Prediction Of Structural Response Research Articles

Thermal–structural response and life prediction of lattice regenerative cooling thrust chambers in liquid rocket engines based on a simplified viscoplastic model

With advances in aerospace technology, the reusability of liquid rocket engines has become the focus of considerable research interest. Traditional channel-type regenerative cooling thrust chambers often experience plastic deformation and microcracks, which limit their lifespan. This study proposed a novel lattice regenerative cooling thrust chamber using a simplified viscoplastic model and ABAQUS finite element software to simulate thermal–structural responses under different pressure conditions. The lattice structure not only enhanced the cooling efficiency and reduced the structural weight but also mitigated the plastic deformation and high-temperature creep of the inner wall. At an inner-wall temperature of 820 K, creep damage was significant. Compared to that of traditional chambers, the lattice structure of the proposed chamber exhibited different mechanical behavior and failure modes, with a more uniform stress distribution and initial failure occurring at the lattice nodes. The proposed design avoided the “doghouse” effect evident in traditional chambers, achieving an inner-wall lifespan of up to 202 cycles, a 359 % improvement. The high design flexibility of the lattice structure in the cooling channels enabled enhanced thrust chamber longevity. The study results provide new insights and technical support for next-generation liquid rocket engine designs.

Multi-fidelity enhanced few-shot time series prediction model for structural dynamics analysis

These days, deep learning (DL) techniques are regarded as an effective substitution of refined finite element models to conduct structural dynamics analysis. Nevertheless, the efficacy of DL methods overwhelmingly depends on the quality and quantity of the data. Since high-fidelity (HF) data are accurate enough but usually time-consuming and costly, while low-fidelity (LF) data are low-cost and efficient but inaccurate, the DL models cannot efficiently and accurately achieve prediction of structural dynamic response solely using either HF or LF data. Under this circumstance, a multi-fidelity enhanced few-shot time series prediction approach is proposed that can significantly promote the efficiency of structural dynamics analysis. Moreover, the K-shape clustering method is utilized to select representative training sample to lessen the need for HF data, further improving efficiency of structural dynamics analysis. For validating the accuracy and efficiency of this method, a case study about the prediction for seismic response on a reinforced concrete frame is conducted, wherein fiber element models are utilized to generate accurate but limited HF seismic response data, while multi-degree of freedom models are utilized to develop a larger LF response database. Eventually, diverse vital factors impacting the performance of the proposed method are also investigated. The results demonstrate that the proposed method can efficiently implement structural dynamics analysis without compromising precision.

Real-time prediction of structural responses in deep-water jacket platforms using Ada-STLNet: A comprehensive analysis with prototype monitoring data

Real-time prediction of the mechanical behaviors based on prototype monitoring data is crucial for ensuring the integrity and safety of deep-water jacket platforms. As complex nonlinear systems, these platforms’ response exhibit varying temporal trends, dynamic spatial correlations, and load dependencies. This makes accurate prediction of future axial force and bending moment responses a significant challenge. In this paper, a novel deep learning method called Adaptive Spatio-Temporal Load Network (Ada-STLNet) is proposed aiming to address the issue of multi-node axial force and bending moment response prediction of deep-water jacket platform. Our model utilizes an enhanced graph convolution (EGCN) and self-attention mechanism for efficient spatial correlation modeling in multi-node response, LSTM for long sequence temporal feature capture. It integrates spatial and temporal, along with load-aware modules to capture intricate patterns in structural responses. Additionally, a multi-gated coupling mechanism with two independent gating modules is designed to adaptively represent the complex dependencies of structural responses, ensuring model stability and robustness. Extensive experiments conducted on prototype structural monitoring data from a deep-water jacket platform in the South China Sea demonstrate that Ada-STLNet outperforms six traditional models, including HA, SVR, KNN, MLP, LSTM, and GRU, across various prediction steps. The proposed model exhibits superior accuracy, particularly in short-term predictions, achieving up to 62.80% improvement in MAE and 48.11% in RMSE for axial force predictions compared to the second-best model. Ablation studies confirm the effectiveness of each component within Ada-STLNet. This research highlights the potential of Ada-STLNet for reliable and accurate prediction of structural responses, contributing significantly to the field of marine engineering.

Machine-learning-based models for predicting seismic demands of SCBFs based on scalar and vector-valued intensity measures

Predicting the building damage due to earthquakes has persistently been a challenge. Various ground motion Intensity Measures (IMs) through correlation analysis with Engineering Demand Parameters (EDPs) have long been employed for structural response prediction. However, considering several Machine Learning (ML) techniques and a comprehensive set of scalar and vector-valued IMs has not been entirely undertaken, especially in the context of special concentrically braced frames. In addressing these limitations, this study employs a blending ensemble learning method along with new IMs extracted in the time-frequency domain and three EDPs, including peak story drift ratio (PSDR), peak floor acceleration (PFA), and peak floor velocity (PFV). Time history analysis is performed using a set of 1126 far-field ground motions and 57 IMs extracted from ground motions in the time domain, frequency domain, time-frequency domain, and spectral domain. Also, some special IMs are proposed to capture ground motion's time and frequency nonstationary characteristics. Four base models—Random forest, Bayesian ridge regression, classification and regression tree, and K-Nearest neighbors—have been used to build a blended ensemble model. The findings showed that the XGBoost meta-model better predicted PSDR, PFA, and PFV, obtaining a coefficient of determination (R2) of 0.901, 0.962, and 0.961, respectively. A prediction accuracy greater than 90 % was achieved using the proposed vector-valued IM (including the mean of instantaneous amplitude, the area under the square of acceleration, and peak ground acceleration) for PSDR (R2 = 90.02 %), PFA (R2 = 94.75 %), and PFV (R2 = 94.41 %). Furthermore, the results showed that the new IMs extracted from the instantaneous amplitude and frequency perform well in predicting EDPs.

Non‐linear time history analyses of a rigid block isolated with unbonded fiber‐reinforced elastomeric isolators (UFREIs): A comparison between 3D finite element and phenomenological models

AbstractNumerical modeling represents a pivotal tool in the seismic analysis and design of structural systems, enabling the detailed prediction and examination of structural responses under seismic loading. This research conducts a comparative analysis of two numerical modeling approaches aimed at simulating the seismic response of unbonded fiber‐reinforced elastomeric isolators (UFREIs). The research focuses on a finite element (FE) model developed using Abaqus and a developed phenomenological model implemented in OpenSees, outlining the development and calibration processes for each. The FE model is developed based on simple rubber material testing data, while the phenomenological model is calibrated using experimental results from cyclic shear tests conducted on the UFREI device and the FE model. The primary objective of this study is to assess the effectiveness of these modeling approaches in predicting UFREI behavior under seismic conditions. This evaluation entails comparing model predictions with experimental data obtained from unidirectional shake table tests performed on a rigid block isolated by two UFREIs. This paper highlights the distinct advantages and limitations of each model in simulating UFREI dynamic responses during seismic events. Furthermore, it provides insights into the modeling techniques and discusses the computational demands and data requirements of each model, thereby aiding in their application to various aspects of seismic analysis and design.

An adaptive physics-informed deep learning approach for structural nonlinear response prediction

An adaptive physics-informed deep learning approach for structural nonlinear response prediction

Attention-based hybrid network for structural nonlinear response prediction under long-period earthquake

To develop structures that can respond to severe seismic events, models and tools are essential for quickly and precisely assessing and controlling the structure's performance. Long-period ground motions may pose potentially significant hazards to the safety of high-rise buildings located in basins or alluvial plains. However, traditional regression-based methods and pure data-driven machine learning methods are insufficient to address this problem of response prediction, which is characterized by non-stationarity, nonlinearity, and scarcity of samples. To tackle this issue, we propose a novel semi-explicit physics-informed deep learning method. The method incorporates the physical information into the model, thereby achieving better prediction accuracy. Through numerical and experimental validations, including hysteresis experimental data, the actual seismic response record of a six-story hotel, as well as data from single-degree-of-freedom structures across various periods and multi-story buildings in Los Angeles, Seattle, and Boston, we verified the proposed method significantly outperforms traditional regression-based methods and data-driven machine learning methods in terms of accuracy, efficiency, and robustness.

State space model-based Runge–Kutta gated recurrent unit networks for structural response prediction

State space model-based Runge–Kutta gated recurrent unit networks for structural response prediction

E-PINN: A fast physics-informed neural network based on explicit time-domain method for dynamic response prediction of nonlinear structures

The physics-informed neural networks (PINNs), serving as the surrogate models, have emerged in the dynamic response prediction of nonlinear systems. However, in the conventional PINN model, the global differential equation of motion of the nonlinear system is directly integrated into the loss function, which requires the network to capture the intricate global dynamic evolution mechanism of the system and thus poses significant challenges for network learning. In this study, inspired by the explicit time-domain method (ETDM), a novel PINN based on ETDM, called E-PINN, is proposed to address the challenges arising from the network learning of the existing PINNs. A lightweight long short-term memory (LSTM) module is trained to learn the nonlinear evolution mechanism of restoring forces, while a single convolutional layer (SCL) module is utilized to reflect the linear evolution mechanism of the primary structure under the combined action of the external excitations and the nonlinear restoring forces. The weights of the SCL module can be directly retrieved from the discrete convolutional formulation of ETDM, and only the parameters in the LSTM module need to be optimized through a loss function solely based on the nonlinear restoring forces, thereby enabling easy network learning of the proposed E-PINN by decoupling the linear and nonlinear evolution mechanisms embedded in the nonlinear system. Three numerical examples are investigated by the present approach, and the results demonstrate the superior training efficiency and prediction accuracy of E-PINN in dynamic response prediction of nonlinear systems.

Application of a novel machine learning model for the prediction and optimization of anti-blast performance of sandwich honeycomb blast walls

Sandwich honeycomb blast wall with the superior energy absorption characteristics could be applied to anti-blast protection of offshore oil and gas platform. Recently, machine learning technique, as an alternative to traditional Finite Element Analysis (FEA), is becoming a powerful tool in understanding structural performance. The aim of this study is to propose a novel data-driven model for fast predictions of structure response of sandwich blast wall under explosion, including the maximum deformation δmax, the maximum internal energy Emax and the energy absorption ratio RE. FEA was firstly conducted to generate sample data for the proposed model by using LS-DYNA software. An improved artificial electric field algorithm (IAEFA) was combined with artificial neural network (ANN) to develop an IAEFA-ANN model. In case studies, the prediction results of IAEFA-ANN approximate the results of FEA well, and comparison results of 9 different ANN models demonstrate that IAEFA-ANN model has the best performance. Then, the effects of explosion parameters (including explosive charge mass Me, stand-off distance d and concave angles θ) on structural response prediction results were investigated by using the proposed model. Moreover, the IAEFA-ANN model was applied to conducting optimal design of the blast wall to obtain optimum anti-blast performance.

An efficient method based on shear models for structural seismic response prediction considering hysteretic characteristics

An efficient method based on shear models for structural seismic response prediction considering hysteretic characteristics

A nonlinear structural pulse-like seismic response prediction method based on pulse-like identification and decomposition learning

Abstract Accurate prediction of structural responses under seismic action is important for the performance evaluation of structures. However, depending on the differences in the characteristics of ground motions, particularly whether they contain impulses, the seismic-response characteristics of structures may differ significantly. Hence, a new method, i.e., WD–AttDL, is proposed in this study to predict structural response under pulse-like ground motions. This method innovatively combines a wavelet decomposition-based velocity pulse-identification method with decomposition learning, where decomposed pulses and high-frequency features are used as inputs to the neural-network model, thus simplifying the identification of pulse features for the model. The decomposition learning module integrates different types of submodules, such as CNN feature-extraction, LSTM temporal-learning, and self-attention mechanism submodules. To reduce the nonlinear time-range analysis calculations required to generate training data, a screening method for impulsive ground motions based on time-series feature clustering is proposed. The accuracy and applicability of the proposed method are verified by numerically simulating three different cycles of reinforced-concrete frame structures and a three-dimensional masonry structure. Compared with existing structural seismic-response models, WD–AttDL synergistically integrates different modules and thus offers a higher prediction accuracy. In particular, it reduces the peak error of the predicted response, which is important for the evaluation of structural performance. Additionally, based on the response predicted by WD–AttDL, a vulnerability analysis of the structure under pulse-like seismic effects can be performed rapidly and accurately.

D’Alembert–Lagrange Principle in Symmetry of Advanced Dynamics of Systems

The D’Alembert–Lagrange principle is a fundamental concept in analytical mechanics that simplifies the analysis of multi-degree-of-freedom mechanical systems, facilitates the dynamic response prediction of structures under various loads, and enhances the control algorithms in robotics. It is essential for solving complex problems in engineering and robotics. This theoretical study aims to highlight the advantages of using acceleration energy to obtain the differential equations of motion and the generalized driving forces, compared to the classical approach based on the Lagrange equations of the second kind. It was considered a mechanical structure with two degrees of freedom (DOF), namely, a planar robot consisting of two homogeneous rods connected by rotational joints. Both the classical Lagrange approach and the acceleration energy model were applied. It was noticed that while both approaches yielded the same results, using acceleration energy requires only a single differentiation operation, whereas the classical approach involves three such operations to achieve the same results. Thus, applying the acceleration energy method involves fewer mathematical steps and simplifies the calculations. This demonstrates the efficiency and effectiveness of using acceleration energy in dynamic system analysis. By incorporating acceleration energy into the model, enhanced robustness and accuracy in predicting system behavior are achieved.

Influence of interfacial bond between rebar and concrete on the lateral resistance of RC columns under different loading rates

The interfacial bond between rebar and concrete is a critical factor that influences the performance of reinforced concrete (RC) structures because it affects the effective force transfer between concrete and rebar and hence the composite actions. In finite element modelling of RC structures, the bond-slip relation between rebar and concrete is generally neglected due to the increased model complexity by considering debonding behaviours. Limited studies show the debonding performance is loading rate dependent, neglecting it in numerical modelling may lead to inaccurate structural response predictions, but there is no systematic investigation of bonding performance on responses of structures under load of different loading rates. The influences of neglecting debonding in structural response analysis are therefore not properly defined yet. In this study, the finite element model was established and validated by the available impact test data. The lateral resistance and damage modes of the column considering and neglecting bond-slip behaviour between rebar and concrete were examined under various loading rates ranging from 50 kN/s to 1.0 × 106 kN/s. It is found that neglecting bond-slip relation in finite element modelling of RC columns leads to underprediction of the peak force and damage. The assumption of perfect bond has a significant influence on predicting the peak force and damage of column under low loading rates, but its influence reduces with the increase in loading rate, especially when the loading rate exceeds 1.0 × 105 kN/s. The maximum relative difference in peak force between considering and neglecting bond-slip at 50 kN/s is 18.63 %. Parametric studies were conducted to investigate the effects of bonding performance on columns of different width, depth, height, and concrete strength. Based on the numerical results, an analytical formula is developed to quantitatively predict the errors in peak force predictions by neglecting debonding between concrete and rebars of RC columns. The results highlight the importance of considering bond-slip in finite element modelling of RC structures subjected to quasi-static and low-rate dynamic loadings, and demonstrate it is reasonable to neglect debonding in structural response analysis under high-rate dynamic loadings.

Time history seismic response prediction of multiple homogeneous building structures using only one deep learning‐based Structure Temporal Fusion Network

AbstractStructural response prediction under earthquakes is crucial for evaluating the structural performance and subsequent functional restoration. Deep learning provides the potential to rapidly obtain the responses by skipping the time‐consuming nonlinear finite element analysis. However, a single deep learning network may only predict the time history responses of one specific structure, resulting in redundancy and resource waste when building multiple networks for modeling different structures. Thus, this study proposes a Structure Temporal Fusion Network (STFN) that can predict responses of various homogeneous structures using a single network. The key concept is that the seismic waves and the structural characteristics, such as story numbers, are fused together to predict diverse time history responses. Two numeric experiments are conducted, including predicting responses of ideal single‐degree‐of‐freedom (SDOF) structures and regular multistory reinforced concrete frames. Furthermore, a series of ablation analyses are carried out to validate the network architecture. The results indicate that STFN can predict nonlinear time history responses of different structures with mean square errors in the magnitude of and for two experiments, respectively. The solutions also highlight the importance of fusing static characteristics for the modeling of various structures with only one network. The STFN presents a promising solution for time history response prediction across multiple structures in regions.

Machine-Learning Applications in Structural Response Prediction: A Review

Machine-Learning Applications in Structural Response Prediction: A Review

Structural nonlinear seismic time-history response prediction of urban-scale reinforced concrete frames based on deep learning

Efficiently predicting the seismic response of urban building clusters is essential for preemptively identifying potential seismic hazards prior to an earthquake and optimizing resource allocation post-event. However, complete information of buildings at a city scale is generally un-accessible or non-existent. Existing methods struggle to reconcile low information demands, high computational accuracy, and computational efficiency. This paper proposes a fast prediction method for structural seismic time-history responses that combines deep learning methods with easy-getting structural parameters at an urban scale. An end-to-end network with adaptive multilevel fusion output is designed, which incorporates the autoencoder concept for predicting the structural seismic time-history responses based on ground motions records and five easy-getting structural parameters. The models are compared and optimized considering the training hyperparameters and network architecture, resulting in an optimized model with low complexity that provides valuable reference values for structural seismic response. Besides, the proposed model is applied to four actual buildings with different construction time, occupancy types, and floor sizes, demonstrating its good prediction performance and significant computational advantages comparing to the universally used MDOF method.

Using In-Building Observations of Small-to-Large Earthquakes to Predict the Seismic Response of Structures

ABSTRACT The main goal of this study is to evaluate the potential value of data from weak-to-moderate earthquakes for structural response analysis. Data recorded over 18 yr by the seismic network installed in the 12-stories Grenoble City Hall Building (France) is considered. The building response is analyzed in terms of intensity measures and engineering demand parameters, and then compared with strong earthquake data recorded in Japanese buildings. The uncertainties of structural response prediction are estimated and defined in terms of “within-building” and “between-building” components in the same way as the components of the ground-motion model. Data complementarity in the response model is observed between the weak-to-moderate (France) and the moderate-to-strong (Japan) earthquake datasets, disclosing nonlinear processes (associated with resonance period elongation) that are activated in buildings during low-to-strong motion. For example, fundamental frequency shifts are triggered at low values of both total structural drift amplitudes and equivalent strain rates (i.e., time derivative of structural drift). In addition, strain rate thresholds from 10−11 s−1 to 10−5 s−1 representing different structural conditions from undamaged to severely damaged buildings are observed to activate nonlinearities. This confirms the link between loading rates and structural conditions. Our results highlight the interest in instrumentation in buildings located in regions of weak-to-moderate seismicity, for (1) the development and calibration of realistic models for predicting the seismic response of structures, (2) for improving our understanding of the components of uncertainties in the risk assessment of existing buildings, and (3) to investigate physical processes activated in structures during seismic loading that influence their response.

Amplitude‐dependent modal viscous damping for distributed stick–slip systems

AbstractAn accurate damping model serves as the foundation for reliable structural analysis. One of the primary sources of structural damping is the stick–slip mechanism caused by interfacial friction. Structural damping is usually represented by the modal damping ratio, and the modal equivalent viscous damping ratio (EVDR) of a stick–slip system is crucial in structural dynamic modeling. To date, an accurate yet simple prediction method for modal amplitude‐dependent EVDR that considers the distribution characteristics of the stick–slip mechanism remains unavailable. In the present study, the modal EVDRs of a distributed stick–slip system (DSSS) extended from a single degree‐of‐freedom stick–slip system were calculated using the modal energy equivalence method. The correlation between the stick–slip parameters and the modal damping behavior was investigated at various amplitude levels on the basis of the assumption of equal stick–slip parameters. A two‐parameter damping model represented by a single stick–slip damping model was developed to capture the amplitude dependence of the frictional EVDR. Furthermore, a practical prediction method based on the stick–slip parameters was proposed for the modal EVDR of the fundamental and higher‐order modes. The seismic analysis of two illustrative structures with nonuniform and uniform interstory stiffness demonstrated the effectiveness and applicability of the proposed method in predicting the modal EVDR of the DSSS. The proposed equivalent linear viscous damping system is suitable for the quick prediction of structural dynamic responses.

Adaptive GN block-based model for seismic response prediction of train-bridge coupled systems

Deep learning (DL) methods has found extensive application in predicting structural responses. However, conventional neural networks often lack the capacity to effectively capture inter-data relationships, relying solely on training data for end-to-end prediction. Consequently, these methods may struggle with generalization, particularly when faced with new structural configurations absent from the training dataset. To overcome this limitation, this study adopts a graph-based framework, representing structures as graphs facilitates the transfer of features between different components, mimicking the transfer of forces in the real world. Subsequently, a Graph Neural Network Blocks (GN Blocks) model is introduced. Leveraging the holistic inference structure inherent in graph representations, the GN Block-based model as an adaptive model exhibits superior generalization performance in response analysis tasks involving unknown structural forms. Illustrated through the application to train-bridge coupled (TBC) systems, the GN Block-based model demonstrates high prediction accuracy and robust generalization performance, underscoring its suitability for tackling complex structural response prediction.