TY - THES A1 - Radmard Rahmani, Hamid T1 - Artificial Intelligence Approach for Seismic Control of Structures N2 - Abstract In the first part of this research, the utilization of tuned mass dampers in the vibration control of tall buildings during earthquake excitations is studied. The main issues such as optimizing the parameters of the dampers and studying the effects of frequency content of the target earthquakes are addressed. Abstract The non-dominated sorting genetic algorithm method is improved by upgrading generic operators, and is utilized to develop a framework for determining the optimum placement and parameters of dampers in tall buildings. A case study is presented in which the optimal placement and properties of dampers are determined for a model of a tall building under different earthquake excitations through computer simulations. Abstract In the second part, a novel framework for the brain learning-based intelligent seismic control of smart structures is developed. In this approach, a deep neural network learns how to improve structural responses during earthquake excitations using feedback control. Abstract Reinforcement learning method is improved and utilized to develop a framework for training the deep neural network as an intelligent controller. The efficiency of the developed framework is examined through two case studies including a single-degree-of-freedom system and a high-rise building under different earthquake excitation records. Abstract The results show that the controller gradually develops an optimum control policy to reduce the vibrations of a structure under an earthquake excitation through a cyclical process of actions and observations. Abstract It is shown that the controller efficiently improves the structural responses under new earthquake excitations for which it was not trained. Moreover, it is shown that the controller has a stable performance under uncertainties. KW - Erdbeben KW - seismic control KW - tuned mass damper KW - reinforcement learning KW - earthquake KW - machine learning KW - Operante Konditionierung KW - structural control Y1 - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20200417-41359 ER - TY - THES A1 - Damanik, Batta Septo Van Bahtiar T1 - Aerodynamic Analysis of Slender Vertical Structure and Response Control with Tuned Mass Damper N2 - Analysis of vortex induced vibration has gained more interest in practical held of civil engineering. The phenomenon often occurs in long and slender vertical structure like high rise building, tower, chimney or bridge pylon, which resulting in unfavorable responses and might lead to the collapse of the structures. The phenomenon appears when frequency of vortex shedding produced in the wake area of body meet the natural frequency of the structure. Even though this phenomenon does not necessarily generate a divergent amplitude response, the structure still may fail due to fatigue damage. To reduce the effect of vortex induced vibration, engineers widely use passive vibration response control system. In this case, the thesis studies the effect of tuned mass damper. The objective of this thesis is to simulate the effect of tuned mass damper in reducing unfavorable responses due to vortex induced vibration and initiated by numerical model validation with respect to wind tunnel test report. The reference structure that being used inside the thesis is Stonecutter Bridge, Hongkong. A numerical solver for computational uid dynamics named VX ow which developed by Morgenthal [6] is utilized for wind and structure simulation. The comparison between numerical model and wind tunnel result shows 10% maximum tip displacement diference in the model of full erection freestanding tower. The tuned mass damper (TMD) model itself built separately in finite element software SOFiSTiK, and the efective damping obtained from this model then applied inside input modal data of VX ow simulation. A single TMD with mass ratio of TMD 0.5% to the mass of first bending frequency, the maximum tip displacement is measured to be average 67% reduced. Considering construction limitation and robustness of TMD, the effects of multiple TMD inside a structure are also studied. An uncoupled procedure of applying aeroelastic loads obtained from VX ow inside finite element software SOFiSTiK is also done to observe the optimum distribution and optimum mass ratio of multiple tuned mass damper. The rest of the properties of TMD are calculated with Den Hartog's formula. The results are as follows: peak displacement in the case of multiple TMD that distributed with polynomial spacing achieve 7.8% more reduction performance than the one that distributed with equal spacing. Optimum mass of tuned mass damper achieved with ratio 1.25% mass of first bending frequency corresponds to across wind direction. KW - aerodynamic KW - wind KW - tuned mass damper KW - bridge KW - structure KW - Aerodynamic Y1 - 2015 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20151030-24714 ER -