• Smart Structures and Systems
• /
• v.31 no.3
• /
• 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.

• Journal of Sensor Science and Technology
• /
• v.26 no.1
• /
• pp.28-34
• /
• 2017

An NIR grism Si optical area sensor spectrometer with in-band reference wavelength is designed and fabricated. It is composed of a transmission type diffraction grating (spatial density 300 line/mm), a rectangular N-BK7 prism (apex angle 30 degree), NIR filter(cutoff wavelength 720 nm), an imaging convex lens(focal length 50 mm F1.8) and an IR modified DSLR camera (Canon EOS40D) of Si optical area sensor ($3,888{\times}2,592$ pixels, pixel size $5.710{\mu}m$). "In-band reference wavelength function" is implemented using non-dispersive 0th diffraction order optical beam. The NIR grism spectrometer is tested in a laboratory using a halogen lamp and a Neon lamp. And the spectrometer is used in an astronomy field for obtaining the planet Jupiter NIR spectrum. In-band reference wavelength i.e. un-deviation wavelength is 846 nm, an wavelength resolution is 0.3027 nm/pixel, an wavelength resolving power is 2,794 and an wavelength range is 650~1,000 nm.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.1 s.178
• /
• pp.113-120
• /
• 2006

This paper proposed the control algorithm fur aspheric surface grinding and was verified by the experiment. The functions of the algorithm were simultaneous control of the position and interpolation of the aspheric curve. The non-linear formula of the tool position was derived from the aspheric equations and the shape of the tool. The function was partitioned by an certain interval and the control parameters were calculated at each control section. The movement in a session was interpolated with acceleration and velocity. The position error was feed-backed by rotary encorder. The concept of feedback algorithm was correcting position error by increasing or decreasing the speed. In the experiment, two-axis machine was controlled to track the aspheric surface by the proposed algorithm. The effect of the control and process parameters was monitored. The result showed that the maximum tracking error was under sub-micro level for the concave and convex surfaces.

• Nuclear Engineering and Technology
• /
• v.43 no.5
• /
• pp.447-458
• /
• 2011

This paper proposes an approximated contact force model to identify the nonlinear behavior of a fuel rod with gap supports; also, the numerical prediction of interfacial forces in the mechanical contact of fuel rods with gap supports is studied. The Newmark integration method requires the current status of the contact force, but the contact force is not given a priori. Taylor's expansion can be used to predict the unknown contact force; therefore, it should be guaranteed that the first derivative of the contact force is continuous. This work proposes a continuous and differentiable contact force model with the ability to estimate the current state of the contact force. An approximated convex and differentiable potential function for the contact force is described, and a variational formulation is also provided. A numerical example that considers the particularly stiff supports has been studied, and a fuel rod with hardening supports was also examined for a realistic simulation. An approximated proper solution can be obtained using the results, and abrupt changes from the contacting state to non-contacting state, or vice versa, can be relieved. It can also be seen that not only the external force but also the developed contact force affects the response.

• Communications for Statistical Applications and Methods
• /
• v.24 no.2
• /
• pp.143-154
• /
• 2017

A variable selection method based on probabilistic principal component analysis (PCA) using penalized likelihood method is proposed. The proposed method is a two-step variable reduction method. The first step is based on the probabilistic principal component idea to identify principle components. The penalty function is used to identify important variables in each component. We then build a model on the original data space instead of building on the rotated data space through latent variables (principal components) because the proposed method achieves the goal of dimension reduction through identifying important observed variables. Consequently, the proposed method is of more practical use. The proposed estimators perform as the oracle procedure and are root-n consistent with a proper choice of regularization parameters. The proposed method can be successfully applied to high-dimensional PCA problems with a relatively large portion of irrelevant variables included in the data set. It is straightforward to extend our likelihood method in handling problems with missing observations using EM algorithms. Further, it could be effectively applied in cases where some data vectors exhibit one or more missing values at random.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3608-3626
• /
• 2021

The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1229-1244
• /
• 2017

In recent years, as demand for data-based analytical methodologies increases in various fields, optimization methods have been developed to handle them. In particular, various constraints required for problems in statistics and machine learning can be solved by convex optimization. Alternating direction method of multipliers (ADMM) can effectively deal with linear constraints, and it can be effectively used as a parallel optimization algorithm. ADMM is an approximation algorithm that solves complex original problems by dividing and combining the partial problems that are easier to optimize than original problems. It is useful for optimizing non-smooth or composite objective functions. It is widely used in statistical and machine learning because it can systematically construct algorithms based on dual theory and proximal operator. In this paper, we will examine applications of ADMM algorithm in various fields related to statistics, and focus on two major points: (1) splitting strategy of objective function, and (2) role of the proximal operator in explaining the Lagrangian method and its dual problem. In this case, we introduce methodologies that utilize regularization. Simulation results are presented to demonstrate effectiveness of the lasso.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.107-110
• /
• 2015

In this paper, we propose a coalitonal game theoritic approach to the power control problem in resource-constrained wireless sensor networks, where the objective is to enhance power efficiency of individual sensors while providing the QoS requirements. We model this problem as two-sided one-to-one matching game and deploly deferred acceptance procedure that produces a single matching in the core. Furthermore, we show that, by applying the procedure repeatedly, a certain stable state is achieved where no sensor can anticipate improvements in their power efficiency as far as all of them are subject to their own QoS constraints. We evaluate our proposal by comparing them with cluster-based and the local optimal solution obtained by maximizing the total system energy efficiency, where the objective function is non-convex.

• Journal of Korea Water Resources Association
• /
• v.52 no.10
• /
• pp.681-695
• /
• 2019

A Transient Storage Model (TSM) is one of the most widely used model accounting for complex solute transport in natural river to understanding natural river properties with four TSM key parameters. The TSM parameters are estimated via inverse modeling. Parameter estimation of the TSM is carried out by solving optimization problem about finding best fitted simulation curve with measured curve obtained from tracer test. Several studies have reported uncertainty in parameter estimation from non-convexity of the problem. In this study, we assessed best combination of optimization method and objective function for TSM parameter estimation using Cheong-mi Creek tracer test data. In order to find best optimization setting guaranteeing convergence and speed, Evolutionary Algorithm (EA) based global optimization methods, such as CCE of SCE-UA and MCCE of SP-UCI, and error based objective functions were compared, using Shuffled Complex-Self Adaptive Hybrid EvoLution (SC-SAHEL). Overall results showed that multi-EA SC-SAHEL with Percent Mean Squared Error (PMSE) objective function is the best optimization setting which is fastest and stable method in convergence.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.3
• /
• pp.259-266
• /
• 2011

We present a new dual sequential approximate optimization (SAO) algorithm called SD-TDQAO (sequential dual two-point diagonal quadratic approximate optimization). This algorithm solves engineering optimization problems with a nonlinear objective and nonlinear inequality constraints. The two-point diagonal quadratic approximation (TDQA) was originally non-convex and inseparable quadratic approximation in the primal design variable space. To use the dual method, SD-TDQAO uses diagonal quadratic explicit separable approximation; this can easily ensure convexity and separability. An important feature is that the second-derivative terms of the quadratic approximation are approximated by TDQA, which uses only information on the function and the derivative values at two consecutive iteration points. The algorithm will be illustrated using mathematical and topological test problems, and its performance will be compared with that of the MMA algorithm.