• 한국분무공학회지
• /
• 제29권3호
• /
• pp.147-154
• /
• 2024

This study explores the rate of injection (ROI) and injection quantities of a solenoid-type high-pressure injector under varying conditions by integrating experimental methods with machine learning (ML) techniques. Experimental data for fuel injection were obtained using a Zeuch-based HDA Moehwald injection rate measurement system, which served as the foundation for developing a machine learning model. An artificial neural network (ANN) was employed to predict the ROI, ensuring accurate representation of injection behaviors and patterns. The present study examines the impact of ambient conditions, including chamber temperature, chamber pressure, and injection pressure, on the transient profiles of the ROI, quasi-steady ROI, and injection duration. Results indicate that increasing the injection pressure significantly increases ROI, with chamber pressure affecting its initial rising peak. However, the chamber temperature effect on ROI is minimal. The trained ANN model, incorporating three input conditions, accurately reflected experimental measurements and demonstrated expected trends and patterns. This model facilitates the prediction of various ROI profiles without the need for additional experiments, significantly reducing the cost and time required for developing injection control systems in next-generation aero-engine combustors.

• Biomedical Engineering Letters
• /
• 제8권4호
• /
• pp.337-344
• /
• 2018

Additive manufacturing (AM) is an alternative metal fabrication technology. The outstanding advantage of AM (3D-printing, direct manufacturing), is the ability to form shapes that cannot be formed with any other traditional technology. 3D-printing began as a new method of prototyping in plastics. Nowadays, AM in metals allows to realize not only net-shape geometry, but also high fatigue strength and corrosion resistant parts. This success of AM in metals enables new applications of the technology in important fields, such as production of medical implants. The 3D-printing of medical implants is an extremely rapidly developing application. The success of this development lies in the fact that patient-specific implants can promote patient recovery, as often it is the only alternative to amputation. The production of AM implants provides a relatively fast and effective solution for complex surgical cases. However, there are still numerous challenging open issues in medical 3D-printing. The goal of the current research review is to explain the whole technological and design chain of bio-medical bone implant production from the computed tomography that is performed by the surgeon, to conversion to a computer aided drawing file, to production of implants, including the necessary post-processing procedures and certification. The current work presents examples that were produced by joint work of Polygon Medical Engineering, Russia and by TechMed, the AM Center of Israel Institute of Metals. Polygon provided 3D-planning and 3D-modelling specifically for the implants production. TechMed were in charge of the optimization of models and they manufactured the implants by Electron-Beam Melting ($EBM^{(R)}$), using an Arcam $EBM^{(R)}$ A2X machine.

• Geomechanics and Engineering
• /
• 제4권3호
• /
• pp.191-208
• /
• 2012

Due to rapid industrialisation, large scale infrastructure development is taking place worldwide. This includes railways, high speed highways, elevated roads etc. To meet the demands of society and industry, many innovative techniques and materials are being developed. In developed nations like USA, Japan etc. for railways applications, new material like geocells, geogrids are being used successfully to enable fast movement of vehicles. The present research work was aimed to develop design methodologies for improvement of grounds subjected to cyclic loads caused by moving vehicles on roads, rail tracks etc. Deformation behavior of ballast under static and cyclic load tests was studied based on square footing test. The paper presents a study of the effect of geo-synthetic reinforcement on the (cumulative) plastic settlement, of point loaded square footing on a thick layer of granular base overlying different compressible bases. The research findings showed that inclusion of geo-synthetics significantly improves the performance of ballasted tracks and reduces the foundation area. If the area is kept same, higher speed trains can be allowed to pass through the same track with insertion of geosynthetics. Similarly, area of machine foundation may also be reduced where geosynthetics is provided in foundation. The model tests results have been validated by numerical modeling, using $FLAC^{3D}$.

• Geomechanics and Engineering
• /
• 제32권3호
• /
• pp.271-291
• /
• 2023

Settlement estimation in cohesion materials is a crucial topic to tackle because of the complexity of the cohesion soil texture, which could be solved roughly by substituted solutions. The goal of this research was to implement recently developed machine learning features as effective methods to predict settlement (S_m) of shallow foundations over cohesion soil properties. These models include hybridized support vector regression (SVR), random forests (RF), and coot optimization algorithm (COM), and black widow optimization algorithm (BWOA). The results indicate that all created systems accurately simulated the S_m, with an R² of better than 0.979 and 0.9765 for the train and test data phases, respectively. This indicates extraordinary efficiency and a good correlation between the experimental and simulated S_m. The model's results outperformed those of ANFIS - PSO, and COM - RF findings were much outstanding to those of the literature. By analyzing established designs utilizing different analysis aspects, such as various error criteria, Taylor diagrams, uncertainty analyses, and error distribution, it was feasible to arrive at the final result that the recommended COM - RF was the outperformed approach in the forecasting process of S_m of shallow foundation, while other techniques were also reliable.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1998년도 가을 학술발표회 논문집
• /
• pp.455-462
• /
• 1998

Analysis and design of vibrating machine foundations subjected to dynamic loads is a very complex problem. Thus it is difficult to set up an accurate analytical modeling. Generally, the design of foundations for vibrating machines has been performed by the equivalent static analysis which is generally based on engineer's experience and various assumptions The purpose of this study is to develop an integrated system which enables structural engineers to produce results of high quality within a short time in works related to structural analysis and design of foundation for vibrating machines. As the result of this study, level-up of application software is expected as well as improvement of quality in structural engineering and reduction of engineers' effort.

• 한국안전학회지
• /
• 제16권4호
• /
• pp.147-152
• /
• 2001

The tower cranes are the very useful construction machine in the high place works. But they are very susceptible to the load balance, the wind load and the hanging load because they are the very slender structures and those center of gravity is located in the upper part. Therefore, the collapse accidents of tower one have repeatedly happened during the assemble or disassemble works. The correcting frame may has often used in order to correct the error in the setting of foundation anchors. The goal of this study is that propose the methods preventible the collapse accident of tower crane which is constructed by using the correcting frame. In order to accomplish the goal of this study, the field survey, the reference investigation and the structure analysis were performed for the collapse accident of tower crane using the correcting frame. This study result in the methods preventible the same accident.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제28권1호
• /
• pp.1-21
• /
• 2024

This review comprehensively explores the evolution, theoretical underpinnings, variations, and applications of diffusion models. Originating as a generative framework, diffusion models have rapidly ascended to the forefront of machine learning research, owing to their exceptional capability, stability, and versatility. We dissect the core principles driving diffusion processes, elucidating their mathematical foundations and the mechanisms by which they iteratively refine noise into structured data. We highlight pivotal advancements and the integration of auxiliary techniques that have significantly enhanced their efficiency and stability. Variants such as bridges that broaden the applicability of diffusion models to wider domains are introduced. We put special emphasis on the ability of diffusion models as a crucial foundation model, with modalities ranging from image, 3D assets, and video. The role of diffusion models as a general foundation model leads to its versatility in many of the downstream tasks such as solving inverse problems and image editing. Through this review, we aim to provide a thorough and accessible compendium for both newcomers and seasoned researchers in the field.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2006년도 춘계학술대회논문집
• /
• pp.996-1001
• /
• 2006

Automatic washing machines have been improved and popularized steadily since the first electric washing machine was produced in the early 1900's. Appliance industry has tried to obtain the performance of washing machine with large capacity, high energy efficiency, low vibration and low noise levels. As the installation peace of a washer becomes closer to the living space, vibration and noise problems become more important challenges. In general, a washing machine has four legs to support its body. Four legs of the washing machine should be attached on a floor. If not so, it may cause severe vibration or walking in the spin-drying process. Unfortunately, the floor of an ordinary house is bumpy in general, and the consumers will not accept bolting washing machines to a foundation; moreover, sometimes they move the location of their washing machines to utility rooms or bath rooms or kitchens and don't care for leveling the legs exactly. In this study, we devise an auto-leg system that prevents the occurrence of abnormal vibration and walking of washing machines. It is simply composed of a spring and a friction damper. Some experiments are implemented to show the dynamic characteristics of the three-dimensional auto-legged washing machine model that is located on the even or uneven ground. A spring parameter is optimized to adjust the length of the auto-leg system automatically up to 10 mm irregularity, and the friction damper is designed to decrease a resonance induced by the spring of the auto-leg system. Some numerical results show that placing the proposed auto-leg system in a washing machine makes good performance with low vibration, as well as low noise, regardless of the unevenness of the floor.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권2호
• /
• pp.267-277
• /
• 2024

This paper explores the use of machine learning in game production to create goal-oriented, realistic animations for skeleton monsters. The purpose of this research is to enhance realism by implementing intelligent movements in monsters within game development. To achieve this, we designed and implemented a learning model for skeleton monsters using reinforcement learning algorithms. During the machine learning process, various reward conditions were established, including the monster's speed, direction, leg movements, and goal contact. The use of configurable joints introduced physical constraints. The experimental method validated performance through seven statistical graphs generated using machine learning methods. The results demonstrated that the developed model allows skeleton monsters to move to their target points efficiently and with natural animation. This paper has implemented a method for creating game monster animations using machine learning, which can be applied in various gaming environments in the future. The year 2024 is expected to bring expanded innovation in the gaming industry. Currently, advancements in technology such as virtual reality, AI, and cloud computing are redefining the sector, providing new experiences and various opportunities. Innovative content optimized for this period is needed to offer new gaming experiences. A high level of interaction and realism, along with the immersion and fun it induces, must be established as the foundation for the environment in which these can be implemented. Recent advancements in AI technology are significantly impacting the gaming industry. By applying many elements necessary for game development, AI can efficiently optimize the game production environment. Through this research, We demonstrate that the application of machine learning to Unity and game engines in game development can contribute to creating more dynamic and realistic game environments. To ensure that VR gaming does not end as a mere craze, we propose new methods in this study to enhance realism and immersion, thereby increasing enjoyment for continuous user engagement.

• 터널과지하공간
• /
• 제29권1호
• /
• pp.1-11
• /
• 2019

본 연구에서는 국내 의료, 제조, 금융, 자동차, 도시 분야와 해외 광업 분야에서 머신러닝 기술이 활용된 사례를 조사하였다. 문헌 조사를 통해 머신러닝 기술이 의학영상 정보시스템 개발, 실시간 모니터링 및 이상 진단 시스템 개발, 정보시스템의 보안 수준 개선, 자율주행차 개발, 도시 통합관리 시스템 개발 등에 광범위하게 활용되어왔음을 알 수 있었다. 현재까지 국내 광업 분야에서는 머신러닝 기술의 활용사례를 찾을 수 없었으나, 해외에서는 광상 탐사나 광산 개발의 생산성 및 안전성을 개선을 위해 머신러닝 기술을 도입한 프로젝트들을 찾을 수 있었다. 향후 머신러닝 기술의 광업 분야 도입은 점차 확산될 것으로 예상된다.