• Smart Structures and Systems
• /
• 제31권3호
• /
• pp.247-257
• /
• 2023

In structural health monitoring of large-scale structures, optimal sensor placement plays an important role because of the high cost of sensors and their supporting instruments, as well as the burden of data transmission and storage. In this study, a vibration sensor placement algorithm based on deep reinforcement learning (DRL) is proposed, which can effectively solve non-convex, high-dimensional, and discrete combinatorial sensor placement optimization problems. An objective function is constructed to estimate the quality of a specific vibration sensor placement scheme according to the modal assurance criterion (MAC). Using this objective function, a DRL-based algorithm is presented to determine the optimal vibration sensor placement scheme. Subsequently, we transform the sensor optimal placement process into a Markov decision process and employ a DRL-based optimization algorithm to maximize the objective function for optimal sensor placement. To illustrate the applicability of the proposed method, two examples are presented: a 10-story braced frame and a sea-crossing bridge model. A comparison study is also performed with a genetic algorithm and particle swarm algorithm. The proposed DRL-based algorithm can effectively solve the discrete combinatorial optimization problem for vibration sensor placements and can produce superior performance compared with the other two existing methods.

• 한국소음진동공학회논문집
• /
• 제18권9호
• /
• pp.972-981
• /
• 2008

The blower which is installed in a FCEV(fuel cell electric vehicle) may cause noise due to misalignment and unbalance of mechanical components that rotate at high speed. One of the key points in efforts to minimize the noise radiation from a blower is the knowledge of the main radiating component and the relation between the surface vibration of a blower and the sound pressure. In this research, the blower model is developed based on FEM(finite element method). FE(finite element) model is reliable by correlation of frequencies and MAC(modal assurance criterion) values between EMA(experimental modal analysis) and FEA(finite element analysis). This model is applied to predict the vibration of a blower by using inverse force identification method and predict the radiating noise by using BEM(boundary element method). Comparing the frequencies of resonance and those mode shapes between EMA and FEA, a structural modification of the FE model is evaluated for reducing the parameters of the blower noise.

• 한국구조물진단유지관리공학회 논문집
• /
• 제27권4호
• /
• pp.1-10
• /
• 2023

구조물의 내진설계 시 지진력은 구조모델 수립 및 구조해석에 기반하여 산정되는데, 구조모델이 실제 구조물의 동특성치를 정확하게 반영하기 위해서는 실제 계측을 통한 보정이 요구된다. 본 연구에서는 실제 건물을 모사한 4층 골조 시험체를 대상으로 각 층별 가속도계를 부착하여 1축 진동대 실험을 수행하였다. 실험체의 주기는 실제 건축물의 주기와 유사하며, 수평부재의 무한강성을 고려하여 기둥은 이중곡률로 거동하도록 설계하였다. 입력지진파의 특성에 따른 영향을 고려하기 위해 다양한 주파수와 가속도 크기를 갖는 역사지진파와 인공지진파를 가력하였다. 동적응답신호를 통해 얻은 주파수응답함수를 이용하여 고유진동수와 감쇠비, 모드벡터를 도출하였으며, Mode assurance criterion(MAC)를 통해 입력지진파에 따른 모드벡터 간의 편차를 확인하였다. 또한 진동대 실험을 통해 도출된 감쇠비를 구조모델에 적용하였으며, 실험 결과와의 비교를 통하여 동특성 도출 방법을 검증하였다.

• Structural Engineering and Mechanics
• /
• 제58권2호
• /
• pp.277-300
• /
• 2016

Cold-formed steel (CFS) sections are becoming an increasingly popular solution for constructing floors in residential, healthcare and education buildings. Their reduced weight, however, makes them prone to excessive vibrations, increasing the need for accurate prediction of CFS floor modal properties. By combining experimental modal analysis of a full-scale CFS framed building and its floors and their numerical finite element (FE) modelling this paper demonstrates that the existing methods (based on the best engineering judgement) for predicting CFS floor modal properties are unreliable. They can yield over 40% difference between the predicted and measured natural frequencies for important modes of vibration. This is because the methods were adopted from other floor types (e.g., timber or standard steel-concrete composite floors) and do not take into account specific features of CFS floors. Using the adjusted and then updated FE model, featuring semi-rigid connections led to markedly improved results. The first four measured and calculated CFS floor natural frequencies matched exactly and all relevant modal assurance criterion (MAC) values were above 90%. The introduction of flexible supports and more realistic modelling of the floor boundary conditions, as well as non-structural $fa{\c{c}}ade$ walls, proved to be crucial in the development of the new more successful modelling strategy. The process used to develop 10 identified and experimentally verified FE modelling parameters is based on published information and parameter adjustment resulting from FE model updating. This can be utilised for future design of similar lightweight steel floors in prefabricated buildings when checking their vibration serviceability, likely to be their governing design criterion.

• Smart Structures and Systems
• /
• 제13권3호
• /
• pp.389-406
• /
• 2014

Optimal sensor placement techniques play a significant role in enhancing the quality of modal data during the vibration based health monitoring of civil structures, where many degrees of freedom are available despite a limited number of sensors. The literature has shown a shift in the trends for solving such problems, from expansion or elimination approach to the employment of heuristic algorithms. Although these heuristic algorithms are capable of providing a global optimal solution, their greatest drawback is the requirement of high computational effort. Because a highly efficient optimisation method is crucial for better accuracy and wider use, this paper presents an improved simulated annealing (SA) algorithm to solve the sensor placement problem. The algorithm is developed based on the sensor locations' coordinate system to allow for the searching in additional dimensions and to increase SA's random search performance while minimising the computation efforts. The proposed method is tested on a numerical slab model that consists of two hundred sensor location candidates using three types of objective functions; the determinant of the Fisher information matrix (FIM), modal assurance criterion (MAC), and mean square error (MSE) of mode shapes. Detailed study on the effects of the sensor numbers and cooling factors on the performance of the algorithm are also investigated. The results indicate that the proposed method outperforms conventional SA and Genetic Algorithm (GA) in the search for optimal sensor placement.