• Smart Structures and Systems
• /
• v.29 no.4
• /
• pp.625-640
• /
• 2022

Maglev rail joints are vital components serving as connections between the adjacent F-type rail sections in maglev guideway. Damage to maglev rail joints such as bolt looseness may result in rough suspension gap fluctuation, failure of suspension control, and even sudden clash between the electromagnets and F-type rail. The condition monitoring of maglev rail joints is therefore highly desirable to maintain safe operation of maglev. In this connection, an online damage detection approach based on three-dimensional (3D) convolutional neural network (CNN) and time-frequency characterization is developed for simultaneous detection of multiple damage of maglev rail joints in this paper. The training and testing data used for condition evaluation of maglev rail joints consist of two months of acceleration recordings, which were acquired in-situ from different rail joints by an integrated online monitoring system during a maglev train running on a test line. Short-time Fourier transform (STFT) method is applied to transform the raw monitoring data into time-frequency spectrograms (TFS). Three CNN architectures, i.e., small-sized CNN (S-CNN), middle-sized CNN (M-CNN), and large-sized CNN (L-CNN), are configured for trial calculation and the M-CNN model with excellent prediction accuracy and high computational efficiency is finally optioned for multiple damage detection of maglev rail joints. Results show that the rail joints in three different conditions (bolt-looseness-caused rail step, misalignment-caused lateral dislocation, and normal condition) are successfully identified by the proposed approach, even when using data collected from rail joints from which no data were used in the CNN training. The capability of the proposed method is further examined by using the data collected after the loosed bolts have been replaced. In addition, by comparison with the results of CNN using frequency spectrum and traditional neural network using TFS, the proposed TFS-CNN framework is proven more accurate and robust for multiple damage detection of maglev rail joints.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.329-346
• /
• 2022

Recently, as the market for short form videos (Instagram, TikTok, YouTube) on social media has gradually increased, research using them is actively being conducted in the artificial intelligence field. A representative research field is Video to Shop, which detects fashion products in videos and searches for product images. In such a video-based artificial intelligence model, product features are extracted using convolution operations. However, due to the limitation of computational resources, extracting features using all the frames in the video is practically impossible. For this reason, existing studies have improved the model's performance by sampling only a part of the entire frame or developing a sampling method using the subject's characteristics. In the existing Video to Shop study, when sampling frames, some frames are randomly sampled or sampled at even intervals. However, this sampling method degrades the performance of the fashion product search model while sampling noise frames where the product does not exist. Therefore, this paper proposes a sampling method MF (Missing Fashion items on frame) sampler that removes noise frames and improves the performance of the search model. MF sampler has improved the problem of resource limitations by developing a keyframe mechanism. In addition, the performance of the search model is improved through noise frame removal using the noise detection model. As a result of the experiment, it was confirmed that the proposed method improves the model's performance and helps the model training to be effective.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.181-190
• /
• 2022

In this paper, we use a LiDAR sensor and an image camera to detect a left-turning waiting vehicle in two ways, unlike the existing image-type or loop-type left-turn detection system, and a left-turn traffic signal corresponding to the waiting length of the left-turning lane. A system that can efficiently assign a system is introduced. For the LiDAR signal transmitted and received by the LiDAR sensor, the left-turn waiting vehicle is detected in real time, and the image by the video camera is analyzed in real time or at regular intervals, thereby reducing unnecessary computational processing and enabling real-time sensitive processing. As a result of performing a performance test for 5 hours every day for one week with an intersection simulation using an actual signal processor, a detection rate of 99.9%, which was improved by 3% to 5% compared to the existing method, was recorded. The advantage is that 99.9% of vehicles waiting to turn left are detected by the LiDAR sensor, and even if an intentional omission of detection occurs, an immediate response is possible through self-correction using the video, so the excessive waiting time of vehicles waiting to turn left is controlled by all lanes in the intersection. was able to guide the flow of traffic smoothly. In addition, when applied to an intersection in the outskirts of which left-turning vehicles are rare, service reliability and efficiency can be improved by reducing unnecessary signal costs.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.6
• /
• pp.65-75
• /
• 2022

As performance measurement is important for systematic management, the key indicators for performance measurement have been consistently researched in the construction industry. However, there are only a few cases in which performance measurement is performed because it requires strenuous efforts to collect data for measurement. Unlike the public sector, which has been collecting project data through laws, the private sector has very little data to measure performance. In contrast, supervision work concerns important data necessary for the performance management on building construction sites in accordance with the Building Act. Therefore, in this study, we used the data from supervisory reports to measure the performance of private building projects. First, we derived 6 performance areas and 15 indicators through a few rounds of expert group discussions and 2 surveys. Then, we identified the performance indicators with high feasibility of data collection and computed their degree of significance via the analytic hierarchy process. It is expected that the performance indicators and their computational processes derived in this study can be used to systematically measure the performance and aid the speedy diagnosis of private building construction sites.

• Journal of the Korean Institute of Gas
• /
• v.26 no.2
• /
• pp.49-55
• /
• 2022

According to reinforce environmental regulations, coal power plants have used selective catalytic reduction using ammonia as a reducing agent to reduce the amount of nitrogen oxide generation. The purpose of the present study was to derive a mixing device for effectively mixing dilute air and ammonia in the ammonia mixing pipe by performing computational fluid dynamic analysis. The mixing effect was compared by analysing the %RMS of ammonia concentration at the down stream cross section in the mixing pipe and the 16 outlets based on the case 1-1 shape, which is an existing mixing pipe without a mixing device. The mixing device was performed by changing the positions of a square plate on the downstream side of the ammonia supply pipe and an arc-shaped plate on the wall of the mixing pipe. In the case of the existing geometry(Case 1-1), the %RMS of ammonia concentration at the 16 outlets was 29.50%. The shape of the mixing device for Case 3-2 had a square plate on the downstream side of the ammonia supply pipe and an arc plate was installed adjacent to it. The %RMS of ammonia concentration for Case 3-2 was 2.08% at 16 outlets and it could be seen that the shape of Case 3-2 was the most effective mixing shape for ammonia mixing.

• Korean Journal of Optics and Photonics
• /
• v.33 no.1
• /
• pp.28-34
• /
• 2022

We study through computational simulation the focal performance of an infrared (IR) Fresnel lens, composed of a multilayer-graphene zone plate formed under a graphene electrode. Here the Fermi level E_F of the patterned multilayer graphene is adjusted by the overlying graphene electrode. The Fresnel lens effect, with respect to the reflectance contrast between the graphene electrode and the 8-layer graphene zone plate placed on a glass substrate, has been analyzed over a broad wavelength range from 4 to 30 ㎛. As the optimal wavelength of 8 ㎛ (considering the reflectance and the reflectance-contrast ratio) is incident upon the Fresnel lens with a focal length of 240 ㎛, the focal intensity is enhanced by a factor of 4.3 as the E_F of multilayer graphene increases from 0.4 eV to 1.6 eV, and is improved by a factor of 5.8 as the number of graphene layers increases from two to eight. As a result, an all-graphene-based IR Fresnel zone-plate lens, exhibiting multifocal function (240 ㎛ and 360 ㎛) according to the selected E_F, is proposed as an ultrathin lens platform.

• Geophysics and Geophysical Exploration
• /
• v.25 no.3
• /
• pp.109-119
• /
• 2022

The computational efficiency of reverse time migration (RTM) based on numerical modeling is not secured due to the high-frequency band of several hundred Hz or higher for data acquired through a three-dimensional (3D) ultra-high-resolution (UHR) seismic survey. Therefore, this study develops an RTM program to derive high-quality 3D geological structures using UHR seismic data. In the traditional 3D RTM program, an excitation amplitude technique that stores only the maximum amplitude of the source wavefield and a domain-limiting technique that minimizes the modeling area where the source and receivers are located were used to significantly reduce memory usage and calculation time. The program developed through this study successfully derived a 3D migration image with a horizontal grid size of 1 m for the 3D UHR seismic survey data obtained from the Korea Institute of Geoscience and Mineral Resources in 2019, and geological analysis was conducted.

• The Mathematical Education
• /
• v.61 no.3
• /
• pp.477-497
• /
• 2022

The rapidly changing world calls for reform in mathematics education from lifelong learning perspectives. This study examines adults' perception of mathematics by reflecting on their experiences of mathematics in and out of school in order to understand what the current needs of adults are. With the two questions: "what experiences do participants have during their learning of mathematics in schools?" and "how do they perceive mathematics in their current life?", we analyzed the semi-structured interviews with 10 adults who have different sociocultural backgrounds using narrative inquiry methodology. As a result, participants tended to accept school mathematics as simply a technique for solving computational problems, and when they had not known the usefulness of mathematical knowledge, they experienced frustration with mathematics in the process of learning mathematics. After formal education, participants recognized mathematics as the basic computation skill inherent in everyday life, the furniture of their mind, and the ability to efficiently express, think, and judge various situations and solve problems. Results show that adults internalized school education to clearly understand the role of mathematics in their lives, and they were using mathematics efficiently in their lives. Accordingly, there was a need to see school education and adult education on a continuum, and the need to conceptualize the mathematical abilities required for adults as mathematical literacy.

• Advances in aircraft and spacecraft science
• /
• v.9 no.5
• /
• pp.415-431
• /
• 2022

Secondary flows have a huge impact on losses generation in modern low pressure gas turbines (LPTs). At design point, the interaction of the blade profile with the end-wall boundary layer is responsible for up to 40% of total losses. Therefore, predicting accurately the end-wall flow field in a LPT is extremely important in the industrial design phase. Since the inlet boundary layer profile is one of the factors which most affects the evolution of secondary flows, the first main objective of the present work is to investigate the impact of two different inlet conditions on the end-wall flow field of the T106A, a well known LPT cascade. The first condition, labeled in the paper as C1, is represented by uniform conditions at the inlet plane and the second, C2, by a flow characterized by a defined inlet boundary layer profile. The code used for the simulations is based on the Discontinuous Galerkin (DG) formulation and solves the Reynolds-averaged Navier-Stokes (RANS) equations coupled with the Spalart Allmaras turbulence model. Secondly, this work aims at estimating the influence of viscosity and turbulence on the T106A end-wall flow field. In order to do so, RANS results are compared with those obtained from an inviscid simulation with a prescribed inlet total pressure profile, which mimics a boundary layer. A comparison between C1 and C2 results highlights an influence of secondary flows on the flow field up to a significant distance from the end-wall. In particular, the C2 end-wall flow field appears to be characterized by greater over turning and under turning angles and higher total pressure losses. Furthermore, the C2 simulated flow field shows good agreement with experimental and numerical data available in literature. The C2 and inviscid Euler computed flow fields, although globally comparable, present evident differences. The cascade passage simulated with inviscid flow is mainly dominated by a single large and homogeneous vortex structure, less stretched in the spanwise direction and closer to the end-wall than vortical structures computed by compressible flow simulation. It is reasonable, then, asserting that for the chosen test case a great part of the secondary flows details is strongly dependent on viscous phenomena and turbulence.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.7
• /
• pp.1231-1237
• /
• 2022

In the present study, the optimization of the main particulars of a ship using AI-based design search techniques was investigated. For the design search techniques, the SHERPA algorithm by HEEDS was applied, and CFD analysis using STAR-CCM+ was applied for the calculation of resistance performance. Main particulars were automatically transformed by modifying the main particulars of the ship at the stage of preprocessing using JAVA script and Python. Small catamaran was chosen for the present study, and the main dimensions of the length, breadth, draft of demi-hull, and distance between demi-hulls were considered as design variables. Total resistance was considered as an objective function, and the range of displaced volume considering the arrangement of the outfitting system was chosen as the constraint. As a result, the changes in the individual design variables were within ±5%, and the total resistance of the optimized hull form was decreased by 11% compared with that of the existing hull form. Throughout the present study, the resistance performance of small catamaran could be improved by the optimization of the main dimensions without direct modification of the hull shape. In addition, the application of optimization using design search techniques is expected for the improvement in the resistance performance of a ship.