Fuzzy prediction of AWJ turbulence characteristics by using typical multi-phase flow models

Abstract

For the purpose of improving the working performance of AWJ (Abrasive waterjet) grinding in actual machining, and revealing the unknown influence mechanism of waterjet machining prediction, this research conducted a theoretical and experimental investigation concerning with the influences caused by multi-phase flow models, on the fuzzy prediction of turbulence characteristics. First, typical flow models describing the abrasive waterjet were presented and enunciated; Second, a series of turbulence characteristics were defined to quantitatively demonstrate the waterjet flow, which are responsible for the actual performances of AWJ grinding in the contact zone; Then a new fuzzy prediction system equipped with logic protocols was established and introduced to predict turbulence characteristics based upon the machining parameters by employing different flow models, therefore a set of quantified prediction results generated from the CFD (Computational Fluid Dynamics) simulation, orthogonal experiments and actual measurements can be obtained and distinguished systematically. Through a detailed performance analysis with benchmark indexes and prediction comparisons, the theoretical superiorities and specific applications of these flow models were fully discussed and then an integrated conclusion assessing their inherent influence mechanism was acquired. Based on these innovative achievements, the instantaneous machining inspection or parameter optimization in AWJ grinding process can be facilitated, simultaneously the new research ideas aimed at waterjet monitoring or grinding improvements can be presented as well. ARTICLE HISTORY

Influence analysis of sprinkler irrigation effectiveness using ANFIS

“…The versatility of ANFIS could be acknowledged easily when the effectiveness index evaluation is applied to study the correlative influences of inputs on outputs. For this aim, the evaluation of SIE indexes using ANFIS is regarded as a mathematical function of flow properties and orthogonal experiment employed by irrigation system, and the detailed process of ANFIS establishment can be learned from Liang et al [43,[48][49][50][51] Here 25% of experimental cases are sampled out for instructive training, by which 50 turns are focused for network training and other cases for testing. It should be noted that each case is repeated for 100 trials to reduce any signal disturbance, and the resultant values of effectiveness indexes, including IFR, AWIE, TL, IDS, and S l , should be averaged by these trials.…”

“…As we all know that, sprinkler irrigation is a complicated process in which a bunch of high-pressure sprinkling stream experiences radical and instantaneous changing state caused from different conditional factors [41,42] , some typical flow properties are therefore applied as the crucial factors for irrigation effectiveness analysis: RMS Velocity (R ms ), Turbulence Intensity (T i ), Turbulence Kinetic Energy (T c ), Turbulence Entropy (T e ) and Reynolds Shear Stress (R s ), since they present an accurate and reliable calibration of irrigation effectiveness [40,43,51] . Firstly their reference levels could be determined, with the selected calculation scheme of sprinkling water distribution and infiltration effectiveness, the constructive influences caused by these flow properties on the working capability of sprinkler system are thereby compared with.…”

Segmentation model based on convolutional neural networks for extracting vegetation from Gaofen-2 images

“…17,18 Advancements in deep learning enable us to address these problems with deep neural networks (DNNs). [19][20][21][22] As one of the most important branches of deep learning, the convolutional neural network (CNN) is commonly applied to image data owing to its superior feature learning ability. [23][24][25] The CNN is a deep learning network composed of multiple, nonlinear mapping layers with strong learning abilities that obtain excellent results in image segmentation.…”

A Hybrid Analytic Network Process and Artificial Neural Network (ANP-ANN) Model for Urban Earthquake Vulnerability Assessment

“…Regrettably, to date, no guidelines exist to define both features of the network. It is feasible to find the ideal and optimal network just by utilizing a trial and error procedure [45][46][47][48][49].…”