Structural Response Research Articles

Simplified assessment of structures with clutching inertia-friction systems by equivalent linearization methods

The innovative Clutching Inertia System (CIS), has garnered increasing recognition for its effectiveness in mitigating structural vibrations. To enhance the efficiency of passive CIS, introducing suitable energy dissipation mechanisms for the rotation inertia component is imperative. This study delves into the dynamic behavior of CIS, augmented with additional friction damping. Initially, the influence of supplementary friction damping within the CIS framework is examined through a dynamic model of a Single-Degree-of-Freedom (SDOF) system, integrated with the CIS and incorporating the Coulomb friction model. Subsequently, to streamline the dynamic analysis of the CIS and optimize the friction force thereby enhancing control efficiency while minimizing inactive durations, the paper introduces two distinct Equivalent Linearization Methods (ELMs). Furthermore, an assessment of the CIS’s dynamic performance, subjected to various external excitations, is presented. The findings highlight the crucial role of supplemental friction damping in reducing the inactivity of CIS and enhancing its overall control effectiveness. The employed ELMs demonstrate commendable accuracy and practicality for both response assessment and CIS performance optimization. In essence, the CIS, when integrated with supplemental friction damping, exhibits superior performance in suppressing structural displacement responses across diverse excitations, particularly in longer-period structures. Conversely, a more pronounced efficacy in managing structural acceleration responses is observed in structures with shorter periods. The study concludes that for specific structural applications, enhancing supplemental friction damping is more advantageous for vibration control than increasing the CIS’s inertia.

Buffeting performance of long-span bridges with different span affected by parametric typhoon wind

Currently, typhoon-related performance of long span bridges usually focus on a specific wind record such as wind speed and turbulence intensity during a full typhoon, however, the inter-correlation among wind characteristic parameters under typhoon wind climate is ignored. The existing investigation about structural responses during typhoon attacks are still limited at case-study analysis, and hardly provide a generalized framework to evaluate the structural performance especially for typhoon landing whole process. This study utilizes the measured wind speeds of the strong typhoon "Hagupit" to establish a unified typhoon parametric model, during which the correlation of typhoon wind parameters including angle of attack (AoA), turbulence intensity, integral length scale and mean wind speed were taken into consideration. The measured typhoon process charactered with center-through effect with M-type average wind speed curve. Furthermore, the structural performance of long-span bridges with different spans from 1500 m to 2500 m main span was systematically studied. The aerodynamic parameters of the bridge deck section, including the aerostatic coefficients, flutter derivatives at different AoAs, and aerodynamic admittance under different oncoming flow conditions were identified through wind tunnel tests. Finally, the wind-induced buffeting performance was calculated by the buffeting frequency domain algorithm, showing various structural wind effect characteristics during the typhoon landing whole process. The maximal buffeting response is not necessarily related with the wind speed, and other wind characteristics especially turbulence intensity and AoA, etc. also affect on the results.

Pulse-type seismic response prediction for uncertain structures based on the attention mechanism and wavelet decomposition augmented decomposition learning

Accurate prediction of structural responses under seismic action is important for the performance assessment of structures. However, depending on the variability of the structure (e.g., the design information) or ground motion characteristics (e.g., the presence of pulses), the seismic response characteristics of the may be significantly different. To overcome this problem, this study proposes a novel structural feature attention mechanism and wavelet decomposition augmented decomposition learning method (SFA-WD-DL) for predicting the time-series of the structural response under pulse-type ground motions. Unlike previous studies, the proposed method can be applied to structures with different shapes. Innovatively, a structural feature attention mechanism is embedded within a neural network model, enabling the consideration of different structural parameters. In addition, a wavelet decomposition-based velocity pulse identification method is combined with decomposition learning, using decomposed pulses and high-frequency features as inputs to the neural network model. This process simplifies pulse feature recognition task of the model. To avoid an unbalanced distribution of ground motion features affecting model performance, a balanced sampling strategy for ground motion datasets combining ground motion clustering and category reorganization methods is proposed, which effectively improves the model robustness. The accuracy and applicability of the proposed method are validated using a dataset containing reinforced concrete frame structures of different shapes and a pulse-type ground motion dataset containing 148 records. In addition, the importance levels of the structural features are obtained through the weight distribution of the structural feature attention mechanism. This indicates that the proposed SFA-WD-DL method is easily interpretable and can extract key features affecting the structural response.

Numerical study of liquid sloshing in three-dimensional flexible cylindrical tank under multi-directional seismic excitation

The present study aims to evaluate the effect of the flexibility of three-dimensional (3D) cylindrical tank on liquid sloshing inside the tank as well as the influence of the hydrodynamic forces on the structure's deformation. A ground-supported cylindrical flexible tank filled with water and subjected to seismic excitation is investigated using a numerical coupling methodology to take into account the fluid–structure interactions. The Navier–Stokes equations in the fluid domain are solved using the finite volume method, while the finite element method is used to solve the linear-elastic equations of the structure. The arbitrary Lagrangian–Eulerian formulation is applied for the moving mesh in two-phase flow system. The simulations are conducted using free open-source software: OpenFOAM for fluid dynamics and FEniCS for solid mechanics, both utilize the preCICE library for data exchanging and fluid–structure coupling. The numerical methodology is validated by the experimental and numerical results given in literature. A multi-directional earthquake ground motion is then considered as external loading, and the elasticity of the tank wall is varied to investigate the effect on the fluid sloshing. It has been shown that the more flexible the tank walls are, the greater will be both the sloshing height and the structural deformations during an earthquake event. Several flow field information and structural responses have been provided, such as the sloshing height, hydrodynamic pressure, structure deformations, and structural stress distribution. The potential elephant's foot buckling phenomenon at the lower part of tank can also be predicted.

Mowing mitigates the negative impacts of long-term warming on community composition and niche characteristics of alpine meadow on the Tibetan Plateau

Climate warming and human disturbance are supposed to have significantly impacted the alpine grasslands. However, it is still unclear how human activity affects the community composition and niche characteristics in response to warming. We conducted a two-factorial experiment in an alpine meadow, and set up four treatments: warming, mowing, warming with mowing, and control. Based on the investigation of community composition and niche characteristics, we evaluated the impacts of soil carbon, nitrogen, and phosphorus on species niche overlap. The results showed that mowing significantly increased species richness of Grass, Sedge, Forbs and the importance value of Sedge compared to warming (P < 0.05). The niche breadth of species (>50%) was reduced by warming, but increased under mowing. The niche overlap mainly occurred between Grass and Forbs in warming, while it was evenly distributed among species after mowing, which alleviated the negative effects of warming on interspecific competitiveness. Warming increased the number of species pairs with a niche overlap value >0.9 by 24.15%, while warming with mowing decreased it by 2.7%. The number of species pairs with niche overlap was significantly correlated with soil total nitrogen and soil available nitrogen (P < 0.05). In particular, the species pairs with highly competitive showed a greater dependency on soil nitrogen. Our work highlights that moderate utilization and soil nitrogen are two crucial factors influencing the response of community structure in alpine meadows to future climate change. The study provides an important reference for predicting and addressing the impact of global climate change on adaptive management and grassland protection.

A novel impact approach based on electromagnetic loading technology: A case study on CFRP/Al riveted structures

To investigate the mechanical response and damage behavior of aircraft fuselage composite structures under out-of-plane impact loads more efficiently and flexibility, this paper proposed a novel impact approach and testing platform based on inductive coils to yield electromagnetic impact force. The influence of system key parameters on the electromagnetic loading waveforms were analyzed using an electromagnetic field finite element model. Single/repeated impact tests on CFRP/aluminium alloy (Al) riveted structures were conducted at different voltages (energies) based on this approach. The results indicate that the electromagnetic impact (EMI) approach exhibits significant advantages in both variable strain rate loading and continuous impact loading scenarios. This device can efficiently achieve multi-point and multiple impact loading. The electromagnetic impact forces with various amplitudes and pulse-widths can be accurately obtained by altering voltage and capacitance values, which can demonstrate the good experimental consistency of such test approach. Besides, with this test method, the load threshold for damage formation can be clearly defined: once the impact force exceeds the damage threshold load, the delamination area of the CFRP laminates expand as the impact energy increases. Note that when the provided out-of-plane impact load is slightly higher than the damage threshold load by changing the voltage, significant delamination damage may suddenly manifest in any one impact event of the repeated impacts.

Dynamic responses of monopile offshore wind turbines under different wind-wave misalignment angles

Wind-wave misalignment is a common occurrence for monopile offshore wind turbines during extreme typhoon conditions. This phenomenon has a significant impact on the structural dynamic response of turbine structures and poses a threat to their structural integrity. In this study, finite element analysis is conducted on 75 sets of working conditions of monopile offshore wind turbines to investigate their dynamic response under different wind turbine operating states, wind-wave misalignment angles, and randomness of wind and wave load conditions. The results of the analysis indicate that the impact of wind-wave misalignment angles on the dynamic response of the monopile offshore wind turbine varies depending on the operational conditions. Furthermore, the study reveals that there are variations in the dynamic response of the monopile offshore wind turbine under different combinations of wind and wave loads. During the parked state and yaw system fault of the monopile offshore wind turbine, the most adverse working conditions need to consider wind-wave misalignment angles of 0° and 180°. In contrast, the most adverse working conditions for operational states emerge when the wind-wave misalignment angle is 90°. These findings highlight the importance of considering wind-wave misalignment angles and the randomness of wind and wave load conditions when assessing the dynamic response and structural integrity of monopile offshore wind turbines.

Defect dynamics modeling of mesoscale plasticity

The collective motion of defects and their interaction are the basic building blocks for plastic deformation and corresponding mechanical behaviors of crystalline metals. Especially, dislocations among various defects are the “carrier” of plastic deformation in many crystalline materials, particularly ductile materials. To get a fundamental understanding of plastic deformation mechanisms, it calls for an integrated computational platform to simultaneously capture detailed defects characteristics across several length scales together with corresponding macroscopic mechanical response. In this paper, we present a three-dimensional mesoscale defect dynamics model to directly couple the three dimensional discrete dislocation dynamics model with continuum finite element method, aiming at capturing both size dependent plasticity at micron-, and submicron scale and constitutive behaviors at larger scales where such size-dependence disappear. Using non-singular dislocation theories, our model could accurately consider both short- and long-range elastic interactions between multiple dislocation segments with even higher computational efficiency than traditional dislocation dynamics simulations, together with the careful consideration of crystal/material rotation in the coupled framework. In addition, our model could directly model dislocation nucleation from stress concentrators such as a void, crack and indentor tip, which could allow us to investigate various defects’ motion and their mutual interactions, predicting macroscopic mechanical response of complex structures. The developed concurrently coupled model could also consider multiphysical phenomena by solving coupled governing equations in finite element framework, which could shed light on complex defect behaviors under various physical environments.

Experimental investigation of the relation between operating conditions and offshore wind turbine drivetrain dynamics

Abstract This study investigates the impact of operating and environmental conditions on the vibration induced on an offshore wind turbine drivetrain. Furthermore, it explores the role of the dynamic response of the global wind turbine structure to vibration on the drivetrain. A prolonged experimental campaign dedicated to condition monitoring the drivetrain provides experimental vibration signals. These vibration signals are acquired under varying operating conditions across multiple locations of an offshore wind turbine drivetrain of a Belgian Offshore Wind farm and serve as the basis for analysis. The signals’ statistics facilitate establishing connections between dynamic behaviour and operational variables, such as active power, rotor speed, blade pitch angle, and turbulence intensity, sampled at every second and provided by Fast-SCADA. The initial phase of the analysis involves a comprehensive examination of various statistical properties of the vibration signals to link the drivetrain’s dynamic response to operational conditions. This exploration includes both active and standstill periods of the wind turbine. A comprehensive summary that relates the global vibration characteristics with the operating conditions is formed by scrutinizing the overall vibration signals. In the study’s second phase, a detailed investigation is conducted on the vibration signals recorded during standstill conditions. Investigation of standstill data ensures that the structural modes’ spectral content does not interfere with the machines’ kinematic content. The analysis of standstill data proceeds from determining the most energetic resonance frequencies through the average power spectral density of the vibration signals. These identified frequency bands enable a thorough exploration, revealing the interlink between the offshore wind turbine drivetrain’s dynamic response and the operating/environmental conditions.

Parameter Optimization of Tuned Inerter Damper for Vibration Suppression in Structures with Damping

This study investigates the parameter optimization of tuned inerter damper (TID) in a single degree of freedom (SDOF) system, with a focus on vibration mitigation. As a type of inerter based dynamic vibration absorber (IDVA), TID achieves vibration suppression of the primary structure by replacing the mass block in traditional dynamic vibration absorber (DVA) with an inerter, thereby minimizing the increase in physical mass. With the displacement response of the primary structure as the objective function, this study first employs the classical fixed point theory (FPT) to derive the analytical formulations for the optimal parameters of TID following the H∞ optimization approach and neglecting the inherent damping of primary structure. The influence of optimal parameter deviations on the vibration mitigation effect of TID is also analyzed, revealing that the deviation of the optimal natural frequency ratio has a significant impact on the vibration mitigation performance. By flattening the amplitude curve of the displacement transfer function of primary structure between the fixed points, this study derives the analytical solution for the optimal damping ratio of TID using the extended fixed point theory (EFPT). When the inherent damping of primary structure is considered, this study employs the approximate extended fixed point theory (AEFPT) to derive the approximate optimal parameters of TID. A comparative study of the optimal natural frequency ratios obtained using FPT, AEFPT and numerical searches reveals that the discrepancies among the three methods are minimal for structures with low inherent damping. However, as the inherent damping ratio of the primary structure increases, the optimal natural frequency ratio obtained using FPT deviates significantly from the exact value, whereas the approximate optimal natural frequency ratio derived using AEFPT can significantly reduce this deviation. Combining the conclusion that the vibration mitigation effect of TID is significantly influenced by the natural frequency ratio, this study suggests that for highly damped primary structures, the use of AEFPT can yield more optimal TID parameters, thereby enhancing the robustness of vibration mitigation performance.

Metagenomic Insights into Coal Slag Remediation Effects on Soil and Microbial Health in Qinghai’s Muli Coal Mine

Long-term coal mining in the Muli coal mine area of Qinghai Province has degraded soil quality and reduced microbial diversity, making it imperative to implement effective ecological restoration measures to restore soil quality and enhance ecosystem functions. This study evaluated soil samples under 11 ecological restoration treatments using metagenomic sequencing combined with soil quality analysis to explore the responses of the microbial community structure and function to identify effective restoration measures. This study demonstrated that ecological restoration significantly increased the soil microbial diversity and richness, with the MLII1 (soil samples treated with a chemical weathering agent, attapulgite, and a microbial agent) and MLIII1 (soil samples treated with sheep manure (2.4 kg/m2), granular organic fertilizer (1.2 kg/m2), and the microbial agent) treatment groups performing exceptionally well. Further analysis of the functional networks revealed that although the MLII2 (soil samples treated with the chemical weathering agent and attapulgite) treatment group did not exhibit the highest species diversity, it exhibited the highest functional network complexity. The results of hierarchical clustering analysis showed that the microbial community of the MLII2 treatment group was most similar to that of the natural meadows compared to the other treatment groups. From the perspective of overall ecological restoration, this study concluded that the MLII2 treatment group exhibited the most favorable ecological restoration outcomes. This finding emphasizes the importance of not only enhancing microbial diversity but also prioritizing the restoration of community functions, especially for the recovery of fragile high-altitude ecosystems.

A composite structure device: vibration control and energy harvesting of tool system in aviation thin-walled parts milling process

Abstract The intense vibration generated by the high-speed milling cutter in the processing process not only seriously affects the surface roughness but also may damage important components of the machine tool, resulting in significant economic losses. Therefore, a composite structure of piezoelectric energy-collector (PEC) and nonlinear energy sink (NES) is innovatively constructed by combining theoretical research and numerical analysis to achieve more efficient vibration suppression and energy recovery in milling. Using the Hamilton principle, the electromechanical model of the composite structure is developed. Then, based on the Galerkin truncation to discretized displacement functions, we solve the amplitude-frequency response of the tool structure by using the harmonic balance method. The validity analysis of the proposed method can be verified by rigorous comparison with the results of the Runge-Kutta method. A novel NES-PEC composite structure presented in this work shows excellent vibration suppression capability in the milling process. More importantly, the structure also enables self-powered sensing of the tool system, significantly reducing dependence on external power sources. This innovative design substantially improves the stability and reliability of milling processes and opens up new ways to optimize the energy efficiency of tool systems. In summary, this paper’s modeling and solving methods, vibration reduction techniques, and energy harvesting strategies have laid a solid foundation for applying a high-speed milling cutter system. More relevant literature on applying vibration suppression and energy harvesting devices in milling must be reviewed. This paper fills in the research gap and provides a valuable reference for future tool systems design and optimization.

Evolutionary mechanism of Y-branches in acoustic Lichtenberg figures just below the water surface

The acoustic Lichtenberg figure (ALF) in an ultrasonic cleaner with a frequency of 28 kHz at different power levels was observed using high-speed photography. The nonlinear response of the cavitation structure was analyzed by the entropy spectrum in the ALF images, which showed the modulation influence of the primary acoustic field, exhibiting the fluctuations of the bubble distribution with time. Typical Y-branches predict the paths by which surrounding bubbles are attracted and converge into the structure, the branches are curved due to bubble-bubble interactions, and the curvature increases as the bubbles are approaching the main chain. The average travelling speed of bubbles along the branches is about 1.1 m/s, almost independent of power level of the ultrasonic cleaner. A theoretical model consisting of free bubbles and a straight bubble chain of finite length was developed to explore the evolutionary mechanism of branching. It was found that the bubble trajectories showed a bending tendency similar to the experimentally observed Y-branches, and the stationary straight bubble chain parallel to the main chain could evolve into a curved chain and eventually become a branch of the main chain. The theoretical predictions agree well with the experimental results, verifying the evolutionary mechanism of Y-branches in ALF.

Rasch Analysis Of The Dermatology Life Quality Index.

Previous results of the Dermatology-Life-Quality-Index (DLQI) validation in Colombia based on the classical test theory (CTT) perspective have showed the need to delve into its measurement properties. Therefore, we aimed to assess the structural validity, internal consistency and item response analysis of the DLQI through the item response theory (IRT) or the Rasch model. We assessed the dimensionality of the DLQI, determined its difficulty, discrimination and differential functioning and went on to evaluate its internal consistency and discriminative validity among patients with inflammatory and non-inflammatory skin disease. We recruited Colombian patients with different skin diseases. Data of 865 patients (mean age, 49.3 years; 61% females) were included. DLQI-scores ranged from 0 up to 30. Internal consistency for dichotomous item #7 showed a McDonald's Omega coefficient of 0.85 (95%CI, 0.84-0.87) and a Cronbach's α coefficient of 0.86 (95%CI, 0.84-0.88). For ordinal item #7, the McDonald's Omega coefficient was 0.87 (95%IC:0.85-0.89) and Cronbach's α coefficient, 0.84 (95%CI, 0.82-0.87). Horn's parallel analysis revealed the presence of DLQI unidimensionality with a 1-factor solution. Only item #1 fitted the PCM model. The remaining items, including item #9, did not show adequate fit due to overlapping responses and order changes. The validity of DLQI-COL based on Rasch analysis proved not to be a suitable instrument to evaluate QoL in our dermatologic population. A refined version of the scale with an adequate cross-cultural adaptation and validation process is needed to obtain an appropriate and reliable version of the instrument for QOL measuring in Colombian patients with skin diseases.

Seismic drifts of buildings through deep neural networks circumventing incremental dynamic analysis: Aims and pitfalls for robust and reliable predictions

In the field of seismic response assessment, simplified procedures have long been pursued to circumvent the rigorous, state-of-the-art nonlinear response history analysis (NRHA) and incremental dynamic analysis (IDA) that typically require tedious computations. To this end, this study investigates artificial neural networks (ANN) as prediction models to bypass IDA and quickly and reliably determine the structural drift responses of buildings, without employing surrogate models or analysis techniques that lower the quality of the estimates. Three designs of such prediction models are identified in terms of their scope, implementation and corresponding database, commonly employed in research, while identifying common pitfalls in their design. The investigations involve ten steel-frame multi-story structures, considering cyclic and in-cycle material deterioration and P-Delta phenomena. More than 17-thousand recorded ground motions (GM) are employed to perform IDA on these frame-building models, resulting in a unique database of responses ranging from linear to collapse, with more than 3-million NRHA. Based on this database, a prediction model is developed for each building, capable of predicting the IDA under a GM excitation not included in the database. Additionally, another prediction model is developed that can predict the IDA of a building under a GM excitation, both of which are not included in the database. These investigations show that ANN are excellent tools to circumvent IDA and capture the record-to-record uncertainty by rapidly and reliably predicting structural drifts ranging from linear responses to the collapse limit state, while building-to-building predictions are additionally feasible if the employed database is appropriate.

Coupled critical plane-pseudo excitation method for multiaxial fatigue analysis of structures under random vibration

This study proposes a coupled critical plane–pseudo excitation method for assessing multiaxial fatigue damage in mechanical structures subjected to random loads. Within the modal coordinate framework, we derive an expression for the spectral moment of the structural stress response using the pseudo excitation method, which facilitates the decoupling of spatial characteristics from frequency domain properties. For the input power spectral density, represented as an integer power function, we employ eigenvalue decomposition and the residue theorem to derive an analytical expression for the spectral moment of the modal displacement response. By constructing equivalent stress modes based on the maximum shear stress and normal stress criteria, we obtain an expression for the equivalent stress variance. Intelligent optimization algorithms are utilized to determine the critical plane position and the corresponding equivalent stress spectral moments, followed by the application of the Dirlik method for fatigue assessment. A numerical example involving random vibration multiaxial fatigue analysis of an L-shaped thin-walled plate demonstrates the effectiveness of the proposed coupled critical plane–pseudo excitation method in comparison to the traditional critical plane method that relies on the stress covariance matrix for calculating equivalent variance. The results confirm the accuracy and efficiency of our approach, and we further explore the impact of different forms of the excitation power spectral density and the damping ratios on the computational outcomes.

Toward first principles-based simulations of dense hydrogen

Accurate knowledge of the properties of hydrogen at high compression is crucial for astrophysics (e.g., planetary and stellar interiors, brown dwarfs, atmosphere of compact stars) and laboratory experiments, including inertial confinement fusion. There exists experimental data for the equation of state, conductivity, and Thomson scattering spectra. However, the analysis of the measurements at extreme pressures and temperatures typically involves additional model assumptions, which makes it difficult to assess the accuracy of the experimental data rigorously. On the other hand, theory and modeling have produced extensive collections of data. They originate from a very large variety of models and simulations including path integral Monte Carlo (PIMC) simulations, density functional theory (DFT), chemical models, machine-learned models, and combinations thereof. At the same time, each of these methods has fundamental limitations (fermion sign problem in PIMC, approximate exchange–correlation functionals of DFT, inconsistent interaction energy contributions in chemical models, etc.), so for some parameter ranges accurate predictions are difficult. Recently, a number of breakthroughs in first principles PIMC as well as in DFT simulations were achieved which are discussed in this review. Here we use these results to benchmark different simulation methods. We present an update of the hydrogen phase diagram at high pressures, the expected phase transitions, and thermodynamic properties including the equation of state and momentum distribution. Furthermore, we discuss available dynamic results for warm dense hydrogen, including the conductivity, dynamic structure factor, plasmon dispersion, imaginary-time structure, and density response functions. We conclude by outlining strategies to combine different simulations to achieve accurate theoretical predictions that are based on first principles.

Multivariate Structural Vibration Coupling Response of the Self-Propelled Straw Pickup Baler Under Time-Varying Loads

Multivariate Structural Vibration Coupling Response of the Self-Propelled Straw Pickup Baler Under Time-Varying Loads

Comparative analysis on the hydrodynamic characteristics of offshore floating photovoltaic systems based on membrane structures under different mooring configurations

In the context of rapidly increasing global energy demand, solar energy is considered one of the most promising alternatives due to its ubiquity and sustainability. Floating photovoltaics, which do not occupy land and offer higher power generation efficiency, are becoming increasingly popular. As a novel type of floating photovoltaic, membrane structures are drawing more attention due to their lightweight nature, easy installation, and cost-effectiveness. Based on the Ocean Sun's floating photovoltaic membrane prototype as a reference, this study designed and fabricated a 1:40 scale model for laboratory experiments. The research investigated the influence of different mooring configurations and lengths on the hydrodynamic characteristics of membrane structures. The conclusions indicate that structures with more anchor chains exhibit smaller amplitudes in various movements and mooring forces. As the mooring length decreases, the amplitudes of various structural movements decrease, but mooring forces increase. Compared to regular wave conditions, mooring has a more significant impact on structural motion responses under irregular waves. In practical engineering, a comprehensive consideration of structural safety and cost-effectiveness is necessary for design. The selection of appropriate mooring configurations and lengths plays a crucial role in ensuring the safe operation and sustainability of membrane structures.

Machine learning-based prediction of seismic response of elevated steel tanks

Seismic response analysis assesses structural safety and integrity during earthquakes and guides design for optimal performance, compliance with regulations, and risk mitigation. This study proposes a novel approach utilizing machine learning (ML) techniques to predict the seismic response of elevated steel tanks accurately. ML is a powerful tool that can handle complexity, improve accuracy, provide data-driven insights, and optimize designs for predicting seismic responses of structures. Moreover, this study evaluates various ML models containing Random Forest, Support Vector Regression, Adaptive Boosting, LightGBM, Histogram-based Gradient Boosting, XGBoost, CatBoost, Bagging Regression, and Decision Trees to identify the most effective predictive model. In general, the developed ML-based predictive models provide a promising tool for engineers involved in the seismic design and retrofitting of elevated steel tanks, aiding in optimizing designs and enhancing structural safety and resilience against seismic hazards. As a result, the HGB model obtained the most suitable performance compared to other developed models with higher R2 and lower RMSE. In addition, a sensitivity analysis was performed based on SHAP values, and it was found that the height of the liquid and the intensity measure were the most influential variables in the seismic response of the tank.