• IE interfaces
• /
• v.18 no.4
• /
• pp.465-476
• /
• 2005

Evolutionary operation is a useful tool for improving full-scale manufacturing process by systematically changing the levels of the process variables without jeopardizing the product. This paper presents a system design for the evolutionary operation software called 'evolutionary optimizer'. Evolutionary optimizer consists of four modules: factorial design, many variables, mixture, and mean/dispersion. Context diagram, data flow diagram and entity-relationship modelling are used to systematically design the evolutionary optimizer system.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 2004.04a
• /
• pp.503-506
• /
• 2004

Evolutionary operation is useful to improve on-line full-scale manufacturing processes by systematically changing the levels of the process variables without jeopardizing the product. This paper presents a system design for an evolutionary operation software called 'evolutionary optimizer'. The system design is based primarily on data flow diagram. Evolutionary optimizer consists of four modules: factorial design module, many variables module, mixture Production module, and mean/dispersion module.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.29 no.7 s.238
• /
• pp.1013-1021
• /
• 2005

In this paper, we developed an automatic design optimization system for parametric shape optimization of cooling passages inside axial turbine blades. A parallel three-dimensional thermoelasticity finite element analysis code from an open source system was used to perform automatic thermal and stress analysis of different blade configuration. The developed code was connected to an evolutionary optimizer and built in a design optimization system. Using the optimization system, 279 feasible and optimal solutions were searched. It is provided not only one best solution of the searched solutions, but also information of variation structure and correlation of the 279 solutions in function, variable, and real design spaces. To explore design information, it is proposed a new interpretation approach based on evolutionary clustering and principal component analysis. The interpretation approach might be applicable to the increasing demands in the general area of design optimization.

• Journal of the Society of Naval Architects of Korea
• /
• v.48 no.4
• /
• pp.325-329
• /
• 2011

Floating, production, storage and offloading (FPSO) is a production facility that refines and saves the drilled crude oil from a drilling facility in the ocean. The flare system in the FPSO is a major part of the pressure relieving system for hydrocarbon processing plants. The flare system consists of a number of pipes and complicated connection systems. Decision of pipe support types is important since the load on the support and the stress in the pipe are influenced by the pipe support type. In this study, we optimally determined the pipe support types that minimized the support cost while satisfying the design constraints on maximum support load, maximum nozzle load and maximum pipe stress ratio. Performance indices included in the design constraints for a specified design were evaluated by pipe structural analysis using CAESAR II. Since pipe support types were all discrete design variables, an evolutionary algorithm (EA) was used as an optimizer. We successfully obtained the optimal solution that reduced the support cost by 27.2% compared to the initial support cost while all the design requirements were satisfied.

• International Journal of Fluid Machinery and Systems
• /
• v.3 no.4
• /
• pp.352-359
• /
• 2010

In recent years, the market has shown increasing interest in pump-turbines. The prompt availability of pumped storage plants and the benefits to the power system achieved by peak lopping, providing reserve capacity, and rapid response in frequency control are providing a growing advantage. In this context, there is a need to develop pumpturbines that can reliably withstand dynamic operation modes, fast changes of discharge rate by adjusting the variable diffuser vanes, as well as fast changes from pumping to turbine operation. In the first part of the present study, various flow patterns linked to operation of a pump-turbine system are discussed. In this context, pump and turbine modes are presented separately and different load cases are shown in each operating mode. In order to create modern, competitive pump-turbine designs, this study further explains what design challenges should be considered in defining the geometry of a pump-turbine impeller. The second part of the paper describes an innovative, staggered approach to impeller development, applied to a low head pump-turbine project. The first level of the process consists of optimization strategies based on evolutionary algorithms together with 3D in-viscid flow analysis. In the next stage, the hydraulic behavior of both pump mode and turbine mode is evaluated by solving the full 3D Navier-Stokes equations in combination with a robust turbulence model. Finally, the progress in hydraulic design is demonstrated by model test results that show a significant improvement in hydraulic performance compared to an existing reference design.

• Smart Structures and Systems
• /
• v.33 no.1
• /
• pp.65-91
• /
• 2024

The use of five optimization techniques for the prediction of a strength-based concrete mixture's best-fit model is examined in this work. Five optimization techniques are utilized for this purpose: Slime Mold Algorithm (SMA), Black Hole Algorithm (BHA), Multi-Verse Optimizer (MVO), Vortex Search (VS), and Whale Optimization Algorithm (WOA). MATLAB employs a hybrid learning strategy to train an artificial neural network that combines least square estimation with backpropagation. Thus, 72 samples are utilized as training datasets and 31 as testing datasets, totaling 103. The multi-layer perceptron (MLP) is used to analyze all data, and results are verified by comparison. For training datasets in the best-fit models of SMA-MLP, BHA-MLP, MVO-MLP, VS-MLP, and WOA-MLP, the statistical indices of coefficient of determination (R²) in training phase are 0.9603, 0.9679, 0.9827, 0.9841 and 0.9770, and in testing phase are 0.9567, 0.9552, 0.9594, 0.9888 and 0.9695 respectively. In addition, the best-fit structures for training for SMA, BHA, MVO, VS, and WOA (all combined with multilayer perceptron, MLP) are achieved when the term population size was modified to 450, 500, 250, 150, and 500, respectively. Among all the suggested options, VS could offer a stronger prediction network for training MLP.