• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.557-569
• /
• 2022

Vibration-based structural health monitoring (SHM) is crucial for the dynamic maintenance of civil building structures to protect property security and the lives of the public. Analyzing these vibrations with modern artificial intelligence and deep learning (DL) methods is a new trend. This paper proposed an unsupervised deep learning method based on a convolutional autoencoder (CAE), which can overcome the limitations of conventional supervised deep learning. With the convolutional core applied to the DL network, the method can extract features self-adaptively and efficiently. The effectiveness of the method in detecting damage is then tested using a benchmark model. Thereafter, this method is used to detect damage and instant disaster events in a rubber bearing-isolated gymnasium structure. The results indicate that the method enables the CAE network to learn the intact vibrations, so as to distinguish between different damage states of the benchmark model, and the outcome meets the high-dimensional data distribution characteristics visualized by the t-SNE method. Besides, the CAE-based network trained with daily vibrations of the isolating layer in the gymnasium can precisely recover newly collected vibration and detect the occurrence of the ground motion. The proposed method is effective at identifying nonlinear variations in the dynamic responses and has the potential to be used for structural condition assessment and safety warning.

• Advances in Computational Design
• /
• v.7 no.1
• /
• pp.81-98
• /
• 2022

This study presents the application of two indices for the locating of cracks in Reinforced Concrete (RC) structures, as well as the development of their modified forms to overcome limitations. The first index is based on mode shape curvature and the second index is based on the fourth derivative of the mode shape. In order to confirm the indices' effectiveness, both eigenvalues coupled with nonlinear static analyses were carried out and the eigenvectors for two different damage locations and intensities of load were obtained from the finite element model of RC beams. The values of the damage-locating indices derived using both indices were then compared. Generally, the mode shape curvature-based index suffered from insensitivity when attempting to detect the damage location; this also applied to the mode shape fourth derivative-based index at lower modes. However, at higher modes, the mode shape fourth derivative-based index gave an acceptable indication of the damage location. Both the indices showed inconsistencies and anomalies at the supports. This study proposed modification to both indices to overcome identified flaws. The results proved that modified forms exhibited better sensitivity for identifying the damage location. In addition, anomalies at the supports were eliminated.

• Journal of Korea Water Resources Association
• /
• v.56 no.10
• /
• pp.655-665
• /
• 2023

In this study, unit hydrographs are calculated when precipitations of 10 scales instantaneously occurs in a virtual watershed with a constant slope and roughness. Then, the relationship between the peak flow rate and the peak occurrence time of the unit hydrograph was calculated for the precipitation scale, respectively. At this time, the virtual watershed simplified with a rhombic shape, a constant slope, and a flow condition with a certain roughness was applied instead of a natural watershed in order to understand the effect the precipitation scale has on the peak value of the unit hydrograph. And it was assumed that the precipitation in the basin was effective rainfall and the runoff was direct runoff, and the runoff flowed in a straight, uniform flow from the drop point to the outlet. The relationship between the peak flow and the peak occurrence time of the unit hydrograph was calculated in the case of 10 types of precipitation scales of 10 mm, 40 mm, 90 mm, 160 mm, 250 mm, 360 mm, 640 mm, 1,000 mm, 1,210 mm, and 1,690 mm of effective precipitation. A noteworthy achievement of this study is that, even without the storage effect of the watershed, as the scale of precipitation increases, the depth of runoff increases, so the flow rate in the watershed increases and the distance per unit time increases, so the peak flow rate increases and the peak occurrence time increases. This is a nonlinear characteristic of watershed runoff.

• Korean Chemical Engineering Research
• /
• v.52 no.5
• /
• pp.581-586
• /
• 2014

Main objects for wastewater treatment operation are to maintain effluent water quality and minimize operation cost. However, the optimal operation is difficult because of the change of influent flow rate and concentrations, the nonlinear dynamics of microbiology growth rate and other environmental factors. Therefore, many wastewater treatment plants are operated for much more redundant oxygen or chemical dosing than the necessary. In this study, the optimal control scheme for dissolved oxygen (DO) is suggested to prevent over-aeration and the reduction of the electric cost in plant operation while maintaining the dissolved oxygen (DO) concentration for the metabolism of microorganisms in oxic reactor. The oxygen uptake rate (OUR) is real-time measured for the identification of influent characterization and the identification of microorganisms' oxygen requirement in oxic reactor. Optimal DO set-point needed for the micro-organism is suggested based on real-time measurement of oxygen uptake of micro-organism and the control of air blower. Therefore, both stable effluent quality and minimization of electric cost are satisfied with a suggested optimal set-point decision system by providing the necessary oxygen supply requirement to the micro-organisms coping with the variations of influent loading.

• Journal of Navigation and Port Research
• /
• v.31 no.6
• /
• pp.447-454
• /
• 2007

To assess the port development and maritime traffic environment, the future traffic volume has been estimated using the number of inbound and outbound vessel for a specific port. The estimation of future traffic volume should be considered as an important factor to establish the degree of fairway congestion, the determination of fairway width and the operational role. Until now, the number of in and out vessel for the port has been only estimated mainly, but the type and size of inbound and outbound ships are different depending on the port's characteristics. So, it is difficult to estimate the future traffic volume using the change of only one item. This paper calculates the future traffic volume using the marine traffic characteristic factors as the number of coastal ship and ocean-going ship, the size of ship and the change of cargo volume per a ship etc. And it compared with the results of Artificial Neural Network(ANN) for accurate identification of nonlinear system.

• Journal of the Society of Naval Architects of Korea
• /
• v.55 no.5
• /
• pp.401-414
• /
• 2018

Planing hull type ships are often equipped with interceptor or trim tab to improve the excessive trim angle which leads to poor resistance and sea keeping performances. The purpose of this study is to design a controller to control the attitude of the ship by controllable stern interceptor and validate the effectiveness of the attitude control by the towing tank test. Embedded controller, servo motor and controllable stern interceptor system were equipped with planing hull type model ship. Prior to designing the control algorithm, a model test was performed to identify the system dynamic model of the planing hull type ship including the stern interceptor. The matrix components of model were optimized by Genetic Algorithm. Using the identified model, PID controller which is a classical controller and sliding mode controller which is a nonlinear robust controller were designed. Gain tuning of the controllers and running simulation was conducted before the towing tank test. Inserting the designed control algorithm into the embedded controller of the model ship, the effectiveness of the active control of the stern interceptor was validated by towing tank test. In still water test with small disturbance, the sliding mode controller showed better performance of canceling the disturbance and the steady-state control performance than the PID controller.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.2
• /
• pp.215-221
• /
• 2006

This paper is concerned with the control of multiple nonlinearities included in a humanoid robot system. A humanoid robot has some problems such as the structural instability, which leads to consider the control of multiple nonlinearities caused by driver parts as well as gear reducer. Saturation and backlash are typical examples of nonlinearities in the system. The conventional algorithms of backlash control were fuzzy algorithm, disturbance observer and neural network, etc. However, it is not easy to control the system by employing only single algorithm since the system usually includes multiple nonlinearities. In this paper, a switching Pill is considered for a control of saturation and a dual feedback algorithm is proposed for a backlash control. To implement the above algorithms, the system identification is firstly performed for the minimization of the difference between the results of simulation and experiment, and then the switching Pill gains are determined using genetic algorithm with some heuristic approach. The performance of the switching Pill controller for saturation and the dual feedback for backlash control is investigated through the simulation. Finally, it is shown that the implemented control system has good results and can be applied to the real humanoid robot system ISHURO.

• Journal of Energy Engineering
• /
• v.23 no.2
• /
• pp.49-56
• /
• 2014

It is important to keep stable effluent water quality and minimize operation cost in biological wastewater treatment plant. However, the optimal operation is difficult because of the change of influent flow rate and concentrations, the nonlinear dynamics of microbiology growth rate and other environmental factors. Therefore, many wastewater treatment plants are operated for much more redundant oxygen or chemical dosing than the necessary. In this study, the optimal control scheme for dissolved oxygen (DO) is suggested to prevent over-aeration and the reduction of the electric cost in plant operation while maintaining the dissolved oxygen (DO) concentration for the metabolism of microorganisms in oxic reactor. For optimal control, The oxygen uptake rate (OUR) is realtime measured for the identification of influent characterization and the identification of microorganisms' oxygen requirement in oxic reactor. Optimal DO seT-Point needed for the microorganism is suggested based on real time measurement of oxygen uptake of microorganism and the control of air blower. Therefore, both stable effluent quality and minimization of electric cost are satisfied with a suggested optimal setpoint decision system by providing the necessary oxygen supply requirement to the microorganisms coping with the variations of influent loading.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.28 no.3
• /
• pp.275-281
• /
• 2015

In this study, vertical motion of a Tuned Liquid Column Damper(TLCD) is measured by a variable voltage measurement system in the electric field and design parameters of the TLCD are determined. First, nonlinear damping term of the TLCD is replaced as the equivalent viscous damping term. The natural frequency and damping ratio of dynamic characteristics of the TLCD are verified. In addition, a novel liquid level measurement system is developed for measuring vertical motion of the TLCD. For the experimental achievement, experimental characterizations of natural frequency and damping ratio of the TLCD are undertaken utilizing the developed variable voltage sensing. Also, shake table testing is performed to determine the dynamic characteristics of the TLCD. As a result, the feasibility of the proposed liquid level measurement system is verified by comparison with the capacitive type wavemeter.

• Journal of Korean Association for Spatial Structures
• /
• v.20 no.2
• /
• pp.51-58
• /
• 2020

Recently, deep learning that is the most popular and effective class of machine learning algorithms is widely applied to various industrial areas. A number of research on various topics about structural engineering was performed by using artificial neural networks, such as structural design optimization, vibration control and system identification etc. When nonlinear semi-active structural control devices are applied to building structure, a lot of computational effort is required to predict dynamic structural responses of finite element method (FEM) model for development of control algorithm. To solve this problem, an artificial neural network model was developed in this study. Among various deep learning algorithms, a recurrent neural network (RNN) was used to make the time history response prediction model. An RNN can retain state from one iteration to the next by using its own output as input for the next step. An eleven-story building structure with semi-active tuned mass damper (TMD) was used as an example structure. The semi-active TMD was composed of magnetorheological damper. Five historical earthquakes and five artificial ground motions were used as ground excitations for training of an RNN model. Another artificial ground motion that was not used for training was used for verification of the developed RNN model. Parametric studies on various hyper-parameters including number of hidden layers, sequence length, number of LSTM cells, etc. After appropriate training iteration of the RNN model with proper hyper-parameters, the RNN model for prediction of seismic responses of the building structure with semi-active TMD was developed. The developed RNN model can effectively provide very accurate seismic responses compared to the FEM model.