Dimensionality-reduction-based surrogate models for real-time design space exploration of a jet engine compressor blade

Bird, Gregory David; Gorrell, Steven E.; Salmon, John L.

doi:10.1016/j.ast.2021.107077

Cited by 12 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While physical models are inherently three-dimensional, FE simulations often use 1D or 2D elements for satisfactory results. Dimension reduction of solid models can significantly reduce model size with improved mesh quality and reasonably accurate results (Bird et al, 2021). 1D elements are suitable for modeling linear geometries such as long shafts, beams and columns, while 2D plate/shell elements represent thin 3D structures such as sheet metal parts and printed circuit boards (Carrera and Scano, 2024).…”

Section: Dimension Reduction Of Modelmentioning

confidence: 99%

See 1 more Smart Citation

Efficiency enhancement techniques in finite element analysis: navigating complexity for agile design exploration

Haider

2024

AEAT

View full text Add to dashboard Cite

Purpose This paper aims to comprehensively explore techniques for reducing solution time in finite element analysis (FEA), addressing the critical need for expediting computations to facilitate agile design exploration within project timelines. Design/methodology/approach Drawing from a wide array of literature sources, this paper synthesizes and analyzes various methodologies used to enhance the efficiency of FEA. Techniques are scrutinized in terms of their applicability, effectiveness and potential limitations. Findings The review signifies application of linear assumptions across multiple facets of analysis and delves into matrix order reduction strategies, geometry simplification, symmetry exploitation, submodeling and mesh attribute control. It reveals how these techniques can effectively reduce computational burdens while maintaining acceptable levels of accuracy. Research limitations/implications While this review provides a comprehensive overview of existing efficiency enhancement techniques in FEA, it acknowledges inherent limitations of any synthesis-based study. Future research should focus on refining these methodologies. Practical implications The insights provided in this paper offer practical guidance for structural engineers and researchers seeking to optimize FEA workflows. By implementing these techniques, practitioners can expedite solution times and enhance their ability to explore design alternatives efficiently ultimately leading to cost savings and more robust structures. Originality/value This review contributes to the existing literature by offering a comprehensive synthesis of efficiency enhancement techniques in FEA. By highlighting the originality and value of each discussed methodology, this paper provides a roadmap for future research and practical implementation in the field of structural engineering.

show abstract

Section: Dimension Reduction Of Modelmentioning

confidence: 99%

Section: Techniques To Reduce Solution Timementioning

confidence: 99%

Efficiency enhancement techniques in finite element analysis: navigating complexity for agile design exploration

Haider

2024

AEAT

View full text Add to dashboard Cite

show abstract

“…To accelerate the design space exploration, many researchers focused on building surrogate models for FEA to establish the relationship between design parameters and responses. [2][3][4][5] Wang et al [3] proposed a convolutional neural network to establish a relationship between the material parameters and its peak stress. Although this model achieves high accuracy of 98.79%, the feasibility of developing a stress analysis agent model using a deep learning approach cannot be verified due to the simple model setup and single target task.…”

Section: Introductionmentioning

confidence: 99%

Accelerating Analysis for Structure Design via Deep Learning Surrogate Models

Shao

Chen

Wang

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Using computer simulation tools such as finite element analysis (FEA) to perform material stress analysis is a common design method in engineering practice. In order to model more realistic real‐world systems, simulation models have become more complex, and calculation becomes more expensive as a result. The rise of artificial intelligence technologies has made it possible to integrate deep learning methods and material stress analysis. Herein, FEA software is employed to obtain a large number of analysis cases as training samples and uses a fully connected neural network and long‐short‐term memory neural network as surrogate models, which can predict the stress distribution and stress sequence in the process of the bullet impacting target plates with different materials. These models can give results similar to FEA with 92.19% and 92.41% accuracy, respectively. The experimental results show that the deep learning surrogate models have great potential in material stress analysis.

show abstract

“…Buna çözüm olarak, türevlerin hesaplama maliyetini tasarım değişkeni sayısından bağımsız hale getiren bir yöntem olan eşlenik (Adjoint) tabanlı türev hesaplama yöntemi geliştirilmiştir [2]. Fakat bu tür yöntemlerin dezavantajı, başlangıç tasarımına büyük ölçüde bağımlı olmasından ve problem çözümünde yerel minimum noktasına takılmasından dolayı optimum noktaların bulunmasında zorlukla karşılaşılmasıdır [3]. Türevden bağımsız algoritmalar ise, türev tanımını kullanmadan çalışan algoritmalardır.…”

Section: Giriş (Introduction)unclassified

Design of the ONERA M6 wing by shape optimization under uncertainty

DEMİR,

GÖRGÜLÜARSLAN,

ARADAĞ ÇELEBİOĞLU

2023

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Aerodinamik şekil optimizasyon süreçleri, tekli veya çoklu tasarım hedeflerini sağlayan kompleks problemler için sıklıkla kullanılmaktadır. Geleneksel ve belirsizliğin dahil edilmediği problemlere nazaran belirsizliklerin dahil edildiği ve yüksek değişken sayısına sahip sağlam optimizasyon yöntemlerinin hesaplama yükü oldukça yüksektir. Bu problemin önüne geçmek için, bu çalışmada, temel bileşenler analizi, tümevarımsal tasarım araştırma yöntemi ile entegre edilerek ONERA M6 kanadının sağlam şekil optimizasyonu gerçekleştirilmiştir. Temel bileşenler analizi yöntemi, kanat geometrisinin tasarım değişkeni sayısını azaltmak için tercih edilmiştir. Hesaplamalı akışkanlar dinamiği analizi kullanımı sonucunda ortaya çıkan yüksek çözüm süreleri ise, temel bileşenler analizi yönteminin bir vekil model tekniği olan radyal bazlı fonksiyon ile birlikte kullanılmasıyla oluşturulan bir veri tahmin modeli ile azaltılmıştır. Transonik akış rejimi için Mach sayısındaki belirsizlikler, önerilen tümevarımsal tasarım araştırma yöntemi tabanlı yönteme dahil edilerek sağlam optimizasyon gerçekleştirilmiştir. Sağlam tasarımların performans tahminlerinin hesaplamalı akışkanlar dinamiği analiz sonuçlarına oldukça yakın elde edilmesi, önerilen yöntemin etkinliğini göstermiştir.

show abstract

Dimensionality-reduction-based surrogate models for real-time design space exploration of a jet engine compressor blade

Cited by 12 publications

References 27 publications

Efficiency enhancement techniques in finite element analysis: navigating complexity for agile design exploration

Efficiency enhancement techniques in finite element analysis: navigating complexity for agile design exploration

Accelerating Analysis for Structure Design via Deep Learning Surrogate Models

Design of the ONERA M6 wing by shape optimization under uncertainty

Contact Info

Product

Resources

About