A multi-fidelity competitive sampling method for surrogate-based stacking sequence optimization of composite shells with multiple cutouts

Tian, Kuo; Ma, Xiangtao; Li, Zengcong; Lin, Shiyao; Wang, Bo; Waas, Anthony M.

doi:10.1016/j.ijsolstr.2020.02.007

Cited by 25 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, the NN model will be trained using a combination of computational data and experimental data with variable fidelity. [31,32] In addition, the trained NN model will be implemented into the EST model for better computation efficiency. ORCID Anthony M. Waas https://orcid.org/0000-0002-4916-2102…”

Section: Discussionmentioning

confidence: 99%

Determining damage initiation of carbon fiber reinforced polymer composites using machine learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

Computational progressive failure analysis (PFA) is vital for the analysis of carbon fiber reinforced polymer (CFRP) composites. The damage initiation criterion is one of the essential components of a PFA code to determine the transition of a material's state from pristine or microscopically damaged to macroscopically damaged. In this paper, data-driven models are developed to determine the matrix damage initiation with the objective to save computation time. For 2D plane stress states, the computational cost for determining damage initiation can be dramatically reduced by implementing a binary search (BS) algorithm and predictive machine learning models. Machine learning models are evaluated against a regression problem of predicting damage crack angle as well as against a classification problem for predicting damage initiation outright. It is found that regression models perform much better for plane stress and 3D stress states when generating failure envelopes. In both cases, a neural network is able to produce a failure envelope that is over 99% accurate while reducing computational cost by over 90%.

show abstract

Section: Discussionmentioning

confidence: 99%

Determining damage initiation of carbon fiber reinforced polymer composites using machine learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another solution is to keep developing more efficient yet accurate multiscale modeling approaches such as MSG, MHT and some reduced-order models (e.g., self-consistent clustering analysis [106], proper orthogonal decomposition (POD) reduced model [107], and non-uniform transformation field analysis [108]). Recently, the multi-fidelity modeling has been used to effectively generate training data for ANN models in composite materials and structures [109][110][111], which provides another approach to balance the accuracy and efficiency in training an ANN model [112]. Also, it would be attractive if a model can be tuned for both low-and high-fidelity models [113].…”

Section: Computational Cost Of High-fidelity Simulation Modelsmentioning

confidence: 99%

How machine learning can help the design and analysis of composite materials and structures?

Liu¹,

Tian²,

Tao³

et al. 2020

Preprint

View full text Add to dashboard Cite

Machine learning models are increasingly used in many engineering fields thanks to the widespread digital data, growing computing power, and advanced algorithms. Artificial neural networks (ANN) is the most popular machine learning model in recent years. Although many ANN models have been used in the design and analysis of composite materials and structures, there are still some unsolved issues that hinder the acceptance of ANN models in the practical design and analysis of composite materials and structures. Moreover, the emerging machine learning techniques are posting new opportunities and challenges in the data-based design paradigm. This paper aims to give a state-of-the-art literature review of ANN models in the nonlinear constitutive modeling, multiscale surrogate modeling, and design optimization of composite materials and structures. This review has been designed to focus on the discussion of the general frameworks and benefits of ANN models to the above problems. Moreover, challenges and opportunities in each key problem are identified and discussed. This paper is expected to open the discussion of future research scope and new directions to enable efficient, robust, and accurate data-driven design and analysis of composite materials and structures.

show abstract

“…In a like manner, in the composite structures field, to improve the stacking optimization of laminated composite shells with multiple cutouts, a multifidelity competitive sampling method was developed by Tian et al (2020). The optimal result, obtained by the authors, of total material cost by the proposed method decreases by 23.0% than the optimal result by the Latin hypercube sampling (LHS) method.…”

Section: Introductionmentioning

confidence: 99%

Multiobjective optimization of the LASER aircraft wing’s composite structural design

Ricco

Coimbra

Gomes

2021

AEAT

View full text Add to dashboard Cite

Purpose Aircraft wings, one of the most important parts of an aircraft, have seen changes in its topological and design arrangement of both the internal structures and external shape during the past decades. This study, a numerical, aims to minimize the weight of multilaminate composite aerospace structures using multiobjective optimization. Design/methodology/approach The methodology started with the determination of the requirements, both imposed by the certifying authority and those inherent to the light, aerobatic, simple, economic and robust (LASER) project. After defining the requirements, the loads that the aircraft would be subjected to during its operation were defined from the flight envelope considering finite element analysis. The design vector consists of material choice for each laminate of the structure (20 in total), ply number and lay-up sequence (respecting the manufacturing rules) and main spar position to obtain a lightweight and cheap structure, respecting the restrictions of stress, margins of safety, displacements and buckling. Findings The results obtained indicated a predominance of the use of carbon fiber. The predominant orientation found on the main spar flange was 0° with its location at 28% of the local chord, in the secondary and main web were ±45°, the skins also had the main orientation at ±45°. Originality/value The key innovations in this paper include the evaluation, development and optimization of a laminated composite structure applied to a LASER aircraft wings considering both structural performance and manufacturing costs in multiobjetive optimization. This paper is one of the most advanced investigations performed to composite LASER aircraft.

show abstract

A multi-fidelity competitive sampling method for surrogate-based stacking sequence optimization of composite shells with multiple cutouts

Cited by 25 publications

References 50 publications

Determining damage initiation of carbon fiber reinforced polymer composites using machine learning

Determining damage initiation of carbon fiber reinforced polymer composites using machine learning

How machine learning can help the design and analysis of composite materials and structures?

Multiobjective optimization of the LASER aircraft wing’s composite structural design

Contact Info

Product

Resources

About