A flow feature detection method for modeling pressure distribution around a cylinder in non-uniform flows by using a convolutional neural network

Abstract

In a myriad of engineering situations, we often hope to establish a model which can acquire load conditions around structures through flow features detection. A data-driven method is developed to predict the pressure on a cylinder from velocity distributions in its wake flow. The proposed deep learning neural network is constituted with convolutional layers and fully–connected layers: The convolutional layers can process the velocity information by features extraction, which are gathered by the fully-connected layers to obtain the pressure coefficients. By comparing the output data of the typical network with Computational Fluid Dynamics (CFD) results as reference values, it suggests that the present convolutional neural network (CNN) is able to predict the pressure coefficient in the vicinity of the trained Reynolds numbers with various inlet flow profiles and achieves a high overall precision. Moreover, a transfer learning approach is adopted to preserve the feature detection ability by keeping the parameters in the convolutional layers unchanged while shifting parameters in the fully-connected layers. Further results show that this transfer learning network has nearly the same precision while significantly lower cost. The active prospects of convolutional neural network in fluid mechanics have also been demonstrated, which can inspire more kinds of loads prediction in the future.

Klasifikasi Tekstur Kematangan Buah Jeruk Manis Berdasarkan Tingkat Kecerahan Warna dengan Metode Deep Learning Convolutional Neural Network

“…Seperti pada komputer pengujian dan dilatih memakai data set yang memiliki label dan dalam jumlah besar selanjutnya diubah kedalam nilai piksel pada gambar untuk dijadikan representasi internal atau feature vector [21] kemudian selanjutnya pengklasifikasian didapatkan dan digunakan pada deteksi untuk mengklasifikasikan pola pada masukan input [22]. Deep learning merupakan pembelajaran reprensentasi untuk membentuk arsitektur jaringan syaraf tiruan dengan multi lapisan layer [23]. Input layer, hidden layer, dan output layer dalam lapisan deep learning, [24].…”

Real World Object Detection Dataset for Quadcopter Unmanned Aerial Vehicle Detection

“…For the purposes of computer vision ANNs typically utilize a combination of Convolutional Neural Networks (CNNs) and Fully Connected Layers (FCs). CNNs have proven to be an effective modeling solution for applications ranging from computer vision (image classification, object detection, neural style transfer) [53], [54], cybersecurity [55], time series processing [56], fluid mechanics [57] and general physics challenges [58]. A simplified CNN based process is shown in Fig.…”

Deep learning-based automated and universal bubble detection and mask extraction in complex two-phase flows

“…In recent years, deep learning has been recognized as a powerful tool in the field of digital image processing, and has also proved promising in addressing various problems in fluid mechanics 20 – 25 . These studies are finding ways to overcome long-lasting problems by applying a deep learning-based methodology to solve governing equations or to improve experimental techniques, which have been shown to enhance model accuracy and save on overall data processing cost, which is dominated by human resources.…”