratio and mass density using the rule of mixtures. Finally, the results of each section are presented in the form of tables. First, the results of this research were verified with the existing results, and then new results were introduced to investigate the effective parameters of the problem. These results include the investigation of the distribution of graphene platelets, the effect of the weight percentage of the filler and the geometric properties of the beam. The results of this research on the dynamic response of the beam show that the effects of increasing the volume percentage of graphene, even to a small extent, can be seen in increasing the natural frequency of the curved beam. [ABSTRACT FROM AUTHOR]

Abstract This article focuses on numerical thermos-structural behavior evaluation of composite steel and concrete beams under fire conditions. Several models of composite beams are analyzed, changing the following parameters: steel beam, span length, load level, slab thickness, concrete and steel strength. The numerical models, validated by experimental results of other authors, were developed using the finite element method on software ANSYS and the language APDL. It was observed that the structural load level is the main parameter that affects the structural behavior of composite steel and concrete beams under fire conditions.

Abstract The time-dependent effects in steel-concrete composite beam bridges can intensify track irregularities, subsequently leading to amplified train-bridge coupling vibrations. This phenomenon may increase the stress amplitudes in the bridge steel, thereby impacting the fatigue performance of the composite structures. This paper employs multiple rigid body dynamics to construct a high-speed train model and utilizes the finite element method to develop a steel-concrete composite beam element model that accounts for time-dependent effects, interfacial slip, and shear hysteresis. This approach enables the computational analysis of the train-bridge coupling system, facilitating an investigation into the influence of concrete’s time-dependent effects on the fatigue performance of railway steel-concrete composite bridges. Focusing on a 40-m simply supported composite bridge, the train-bridge coupling dynamic responses were computed for each operational year within a decade of the completion of construction. Applying the P-M linear fatigue damage accumulation theory, statistical analysis of stress history data across various operational periods was conducted to quantify the fatigue damage induced by a single eight-car high-speed train on the lower flange of the mid-span steel beam and the beam-end studs. The findings reveal that the beam-end studs sustain greater damage than the mid-span steel beam. Moreover, the detrimental impact of time-dependent effects diminishes with the increase of operational years. Notably, compared to the initial year, the fatigue damage to the lower flange of the mid-span steel beam by an eight-car train in the tenth year has surged by 39.3%. Conversely, the damage to the beam-end studs has decreased by 47.5%.

The time-dependent effects in steel-concrete composite beam bridges can intensify track irregularities, subsequently leading to amplified train-bridge coupling vibrations. This phenomenon may increase the stress amplitudes in the bridge steel, thereby impacting the fatigue performance of the composite structures. This paper employs multiple rigid body dynamics to construct a high-speed train model and utilizes the finite element method to develop a steel-concrete composite beam element model that accounts for time-dependent effects, interfacial slip, and shear hysteresis. This approach enables the computational analysis of the train-bridge coupling system, facilitating an investigation into the influence of concrete's time-dependent effects on the fatigue performance of railway steel-concrete composite bridges. Focusing on a 40-m simply supported composite bridge, the train-bridge coupling dynamic responses were computed for each operational year within a decade of the completion of construction. Applying the P-M linear fatigue damage accumulation theory, statistical analysis of stress history data across various operational periods was conducted to quantify the fatigue damage induced by a single eight-car high-speed train on the lower flange of the mid-span steel beam and the beam-end studs. The findings reveal that the beam-end studs sustain greater damage than the mid-span steel beam. Moreover, the detrimental impact of time-dependent effects diminishes with the increase of operational years. Notably, compared to the initial year, the fatigue damage to the lower flange of the mid-span steel beam by an eight-car train in the tenth year has surged by 39.3%. Conversely, the damage to the beam-end studs has decreased by 47.5%. [ABSTRACT FROM AUTHOR]

The presence of faults is common in engineering composite structures. Precise detection of faults prior to failure has been the focal point for researchers working in this domain. Detection of damage from the modal characteristics is an age-old promising technique besides the artificial intelligence techniques such as neural network (NN), Artificial neural network (ANN), recurrent neural network (RNN), and particle swarm optimization (PSO) methods. However, multiple detection techniques combined can give better results. In this regard, recurrent neural networks (RNN) and modified particle swarm optimization (mPSO) are combined to detect damages in a glass fiber reinforced polymer (GFRP) composite cantilever beam. The proposed hybrid model consists of two stages; indices of relative natural frequencies applied to locate crack parameters (position and severity) by recurrent neural network technique and optimization of the results (position and severity) by mPSO. The results illustrate this method can be implemented to predict multiple transverse cracks and their parameters in a composite beam, manifested in the change of natural frequencies where the error is limited to 0.97% only. [ABSTRACT FROM AUTHOR]