scholarly journals Development of Seismic Response Simulation Model for Building Structures with Semi-Active Control Devices Using Recurrent Neural Network

2020 ◽  
Vol 10 (11) ◽  
pp. 3915
Author(s):  
Hyun-Su Kim
Keyword(s):  
Neural Network ◽  
Control System ◽  
Seismic Response ◽  
Active Control ◽  
Recurrent Neural Network ◽  
Ground Motions ◽  
Building Structures ◽  
Building Structure ◽  
Control Devices ◽  
Story Building

A structural analysis model to represent the dynamic behavior of building structure is required to develop a semi-active seismic response control system. Although the finite element method (FEM) is the most widely used method for seismic response analysis, when the FEM is applied to the dynamic analysis of building structures with nonlinear semi-active control devices, the computational effort required for the simulation for optimal design of the semi-active control system can be considerable. To solve this problem, this paper used recurrent neural network (RNN) to make a time history response simulation model for building structures with a semi-active control system. Example structures were selected of an 11-story building structure with a semi-active tuned mass damper (TMD), and a 27-story building having a semi-active mid-story isolation system. A magnetorheological damper was used as the semi-active control device. Five historical earthquakes and five artificial ground motions were used as ground excitations to train the RNN model. Two artificial ground motions and one historical earthquake, which were not used for training, were used to verify the developed the RNN model. Compared to the FEM model, the developed RNN model could effectively provide very accurate seismic responses, with significantly reduced computational cost.

Disturbance learning controller design for unmanned surface vehicle using LSTM technique of recurrent neural network

2021 ◽  
pp. 1-11
Author(s):  
Sang-Ki Jeong ◽  
Dea-Hyeong Ji ◽  
Ji-Youn Oh ◽  
Jung-Min Seo ◽  
Hyeung-Sik Choi
Keyword(s):  
Neural Network ◽  
Control System ◽  
Flow Velocity ◽  
Recurrent Neural Network ◽  
Pid Controller ◽  
Short Term Memory ◽  
Ocean Currents ◽  
Ocean Current ◽  
Movement Speed ◽  
Marine Research

In this study, to effectively control small unmanned surface vehicles (USVs) for marine research, characteristics of ocean current were learned using the long short-term memory (LSTM) model algorithm of a recurrent neural network (RNN), and ocean currents were predicted. Using the results, a study on the control of USVs was conducted. A control system model of a small USV equipped with two rear thrusters and a front thruster arranged horizontally was designed. The system was also designed to determine the output of the controller by predicting the speed of the following currents and utilizing this data as a system disturbance by learning data from ocean currents using the LSTM algorithm of a RNN. To measure ocean currents on the sea when a small USV moves, the speed and direction of the ship’s movement were measured using speed, azimuth, and location (latitude and longitude) data from GPS. In addition, the movement speed of the fluid with flow velocity is measured using the installed flow velocity measurement sensor. Additionally, a control system was designed to control the movement of the USV using an artificial neural network-PID (ANN-PID) controller [12]. The ANN-PID controller can manage disturbances by adjusting the control gain. Based on these studies, the control results were analyzed, and the control algorithm was verified through a simulation of the applied control system [8, 9].

Optimal tuned direct adaptive controller for seismic protecting of structures

2021 ◽  
pp. 1045389X2098878
Author(s):  
Amin Hosseini ◽  
Touraj Taghikhany ◽  
Milad Jahangiri
Keyword(s):  
Sensitivity Analysis ◽  
Adaptive Control ◽  
Optimization Problem ◽  
Adaptive Controller ◽  
Sensitivity Analyses ◽  
Building Structures ◽  
Building Structure ◽  
The Past ◽  
Innovative Method ◽  
Story Building

In the past few years, many studies have proved the efficiency of Simple Adaptive Control (SAC) in mitigating earthquakes’ damages to building structures. Nevertheless, the weighting matrices of this controller should be selected after a large number of sensitivity analyses. This step is time-consuming and it will not necessarily yield a controller with optimum performance. In the current study, an innovative method is introduced to tuning the SAC’s weighting matrices, which dispenses with excessive sensitivity analysis. In this regard, we try to define an optimization problem using intelligent evolutionary algorithm and utilized control indices in an objective function. The efficiency of the introduced method is investigated in 6-story building structure equipped with magnetorheological dampers under different seismic actions with and without uncertainty in the model of the proposed structure. The results indicate that the controller designed by the introduced method has a desirable performance under different conditions of uncertainty in the model. Furthermore, it improves the seismic performance of structure as compared to controllers designed through sensitivity analysis.

Seismic Response Control for Four High-Rise Building Structures Using Connected Control Method

2007 ◽  
Author(s):  
Kazuto Seto ◽  
Chinori Iio ◽  
Shigeru Inaba ◽  
Shingo Mitani ◽  
Fadi Dohnal ◽  
...  
Keyword(s):  
Seismic Response ◽  
Active Control ◽  
Control Method ◽  
Control Force ◽  
Building Structures ◽  
Response Control ◽  
Control Approach ◽  
Seismic Response Control ◽  
High Rise ◽  
Lq Control

This paper presents a vibration control method for multiple high-rise buildings against large earthquake motion. This method is called as “Connected Control Method (CCM)” and has the merit of obtaining enough control force to protect high-rise buildings from large earthquakes using passive and semiactive devices. In this paper, first a modeling approach for four scaled building structures is shown and effectiveness of the CCM using LQ control approach for them is demonstrated by seismic response control results. Next, in order to reduce the supplied power, a semi-active control approach in place of active control is applied for the CCM. For this purpose, a new MR damper is developed and designed to have a close performance with results of the LQ control. This performance is verified by measured frequency responses.

Semi-Active Control of Structural Systems Aiming to Approximate the Performance of the Targeted Active Control Law: Output Emulation Approach

2013 ◽  
Author(s):  
Kazuhiko Hiramoto ◽  
Taichi Matsuoka ◽  
Katsuaki Sunakoda
Keyword(s):  
Control System ◽  
Active Control ◽  
Variable Parameter ◽  
Control Law ◽  
Structural Systems ◽  
Control Force ◽  
Control Performance ◽  
Control Devices ◽  
Active Control System ◽  
Control Output

As a method for semi-active control of structural systems, the active-control-based method that emulates the control force of a targeted active control law by semi-active control devices has been studied. In the active-control-based method, the semi-active control devices are not necessarily able to generate the targeted active control force because of the dissipative nature of those devices. In such a situation, the meaning of the targeted active control law becomes unclear in the sense of the control performance achieved by the resulting semi-active control system. In this study, a new semi-active control strategy that approximates the control output (not the control force) of the targeted active control is proposed. The variable parameter of the semi-active control device is selected at every time instant so that the predicted control output of the semi-active control system becomes close to the corresponding predicted control output of the targeted active control as much as possible. Parameters of the targeted active control law are optimized in the premise of the above “output emulation” strategy so that the control performance of the semi-active control becomes good and the “error” of the achieved control performance between the targeted active control and the semi-active control becomes small.

Simulation and analysis of a vertically irregular building subjected to near-fault ground motions

2020 ◽  
Vol 36 (3) ◽  
pp. 1485-1516
Author(s):  
Jui-Liang Lin ◽  
Wen-Hui Chen ◽  
Fu-Pei Hsiao ◽  
Yuan-Tao Weng ◽  
Wen-Cheng Shen ◽  
...  
Keyword(s):  
Numerical Model ◽  
Seismic Response ◽  
Ground Motion ◽  
Ground Motions ◽  
Far Field ◽  
Near Fault ◽  
Study Results ◽  
Rc Building ◽  
Near Fault Ground Motion ◽  
Story Building

A shaking table test of a three-story reinforced concrete (RC) building was conducted. The tested building is vertically irregular because of the first story’s elevated height and the third story’s added RC walls. In addition to far-field ground motions, near-fault ground motions were exerted on this building. A numerical model of the three-story building was constructed. Comparing with the test results indicates that the numerical model is satisfactory for simulating the seismic response of the three-story building. This validated numerical model was then further applied to look into two issues: the effective section rigidities of RC members and the effects of near-fault ground motions. The study results show the magnitude of the possible discrepancy between the actual seismic response and the estimated seismic response, when the effective section rigidities of the RC members are treated as in common practice. An incremental dynamic analysis of the three-story RC building subjected to one far-field and one near-fault ground motion, denoted as CHY047 and TCU052, respectively, was conducted. In comparison with the far-field ground motion, the near-fault ground motion is more destructive to this building. In addition, the effect of the selected near-fault ground motion (i.e. TCU052) on the building’s collapse is clearly identified.

Application of Magnetorheological Damper Semi-Active Control Based on Artificial Neural Networks

2010 ◽  
Vol 171-172 ◽  
pp. 654-658
Author(s):  
De Kun Yue ◽  
Qi Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
System Identification ◽  
Active Control ◽  
Bp Neural Network ◽  
Structural Response ◽  
Magnetorheological Damper ◽  
Building Structure ◽  
Artificial Neural

Uncertainty for the building structure and nonlinear, this simulation of a multi-storey structure under earthquake is presented based on the BP neural network and system identification, controller will be built to effectively reduce the structural response, and to strengthen the unique damper performance.

A Hierarchical Fuzzy-Neural Multi-Model Applied in Nonlinear Systems Identification and Control

2013 ◽  
Vol 347-350 ◽  
pp. 617-622
Author(s):  
Feng Ye ◽  
Wei Min Qi
Keyword(s):  
Neural Network ◽  
Control System ◽  
Recurrent Neural Network ◽  
Systems Design ◽  
Membership Functions ◽  
Neural Network Models ◽  
Trajectory Tracking Control ◽  
Fuzzy Neural ◽  
Systems Identification ◽  
And Control

The paper brings forward a hierarchical fuzzy-neural multi-model with recurrent neural procedural consequent par for systems identification, states estimation and adaptive control of complex nonlinear plants. The parameters and states of the local recurrent neural network models are used for a local direct and indirect adaptive trajectory tracking control systems design. The designed local control laws are coordinated by a fuzzy rule-based control system. The upper level defuzzyfication is performed by a recurrent neural network. The applicability of the proposed intelligent control system is confirmed by simulation examples and by a DC-motor identification and control experimental results. Two main cases of a reference and plant output fuzzyfication are considereda two membership functions without overlapping and a three membership functions with overlapping. In both cases a good convergent results are obtained.

Sign in / Sign up

Export Citation Format

Share Document