An official website of the United States government
A multiterminal obstacle-avoiding pathfinding approach is proposed. The approach is inspired by deep image learning. The key idea is based on training a conditional generative adversarial network (cGAN) to interpret a pathfinding task as a graphical bitmap and consequently map a pathfinding task onto a pathfinding solution represented by another bitmap. To enable the proposed cGAN pathfinding, a methodology for generating synthetic dataset is also proposed. The cGAN model is implemented in Python/Keras, trained on synthetically generated data, evaluated on practical VLSI benchmarks, and compared with state-of-the-art. Due to effective parallelization on GPU hardware, the proposed approach yields a state-of-the-art-like wirelength and a better runtime and throughput for moderately complex pathfinding tasks. However, the runtime and throughput with the proposed approach remain constant with an increasing task complexity, promising orders of magnitude improvement over state-of-the-art in complex pathfinding tasks. The cGAN pathfinder can be exploited in numerous high throughput applications, such as, navigation, tracking, and routing in complex VLSI systems. The last is of particular interest to this work.
more »
« less
Deep Learning of Forced Convection Heat Transfer
Abstract We present the deep learning model for internal forced convection heat transfer problems. Conditional generative adversarial networks (cGAN) are trained to predict the solution based on a graphical input describing fluid channel geometries and initial flow conditions. Without interactively solving the physical governing equations, a trained cGAN model rapidly approximates the flow temperature, Nusselt number (Nu), and friction factor (f) of a flow in a heated channel over Reynolds number ranging from 100 to 27,750. For an effective training, we optimize the dataset size, training epoch, and a hyperparameter λ. The cGAN model exhibited an accuracy up to 97.6% when predicting the local distributions of Nu and f. We also show that the trained cGAN model can predict for unseen fluid channel geometries such as narrowed, widened, and rotated channels if the training dataset is properly augmented. A simple data augmentation technique improved the model accuracy up to 70%. This work demonstrates the potential of deep learning approach to enable cost-effective predictions for thermofluidic processes.
more »
« less
- Award ID(s):
- 2053413
- PAR ID:
- 10320044
- Date Published:
- Journal Name:
- Journal of Heat Transfer
- Volume:
- 144
- Issue:
- 2
- ISSN:
- 0022-1481
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Predicting the behavior of nanomaterials under various conditions presents a significant challenge due to their complex microstructures. While high-fidelity modeling techniques, such as molecular dynamics (MD) simulations, are effective, they are also computationally demanding. Machine learning (ML) models have opened new avenues for the rapid exploration of design spaces. In this work, we developed a deep learning framework based on a conditional generative adversarial network (cGAN) to predict the evolution of grain boundary (GB) networks in nanocrystalline materials under mechanical loads, incorporating both morphological and atomic details. We conducted MD simulations on nanocrystalline tungsten and used the resulting ground-truth data to train our cGAN model. We assessed the performance of our cGAN model by comparing it to a Convolutional Autoencoder (ConvAE) model and examining the impact of changes in geometric morphology and loading conditions on the model's performance. Our cGAN model demonstrated high accuracy in predicting GB network evolution under a variety of conditions. This developed framework shows potential for predicting various materials' behaviors across a wide range of nanomaterials.more » « less
-
Traditional machine learning approaches for recognizing modes of transportation rely heavily on hand-crafted feature extraction methods which require domain knowledge. So, we propose a hybrid deep learning model: Deep Convolutional Bidirectional-LSTM (DCBL) which combines convolutional and bidirectional LSTM layers and is trained directly on raw sensor data to predict the transportation modes. We compare our model to the traditional machine learning approaches of training Support Vector Machines and Multilayer Perceptron models on extracted features. In our experiments, DCBL performs better than the feature selection methods in terms of accuracy and simplifies the data processing pipeline. The models are trained on the Sussex-Huawei Locomotion-Transportation (SHL) dataset. The submission of our team, Vahan, to SHL recognition challenge uses an ensemble of DCBL models trained on raw data using the different combination of sensors and window sizes and achieved an F1-score of 0.96 on our test data.more » « less
-
Abstract Prediction of the spatial‐temporal dynamics of the fluid flow in complex subsurface systems, such as geologic storage, is typically performed using advanced numerical simulation methods that solve the underlying governing physical equations. However, numerical simulation is computationally demanding and can limit the implementation of standard field management workflows, such as model calibration and optimization. Standard deep learning models, such as RUNET, have recently been proposed to alleviate the computational burden of physics‐based simulation models. Despite their powerful learning capabilities and computational appeal, deep learning models have important limitations, including lack of interpretability, extensive data needs, weak extrapolation capacity, and physical inconsistency that can affect their adoption in practical applications. We develop a Fluid Flow‐based Deep Learning (FFDL) architecture for spatial‐temporal prediction of important state variables in subsurface flow systems. The new architecture consists of a physics‐based encoder to construct physically meaningful latent variables, and a residual‐based processor to predict the evolution of the state variables. It uses physical operators that serve as nonlinear activation functions and imposes the general structure of the fluid flow equations to facilitate its training with data pertaining to the specific subsurface flow application of interest. A comprehensive investigation of FFDL, based on a field‐scale geologic storage model, is used to demonstrate the superior performance of FFDL compared to RUNET as a standard deep learning model. The results show that FFDL outperforms RUNET in terms of prediction accuracy, extrapolation power, and training data needs.more » « less
-
We introduce a wall model for large-eddy simulation (WMLES) applicable to rough surfaces with Gaussian and non-Gaussian distributions for both the transitionally and fully rough regimes. The model is applicable to arbitrary complex geometries where roughness elements are assumed to be underresolved, i.e. subgrid-scale roughness. The wall model is implemented using a multi-hidden-layer feedforward neural network, with the mean geometric properties of the roughness topology and near-wall flow quantities serving as input. The optimal set of non-dimensional input features is identified using information theory, selecting variables that maximize information about the output while minimizing redundancy among inputs. The model also incorporates a confidence score based on Gaussian process modelling, enabling the detection of potentially low model performance for untrained rough surfaces. The model is trained using a direct numerical simulation (DNS) roughness database comprising approximately 200 cases. The roughness geometries for the database are selected from a large repository through active learning. This approach ensures that the rough surfaces incorporated into the database are the most informative, achieving higher model performance with fewer DNS cases compared with passive learning techniques. The performance of the model is evaluated bothaprioriandaposterioriin WMLES of turbulent channel flows with rough walls. Over 550 channel flow cases are considered, including untrained roughness geometries, roughness Reynolds numbers and grid resolutions for both transitionally and fully rough regimes. Our rough-wall model offers higher accuracy than existing models, generally predicting wall shear stress within an accuracy range of 1%–15 %. The performance of the model is also assessed on a high-pressure turbine blade with two different rough surfaces. We show that the new wall model predicts the skin friction and the mean velocity deficit induced by the rough surface on the blade within 1%–10 % accuracy except the region with transition or shock waves. This work extends the building-block flow wall model (BFWM) introduced by Lozano-Durán & Bae (2023.J. Fluid Mech.963, A35) for smooth walls, expanding the BFWM framework to account for rough-wall scenarios.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1115/1.4052893
