Advancing Reacting Flow Simulations with Data-Driven Models

Zdybał, Kamila; D’Alessio, G.; Aversano, G.; Malik, Mohammad Rafi; Coussement, Axel; Sutherland, James C.; Parente, Alessandro

doi:10.1017/9781108896214.022

Cited by 8 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Local Principal Component Analysis (LPCA) is a dimensionality reduction technique, proposed by Kambhatla et al [37], based on the projection of high-dimensional data onto k sets of lower-dimensional manifolds. Although this algorithm was originally proposed for dimensionality reduction, it has been frequently utilized for clustering tasks in the last years [38][39][40][41]. In addition, it has been shown that, when applied to reacting flow databases, LPCA can ensure a better partitioning with respect to popular unsupervised algorithms such as k-Means and Self-Organzing Maps (SOMs) [32].…”

Section: Clustering Via Local Principal Component Analysismentioning

confidence: 99%

See 1 more Smart Citation

Automated adaptive chemistry for Large Eddy Simulations of turbulent reacting flows

Amaduzzi,

D’Alessio,

Pagani

et al. 2024

Combustion and Flame

View full text Add to dashboard Cite

Section: Clustering Via Local Principal Component Analysismentioning

confidence: 99%

“…• Initialization: the clusters' centers of mass (centroids) Additional information on the PCA decomposition and reconstruction error, as well as the on LPCA partitioning algorithm, can be found in [38][39][40][41].…”

Section: Clustering Via Local Principal Component Analysismentioning

confidence: 99%

Automated adaptive chemistry for Large Eddy Simulations of turbulent reacting flows

Amaduzzi,

D’Alessio,

Pagani

et al. 2024

Combustion and Flame

View full text Add to dashboard Cite

“…However, as PCA assumes linearity, Frequently, it identifies additional components to compensate for non-linearity in the data, resulting in an overestimate of the actual number of dimensions in question, given that typical response flow data exhibit strong non-linear characteristics. To address this limitation of traditional PCA in non-linear systems, In the field of combustion research, there has been a proposal to utilize non-linear methods such as non-linear PCA, Kernel PCA (KPCA) [112], Isometric Mapping (IsoMap) [113], T-distributed Stochastic Neighbour Embedding (T-SNE) [114], and Autoencoders (AEs) [115] are some of the techniques used. Recently, fresh data-driven algorithms for regime identification using Convolutional Neural Networks (CNNs) have been developed [116].…”

Section: And DL Applications In Aero-engine Combustionmentioning

confidence: 99%

A review: Applications of machine learning and deep learning in aerospace engineering and aero-engine engineering

Wang,

2024

AEI

View full text Add to dashboard Cite

The domain of aeronautical engineering and aero-engine engineering has witnessed considerable interest in the application of machine learning (ML) and deep learning (DL) techniques, revolutionizing various aspects of the field. This review provides a comprehensive review of the application of ML and DL in aerospace engineering and aero-engine engineering, focusing on aircraft aerodynamics, CFD, aircraft design and aeroacoustics and for aero-engine engineering focusing on health state evaluation, component optimization, blade defect detection and combustion. The review highlights the advantages and challenges of ML methods, presenting key concepts and strategies for ML. Furthermore, in terms of technical applications, DL has the potential to be on par with ML, despite being a branch of ML. The review further emphasizes the pressing requirement for a comprehensive examination of DL techniques concerning data-driven challenges within the realms of aerospace engineering and aero-engine engineering. It introduces representative DL methods and presents their mathematical definitions and illustrative applications.

show abstract

“…With the advent of data science [5,6,7], new challenges and research opportunities are emerging, related to how to make the best use of the data provided by experiments and high-fidelity simulations. A thorough description of the use of data-driven machine learning in combustion can be found in Ref.…”

Section: Introductionmentioning

confidence: 99%

A predictive physics-aware hybrid reduced order model for reacting flows

Corrochano¹,

Freitas²,

Parente³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this work, a new hybrid predictive Reduced Order Model (ROM) is proposed to solve reacting flow problems. This algorithm is based on a dimensionality reduction using Proper Orthogonal Decomposition (POD) combined with deep learning architectures. The number of degrees of freedom is reduced from thousands of temporal points to a few POD modes with their corresponding temporal coefficients. Two different deep learning architectures have been tested to predict the temporal coefficients, based on recursive (RNN) and convolutional (CNN) neural networks. From each architecture, different models have been created to understand the behavior of each parameter of the neural network. Results show that these architectures are able to predict the temporal coefficients of the POD modes, as well as the whole snapshots. The RNN shows lower prediction error for all the variables analyzed. The model was also found capable of predicting more complex simulations showing transfer learning capabilities.

show abstract

Advancing Reacting Flow Simulations with Data-Driven Models

Cited by 8 publications

References 0 publications

Automated adaptive chemistry for Large Eddy Simulations of turbulent reacting flows

Automated adaptive chemistry for Large Eddy Simulations of turbulent reacting flows

A review: Applications of machine learning and deep learning in aerospace engineering and aero-engine engineering

A predictive physics-aware hybrid reduced order model for reacting flows

Contact Info

Product

Resources

About