Active Learning for Gaussian Process Considering Uncertainties With Application to Shape Control of Composite Fuselage

Yue, Xiaowei; Wen, Yuchen; Hunt, James B.; Shi, Jianjun

doi:10.1109/tase.2020.2990401

Cited by 48 publications

(19 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[33]. It is worth noting that the acquisition function in Bayesian optimization shares the same idea with active learning and sequential optimal design [6]. In machine learning domain, active learning iteratively selects the next data point for maximizing information acquisition to improve model performance.…”

Section: Acquisition Functionsmentioning

confidence: 99%

“…Sequential optimal design, which is the term in statistics domain, can explore the most informative new experimental samples according to the current existing data. More detailed literature review on active learning and sequential design refers to [6].…”

Section: Acquisition Functionsmentioning

confidence: 99%

“…Acquisition functions are mathematical equations used to trade off exploration and exploitation to iteratively determine the next-step query point over a bounded domain x ∈ D X [4]. The acquisition functions are closely associated with sequential optimal designs in statistics [5] or active learning functions in machine learning [6]. More discussion related to surrogate models and acquisition functions can be found in Section II.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Robust Asymmetric Kernel Function for Bayesian Optimization, With Application to Image Defect Detection in Manufacturing Systems

AlBahar

Kim

Yue

2022

IEEE Trans. Automat. Sci. Eng.

Self Cite

View full text Add to dashboard Cite

Some response surface functions in complex engineering systems are usually highly nonlinear, unformed, and expensive-to-evaluate. To tackle this challenge, Bayesian optimization, which conducts sequential design via a posterior distribution over the objective function, is a critical method used to find the global optimum of black-box functions. Kernel functions play an important role in shaping the posterior distribution of the estimated function. The widely used kernel function, e.g., radial basis function (RBF), is very vulnerable and susceptible to outliers; the existence of outliers is causing its Gaussian process surrogate model to be sporadic. In this paper, we propose a robust kernel function, Asymmetric Elastic Net Radial Basis Function (AEN-RBF). Its validity as a kernel function and computational complexity are evaluated. When compared to the baseline RBF kernel, we prove theoretically that AEN-RBF can realize smaller mean squared prediction error under mild conditions. The proposed AEN-RBF kernel function can also realize faster convergence to the global optimum. We also show that the AEN-RBF kernel function is less sensitive to outliers, and hence improves the robustness of the corresponding Bayesian optimization with Gaussian processes. Through extensive evaluations carried out on synthetic and real-world optimization problems, we show that AEN-RBF outperforms existing benchmark kernel functions.Note to Practitioners-Some industrial systems cannot be accurately represented by physical models. In this situation, data-driven black-box optimization is necessary for advancing the system automation and intelligence. Bayesian optimization is one widely used strategy for learning the global optimum of black-box functions. Bayesian optimization has been applied to robotics, anomaly detection, automatic learning algorithm configuration, reinforcement learning, and deep learning. This paper proposes one new kernel function, named after AEN-RBF. The new kernel function will make Bayesian optimization with Gaussian processes more robust to outliers and lower the data quality barrier of model training. This paper was motivated by the hyperparameters tuning problem of deep learning models for image defect detection in advanced manufacturing, but the method can be easily extended to other applications where kernel functions are needed. Our proposed method is verified by synthetic and real-world optimization problems.

show abstract

Section: Acquisition Functionsmentioning

confidence: 99%

Section: Acquisition Functionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Asymmetric Kernel Function for Bayesian Optimization, With Application to Image Defect Detection in Manufacturing Systems

AlBahar

Kim

Yue

2022

IEEE Trans. Automat. Sci. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Active learning is already well researched in terms of optimal use of resources for parameter optimization of a model, i.e., generating training data, see [12,[32][33][34]. The process of generating training data means obtaining labels Y train for an input X train , such that a dataset D train = (X train , Y train ) can be used to fit or optimize parameters of a model.…”

Section: Active Learningmentioning

confidence: 99%

“…Hu et al [11] use GP regression to estimate residual stresses field of machined parts from two-dimensional numerical simulations. Yue et al [12] propose two active learning approaches using GP regression for a composite fuselage use case. In the work of Ortali et al [13] GP regression is used as a reduced-order surrogate model for fluid dynamics use cases.…”

Section: Introductionmentioning

confidence: 99%

Gaussian Process Surrogates for Modeling Uncertainties in a Use Case of Forging Superalloys

2022

View full text Add to dashboard Cite

The avoidance of scrap and the adherence to tolerances is an important goal in manufacturing. This requires a good engineering understanding of the underlying process. To achieve this, real physical experiments can be conducted. However, they are expensive in time and resources, and can slow down production. A promising way to overcome these drawbacks is process exploration through simulation, where the finite element method (FEM) is a well-established and robust simulation method. While FEM simulation can provide high-resolution results, it requires extensive computing resources to do so. In addition, the simulation design often depends on unknown process properties. To circumvent these drawbacks, we present a Gaussian Process surrogate model approach that accounts for real physical manufacturing process uncertainties and acts as a substitute for expensive FEM simulation, resulting in a fast and robust method that adequately depicts reality. We demonstrate that active learning can be easily applied with our surrogate model to improve computational resources. On top of that, we present a novel optimization method that treats aleatoric and epistemic uncertainties separately, allowing for greater flexibility in solving inverse problems. We evaluate our model using a typical manufacturing use case, the preforming of an Inconel 625 superalloy billet on a forging press.

show abstract

Design of experiments and machine learning with application to industrial experiments

et al. 2023

View full text Add to dashboard Cite

In the context of product innovation, there is an emerging trend to use Machine Learning (ML) models with the support of Design Of Experiments (DOE). The paper aims firstly to review the most suitable designs and ML models to use jointly in an Active Learning (AL) approach; it then reviews ALPERC, a novel AL approach, and proves the validity of this method through a case study on amorphous metallic alloys, where this algorithm is used in combination with a Random Forest model.

show abstract

Active Learning for Gaussian Process Considering Uncertainties With Application to Shape Control of Composite Fuselage

Cited by 48 publications

References 30 publications

A Robust Asymmetric Kernel Function for Bayesian Optimization, With Application to Image Defect Detection in Manufacturing Systems

A Robust Asymmetric Kernel Function for Bayesian Optimization, With Application to Image Defect Detection in Manufacturing Systems

Gaussian Process Surrogates for Modeling Uncertainties in a Use Case of Forging Superalloys

Design of experiments and machine learning with application to industrial experiments

Contact Info

Product

Resources

About