A bi-level meta-modeling approach for structural optimization using modified POD bases and Diffuse Approximation

2013 ◽  
Vol 127 ◽  
pp. 19-28 ◽  
Author(s):  
Balaji Raghavan ◽  
Mohamed Hamdaoui ◽  
Manyu Xiao ◽  
Piotr Breitkopf ◽  
Pierre Villon
Keyword(s):  
Structural Optimization ◽  
Modeling Approach ◽  
Meta Modeling ◽  
Diffuse Approximation

scholarly journals Implicit constraint handling for shape optimisation with POD-morphing

2012 ◽  
Author(s):  
Balaji Raghavan ◽  
Manyu Xiao ◽  
Piotr Breitkopf ◽  
Pierre Villon
Keyword(s):  
Structural Optimization ◽  
Proper Orthogonal Decomposition ◽  
Orthogonal Decomposition ◽  
Shape Optimisation ◽  
Design Domain ◽  
Cad Models ◽  
Typical Shape ◽  
Global Understanding ◽  
Proper Orthogonal ◽  
Diffuse Approximation

In the former paper, we have introduced an original morphing approach based on Proper Orthogonal Decomposition (POD) of shapes, designed to replace parametrized CAD models in structural optimization. Here, we expand the method to interpolate exclusively between admissible instances of structural shapes, thus permitting a global understanding of the design domain and also reducing the size of the optimisation problem. The result is a bilevel reparametrization approach for structural geometries based on Diffuse Approximation in a properly chosen locally linearized space, and the geometric parameters are replaced with the smallest set of variables needed to represent a manifold of admissible shapes for a chosen precision. We demonstrate the approach in a typical shape optimisation problem.

scholarly journals Adaptive meta-modeling-based simulation optimization in basin-scale optimum water allocation: a comparative analysis of meta-models

2015 ◽  
Vol 18 (3) ◽  
pp. 446-465 ◽  
Author(s):  
Golnazalsadat Mirfenderesgi ◽  
S. Jamshid Mousavi
Keyword(s):  
River Basin ◽  
Water Allocation ◽  
Optimization Problems ◽  
Computational Cost ◽  
Search Space ◽  
Support Vector ◽  
Meta Model ◽  
Modeling Approach ◽  
Basin Scale ◽  
Meta Modeling

Incorporating river basin simulation models in heuristic optimization algorithms can help modelers address complex, basin-scale water resource problems. We have developed a hybrid optimization-simulation model by linking a stretching particle swarm optimization (SPSO) algorithm and the MODSIM river basin decision support system (DSS), and have used the SPSO-MODSIM model to optimize water allocation at basin scale. Due to high computational cost of the SPSO-MODSIM model, we have, subsequently, used four meta-model types of artificial neural networks (ANN), support vector machines (SVM), kriging and polynomial response functions, replacing the MODSIM DSS, in an adaptively learning meta-modeling approach. The performances of the meta-models are first compared in two Ackley and Dejong benchmark functions optimization problems, and the meta-models are then evaluated by solving the Atrak river basin water allocation optimization problem in Iran. The results demonstrate that independent of the meta-model type, the sequentially space-filling meta-modeling approach can improve the performance of meta-models in the course of optimization by adaptively locating the promising regions of the search space where more samples need to be generated. However, the ANN and SVM meta-models perform better than others in saving the number of costly, original objective function evaluations.

Mission Engineering and Design using Real-Time Strategy Games: An Explainable-AI Approach

2021 ◽  
pp. 1-15
Author(s):  
Adam Dachowicz ◽  
Kshitij Mall ◽  
Prajwal Balasubramani ◽  
Apoorv Maheshwari ◽  
Jitesh H. Panchal ◽  
...  
Keyword(s):  
Real Time ◽  
Initial Conditions ◽  
Computational Design ◽  
Mission Design ◽  
Modeling Approach ◽  
Strategy Games ◽  
Explainable Ai ◽  
Additional Data Collection ◽  
Meta Modeling ◽  
Rts Game

Abstract In this paper, we adapt computational design approaches, widely used by the engineering design community, to address the unique challenges associated with mission design using RTS games. Specifically, we present a modeling approach that combines experimental design techniques, meta-modeling using convolutional neural networks (CNNs), uncertainty quantification, and explainable AI (XAI). We illustrate the approach using an open-source real-time strategy (RTS) game called microRTS. The modeling approach consists of microRTS player agents (bots), design of experiments that arranges games between identical agents with asymmetric initial conditions, and an AI infused layer comprising CNNs, XAI, and uncertainty analysis through Monte Carlo Dropout Network analysis that allows analysis of game balance. A sample balanced game and corresponding predictions and SHapley Additive exPlanations (SHAP) are presented in this study. Three additional perturbations were introduced to this balanced gameplay and the observations about important features of the game using SHAP are presented. Our results show that this analysis can successfully predict probability of win for self-play microRTS games, as well as capture uncertainty in predictions that can be used to guide additional data collection to improve the model, or refine the game balance measure.

scholarly journals An objective meta-modeling approach for indentation-based material characterization

2017 ◽  
Vol 107 ◽  
pp. 31-44 ◽  
Author(s):  
Liang Meng ◽  
Balaji Raghavan ◽  
Olivier Bartier ◽  
Xavier Hernot ◽  
Gerard Mauvoisin ◽  
...  
Keyword(s):  
Material Characterization ◽  
Modeling Approach ◽  
Meta Modeling
Sign in / Sign up

Export Citation Format

Share Document