scholarly journals Industrial Applications of Intelligent Adaptive Sampling Methods for Multi-Objective Optimization

2020 ◽  
Author(s):  
Jesper Kristensen ◽  
Waad Subber ◽  
Yiming Zhang ◽  
Sayan Ghosh ◽  
Natarajan Chennimalai Kumar ◽  
...  
Keyword(s):  
Adaptive Sampling ◽  
Sampling Methods ◽  
Industrial Applications ◽  
Multi Objective Optimization ◽  
Multi Objective

Expected-Improvement-Based Methods for Adaptive Sampling in Multi-Objective Optimization Problems

2016 ◽  
Author(s):  
Jesper Kristensen ◽  
You Ling ◽  
Isaac Asher ◽  
Liping Wang
Keyword(s):  
Convex Hull ◽  
Design Optimization ◽  
Adaptive Sampling ◽  
Pareto Front ◽  
Performance Metrics ◽  
Sampling Methods ◽  
Optimization Problems ◽  
Expected Improvement ◽  
Multi Objective Optimization ◽  
Multi Objective

Adaptive sampling methods have been used to build accurate meta-models across large design spaces from which engineers can explore data trends, investigate optimal designs, study the sensitivity of objectives on the modeling design features, etc. For global design optimization applications, adaptive sampling methods need to be extended to sample more efficiently near the optimal domains of the design space (i.e., the Pareto front/frontier in multi-objective optimization). Expected Improvement (EI) methods have been shown to be efficient to solve design optimization problems using meta-models by incorporating prediction uncertainty. In this paper, a set of state-of-the-art methods (hypervolume EI method and centroid EI method) are presented and implemented for selecting sampling points for multi-objective optimizations. The classical hypervolume EI method uses hyperrectangles to represent the Pareto front, which shows undesirable behavior at the tails of the Pareto front. This issue is addressed utilizing the concepts from physical programming to shape the Pareto front. The modified hypervolume EI method can be extended to increase local Pareto front accuracy in any area identified by an engineer, and this method can be applied to Pareto frontiers of any shape. A novel hypervolume EI method is also developed that does not rely on the assumption of hyperrectangles, but instead assumes the Pareto frontier can be represented by a convex hull. The method exploits fast methods for convex hull construction and numerical integration, and results in a Pareto front shape that is desired in many practical applications. Various performance metrics are defined in order to quantitatively compare and discuss all methods applied to a particular 2D optimization problem from the literature. The modified hypervolume EI methods lead to dramatic resource savings while improving the predictive capabilities near the optimal objective values.

Lightweight Design of a Brake Caliper

2013 ◽  
Author(s):  
Federico Maria Ballo ◽  
Massimiliano Gobbi ◽  
Giampiero Mastinu ◽  
Amir Pishdad
Keyword(s):  
Cross Sections ◽  
Lightweight Design ◽  
Optimal Solution ◽  
Element Model ◽  
Industrial Applications ◽  
Structural Topology ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Beam Elements ◽  
Starting Point

As lightweight design assumes greater importance in road vehicles development, the present paper is mainly devoted to the structural optimization of a brake caliper. In the first part of the study a simplified finite element model based on beam elements of a brake caliper has been developed and validated. By using the developed model, a multi-objective optimization has been completed. The total mass of the caliper and the deformations at some critical locations have been minimised. The considered design variables are related to the shape of the caliper and the cross sections of the beam elements. The obtained optimal solutions are characterized by an asymmetric shape of the caliper. Optimised symmetric shapes currently used have been compared with the asymmetric ones in terms of performance. In the second part of the study, a detailed analysis on the optimal caliper shape has been carried out by performing a structural topology optimization. The minimum compliance problem has been solved using the SIMP (solid isotropic material with penalization) approach and the optimal solution has been compared with the ones obtained by applying the multi-objective optimization on the simplified model (beam elements). The obtained design solutions represent a good starting point for future developments in actual industrial applications.

Multi-objective optimization of tensile properties of the corrugated composite sheet

2021 ◽  
pp. 002199832110595
Author(s):  
Nastaran Bahrami-Novin ◽  
Ehsan Mahdavi ◽  
Mahdi Shaban ◽  
Hashem Mazaheri
Keyword(s):  
Tensile Test ◽  
Optimization Problems ◽  
Lightweight Design ◽  
Industrial Applications ◽  
Experimental Results ◽  
Displacement Curve ◽  
Multi Objective Optimization ◽  
Element Analysis ◽  
Programming Technique ◽  
Multi Objective

Corrugated sheets with optimized mechanical properties are crucial for lightweight design in industrial applications. This study considered and optimized a corrugated sheet with a sinusoidal profile to enhance elastic modulus, tensile-bending coupling, and weight reduction. For this aim, first, flat specimens consisting of E-glass woven fiber and epoxy resin were made by hand lay-up method, following ASTM D3039. The tensile test determined young’s modulus of flat samples. Afterward, two molds with supports were fabricated. The corrugated specimens were constructed and exposed to a standard tensile test. The finite element analysis was used to simulate the tensile test of corrugated samples. The numerical force-displacement curve is derived from numerical analysis and verified by experimental results. After that, two multi-objective optimization problems, mass-constraint and global optimization, were implemented. Analytical formulations were verified by numerical and experimental results and utilized for optimization purposes. The genetic algorithm was used to examine and confirm trade-off behavior between objective functions. The Pareto fronts diagrams for mentioned two multi-objective optimization problem were obtained. Finally, the optimum parameters are calculated by using the LINMAP (Linear Programming Technique for Multi-dimensional Analysis of Preference) method.

Bayesian Optimization for Multi-Objective High-Dimensional Turbine Aero Design

2021 ◽  
Author(s):  
Yiming Zhang ◽  
Sayan Ghosh ◽  
Thomas Vandeputte ◽  
Liping Wang
Keyword(s):  
Design Space Exploration ◽  
Design Space ◽  
Industrial Applications ◽  
Bayesian Optimization ◽  
High Dimensional ◽  
Multi Objective Optimization ◽  
Loop Optimization ◽  
Multi Objective ◽  
Input Design ◽  
Design Variables

Abstract Industrial design fundamentally relies on high-dimensional multi-objective optimization. Bayesian Optimization (BO) based on Gaussian Processes (GPs) has been shown to be effective for this practice where new designs are picked in each iteration for varying objectives including optimization and model refinement. This paper introduces two industrial applications of BO for turbine aero design. The first application is GE’s Aviation & Power DT4D Turbo Aero Design with 32 design variables. It has a single objective to maximize with 32 input/design variables and thus considered high-dimensional in terms of the input space. BO has significantly succeeded the traditional design schemes. It has been shown that finding the maximum-EI points (inner-loop optimization) could be critical and the influence of inner-loop optimization was evaluated. The second application is for multi-objective optimization. Each simulation run is the aggregate result from multiple CFD runs tuning geometry and took 24 hours to complete. BO has been capable to extend the existing Pareto front with a few additional runs. BO has been searching along the border of the design space and therefore motivate the open-up of design space exploration. For both applications, BO successfully guide the CFD run and allocate design variables more optimum than previous design approaches.

Synchronous R-NSGA-II: An Extended Preference-Based Evolutionary Algorithm for Multi-Objective Optimization

Informatica ◽  
2015 ◽  
Vol 26 (1) ◽  
pp. 33-50 ◽  
Author(s):  
Ernestas Filatovas ◽  
Olga Kurasova ◽  
Karthik Sindhya
Keyword(s):  
Evolutionary Algorithm ◽  
Multi Objective Optimization ◽  
Nsga Ii ◽  
Multi Objective
Sign in / Sign up

Export Citation Format

Share Document