Using neural networks to predict icephobic performance

• URL: http://arxiv.org/abs/2008.00966v1
• Date: Fri, 31 Jul 2020 05:37:06 GMT
• Title: Using neural networks to predict icephobic performance
• Authors: Rahul Ramachandran
• Abstract summary: Icephobic surfaces inspired by superhydrophobic surfaces offer a passive solution to the problem of icing. Modeling icephobicity is challenging because some material features that aid superhydrophobicity can adversely affect the icephobic performance. This study presents a new approach based on artificial neural networks to model icephobicity.
• Score: 0.5076419064097732
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Icephobic surfaces inspired by superhydrophobic surfaces offer a passive solution to the problem of icing. However, modeling icephobicity is challenging because some material features that aid superhydrophobicity can adversely affect the icephobic performance. This study presents a new approach based on artificial neural networks to model icephobicity. Artificial neural network models were developed to predict the icephobic performance of concrete. The models were trained on experimental data to predict the surface ice adhesion strength and the coefficient of restitution (COR) of water droplet bouncing off the surface under freezing conditions. The material and coating compositions, and environmental condition were used as the models' input variables. A multilayer perceptron was trained to predict COR with a root mean squared error of 0.08, and a 90% confidence interval of [0.042, 0.151]. The model had a coefficient of determination of 0.92 after deployment. Since ice adhesion strength varied over a wide range of values for the samples, a mixture density network was model was developed to learn the underlying relationship in the multimodal data. Coefficient of determination for the model was 0.96. The relative importance of the input variables in icephobic performance were calculated using permutation importance. The developed models will be beneficial to optimize icephobicity of concrete.

Related papers

• Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations [6.4020980835163765]
  This paper introduces a novel deep architecture named Unicorn, designed to forecast weekly sea ice. Our model integrates multiple time series images within its architecture to enhance its forecasting performance.
  arXiv  Detail & Related papers  (2024-05-07T01:17:06Z)
• Towards Theoretical Understandings of Self-Consuming Generative Models [56.84592466204185]
  This paper tackles the emerging challenge of training generative models within a self-consuming loop. We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models. We present results for kernel density estimation, delivering nuanced insights such as the impact of mixed data training on error propagation.
  arXiv  Detail & Related papers  (2024-02-19T02:08:09Z)
• Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation [1.4364491422470593]
  We show how three loss functions affect the performance of CNN models trained to predict the dominant ice type in Sentinel-1 images. Despite the fact that Dice and Focal loss produce higher metrics, results from cross-entropy seem generally more physically consistent.
  arXiv  Detail & Related papers  (2023-10-26T04:18:00Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• A Hybrid Deep Neural Operator/Finite Element Method for Ice-Sheet Modeling [0.0]
  We develop a hybrid approach to approximate existing ice sheet computational models at a fraction of their cost. We show that the resulting hybrid model is very accurate and it is an order of magnitude faster than the traditional finite element model. We then target the evolution of the Humboldt glacier in Greenland and show that our hybrid model can provide accurate statistics of the glacier mass loss.
  arXiv  Detail & Related papers  (2023-01-26T20:28:34Z)
• Physics-informed CoKriging model of a redox flow battery [68.8204255655161]
  Redox flow batteries (RFBs) offer the capability to store large amounts of energy cheaply and efficiently. There is a need for fast and accurate models of the charge-discharge curve of a RFB to potentially improve the battery capacity and performance. We develop a multifidelity model for predicting the charge-discharge curve of a RFB.
  arXiv  Detail & Related papers  (2021-06-17T00:49:55Z)
• Capabilities of Deep Learning Models on Learning Physical Relationships: Case of Rainfall-Runoff Modeling with LSTM [0.0]
  This study investigates the relationships which deep learning methods can identify between the input and output data. Daily precipitation and mean air temperature were used as model input to estimate daily flow discharge. The results of this study indicated that a deep learning method may not properly learn the explicit physical relationships between input and target variables.
  arXiv  Detail & Related papers  (2021-06-15T08:36:16Z)
• Churn Reduction via Distillation [54.5952282395487]
  We show an equivalence between training with distillation using the base model as the teacher and training with an explicit constraint on the predictive churn. We then show that distillation performs strongly for low churn training against a number of recent baselines.
  arXiv  Detail & Related papers  (2021-06-04T18:03:31Z)
• Hybrid Physics and Deep Learning Model for Interpretable Vehicle State Prediction [75.1213178617367]
  We propose a hybrid approach combining deep learning and physical motion models. We achieve interpretability by restricting the output range of the deep neural network as part of the hybrid model. The results show that our hybrid model can improve model interpretability with no decrease in accuracy compared to existing deep learning approaches.
  arXiv  Detail & Related papers  (2021-03-11T15:21:08Z)
• Contextual Dropout: An Efficient Sample-Dependent Dropout Module [60.63525456640462]
  Dropout has been demonstrated as a simple and effective module to regularize the training process of deep neural networks. We propose contextual dropout with an efficient structural design as a simple and scalable sample-dependent dropout module. Our experimental results show that the proposed method outperforms baseline methods in terms of both accuracy and quality of uncertainty estimation.
  arXiv  Detail & Related papers  (2021-03-06T19:30:32Z)
• Constraining subglacial processes from surface velocity observations using surrogate-based Bayesian inference [0.0]
  Basal motion is the primary mechanism for ice flux outside Antarctica, yet a widely applicable model for predicting it remains elusive. This is due to the difficulty in both observing small-scale bed properties and predicting a time-varying water pressure on which basal motion putatively depends. We take a Bayesian approach to these problems by coupling models of ice dynamics and subglacial hydrology and conditioning on observations of surface velocity in southwestern Greenland.
  arXiv  Detail & Related papers  (2020-06-22T16:47:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.