Neural Network Based Vibration Control of Seismically Excited Civil Structures

This study proposes a neural network based vibration control system designed to attenuate structural vibrations induced by an earthquake. Classical feedback control algorithms are susceptible to parameter changes. For structures with uncertain parameters they can even cause instability problems. The proposed neural network based control system can identify the structural properties of the system and avoids the above mentioned problems. In the present study it is assumed that a full state of the structure is known, which means the at each floor horizontal displacements and rotations about the vertical axis are measured. Additionally, it is assumed the acceleration signal coming from the earthquake is also available. The proposed neural control strategy is compared with the classical linear quadratic regulator (LQR) not only in terms of displacement responses, but also required control forces. Moreover, the influence of different weighting matrices on performance of the proposed control strategy has been presented.The effectiveness of the neuro-controller has been demonstrated on two numerical examples: a simple single degree of freedom (DOF) structure and a multi-DOF structure representing a twelve story building. Both structures under consideration have been excited with El Centro acceleration signal. The results of numerical simulations on the SDOF system indicate that using neuro-controller it would be possible to obtain smaller amplitudes as compared with the LQ regulator, but it would require higher control effort.

Download Full-text

Fuzzy neural network control algorithm for asymmetric building structure with active tuned mass damper

Journal of Vibration and Control ◽

10.1177/1077546320910003 ◽

2020 ◽

Vol 26 (21-22) ◽

pp. 2037-2049

Author(s):

Xiao Yan ◽

Zhao-Dong Xu ◽

Qing-Xuan Shi

Keyword(s):

Neural Network ◽

Control System ◽

Fuzzy Neural Network ◽

Linear Quadratic Regulator ◽

Tuned Mass Damper ◽

Linear Quadratic ◽

Mass Damper ◽

Fuzzy Neural ◽

Neural Network Algorithm ◽

Damper Control

Asymmetric structures experience torsional effects when subjected to seismic excitation. The resulting rotation will further aggravate the damage of the structure. A mathematical model is developed to study the translation and rotation response of the structure during seismic excitation. The motion equations of the structures which cover the translation and rotation are obtained by the theoretical derivations and calculations. Through the simulated computation, the translation and rotation response of the structure with the uncontrolled system, the tuned mass damper control system, and active tuned mass damper control system using linear quadratic regulator algorithm are compared to verify the effectiveness of the proposed active control system. In addition, the linear quadratic regulator and fuzzy neural network algorithm are used to the active tuned mass damper control system as a contrast group to study the response of the structure with different active control method. It can be concluded that the structure response has a significant reduction by using active tuned mass damper control system. Furthermore, it can be also found that fuzzy neural network algorithm can replace the linear quadratic regulator algorithm in an active control system. Because fuzzy neural network algorithm can control the process on an uncertain mathematical model, it has more potential in practical applications than the linear quadratic regulator control method.

Download Full-text

Swing Vibration Control of Suspended Structure Using Active Rotary Inertia Driver System: Parametric Analysis and Experimental Verification

Applied Sciences ◽

10.3390/app9153144 ◽

2019 ◽

Vol 9 (15) ◽

pp. 3144 ◽

Cited By ~ 12

Author(s):

Chunwei Zhang ◽

Hao Wang

Keyword(s):

Mathematical Model ◽

Control System ◽

Vibration Control ◽

Parametric Analysis ◽

Linear Quadratic Regulator ◽

Shaking Table ◽

Rotary Inertia ◽

System Control ◽

Linear Quadratic ◽

Control Effectiveness

The Active Rotary Inertia Driver (ARID) system is a novel vibration control system that can effectively mitigate the swing vibration of suspended structures. Parametric analysis is carried out using Simulink based on the mathematical model and the effectiveness is further validated by a series of experiments. Firstly, the active controller is designed based on the system mathematical model and the LQR (linear quadratic regulator) algorithm. Next, the parametric analysis is carried out using Simulink to study the key parameters such as the coefficient of the control algorithm, the rotary inertia ratio. Lastly, the ARID system control effectiveness and the parametric analysis results are further validated by the shaking table experiments. The effectiveness and robustness of the ARID system are well verified. The dynamic characteristics of this system are further studied, and the conclusions of this paper provide a theoretical basis for further development of such unique control system.

Download Full-text

Active Vibration Control of the Sting Used in Wind Tunnel: Comparison of Three Control Algorithms

Shock and Vibration ◽

10.1155/2018/1905049 ◽

2018 ◽

Vol 2018 ◽

pp. 1-10 ◽

Cited By ~ 8

Author(s):

Xing Shen ◽

Yuke Dai ◽

Mingxuan Chen ◽

Lei Zhang ◽

Li Yu

Keyword(s):

Optimal Control ◽

Wind Tunnel ◽

Vibration Control ◽

Control Algorithm ◽

Active Vibration Control ◽

Linear Quadratic Regulator ◽

Real Time Control ◽

Linear Quadratic ◽

Control Effort ◽

Active Vibration

In wind tunnel tests, cantilever stings are often used as model-mount in order to reduce flow interference on experimental data. In this case, however, large-amplitude vibration and low-frequency vibration are easily produced on the system, which indicates the potential hazards of gaining inaccurate data and even damaging the structure. This paper details three algorithms, respectively, Classical PD Algorithm, Artificial Neural Network PID (NNPID), and Linear Quadratic Regulator (LQR) Optimal Control Algorithm, which can realize active vibration control of sting used in wind tunnel. The hardware platform of the first-order vibration damping system based on piezoelectric structure is set up and the real-time control software is designed to verify the feasibility and practicability of the algorithms. While the PD algorithm is the most common method in engineering, the results show that all the algorithms can achieve the purpose of over 80% reduction, and the last two algorithms perform even better. Besides, self-tuning is realized in NNPID, and with the help of the Observer/Kalman Filter Identification (OKID), LQR optimal control algorithm can make the control effort as small as possible. The paper proves the superiority of NNPID and LQR algorithms and can be an available reference for vibration control of wind tunnel system.

Download Full-text

Robustness of the Active Rotary Inertia Driver System for Structural Swing Vibration Control Subjected to Multi-Type Hazard Excitations

Applied Sciences ◽

10.3390/app9204391 ◽

2019 ◽

Vol 9 (20) ◽

pp. 4391 ◽

Cited By ~ 5

Author(s):

Chunwei Zhang ◽

Hao Wang

Keyword(s):

Control System ◽

Vibration Control ◽

Equations Of Motion ◽

Linear Quadratic Regulator ◽

Numerical Analyses ◽

Rotary Inertia ◽

Experimental Investigations ◽

Linear Quadratic ◽

Earthquake Excitation ◽

Mass Damper

In traditional structural disaster prevention design, the effects of various disasters on structures are usually considered separately, and the effects of multi-type hazards are rarely considered. The traditional Tuned Mass Damper (TMD) and Active Mass Damper/Driver (AMD) are ineffective for the control of swing vibration. The Tuned Rotary Inertia Damper (TRID) system has the problems of being ineffective under multi-type hazard excitation and exhibiting a limited robustness. The Active Rotary Inertia Driver (ARID) system is proposed to solve these problems and the robustness of such an active control system is investigated in this paper. Firstly, the equations of motion corresponding to the in-plane swing vibration of the suspended structure with the ARID/TRID system are established. The control algorithm for the ARID system is designed based on the Linear Quadratic Regulator (LQR) algorithm. Next, numerical analyses carried out using Simulink are presented. Then, numerical analyses and experimental investigations corresponding to five working conditions, i.e., free vibration, forced vibration, sweep excitation, earthquake excitation, and sea wave excitation, are introduced. Lastly, the numerical analyses and experimental results of the ARID system, and numerical results of the TRID system, are compared to demonstrate the effectiveness and robustness of the ARID control system. It can be concluded that the ARID system is effective and feasible in structural swing vibration control and it exhibits a better control robustness than the TRID system. Furthermore, the feasibility of applying the ARID control system to multi-type hazard excitations is validated.

Download Full-text

A Unified Control Strategy of Distributed Generation for Grid-Connected and Islanded Operation Conditions Using an Artificial Neural Network

Sustainability ◽

10.3390/su13116388 ◽

2021 ◽

Vol 13 (11) ◽

pp. 6388

Author(s):

Karim M. El-Sharawy ◽

Hatem Y. Diab ◽

Mahmoud O. Abdelsalam ◽

Mostafa I. Marei

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Control System ◽

Distributed Generation ◽

Control Strategy ◽

Current Control ◽

Operating Conditions ◽

Pi Controllers ◽

Artificial Neural ◽

The Stability

This article presents a control strategy that enables both islanded and grid-tied operations of a three-phase inverter in distributed generation. This distributed generation (DG) is based on a dramatically evolved direct current (DC) source. A unified control strategy is introduced to operate the interface in either the isolated or grid-connected modes. The proposed control system is based on the instantaneous tracking of the active power flow in order to achieve current control in the grid-connected mode and retain the stability of the frequency using phase-locked loop (PLL) circuits at the point of common coupling (PCC), in addition to managing the reactive power supplied to the grid. On the other side, the proposed control system is also based on the instantaneous tracking of the voltage to achieve the voltage control in the standalone mode and retain the stability of the frequency by using another circuit including a special equation (wt = 2πft, f = 50 Hz). This utilization provides the ability to obtain voltage stability across the critical load. One benefit of the proposed control strategy is that the design of the controller remains unconverted for other operating conditions. The simulation results are added to evaluate the performance of the proposed control technology using a different method; the first method used basic proportional integration (PI) controllers, and the second method used adaptive proportional integration (PI) controllers, i.e., an Artificial Neural Network (ANN).

Download Full-text

Neural Network Based Contact Force Control Algorithm for Walking Robots

Sensors ◽

10.3390/s21010287 ◽

2021 ◽

Vol 21 (1) ◽

pp. 287

Author(s):

Byeongjin Kim ◽

Soohyun Kim

Keyword(s):

Neural Network ◽

Contact Force ◽

Force Control ◽

Control Algorithm ◽

Position Control ◽

Linear Quadratic Regulator ◽

Walking Robots ◽

Test Model ◽

Linear Quadratic ◽

Contact Force Control

Walking algorithms using push-off improve moving efficiency and disturbance rejection performance. However, the algorithm based on classical contact force control requires an exact model or a Force/Torque sensor. This paper proposes a novel contact force control algorithm based on neural networks. The proposed model is adapted to a linear quadratic regulator for position control and balance. The results demonstrate that this neural network-based model can accurately generate force and effectively reduce errors without requiring a sensor. The effectiveness of the algorithm is assessed with the realistic test model. Compared to the Jacobian-based calculation, our algorithm significantly improves the accuracy of the force control. One step simulation was used to analyze the robustness of the algorithm. In summary, this walking control algorithm generates a push-off force with precision and enables it to reject disturbance rapidly.

Download Full-text

Satellite Attitude Control System Design Taking into Account the Fuel Slosh and Flexible Dynamics

Mathematical Problems in Engineering ◽

10.1155/2014/820586 ◽

2014 ◽

Vol 2014 ◽

pp. 1-8 ◽

Cited By ~ 7

Author(s):

Alain G. de Souza ◽

Luiz C. G. de Souza

Keyword(s):

Control System ◽

Attitude Control ◽

Center Of Mass ◽

Rigid Motion ◽

Linear Quadratic Regulator ◽

Comparative Investigation ◽

Attitude Control System ◽

Linear Quadratic ◽

Deformable Structure ◽

Fuel Slosh

The design of the spacecraft Attitude Control System (ACS) becomes more complex when the spacecraft has different type of components like, flexible solar panels, antennas, mechanical manipulators and tanks with fuel. The interaction between the fuel slosh motion, the panel’s flexible motion and the satellite rigid motion during translational and/or rotational manoeuvre can change the spacecraft center of mass position damaging the ACS pointing accuracy. This type of problem can be considered as a Fluid-Structure Interaction (FSI) where some movable or deformable structure interacts with an internal fluid. This paper develops a mathematical model for a rigid-flexible satellite with tank with fuel. The slosh dynamics is modelled using a common pendulum model and it is considered to be unactuated. The control inputs are defined by a transverse body fixed force and a moment about the centre of mass. A comparative investigation designing the satellite ACS by the Linear Quadratic Regulator (LQR) and Linear Quadratic Gaussian (LQG) methods is done. One has obtained a significant improvement in the satellite ACS performance and robustness of what has been done previously, since it controls the rigid-flexible satellite and the fuel slosh motion, simultaneously.

Download Full-text

Lookup Table and Neural Network Hybrid Strategy for Wind Turbine Pitch Control

Sustainability ◽

10.3390/su13063235 ◽

2021 ◽

Vol 13 (6) ◽

pp. 3235

Author(s):

J. Enrique Sierra-García ◽

Matilde Santos

Keyword(s):

Neural Network ◽

Wind Turbine ◽

Control Strategy ◽

Neural Control ◽

Mapping Function ◽

Energy System ◽

Lookup Table ◽

Hybrid Strategy ◽

Pitch Control ◽

The Neural Network

Wind energy plays a key role in the sustainability of the worldwide energy system. It is forecasted to be the main source of energy supply by 2050. However, for this prediction to become reality, there are still technological challenges to be addressed. One of them is the control of the wind turbine in order to improve its energy efficiency. In this work, a new hybrid pitch-control strategy is proposed that combines a lookup table and a neural network. The table and the RBF neural network complement each other. The neural network learns to compensate for the errors in the mapping function implemented by the lookup table, and in turn, the table facilitates the learning of the neural network. This synergy of techniques provides better results than if the techniques were applied individually. Furthermore, it is shown how the neural network is able to control the pitch even if the lookup table is poorly designed. The operation of the proposed control strategy is compared with the neural control without the table, with a PID regulator, and with the combination of the PID and the lookup table. In all cases, the proposed hybrid control strategy achieves better results in terms of output power error.

Download Full-text

The linear quadratic regular algorithm-based control system of the direct current motor

International Journal of Power Electronics and Drive Systems (IJPEDS) ◽

10.11591/ijpeds.v10.i2.pp768-776 ◽

2019 ◽

Vol 10 (2) ◽

pp. 768

Author(s):

Trong-Thang Nguyen

Keyword(s):

Control System ◽

Direct Current ◽

State Space Model ◽

Linear Quadratic Regulator ◽

Response Speed ◽

Dc Motor ◽

Linear Quadratic ◽

Lqr Controller ◽

Mathematical Equations ◽

Feed Forward Controller

<span>This research aims to propose an optimal controller for controlling the speed of the Direct Current (DC) motor. Based on the mathematical equations of DC Motor, the author builds the equations of the state space model and builds the linear quadratic regulator (LQR) controller to minimize the error between the set speed and the response speed of DC motor. The results of the proposed controller are compared with the traditional controllers as the PID, the feed-forward controller. The simulation results show that the quality of the control system in the case of LQR controller is much higher than the traditional controllers. The response speed always follows the set speed with the short conversion time, there isn't overshoot. The response speed is almost unaffected when the torque impact on the shaft is changed.</span>

Download Full-text

Experimental implementation of artificial neural network-based active vibration control & chatter suppression

10.32920/ryerson.14663340.v1 ◽

2021 ◽

Author(s):

Yong Xia

Keyword(s):

Neural Network ◽

Neural Networks ◽

Artificial Neural Network ◽

Control System ◽

Vibration Control ◽

Control Strategies ◽

Active Vibration Control ◽

Chatter Suppression ◽

Active Vibration ◽

Artificial Neural

Vibration control strategies strive to reduce the effect of harmful vibrations such as machining chatter. In general, these strategies are classified as passive or active. While passive vibration control techniques are generally less complex, there is a limit to their effectiveness. Active vibration control strategies, which work by providing an additional energy supply to vibration systems, on the other hand, require more complex algorithms but can be very effective. In this work, a novel artificial neural network-based active vibration control system has been developed. The developed system can detect the sinusoidal vibration component with the highest power and suppress it in one control cycle, and in subsequent cycles, sinusoidal signals with the next highest power will be suppressed. With artificial neural networks trained to cover enough frequency and amplitude ranges, most of the original vibration can be suppressed. The efficiency of the proposed methodology has been verified experimentally in the vibration control of a cantilever beam. Artificial neural networks can be trained automatically for updated time delays in the system when necessary. Experimental results show that the developed active vibration control system is real time, adaptable, robust, effective and easy to be implemented. Finally, an experimental setup of chatter suppression for a lathe has been successfully implemented, and the successful techniques used in the previous artificial neural network-based active vibration control system have been utilized for active chatter suppression in turning.

Download Full-text