Residual displacement estimation of the bilinear SDOF systems under the near-fault ground motions using the BP neural network

2021 ◽  
pp. 136943322110585
Author(s):  
Mingkang Wei ◽  
Xiaobin Hu ◽  
Huanxin Yuan
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Structural Parameters ◽  
Ground Motions ◽  
Calculated Data ◽  
Time History ◽  
Strength Reduction Factor ◽  
Residual Displacement ◽  
Near Fault ◽  
Residual Displacements

This paper presents a comprehensive study of residual displacements of the bilinear single degree of freedom (SDOF) systems under the near-fault ground motions (NFGMs). Five sets of NFGMs were constructed in this study, in which the natural ones as well as the synthesized ones were both considered. By way of the nonlinear time history analyses, three different residual displacement spectrums were obtained and analyzed in detail. Utilizing the calculated data, a back propagation (BP) neural network was established to predict the residual displacements of the bilinear SDOF systems under the NFGMs. The results show that the structural parameters, including the strength reduction factor and the post-yield strength ratio, have significant and relatively consistent impacts on the residual displacement spectrum. However, the ground motion characteristics, including the fault type, the closest distance from the site to the fault rupture, the earthquake magnitude, and the site soil condition, exhibit more complex effects on the residual displacement spectrum. In addition, the proposed BP neural network can fully incorporate the parameters affecting the residual displacements of the bilinear SDOF systems under the NFGMs, while having a fairly good accuracy in predicting the residual displacements.

Strength reduction factor of self-centering structures under near-fault pulse-like ground motions

2020 ◽  
Vol 24 (1) ◽  
pp. 119-133
Author(s):  
Huihui Dong ◽  
Qiang Han ◽  
Xiuli Du ◽  
Canxing Qiu
Keyword(s):  
Ground Motions ◽  
Time History ◽  
Reduction Factor ◽  
Strength Reduction ◽  
The Self ◽  
Hysteretic Behavior ◽  
Hysteretic Model ◽  
Strength Reduction Factor ◽  
Vibration Period ◽  
Near Fault

Many studies on the strength reduction factor mainly focused on structures with the conventional hysteretic models. However, for the self-centering structure with the typical flag-shaped hysteretic behavior, the corresponding study is limited. The main purpose of this study is to investigate the strength reduction factor of the self-centering structure with flag-shaped hysteretic behavior subjected to near-fault pulse-like ground motions by the time history analysis. For this purpose, the smooth flag-shaped model based on Bouc-Wen model which can show flag-shaped hysteretic behavior is first described. The strength reduction factor spectra of the flag-shaped model are then calculated under 85 near-fault pulse-like ground motions. The influences of the ductility level, vibration period, site condition, hysteretic parameter, and hysteretic model are investigated statistically. For comparison, the strength reduction factors under ordinary ground motions are also analyzed. The results show that the strength reduction factor from near-fault pulse-like ground motions is smaller. Finally, a predictive model is proposed to estimate the strength reduction factor for the self-centering structure with the flag-shaped model under near-fault pulse-like ground motions.

Longitudinal vibration analysis and suppression of electric wheel system driven by in-wheel motor considering unbalanced magnetic pull

2018 ◽  
Vol 233 (11) ◽  
pp. 2729-2745 ◽  
Author(s):  
Shuguang Zuo ◽  
Duoqiang Li ◽  
Yu Mao ◽  
Wenzhe Deng
Keyword(s):  
Neural Network ◽  
Finite Element ◽  
Dynamic Model ◽  
Electric Vehicles ◽  
Bp Neural Network ◽  
Longitudinal Vibration ◽  
Structural Parameters ◽  
Torque Ripple ◽  
Longitudinal Dynamics ◽  
Unbalanced Magnetic Pull

With the blowout of electric vehicles recently, the key parts of the electric vehicles driven by in-wheel motors named the electric wheel system become the core of development research. The torque ripple of the in-wheel motor mainly results in the longitudinal dynamics of the electric wheel system. The excitation sources are first analyzed through the finite element method, including the torque ripple induced by the in-wheel motor and the unbalanced magnetic pull produced by the relative motion between the stator and rotor. The accuracy of the finite element model is verified by the back electromotive force test of the in-wheel motor. Second, the longitudinal-torsional coupled dynamic model is established. The proposed model can take into account the unbalanced magnetic pull. Based on the model, the modal characteristics and the longitudinal dynamics of the electric wheel system are analyzed. The coupled dynamic model is verified by the vibration test of the electric wheel system. Two indexes, namely, the root mean square of longitudinal vibration of the stator and the signal-to-noise ratio of the tire slip rate, are proposed to evaluate the electric wheel longitudinal performance. The influence of unbalanced magnetic pull on the evaluation indexes of the longitudinal dynamics is analyzed. Finally, the influence of motor’s structural parameters on the average torque, torque ripple, and equivalent electromagnetic stiffness are analyzed through the orthogonal test. A surrogate model between the structural parameters of the in-wheel motor and the average torque, torque ripple, and equivalent electromagnetic stiffness is established based on the Bp neural network. The torque ripple and the equivalent electromagnetic stiffness are then reduced through optimizing the structural parameters of the in-wheel motor. It turns out that the proposed Bp neural network–based method is effective to suppress the longitudinal vibration of the electric wheel system.

Simulation of Palu IV Bridge Collapse using Near-Fault Ground Motions

2019 ◽  
Author(s):  
Iswandi Imran ◽  
Budi Santoso ◽  
Ary Pramudito ◽  
Muhammad Kadri Zamad
Keyword(s):  
Spatial Variation ◽  
Ground Motions ◽  
Time History ◽  
Seismic Demand ◽  
Fault Line ◽  
Near Fault ◽  
Failure Simulation ◽  
Bridge Collapse ◽  
Pulse Type ◽  
Bridge Bearing

<p>The earthquake near Palu, Sulawesi (Indonesia) on September 28, 2018 with a magnitude of M7.4 was caused by a shallow strike-slip of Palu-Koro fault. The earthquake and the subsequent tsunami have caused the collapse of the Ponulele Bridge (Palu IV Bridge). The steel box bowstring arch bridge was located near-fault regions (within 1,5 km from fault line) that have not been identified during the design process. This bridge may have been damaged by the presence of fling-step pulses in the near-fault pulse-type ground motions that increases the damaging potential of such ground motions. This paper presents the failure simulation of the bridge subjected to the near fault pulse type time history with spatial variation ground motions applied on multiple bridge supports. From the simulation, it is concluded that the near fault effects and the spatial variation of the ground motion have increased significantly the seismic demand on the bridge. This increase causes the failure in the anchorage of the bridge bearing system.</p>

scholarly journals Assessment of Earthquake Destructive Power to Structures Based on Machine Learning Methods

2020 ◽  
Vol 10 (18) ◽  
pp. 6210
Author(s):  
Ruihao Zheng ◽  
Chen Xiong ◽  
Xiangbin Deng ◽  
Qiangsheng Li ◽  
Yi Li
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Ground Motions ◽  
Low Frequency ◽  
Time History ◽  
Time History Analysis ◽  
Machine Learning Algorithms ◽  
Learning Networks ◽  
History Analysis ◽  
Deep Layers

This study presents a machine learning-based method for the destructive power assessment of earthquake to structures. First, the analysis procedure of the method is presented, and the backpropagation neural network (BPNN) and convolutional neural network (CNN) are used as the machine learning algorithms. Second, the optimized BPNN architecture is obtained by discussing the influence of a different number of hidden layers and nodes. Third, the CNN architecture is proposed based on several classical deep learning networks. To build the machine learning models, 50,570 time-history analysis results of a structural system subjected to different ground motions are used as training, validation, and test samples. The results of the BPNN indicate that the features extraction method based on the short-time Fourier transform (STFT) can well reflect the frequency-/time-domain characteristics of ground motions. The results of the CNN indicate that the CNN exhibits better accuracy (R2 = 0.8737) compared with that of the BPNN (R2 = 0.6784). Furthermore, the CNN model exhibits remarkable computational efficiency, the prediction of 1000 structures based on the CNN model takes 0.762 s, while 507.81 s are required for the conventional time-history analysis (THA)-based simulation. Feature visualization of different layers of the CNN reveals that the shallow to deep layers of the CNN can extract the high to low-frequency features of ground motions. The proposed method can assist in the fast prediction of engineering demand parameters of large-number structures, which facilitates the damage or loss assessments of regional structures for timely emergency response and disaster relief after earthquake.

scholarly journals Intelligent Classification Method for Tunnel Lining Cracks Based on PFC-BP Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Hao Ding ◽  
Xinghong Jiang ◽  
Ke Li ◽  
Hongyan Guo ◽  
Wenfeng Li
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Structural Parameters ◽  
Crack Depth ◽  
Tunnel Lining ◽  
Parameter Analysis ◽  
Training Data ◽  
Concrete Lining ◽  
Common Disease ◽  
Lining Structure

Tunnel lining crack is the most common disease and also the manifestation of other diseases, which widely exists in plain concrete lining structure. Proper evaluation and classification of engineering conditions directly relate to operation safety. Particle flow code (PFC) calculation software is applied in this study, and the simulation reliability is verified by using the laboratory axial compression test and 1 : 10 model experiment to calibrate the calculation parameters. Parameter analysis is carried out focusing on the load parameters, structural parameters, dimension, and direction which affect the crack diseases. Based on that, an evaluation index system represented by tunnel buried depth (H), crack position (P), crack length (L), crack width (W), crack depth (D), and crack direction (A) is put forward. The training data of the back propagation (BP) neural network which takes load-bearing safety and crack stability as the evaluation criteria are obtained. An expert system is introduced into the BP neural network for correction of prediction results, realizing classified dynamic optimization of complex engineering conditions. The results of this study can be used to judge the safety state of cracked lining structure and provide guidance to the prevention and control of crack diseases, which is significant to ensure the safety of tunnel operation.

scholarly journals Seismic Design of Bridges against Near-Fault Ground Motions Using Combined Seismic Isolation and Restraining Systems of LRBs and CDRs

2019 ◽  
Vol 2019 ◽  
pp. 1-11
Author(s):  
Xiaoli Li ◽  
Yan Shi
Keyword(s):  
Control System ◽  
Seismic Design ◽  
High Intensity ◽  
Seismic Isolation ◽  
Ground Motions ◽  
Time History ◽  
Nonlinear Time History Analysis ◽  
Near Fault ◽  
Combined Control ◽  
Quantitative Design

This paper focuses on the seismic isolation design of near-fault bridges under the seismic excitations of near-fault ground motions in high-intensity earthquake zones and proposes a combined control system using lead rubber bearings (LRBs) and cable displacement restrainers (CDRs) along with ductility seismic resistance for the reinforced concrete piers. As part of the performance-based seismic design framework, this study provides the quantitative design criteria for multilevel performance-based objectives of a combined control system under conditions of frequent earthquake (E1), design earthquake (medium earthquake), and rare earthquake (E2). Moreover, in this study, a preliminary performance-based seismic isolation design for a near-fault actual highway bridge in high-intensity earthquake zones (basic peak of ground acceleration 0.4 g) was developed. Using nonlinear time-history analysis of the actual bridge under near-fault ground motions, the feasibility of a performance-based design method was validated. Furthermore, to ensure the predicted performance of the isolated bridges during a strong earthquake, a relatively quantitative design in structural details derived from the stirrup ratio of piers, expansion joints gap, supported length of capping beams, and limited vertical displacement response was obtained.

Modeling on Hydrocyclone Separation Performance by Neural Network

2011 ◽  
Vol 105-107 ◽  
pp. 185-188
Author(s):  
Feng Qin He ◽  
Ping Zhou ◽  
Jian Gang Wang
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Structural Parameters ◽  
Input Parameter ◽  
Network Models ◽  
Separation Performance ◽  
Sampled Data ◽  
Neural Network Models

A 17-27-5 type BP neural network model was built, whose sampled data was got by hydrocyclone separation experiments; another 6-30-5 type BP neural network was also built, whose sampled data came from the simulation results of the LZVV of a hydrocyclone with CFD code FLUENT. The two neural network models also have good predictive validity aimed at hydrocyclone separation performance. It demonstrates LZVV structural parameters can embody hydrocyclone separation performance and reduce input parameter numbers of neural network model. It also indicates that the predictive model of hydrocyclone separation performance can be built by neural network.

Evaluation of artificial neural network-based formulations for tuned mass dampers

2021 ◽  
Vol 7 (1) ◽  
pp. 17
Author(s):  
Melda Yucel ◽  
Sinan Melih Nigdeli ◽  
Gebrail Bekdaş
Keyword(s):  
Neural Network ◽  
Time History ◽  
Seismic Structure ◽  
Tuned Mass Dampers ◽  
Near Fault ◽  
Metaheuristic Methods ◽  
Ann Models ◽  
Artificial Neural ◽  
Ground Motion Records ◽  
Near Fault Ground Motion

Tuned mass dampers (TMDs) are used to damp vibration of mechanical systems. TMDs are also used on structures to reduce the effects of strong forces such as winds and earthquakes. For the efficiency of TMD, optimization of TMD parameters is needed. Several classical formulations were proposed, but metaheuristic methods are generally used to find the best result. In addition, the metaheuristic based optimum results are used in machine learning of artificial intelligence-based models like artificial neural networks (ANN). These ANN models are also used in development of tuning equation via curve fitting. The classical and ANN-based formulations were found according to frequency domain responses. In the present study, the classical and ANN-based formulations were evaluated by comparing on time-history responses of seismic structure. In comparison, near-fault ground motion records including directivity pulses are used. The ANN based methods have advantages by providing smaller stroke requirement and damping for TMDs.

A Stochastic Model for Simulating Vertical Pulseless Near-Fault Seismic Ground Motions

2021 ◽  
Author(s):  
Xi Zhong Cui ◽  
Yong Xu Liu ◽  
Han Ping Hong
Keyword(s):  
Stochastic Model ◽  
Ground Motion ◽  
Ground Motions ◽  
Time History ◽  
Structural Deformation ◽  
Time Frequency ◽  
Motion Models ◽  
Near Fault ◽  
Simulation Techniques ◽  
Ground Motion Records

ABSTRACT The vertical near-fault seismic ground-motion component can cause significant structural deformation and damage, which can be evaluated from time history analysis using actual or synthetic ground-motion records. In this study, we propose a new stochastic model for the vertical pulseless near-fault ground motions that depends on earthquake magnitude, rupture distance, and site condition. The proposed model is developed based on the time–frequency characteristics of 606 selected actual vertical record components in strike-slip earthquakes. The use and validation of the model are presented using simulated records obtained by two simulation techniques. For the validation, the statistics of time–frequency-dependent power spectral acceleration estimated from the simulated records using the proposed stochastic model are compared with those from the actual records and the ground-motion models available in the literature.

Sign in / Sign up

Export Citation Format

Share Document