scholarly journals A Novel Active Optimization Approach for Rapid and Efficient Design Space Exploration Using Ensemble Machine Learning

2020 ◽  
Vol 143 (3) ◽  
Author(s):  
Opeoluwa Owoyele ◽  
Pinaki Pal
Keyword(s):  
Machine Learning ◽  
Design Space Exploration ◽  
Design Space ◽  
Optimization Technique ◽  
Global Optimum ◽  
Optimization Techniques ◽  
Machine Learning Algorithms ◽  
Optimization Approach ◽  
Ic Engine ◽  
Weak Learner

Abstract In this work, a novel design optimization technique based on active learning, which involves dynamic exploration and exploitation of the design space of interest using an ensemble of machine learning algorithms, is presented. In this approach, a hybrid methodology incorporating an explorative weak learner (regularized basis function model) that fits high-level information about the response surface and an exploitative strong learner (based on committee machine) that fits finer details around promising regions identified by the weak learner is employed. For each design iteration, an aristocratic approach is used to select a set of nominees, where points that meet a threshold merit value as predicted by the weak learner are selected for evaluation. In addition to these points, the global optimum as predicted by the strong learner is also evaluated to enable rapid convergence to the actual global optimum once the most promising region has been identified by the optimizer. This methodology is first tested by applying it to the optimization of a two-dimensional multi-modal surface and, subsequently, to a complex internal combustion (IC) engine combustion optimization case with nine control parameters related to fuel injection, initial thermodynamic conditions, and in-cylinder flow. It is found that the new approach significantly lowers the number of function evaluations that are needed to reach the optimum design configuration (by up to 80%) when compared to conventional optimization techniques, such as particle swarm and genetic algorithm-based optimization techniques.

scholarly journals A Novel Active Optimization Approach for Rapid and Efficient Design Space Exploration Using Ensemble Machine Learning

2019 ◽  
Author(s):  
Opeoluwa Owoyele ◽  
Pinaki Pal
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Active Learning ◽  
Design Space ◽  
Particle Swarm ◽  
Global Optimum ◽  
Optimization Techniques ◽  
Machine Learning Algorithms ◽  
Ic Engine ◽  
Weak Learner

Abstract In this work, a novel design optimization technique based on active learning, which involves dynamic exploration and exploitation of the design space of interest using an ensemble of machine learning algorithms, is presented. In this approach, a hybrid methodology incorporating an explorative weak learner (regularized basis function model) which fits high-level information about the response surface, and an exploitative strong learner (based on committee machine) that fits finer details around promising regions identified by the weak learner, is employed. For each design iteration, an aristocratic approach is used to select a set of nominees, where points that meet a threshold merit value as predicted by the weak learner are selected to be evaluated using expensive function evaluation. In addition to these points, the global optimum as predicted by the strong learner is also evaluated to enable rapid convergence to the actual global optimum once the most promising region has been identified by the optimizer. This methodology is first tested by applying it to the optimization of a two-dimensional multi-modal surface. The performance of the new active learning approach is compared with traditional global optimization methods, namely micro-genetic algorithm (μGA) and particle swarm optimization (PSO). It is demonstrated that the new optimizer is able to reach the global optimum much faster, with a significantly fewer number of function evaluations. Subsequently, the new optimizer is also applied to a complex internal combustion (IC) engine combustion optimization case with nine control parameters related to fuel injection, initial thermodynamic conditions, and in-cylinder flow. It is again found that the new approach significantly lowers the number of function evaluations that are needed to reach the optimum design configuration (by up to 80%) when compared to particle swarm and genetic algorithm-based optimization techniques.

Bayesian Network Structure Optimization for Improved Design Space Mapping for Design Exploration With Materials Design Applications

2017 ◽  
Author(s):  
Conner Sharpe ◽  
Clinton Morris ◽  
Benjamin Goldsberry ◽  
Carolyn Conner Seepersad ◽  
Michael R. Haberman
Keyword(s):  
Machine Learning ◽  
Bayesian Network ◽  
Design Space ◽  
Computational Cost ◽  
Materials Design ◽  
Optimization Techniques ◽  
Machine Learning Algorithms ◽  
Data Set ◽  
Design Problems ◽  
Highly Nonlinear

Modern design problems present both opportunities and challenges, including multifunctionality, high dimensionality, highly nonlinear multimodal responses, and multiple levels or scales. These factors are particularly important in materials design problems and make it difficult for traditional optimization algorithms to search the space effectively, and designer intuition is often insufficient in problems of this complexity. Efficient machine learning algorithms can map complex design spaces to help designers quickly identify promising regions of the design space. In particular, Bayesian network classifiers (BNCs) have been demonstrated as effective tools for top-down design of complex multilevel problems. The most common instantiations of BNCs assume that all design variables are independent. This assumption reduces computational cost, but can limit accuracy especially in engineering problems with interacting factors. The ability to learn representative network structures from data could provide accurate maps of the design space with limited computational expense. Population-based stochastic optimization techniques such as genetic algorithms (GAs) are ideal for optimizing networks because they accommodate discrete, combinatorial, and multimodal problems. Our approach utilizes GAs to identify optimal networks based on limited training sets so that future test points can be classified as accurately and efficiently as possible. This method is first tested on a common machine learning data set, and then demonstrated on a sample design problem of a composite material subjected to a planar sound wave.

scholarly journals MODC: A Pareto-Optimal Optimization Approach for Network Traffic Classification Based on the Divide and Conquer Strategy

Information ◽  
2018 ◽  
Vol 9 (9) ◽  
pp. 233 ◽  
Author(s):  
Zuleika Nascimento ◽  
Djamel Sadok
Keyword(s):  
Machine Learning ◽  
Network Traffic ◽  
Machine Learning Algorithms ◽  
Divide And Conquer ◽  
Pareto Optimal ◽  
Optimization Approach ◽  
Traffic Classification ◽  
Multi Objective ◽  
Network Traffic Classification ◽  
Changes Over Time

Network traffic classification aims to identify categories of traffic or applications of network packets or flows. It is an area that continues to gain attention by researchers due to the necessity of understanding the composition of network traffics, which changes over time, to ensure the network Quality of Service (QoS). Among the different methods of network traffic classification, the payload-based one (DPI) is the most accurate, but presents some drawbacks, such as the inability of classifying encrypted data, the concerns regarding the users’ privacy, the high computational costs, and ambiguity when multiple signatures might match. For that reason, machine learning methods have been proposed to overcome these issues. This work proposes a Multi-Objective Divide and Conquer (MODC) model for network traffic classification, by combining, into a hybrid model, supervised and unsupervised machine learning algorithms, based on the divide and conquer strategy. Additionally, it is a flexible model since it allows network administrators to choose between a set of parameters (pareto-optimal solutions), led by a multi-objective optimization process, by prioritizing flow or byte accuracies. Our method achieved 94.14% of average flow accuracy for the analyzed dataset, outperforming the six DPI-based tools investigated, including two commercial ones, and other machine learning-based methods.

Ranked-Based Sensitivity Analysis for Size Optimization of Structures

2015 ◽  
Vol 137 (12) ◽  
Author(s):  
Babak Dizangian ◽  
Mohammad Reza Ghasemi
Keyword(s):  
Sensitivity Analysis ◽  
Design Space ◽  
Optimization Technique ◽  
Optimization Procedure ◽  
Global Optimum ◽  
Size Optimization ◽  
Second Phase ◽  
Local Optimum ◽  
Blast Search ◽  
Sliding Technique

This article proposes a novel ranked-based method for size optimization of structures. This method uses violation-based sensitivity analysis and borderline adaptive sliding technique (ViS-BLAST) on the margin of feasible nonfeasible (FNF) design space. ViS-BLAST maybe considered a multiphase optimization technique, where in the first phase, the first arbitrary local optimum is found by few analyses and in the second phase, a sequence of local optimum points is found through jumps and BLASTs until the global optimum is found. In fact, this technique reaches a sensitive margin zone where the global optimum is located, with a small number of analyses, utilizing a space-degradation strategy (SDS). This strategy substantially degrades the high order searching space and then proceeds with the proposed ViS-BLAST search for the optimum design. Its robustness and effectiveness are then defied by some well-known benchmark examples. The ViS-BLAST not only speeds up the optimization procedure but also it ensures nonviolated optimum designs.

Sign in / Sign up

Export Citation Format

Share Document