An Automated Machine Learning-Genetic Algorithm (AutoML-GA) Framework With Active Learning for Design Optimization

2021 ◽  
Author(s):  
Opeoluwa Owoyele ◽  
Pinaki Pal ◽  
Alvaro Vidal Torreira
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Active Learning ◽  
Design Optimization ◽  
Automated Machine Learning

An Automated Machine Learning-Genetic Algorithm Framework With Active Learning for Design Optimization

2021 ◽  
Vol 143 (8) ◽  
Author(s):  
Opeoluwa Owoyele ◽  
Pinaki Pal ◽  
Alvaro Vidal Torreira
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Design Optimization ◽  
Fuel Injection ◽  
A Priori ◽  
Computational Cost ◽  
Learning Approach ◽  
Data Generation ◽  
Compression Ignition Engine ◽  
Hyperparameter Selection

AbstractThe use of machine learning (ML)-based surrogate models is a promising technique to significantly accelerate simulation-driven design optimization of internal combustion (IC) engines, due to the high computational cost of running computational fluid dynamics (CFD) simulations. However, training the ML models requires hyperparameter selection, which is often done using trial-and-error and domain expertise. Another challenge is that the data required to train these models are often unknown a priori. In this work, we present an automated hyperparameter selection technique coupled with an active learning approach to address these challenges. The technique presented in this study involves the use of a Bayesian approach to optimize the hyperparameters of the base learners that make up a super learner model. In addition to performing hyperparameter optimization (HPO), an active learning approach is employed, where the process of data generation using simulations, ML training, and surrogate optimization is performed repeatedly to refine the solution in the vicinity of the predicted optimum. The proposed approach is applied to the optimization of a compression ignition engine with control parameters relating to fuel injection, in-cylinder flow, and thermodynamic conditions. It is demonstrated that by automatically selecting the best values of the hyperparameters, a 1.6% improvement in merit value is obtained, compared to an improvement of 1.0% with default hyperparameters. Overall, the framework introduced in this study reduces the need for technical expertise in training ML models for optimization while also reducing the number of simulations needed for performing surrogate-based design optimization.

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.

An Automated Machine Learning-Genetic Algorithm (AutoML-GA) Framework With Active Learning for Design Optimization

2020 ◽  
Author(s):  
Opeoluwa Owoyele ◽  
Pinaki Pal ◽  
Alvaro Vidal Torreira
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Design Optimization ◽  
Test Performance ◽  
Computational Cost ◽  
Learning Approach ◽  
Data Generation ◽  
Compression Ignition Engine ◽  
Ic Engine ◽  
Hyperparameter Selection

Abstract The use of machine learning (ML) based surrogate models is a promising technique to significantly accelerate simulation-based design optimization of IC engines, due to the high computational cost of running computational fluid dynamics (CFD) simulations. However, surrogate-based optimization for IC engine applications suffers from two main issues. First, training ML models requires hyperparameter selection, often involving trial-and-error combined with domain expertise. The second issue is that the data required to train these models is often unknown a priori. In this work, we present an automated hyperparameter selection technique coupled with an active learning approach to address these challenges. The technique presented in this study involves the use of a Bayesian approach to optimize the hyperparameters of the base learners that make up a Super Learner model to obtain better test performance. In addition to performing hyperparameter optimization (HPO), an active learning approach is employed, where the process of data generation using simulations, ML training, and surrogate optimization, is performed repeatedly to refine the solution in the vicinity of the predicted optimum. The proposed approach is applied to the optimization of a compression ignition engine with control parameters relating to fuel injection, in-cylinder flow, and thermodynamic conditions. It is demonstrated that by automatically selecting the best values of the hyperparameters, a 1.6% improvement in merit value is obtained, compared to an improvement of 1.0% with default hyperparameters. Overall, the framework introduced in this study reduces the need for technical expertise in training ML models for optimization, while also reducing the number of simulations needed for performing surrogate-based design optimization.

scholarly journals Development and Initial Validation of Two Brief Measures of Left-wing Authoritarianism: A Machine Learning Approach

2021 ◽  
Author(s):  
Thomas H Costello ◽  
Christopher Patrick
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Political Violence ◽  
Community Sample ◽  
Learning Approach ◽  
Left Wing ◽  
Initial Validation ◽  
Machine Learning Approach ◽  
Automated Machine Learning ◽  
Political Spectrum

Although authoritarianism has predominantly been studied among conservatives, newer work on left-wing authoritarianism (LWA) has suggested that authoritarian individuals exist on both poles of the political spectrum. A 39-item multidimensional measure, the Left-wing Authoritarianism Index, was recently developed to measure LWA. The present study used a fully automated machine learning approach (i.e., a genetic algorithm) in a large, demographically representative American sample (N = 834) to generate two abbreviated versions of the LWA Index. A second community sample (N = 477) was used to conduct extensive validational tests of the abbreviated measures, which comprise 25- and 13-items. The abbreviated forms demonstrated remarkable convergence with the full LWA Index in terms of their psychometric (e.g., internal consistency) and distributional (e.g., mean, standard deviation, skew, kurtosis) properties. Further, this convergence extended to virtually identical cross-measure patterns of correlations with 14 external criteria, including need for chaos, political violence, anomia, and low institutional trust. In light of these results, the LWA-25 and LWA-13 scales appeared to function effectively as measures of LWA. We conclude by examining the items retained (vs. excluded) by the genetic algorithm to clarify the central vs. peripheral conceptual elements of LWA.

scholarly journals Application of an automated machine learning-genetic algorithm (AutoML-GA) coupled with computational fluid dynamics simulations for rapid engine design optimization

2021 ◽  
pp. 146808742110234
Author(s):  
Opeoluwa Owoyele ◽  
Pinaki Pal ◽  
Alvaro Vidal Torreira ◽  
Daniel Probst ◽  
Matthew Shaxted ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fluid Dynamics ◽  
Genetic Algorithm ◽  
Computational Fluid Dynamics ◽  
Design Optimization ◽  
Internal Combustion Engines ◽  
Bayesian Optimization ◽  
Cfd Simulations ◽  
Engine Design ◽  
Design Optimum

In recent years, the use of machine learning-based surrogate models for computational fluid dynamics (CFD) simulations has emerged as a promising technique for reducing the computational cost associated with engine design optimization. However, such methods still suffer from drawbacks. One main disadvantage is that the default machine learning (ML) hyperparameters are often severely suboptimal for a given problem. This has often been addressed by manually trying out different hyperparameter settings, but this solution is ineffective in case of a high-dimensional hyperparameter space. Besides this problem, the amount of data needed for training is also not known a priori. In response to these issues that need to be addressed, the present work describes and validates an automated active learning approach, AutoML-GA, for surrogate-based optimization of internal combustion engines. In this approach, a Bayesian optimization technique is used to find the best machine learning hyperparameters based on an initial dataset obtained from a small number of CFD simulations. Subsequently, a genetic algorithm is employed to locate the design optimum on the ML surrogate surface. In the vicinity of the design optimum, the solution is refined by repeatedly running CFD simulations at the projected optima and adding the newly obtained data to the training dataset. It is demonstrated that AutoML-GA leads to a better optimum with a lower number of CFD simulations, compared to the use of default hyperparameters. The proposed framework offers the advantage of being a more hands-off approach that can be readily utilized by researchers and engineers in industry who do not have extensive machine learning expertise.

Machine Learning Accelerated Genetic Algorithms for Computational Materials Search

2018 ◽  
Author(s):  
Steen Lysgaard ◽  
Paul C. Jennings ◽  
Jens Strabo Hummelshøj ◽  
Thomas Bligaard ◽  
Tejs Vegge
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Genetic Algorithms ◽  
Au Nanoparticles ◽  
Learning Model ◽  
Energy Calculations ◽  
Atomic Distribution ◽  
Machine Learning Model ◽  
Fold Reduction ◽  
Computational Materials

A machine learning model is used as a surrogate fitness evaluator in a genetic algorithm (GA) optimization of the atomic distribution of Pt-Au nanoparticles. The machine learning accelerated genetic algorithm (MLaGA) yields a 50-fold reduction of required energy calculations compared to a traditional GA.

Bandit-Based Automated Machine Learning

2018 ◽  
Author(s):  
Silvia Cristina Nunes das Dores ◽  
Carlos Soares ◽  
Duncan Ruiz
Keyword(s):  
Machine Learning ◽  
Automated Machine Learning

scholarly journals Hybrid Seven-bar Press Mechanism

2018 ◽  
Vol 12 (3) ◽  
pp. 181-187
Author(s):  
M. Erkan Kütük ◽  
L. Canan Dülger
Keyword(s):  
Genetic Algorithm ◽  
Objective Function ◽  
Design Optimization ◽  
Hybrid System ◽  
Degrees Of Freedom ◽  
Dimensional Synthesis ◽  
Design Variables ◽  
Optimization Study ◽  
Metal Stamping

An optimization study with kinetostatic analysis is performed on hybrid seven-bar press mechanism. This study is based on previous studies performed on planar hybrid seven-bar linkage. Dimensional synthesis is performed, and optimum link lengths for the mechanism are found. Optimization study is performed by using genetic algorithm (GA). Genetic Algorithm Toolbox is used with Optimization Toolbox in MATLAB®. The design variables and the constraints are used during design optimization. The objective function is determined and eight precision points are used. A seven-bar linkage system with two degrees of freedom is chosen as an example. Metal stamping operation with a dwell is taken as the case study. Having completed optimization, the kinetostatic analysis is performed. All forces on the links and the crank torques are calculated on the hybrid system with the optimized link lengths

scholarly journals How to measure uncertainty in uncertainty sampling for active learning

2021 ◽  
Author(s):  
Vu-Linh Nguyen ◽  
Mohammad Hossein Shaker ◽  
Eyke Hüllermeier
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Sampling Strategies ◽  
Total Uncertainty ◽  
Uncertainty Sampling ◽  
Different Types ◽  
Alternative Approaches ◽  
Active Learner ◽  
Probabilistic Nature ◽  
Different Sources

AbstractVarious strategies for active learning have been proposed in the machine learning literature. In uncertainty sampling, which is among the most popular approaches, the active learner sequentially queries the label of those instances for which its current prediction is maximally uncertain. The predictions as well as the measures used to quantify the degree of uncertainty, such as entropy, are traditionally of a probabilistic nature. Yet, alternative approaches to capturing uncertainty in machine learning, alongside with corresponding uncertainty measures, have been proposed in recent years. In particular, some of these measures seek to distinguish different sources and to separate different types of uncertainty, such as the reducible (epistemic) and the irreducible (aleatoric) part of the total uncertainty in a prediction. The goal of this paper is to elaborate on the usefulness of such measures for uncertainty sampling, and to compare their performance in active learning. To this end, we instantiate uncertainty sampling with different measures, analyze the properties of the sampling strategies thus obtained, and compare them in an experimental study.

Sign in / Sign up

Export Citation Format

Share Document