scholarly journals Multi-Fidelity Multi-Objective Efficient Global Optimization Applied to Airfoil Design Problems

2017 ◽  
Vol 7 (12) ◽  
pp. 1318 ◽  
Author(s):  
Atthaphon Ariyarit ◽  
Masahiro Kanazaki
Keyword(s):  
Global Optimization ◽  
Efficient Global Optimization ◽  
Design Problems ◽  
Multi Objective

Simulation-based multi-objective muffler optimization using efficient global optimization

2020 ◽  
Vol 68 (6) ◽  
pp. 441-458
Author(s):  
Jobin Puthuparampil ◽  
Pierre Sullivan
Keyword(s):  
Global Optimization ◽  
Transmission Loss ◽  
Effective Means ◽  
Plug Flow ◽  
Efficient Global Optimization ◽  
Nsga Ii ◽  
Multi Objective ◽  
Simulation Based ◽  
Gas Generators ◽  
Computer Based

Noise control of large diesel and natural gas generators is achieved through industrial mufflers. Design of such mufflers relies heavily on general guidelines. However, these guidelines are not suitable for complex mufflers; instead, computer-based optimization provides an effective means of design. Optimization of a plug flow muffler is conducted in this work with a multi-objective (transmission loss and pressure drop) finite element simulation-based optimization using the efficient global optimization (EGO) algorithm. The EGO algorithm is shown to be well suited for computationally expensive muffler optimization, performing vastly better than genetic algorithms, such as the commonly used NSGA-II algorithm.

Multi-Objective Selection of Cutting Conditions in Advanced Machining Processes via an Efficient Global Optimization Approach

2014 ◽  
Author(s):  
Mohamed Aly ◽  
Karim Hamza ◽  
Mohammed Tauhiduzzaman ◽  
Mouhab Meshreki ◽  
Ashraf O. Nassef ◽  
...  
Keyword(s):  
Global Optimization ◽  
High Speed ◽  
Diamond Turning ◽  
Cutting Conditions ◽  
Efficient Global Optimization ◽  
Experimental Sample ◽  
Machining Processes ◽  
Multi Objective ◽  
Ultra Precision ◽  
Selection Of

Optimum selection of cutting conditions in high-speed and ultra-precision machining processes often poses a challenging task due to several reasons; such as the need for costly experimental setup and the limitation on the number of experiments that can be performed before tool degradation starts becoming a source of noise in the readings. Moreover, oftentimes there are several objectives to consider, some of which may be conflicting, while others may be somewhat correlated. Pareto-optimality analysis is needed for conflicting objectives; however the existence of several objectives (high-dimension Pareto space) makes the generation and interpretation of Pareto solutions difficult. The approach adopted in this paper is a modified multi-objective efficient global optimization (m-EGO). In m-EGO, sample data points from experiments are used to construct Kriging meta-models, which act as predictors for the performance objectives. Evolutionary multi-objective optimization is then conducted to spread a population of new candidate experiments towards the zones of search space that are predicted by the Kriging models to have favorable performance, as well as zones that are under-explored. New experiments are then used to update the Kriging models, and the process is repeated until termination criteria are met. Handling a large number of objectives is improved via a special selection operator based on principle component analysis (PCA) within the evolutionary optimization. PCA is used to automatically detect correlations among objectives and perform the selection within a reduced space in order to achieve a better distribution of experimental sample points on the Pareto frontier. Case studies show favorable results in ultra-precision diamond turning of Aluminum alloy as well as high-speed drilling of woven composites.

Trust Region Based Mode Pursuing Sampling Method for Global Optimization of High Dimensional Design Problems

2015 ◽  
Vol 137 (2) ◽  
Author(s):  
George H. Cheng ◽  
Adel Younis ◽  
Kambiz Haji Hajikolaei ◽  
G. Gary Wang
Keyword(s):  
Global Optimization ◽  
Optimization Problems ◽  
Trust Region ◽  
Standard Test ◽  
Black Box ◽  
High Dimensional ◽  
Efficient Global Optimization ◽  
Test Problems ◽  
Design Problems ◽  
Design Variables

Mode pursuing sampling (MPS) was developed as a global optimization algorithm for design optimization problems involving expensive black box functions. MPS has been found to be effective and efficient for design problems of low dimensionality, i.e., the number of design variables is less than 10. This work integrates the concept of trust regions into the MPS framework to create a new algorithm, trust region based mode pursuing sampling (TRMPS2), with the aim of dramatically improving performance and efficiency for high dimensional problems. TRMPS2 is benchmarked against genetic algorithm (GA), dividing rectangles (DIRECT), efficient global optimization (EGO), and MPS using a suite of standard test problems and an engineering design problem. The results show that TRMPS2 performs better on average than GA, DIRECT, EGO, and MPS for high dimensional, expensive, and black box (HEB) problems.

Sign in / Sign up

Export Citation Format

Share Document