An official website of the United States government
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
Inverse Design With Conditional Cascaded Diffusion Models
Abstract Adjoint-based design optimizations are usually computationally expensive and those costs scale with resolution. To address this, researchers have proposed machine learning approaches for inverse design that can predict higher-resolution solutions from lower cost/resolution ones. Due to the recent success of diffusion models over traditional generative models, we extend the use of diffusion models for multi-resolution tasks by proposing the conditional cascaded diffusion model (cCDM). Compared to GANs, cCDM is more stable to train, and each diffusion model within the cCDM can be trained independently, thus each model’s parameters can be tuned separately to maximize the performance of the pipeline. Our study compares cCDM against a cGAN model with transfer learning. Our results demonstrate that the cCDM excels in capturing finer details, preserving volume fraction constraints, and minimizing compliance errors in multi-resolution tasks when a sufficient amount of high-resolution training data (more than 102 designs) is available. Furthermore, we explore the impact of training data size on the performance of both models. While both models show decreased performance with reduced high-resolution training data, the cCDM loses its superiority to the cGAN model with transfer learning when training data is limited (less than 102), and we show the break-even point for this transition. Also, we highlight that while the diffusion model may achieve better pixel-wise performance in both low-resolution and high-resolution scenarios, this does not necessarily guarantee that the model produces optimal compliance error or constraint satisfaction.
more »
« less
- Award ID(s):
- 1943699
- PAR ID:
- 10651203
- Publisher / Repository:
- American Society of Mechanical Engineers
- Date Published:
- 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
-
Abstract The biodiversity crisis necessitates spatially extensive methods to monitor multiple taxonomic groups for evidence of change in response to evolving environmental conditions. Programs that combine passive acoustic monitoring and machine learning are increasingly used to meet this need. These methods require large, annotated datasets, which are time‐consuming and expensive to produce, creating potential barriers to adoption in data‐ and funding‐poor regions. Recently released pre‐trained avian acoustic classification models provide opportunities to reduce the need for manual labelling and accelerate the development of new acoustic classification algorithms through transfer learning. Transfer learning is a strategy for developing algorithms under data scarcity that uses pre‐trained models from related tasks to adapt to new tasks.Our primary objective was to develop a transfer learning strategy using the feature embeddings of a pre‐trained avian classification model to train custom acoustic classification models in data‐scarce contexts. We used three annotated avian acoustic datasets to test whether transfer learning and soundscape simulation‐based data augmentation could substantially reduce the annotated training data necessary to develop performant custom acoustic classifiers. We also conducted a sensitivity analysis for hyperparameter choice and model architecture. We then assessed the generalizability of our strategy to increasingly novel non‐avian classification tasks.With as few as two training examples per class, our soundscape simulation data augmentation approach consistently yielded new classifiers with improved performance relative to the pre‐trained classification model and transfer learning classifiers trained with other augmentation approaches. Performance increases were evident for three avian test datasets, including single‐class and multi‐label contexts. We observed that the relative performance among our data augmentation approaches varied for the avian datasets and nearly converged for one dataset when we included more training examples.We demonstrate an efficient approach to developing new acoustic classifiers leveraging open‐source sound repositories and pre‐trained networks to reduce manual labelling. With very few examples, our soundscape simulation approach to data augmentation yielded classifiers with performance equivalent to those trained with many more examples, showing it is possible to reduce manual labelling while still achieving high‐performance classifiers and, in turn, expanding the potential for passive acoustic monitoring to address rising biodiversity monitoring needs.more » « less
-
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
-
Modern NLP applications have enjoyed a great boost utilizing neural networks models. Such deep neural models, however, are not applicable to most human languages due to the lack of annotated training data for various NLP tasks. Cross-lingual transfer learning (CLTL) is a viable method for building NLP models for a low-resource target language by leveraging labeled data from other (source) languages. In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance. Unlike most existing methods that rely only on language-invariant features for CLTL, our approach coherently utilizes both language invariant and language-specific features at instance level. Our model leverages adversarial networks to learn language-invariant features, and mixture-of-experts models to dynamically exploit the similarity between the target language and each individual source language1. This enables our model to learn effectively what to share between various languages in the multilingual setup. Moreover, when coupled with unsupervised multilingual embeddings, our model can operate in a zero-resource setting where neither target language training data nor cross-lingual resources are available. Our model achieves significant performance gains over prior art, as shown in an extensive set of experiments over multiple text classification and sequence tagging.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1115/DETC2024-143607
