• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.11
• /
• pp.22-35
• /
• 1999

The block assembly process takes more than half of the total shipbuilding processes. Therefore, it is very important to have a practically useful block assembly process planning system which can build plans of maximum efficiency with minimum man-hours required. However, the process plans are often not readily executable in the assembly shops due to severe imbalance of workloads. This problem arises because the process planning is done on block by block basis in current practice without paying any attention to the load distribution among the assembly shops. this paper presents the development of an automated hull block assembly process planning system which results in the most effective use of production resources and also produces plans that enable efficient time management. If the load balance of assembly shops is to be considered at the time of process planning, the task becomes complicated because of the increased computational complexity. To solve this problem, a new approach is adopted in this research in which the load balancing function and process planning function are iterated alternately providing to each other contexts for subsequent improvement. The result of case study with the data supplied from the shipyard shows that the system developed in this research is very effective and useful.

• Journal of the Society of Disaster Information
• /
• v.10 no.1
• /
• pp.15-24
• /
• 2014

The study presents work information classification system of apartment house which can organize all construction management services throughout the planning and management of a construction such as the decomposition of the design process, the assembly of construction process and cost estimating, etc. In addition, the study suggested a way to connect work information classification system based on a relational database in working order and built a conceptual model for automated cost estimating by utilizing established data base. A conceptual model for automated cost estimating will resolve the fundamental problems of the existing cost estimating system and will be able to take advantage of scientific cost estimating system at the construction site of apartment house.

• Journal of the Korean Solar Energy Society
• /
• v.33 no.2
• /
• pp.84-92
• /
• 2013

Blinds are a common type of shading device and are increasingly operated automatically to overcome the limitations of manual operation. Automated blinds need to be controlled to maximize benefits of daylight in the point of occupant comfort and energy consumption. However, the previous control methods could cause occupant's distractions by the undesirable control time interval and amount of blind movement. A few researches suggested the control concept for minimizing occupant's distractions by automatic blind control, but they did not provide optimal control algorithm to be useful in practice. In this paper, we propose an optimal control algorithm for automated blinds that can maximize not only visual comfort but also sunlight penetration into buildings based on occupants' preferences on blind movement and sunlight. The proposed control algorithm can prevent solar glare on workplane and minimize occupant's distractions to maximize occupants' visual comfort.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.613-623
• /
• 2022

Autism spectrum disorder (ASD) is a developmental disorder associated with cognitive and neurobehavioral disorders. It affects the person's behavior and performance. Autism affects verbal and non-verbal communication in social interactions. Early screening and diagnosis of ASD are essential and helpful for early educational planning and treatment, the provision of family support, and for providing appropriate medical support for the child on time. Thus, developing automated methods for diagnosing ASD is becoming an essential need. Herein, we investigate using various machine learning methods to build predictive models for diagnosing ASD in children using facial images. To achieve this, we used an autistic children dataset containing 2936 facial images of children with autism and typical children. In application, we used classical machine learning methods, such as support vector machine and random forest. In addition to using deep-learning methods, we used a state-of-the-art method, that is, automated machine learning (AutoML). We compared the results obtained from the existing techniques. Consequently, we obtained that AutoML achieved the highest performance of approximately 96% accuracy via the Hyperpot and tree-based pipeline optimization tool optimization. Furthermore, AutoML methods enabled us to easily find the best parameter settings without any human efforts for feature engineering.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.1307-1311
• /
• 2004

This paper deals with an automated computer-aided process planning and die design system by which designer can determine operation sequences even if they have a little experience in process planning and die design for axisymmetric products. An attempt is made to link programs incorporating a number of expert design rules with the process variables obtained by commercial FEM softwares, DEFORM and ANSYS, to form a useful package. They can provide a flexible process based on either the reduction in the number of forming sequences by combining the possible two processes in sequence, or the reduction of deviation of the distribution on the level of the required forming loads by controlling the forming ratios. Especially in die design module an optimal design technique and horizontal split die were investigated for determining appropriate dimensions of components of multi-former die set. It is constructed that the proposed method can be beneficial for improving the tool life of die set at practice.

• Journal of Construction Engineering and Project Management
• /
• v.2 no.1
• /
• pp.35-44
• /
• 2012

In the last two decades, several tele-operated and machine-vision-assisted systems have been developed in the construction and maintenance area, such as pavement crack sealing, sewer pipe rehabilitation, and excavation. In developing such tele-operated and machine-vision-assisted systems, trajectory plans are very important tasks for the optimal motions of robots whether their environments are structured or unstructured. This paper presents an optimal trajectory planning algorithm used for a machine-vision-assisted automatic pavement crack sealing system. In this paper, the performance of the proposed optimal trajectory planning algorithm is compared with the greedy trajectory plans, which are used in the previously developed pavement crack sealing systems. The comparison is based on the computational cost vs. the overall gains in crack sealing efficiency. Finally, it is concluded that the proposed algorithm plays an important role in the productivity improvement of the developed automatic pavement crack sealing system.

• Industrial Engineering and Management Systems
• /
• v.4 no.1
• /
• pp.47-53
• /
• 2005

The efficiency of fabrication (fab) operation is one of the key factors in order for a semiconductor manufacturing company to stay competitive. Optimization of manpower and forecasting manpower needs in a modern fab is an essential part of the future strategic planing and a very important to the operational efficiency. As the semiconductor manufacturing technology has entered the 8-inch wafer era, the complexity of fab operation increases with the increase of wafer size. The wafer handling method has evolved from manual mode in 6-inch wafer fab to semi-automated or fully automated factory in 8-inch and 12-inch wafer fab. The distribution of manpower requirement in each specialty varied as the trend of fab operation goes for downsizing manpower with automation and outsourcing maintenance work. This paper is to study the specialty distribution of manpower from the requirement in a typical 6-inch, 8-inch to 12-inch wafer fab. The human resource planning in today’s fab operation shall consider many factors, which include the stability of technical talents. This empirical study mainly focuses on the human resource planning, the manpower distribution of specialty structure and the forecast model of internal demand/supply in current semiconductor manufacturing company. Considering the market fluctuation with the demand of varied products and the advance in process technology, the study is to design a headcount forecast model based on current manpower planning for direct labour (DL) and indirect labour (IDL) in Taiwan’s fab. The model can be used to forecast the future manpower requirement on each specialty for the strategic planning of human resource to serve the development of the industry.

• Korean Journal of Computational Design and Engineering
• /
• v.14 no.1
• /
• pp.60-68
• /
• 2009

Because of the reduced product life-cycle, industries are making an effort to bring down the process planning time. In the traditional approach, we have to analyze established process planning, then design the time chart based on process information and drawing the formal time chart such as SOP(sequence of operation). Thereafter, it will be converted to PLC code that is a time consuming and redundant job. Similarly, Industrial automated process uses PLC Code to control the factory; however, control information and control code(PLC code) are difficult to understand. Hence, industries prefer writing new control code instead of using the existing one. It shows the lack of information reusability in the existing process planning. As a result, to reduce this redundancy and lack of reusability, we propose SOS-Net modeling method. Unlike past stabilized process planning that is rigid to any change; our proposed SOS-Net modeling method is more adaptable to the new changes. The SOS-Net model is easy to understand and easy to convert into PLC Code accordingly. Therefore, we can easily modify the control information and reuse it for new process planning. The proposed model plays an intermediary role between process planning and PLC code generation. It can reduce the process planning and implementation time as well as cost.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.7
• /
• pp.39-48
• /
• 1997

This paper describes the process planning system of a computer-aided design of blanking and piercing for irregularly shaped sheet metal products. An approach to the system is based on knowledge-based rules. The process planning system is designed by considering several factors, such as the complexity of blank geometry, production feasibility of products, and punch profile complexity. Therefore this system which was implemented production feasibility check and strip layout module can carry out a process planning considering a production feasibility area of both internal and external features, a dimension of blanked hole, a coner and a fillet radius for irregualrly shaped sheet metal products and generate the strip layout in graphic froms. Knowledges for process planning are extracted from plasticity theories, handbooks, relevant references and empirical know- hows of experts in blanking companies. This provides powerful capabilities for process planning system of irregularly shaped sheet metal products.

• IE interfaces
• /
• v.15 no.4
• /
• pp.325-337
• /
• 2002

In this study we consider the problem of production planning of TFT-LCD(Thin Film Transistor - Liquid Crystal Display) production factory. Due to the complexities of the TFT-LCD production processes, it is difficult to schedule the production planning, and the study about automated scheduler is insufficient. In addition, the existing production method is a Push-System to raise the operation rate with expensive equipment, that has the problem to satisfy the due-date. This study presents an algorithm having a concept of Pull-System that satisfies the due-date and considers specialties of TFT-LCD production process. We make MPS(Master Production Schedule) according to the sales order, and present algorithms for scheduling about In/Out plan considering factory capacity, line balancing, material requirement, and inventory level of all Array, Cell, and Module processes. These algorithms are integrated as an automated production system, and we implement them in the actual TFT-LCD factory circumstance.