Injection-molded products frequently exhibit localized surface defects such as weld lines, flow marks, scratches, bubbles, and burn marks due to variations in material flow, mold temperature, and cooling conditions. Conventional visual inspection is highly dependent on operator experience, while rule-based machine vision methods are limited under variations in lighting and surface texture. This study proposes a deep learning–based defect detection model using YOLOv8 combined with a novel Defect-Aware Augmentation technique designed to enhance robustness for small, local defect regions. The proposed augmentation pipeline includes geometric transformations, optical perturbations, local defect patch synthesis, and diffusion-based synthetic defect generation. Experiments were conducted on a custom dataset of 5,000 images (3,000 normal and 2,000 defective). Results show that the proposed model achieves significant improvements over baseline models, obtaining 95% precision, 90% recall, and 0.96 mAP@0.5, outperforming the default YOLOv8 model by 7%p in mAP. Ablation studies verify that defect-aware augmentation is the dominant factor contributing to the performance gain. The proposed system demonstrates high applicability for automated quality inspection in injectionmolding production lines.

This study proposes a deep learning–based predictive maintenance model for condition monitoring and remaining useful life (RUL) estimation of a 1 kW brushless DC (BLDC) motor. Multi-sensor signals, including vibration (10 kHz), current (20 kHz), and surface temperature (10 Hz), were acquired under six health conditions: normal, bearing outer race fault (BPFO), bearing inner race fault (BPFI), unbalance, misalignment, and stator insulation degradation. To jointly exploit spatial patterns and temporal degradation behaviors, a hybrid CNN–LSTM model with a multi-task learning framework was developed to perform 6-class fault classification and RUL regression simultaneously. Experimental results on the constructed BLDC motor dataset show that the proposed model achieves a classification accuracy of 95.8%, outperforming conventional SVM and 1D-CNN baselines (85.2% and 90.7%, respectively). In addition, the proposed method significantly reduces RUL prediction error, yielding an RMSE of 9.6 and an MAE of 6.8, which corresponds to approximately 39% improvement over a single LSTM-based regression model. These results demonstrate that the proposed CNN– LSTM multi-sensor fusion framework is effective for intelligent condition monitoring and predictive maintenance of BLDC motor systems, and it can be extended to a wide range of rotating machinery applications.

This paper presents an AI-based PHM (Prognostics and Health Management) framework for quantitative motor health assessment and remaining useful life (RUL) prediction. The proposed method first defines a health index using vibration and current signals of an industrial motor, and then adopts a two-stage PHM architecture consisting of health-state classification and deep learning-based RUL prediction. A degradation test bench is designed to obtain condition monitoring data for normal, warning, and critical states, and a hybrid 1D CNN– BiLSTM–attention model is developed to capture both local features and long-term temporal dependencies. Experimental results demonstrate that the proposed model outperforms conventional SVM and single LSTM baselines in terms of both health-state classification accuracy and RUL prediction accuracy, achieving a 20– 30% reduction in RMSE and more than 80% of RUL predictions within ±10% error. The proposed approach provides a practical PHM framework and modeling guidelines for implementing condition-based maintenance of electric motors in smart manufacturing environments.

This paper describes the use of approximation in Collaborative Optimization (CO) method, one of the Multidisciplinary Design Optimization (MDO) techniques. The approximation is used to model the result of a disciplinary design, optimal discrepancy function value, as a function of the interdisciplinary target variables passed from system level to the discipline. The optimal discrepancy function value is used to examine the interdisciplinary compatibility constraint (discrepancy function = 0) duringthe system level optimization. However, the peculiar shape of the compatibility constraint makes it difficult to exploit well–developed conventional approximation methods. This paper introduces the combination of neural network classification and kriging to resolve this problem. In addition, for the purpose of enhancing the accuracy of the approximation, the approximation is continuously updated using the information obtained from the system level optimization. This iterative process is continued until acceptable convergence is achieved.

Multidisciplinary Design Optimization(MDO) method that considers principles in various fields affecting big scale structure and system design at the same time is used. Because most variables are connected many engineering phenomena under the classic optimized design method(all-in-one design approach), it is hard to judge the meaning of final design solution obtained, and there are cases where all variables converge before reaching the optimal design value in large-scale design problems with many variables. Collaborative Optimization (CO) method, the most advanced MDO approach, is used to efficiently solve these optimum problems, to efficiently analyze design problems involving numerous design variables and constraints and in which various engineering phenomena occur. However, the application of the MDO problem to CO introduces a number of numerical problems by destroying the numerical properties of the original optimal design problem. Therefore, this study researches one solution by listing the problems of CO after organizing various approaches of MDO.

Engineering design primarily focuses on product improvement through enhancing existing functionalities, integrating features, or adding new capabilities. In other words, it can be said that more design(adaptive design) changes to existing products based on benchmarking with competing products, differentiation strategies, changes in customer needs, etc. are actually performed rather than developing new products that did not exist before. Especially in the case of custom production, such as ships or buildings, a significant portion of actual design work involves modifying and adjusting past performance data according to the current customer's requirements. Therefore, design methods should be developed in a way that effectively supports these processes. Therefore, in this study, as QFD (Quality Function Deployment) ‘analysis of existing products’ and ‘creation of new alternatives’ is supported in Marine Concept Design with AHP (Analytic Hierarchy Process) techniques such as ‘Value Evaluation in Analysis Work’ and ‘Design Alternative Evaluation’, as a result, basic research was conducted on whether it could be used as a tool to effectively support the flow of the design process.

Engineering design involves making numerous decisions as the design process. These decisions can be broadly categorized into selection decisions and compromise decisions. The outcomes of these decisions heavily depend on the designer's intentions, highlighting the need to systematically and accurately incorporate the designer's intentions. The Analytic Hierarchy Process (AHP) is a design technique that systematically reflects the designer's intentions by hierarchically analyzing and evaluating ambiguous decision problems. Therefore, in this study, effective optimal structure designs that maximally reflect the designer's intentions were confirmed by introducing AHP (Analytic Hierarchy Process) and Neural Network into the foundational decision-making process of engineering design.

One major concern of Seoul City is the premature failure occurrence such as fatigue cracking and rutting in the pavement. Due to the acceleration at intersections and low vehicle speed at bus stops that cause higher shear and critical strain on the pavement. Because of this, there is a need to develop a new mixture that can withstand bus stop and intersection traffic while preventing premature failure. In this study, a high modulus asphalt mixture was adapted and developed to address the cracking and rutting concerns at bus stops and intersections of Seoul City. Indirect tensile (IDT) and beam fatigue testing were conducted to determine the fatigue performance of the high modulus asphalt mixture (HMB). In addition, the behaviour of the HMB considering loading speed and temperature were investigated using the IDT dynamic modulus test. It was found that the HMB performs 3 and 1.5 times better compared to conventional asphalt using IDT and beam fatigue test respectively. Moreover, it was observed that modulus value of HMB is two times better at low frequency (high temperature) compared to conventional asphalt. The dynamic modulus value of the HMB was then used as input for bus stop and intersection scenario analyses. It was found that HMB can reduce the total thickness of the pavement around 4 to 6cm compared to the conventional asphalt. It can be concluded that because of the better fatigue and rutting performance and high modulus value of HMB at low frequency, it can perform better in bus stops and intersections. It is recommended to conduct field construction to further evaluate the performance of HMB asphalt mixtures in the field.

This paper describes a preliminary ship design optimal design method in the process of hull form design. In the deterministic approach, an interdisciplinary ship design method integrates principal dimension decisions and hull form variations in the preliminary ship design stage. Integrated ship design, as presented in this paper, has the distinctive feature that these parameters are evaluated simultaneously. Conversely, in sequential design, which is based on the traditional preliminary ship design process, hull form designs and principal dimension decisions are determined separately and sequentially. The current study adopts the first method to enhance the design quality in the early design stage.

In product development, different divisions and businesses often have heterogeneous CAD/CAE systems and methods for expressing product data, and addressing this heterogeneity creates additional costs and causes longer development periods. To ensure successful collaboration in the design process, it is therefore imperative that different CAD, CAE, and other related systems be managed in an organic and integrated manner from the initial stages of product development. Therefore, this study suggests an integrated CAD/CAE system including optimal design in a more effective and integrated manner but also to support interfacing and the collective use of design and analysis tools. To validate the proposed method, a stiffened plate example is taken as an example. It is found that the proposed method could overcome the bottleneck of CAD and CAE such as transferability of data, though CATIA and ANSYS are used at the moment.

This study was conducted to explore if the ground beetle (Coleoptera: Carabidae) can be used as an indicator classifying habitat types. Thirteen land use types were selected as survey sites in Jeonju. Ground beetles were collected by 3 pitfall traps (15 cm diameter) for each site from June 20 to September 22, 2008. Pitfall traps were replaced at one month interval. Total 919 ground beetles of 31 species belonging to 17 genera were collected. Land use types were classified and ordinated by two-way indicator species analysis and detrended correspondence analysis. Land use types were classified and ordinated into two major groups, forest and non-forest, by Synuchus nitidus and Dolichus halensis. Two major groups were subdivided into 4 end groups; forest, riverside, upland and other sites. Other sites group including 4 sites; levee, public garden, outfield and manufacturing area were not coincided with land use types. Nevertheless, ground beetles appear to be used as indicators of habitat types.

고강도 콘크리트 보의 극한상태의 거동을 강도에 따라 연구하였다. 13개의 보를 해석하고 그 결과를 제시하였다. 변수는 콘크리트의 압축강도로 범위는 57~184 MPa이며, 횡방향 철근비로 범위는0.35~1.49%이다. 실험에서 측정한 극한 비틀림 강도를 본 논문에서 제안한 값과 ACI 기준에 따른 값을 비교하였다. 그 결과 본 논문에서 제안한 이론에 의한 극한 비틀림 강도가 ACI 기준에 따른 값보다 더 좋은 결과를 보였다.