scholarly journals Machine Learning Applications in Modelling and Analysis of Base Pressure in Suddenly Expanded Flows

Aerospace ◽  
2021 ◽  
Vol 8 (11) ◽  
pp. 318
Author(s):  
Jaimon Dennis Quadros ◽  
Sher Afghan Khan ◽  
Abdul Aabid ◽  
Mohammad Shohag Alam ◽  
Muneer Baig
Keyword(s):  
Machine Learning ◽  
Pressure Ratio ◽  
Geometric Parameters ◽  
Base Pressure ◽  
Support Vector ◽  
Nozzle Pressure ◽  
Machine Learning Applications ◽  
The Right ◽  
Base Drag ◽  
Pressure Analysis

Base pressure becomes a decisive factor in governing the base drag of aerodynamic vehicles. While several experimental and numerical methods have already been used for base pressure analysis in suddenly expanded flows, their implementation is quite time-consuming. Therefore, we must develop a progressive approach to determine base pressure (β). Furthermore, a direct consideration of the influence of flow and geometric parameters cannot be studied by using these methods. This study develops a platform for data-driven analysis of base pressure (β) prediction in suddenly expanded flows, in which the influence of flow and geometric parameters including Mach number (M), nozzle pressure ratio (η), area ratio (α), and length to diameter ratio (φ) have been studied. Three different machine learning (ML) models, namely, artificial neural networks (ANN), support vector machine (SVM), and random forest (RF), have been trained using a large amount of data developed from response equations. The response equations for base pressure (β) were created using the response surface methodology (RSM) approach. The predicted results are compared with the experimental results to validate the proposed platform. The results obtained from this work can be applied in the right way to maximize base pressure in rockets and missiles to minimize base drag.

scholarly journals Effect of Area Ratio on Base Pressure and Control Effectiveness

2019 ◽  
Vol 8 (2S3) ◽  
pp. 953-958
Keyword(s):  
Pressure Ratio ◽  
Base Pressure ◽  
Percentage Change ◽  
Nozzle Pressure Ratio ◽  
Control Effectiveness ◽  
Nozzle Pressure ◽  
Mach Numbers ◽  
And Control ◽  
Base Drag ◽  
Experimental Effort

Reducing the base drag and increasing the base pressure from aerodynamic devices involving suddenly expanded flows is of vital importance due to the higher rate of drag associated with them. The experimental effort put into understanding the variation in base pressure using active control of suddenly expanded flows employing microjets is reported in this article. The effect of tiny jets and nozzle pressure ratio (NPR), and length to diameter (L/D) ratio on the percentage change in base pressure is investigated at supersonic Mach numbers at 1.7, 2.3, and 2.7, for area ratios of 2.56, 5.06, and 7.56. Apart from NPR, the L/D ratio has an influential role in percentage change in base pressure at different Mach numbers. An improvement of up to 360 % in base pressure is obtained with the use of sonic micro jets at a particular Mach number and L/D ratio.

scholarly journals Investigation of efficacy of low length-to-diameter ratio and nozzle pressure ratio on base pressure in an abruptly expanded flow

2018 ◽  
Vol 172 ◽  
pp. 01004
Author(s):  
Fharrukh Ahmed ◽  
S. A. Khan
Keyword(s):  
Pressure Ratio ◽  
Flow Regulation ◽  
Base Pressure ◽  
Regulation Mechanism ◽  
Nozzle Pressure Ratio ◽  
Control Efficacy ◽  
Remarkable Change ◽  
Cross Sectional ◽  
Circular Duct ◽  
Nozzle Pressure

This study has been carried out to assess the efficacy of the flow regulations in the form of tiny jets to regulate the pressure in the base region of an abruptly expanded duct. Four tiny jets of 1mm diameter placed at 90° intervals at 6.5 mm distance from the main jet in the wake region of the base were employed as flow management mechanism. The experiments were conducted at the inertia level of M = 2.5 & 3.0. The jets from the nozzles were expanded abruptly into a circular duct with four cross-sectional areas of 2.56, 3.24, 4.84 and 6.25. The L/D ratio of the enlarged duct considered was from 10 to 1 and experiments were conducted for Nozzle Pressure Ratio (NPR) from 3 to 11. Since the jets Mach numbers are high and the highest NPR tested was 11 which imply that the flow remains over expanded, even though, with increase in the NPR, the level of over expansion will decrease. It is well known that for over expanded nozzles an oblique shock will be formed at the nozzle lip, which in turn will result in the increase of the base pressure once it passes through the shock wave. From the results it is observed that for the NPRs 3 and 5 there is no appreciable gain in the base pressure, and hence, control employed as tiny jets are not effective, however, at NPR 7, 9, and 11 there is remarkable change in the base pressure values. This clearly indicates that NPR plays a significant role to decide on the magnitude of the base pressure and the control efficacy of the flow regulation mechanism as the tiny jets. It is found that the present method of flow regulation mechanism can be used as effective regulator of the base flows in an abruptly expanded duct. The control does not alter the nature of the flow in the enlarge duct.

Effect of Cavities in Suddenly Expanded Flow at Supersonic Mach Number

CFD letters ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 57-71
Author(s):  
Atifatul Ismah Ismail
Keyword(s):  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Mach Number ◽  
Pressure Ratio ◽  
Area Ratio ◽  
Base Pressure ◽  
Sudden Expansion ◽  
Expansion Level ◽  
Computational Fluid Dynamics Cfd ◽  
Base Drag

The contribution from the base drag due to the sub-atmospheric pressure is significant. It can be more than two-thirds of the net drag. There is a need to increase the base pressure and hence decrease the base drag. This research examines the effect of Mach Number on base pressure. To accomplish this objective, it controls the efficacy in an enlarged duct computed by the numerical approach using Computational Fluid Dynamics (CFD) Analysis. This experiment was carried out by considering the expansion level and the aspect cavity ratio. The computational fluid dynamics method is used to model supersonic motion with the sudden expansion, and a convergent-divergent nozzle is used. The Mach number is 1.74 for the present study, and the area ratio is 2.56. The L/D ratio varied from 2, 4, 6, 8, and 10, and the simulated nozzle pressure ratio ranged from 3 to 11. The two-dimensional planar design used commercial software from ANSYS. The airflow from a Mach 1.74 convergent-divergent axi-symmetric nozzle expanded suddenly into circular ducts of diameters 17 and 24.5 mm with and without annular rectangular cavities. The diameter of the duct is taken D=17mm and D=24.5mm. The C-D nozzle was developed and modeled in the present study: K-ε standard wall function turbulence model was used with the commercial computational fluid dynamics (CFD) and validated. The result indicates that the base pressure is impacted by the expansion level, the enlarged duct size, and the passage’s area ratio.

scholarly journals Machine Learning Applications on Agricultural Datasets for Smart Farm Enhancement

Machines ◽  
2018 ◽  
Vol 6 (3) ◽  
pp. 38 ◽  
Author(s):  
Fabrizio Balducci ◽  
Donato Impedovo ◽  
Giuseppe Pirlo
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Agricultural Field ◽  
Heterogeneous Information ◽  
Learning Techniques ◽  
Farm Model ◽  
Machine Learning Applications ◽  
Crop Harvest ◽  
The Right ◽  
The Internet Of Things

This work aims to show how to manage heterogeneous information and data coming from real datasets that collect physical, biological, and sensory values. As productive companies—public or private, large or small—need increasing profitability with costs reduction, discovering appropriate ways to exploit data that are continuously recorded and made available can be the right choice to achieve these goals. The agricultural field is only apparently refractory to the digital technology and the “smart farm” model is increasingly widespread by exploiting the Internet of Things (IoT) paradigm applied to environmental and historical information through time-series. The focus of this study is the design and deployment of practical tasks, ranging from crop harvest forecasting to missing or wrong sensors data reconstruction, exploiting and comparing various machine learning techniques to suggest toward which direction to employ efforts and investments. The results show how there are ample margins for innovation while supporting requests and needs coming from companies that wish to employ a sustainable and optimized agriculture industrial business, investing not only in technology, but also in the knowledge and in skilled workforce required to take the best out of it.

scholarly journals Investigation on the Optimal Design and Flow Mechanism of High Pressure Ratio Impeller with Machine Learning Method

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Weilin Yi ◽  
Hongliang Cheng
Keyword(s):  
Machine Learning ◽  
High Pressure ◽  
Flow Field ◽  
Performance Improvement ◽  
Pressure Ratio ◽  
Leading Edge ◽  
Design Parameters ◽  
Support Vector ◽  
Peak Efficiency ◽  
High Pressure Ratio

The optimization of high-pressure ratio impeller with splitter blades is difficult because of large-scale design parameters, high time cost, and complex flow field. So few relative works are published. In this paper, an engineering-applied centrifugal impeller with ultrahigh pressure ratio 9 was selected as datum geometry. One kind of advanced optimization strategy including the parameterization of impeller with 41 parameters, high-quality CFD simulation, deep machine learning model based on SVR (Support Vector Machine), random forest, and multipoint genetic algorithm (MPGA) were set up based on the combination of commercial software and in-house python code. The optimization objective is to maximize the peak efficiency with the constraints of pressure-ratio at near stall point and choked mass flow. Results show that the peak efficiency increases by 1.24% and the overall performance is improved simultaneously. By comparing the details of the flow field, it is found that the weakening of the strength of shock wave, reduction of tip leakage flow rate near the leading edge, separation region near the root of leading edge, and more homogenous outlet flow distributions are the main reasons for performance improvement. It verified the reliability of the SVR-MPGA model for multiparameter optimization of high aerodynamic loading impeller and revealed the probable performance improvement pattern.

scholarly journals Machine Learning Applications and Optimization of Clustering Methods Improve the Selection of Descriptors in Blackberry Germplasm Banks

Plants ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 247
Author(s):  
Juan Camilo Henao-Rojas ◽  
María Gladis Rosero-Alpala ◽  
Carolina Ortiz-Muñoz ◽  
Carlos Enrique Velásquez-Arroyo ◽  
William Alfonso Leon-Rueda ◽  
...  
Keyword(s):  
Machine Learning ◽  
Support Vector ◽  
P Value ◽  
Clustering Methods ◽  
Agglomerative Clustering ◽  
Discriminating Power ◽  
Hierarchical Agglomerative Clustering ◽  
Machine Learning Applications ◽  
Germplasm Banks ◽  
Selection Of

Machine learning (ML) and its multiple applications have comparative advantages for improving the interpretation of knowledge on different agricultural processes. However, there are challenges that impede proper usage, as can be seen in phenotypic characterizations of germplasm banks. The objective of this research was to test and optimize different analysis methods based on ML for the prioritization and selection of morphological descriptors of Rubus spp. 55 descriptors were evaluated in 26 genotypes and the weight of each one and its ability to discriminating capacity was determined. ML methods as random forest (RF), support vector machines, in the linear and radial forms, and neural networks were optimized and compared. Subsequently, the results were validated with two discriminating methods and their variants: hierarchical agglomerative clustering and K-means. The results indicated that RF presented the highest accuracy (0.768) of the methods evaluated, selecting 11 descriptors based on the purity (Gini index), importance, number of connected trees, and significance (p value < 0.05). Additionally, K-means method with optimized descriptors based on RF had greater discriminating power on Rubus spp., accessions according to evaluated statistics. This study presents one application of ML for the optimization of specific morphological variables for plant germplasm bank characterization.

scholarly journals Systematic Review of Machine Learning Applications in Mining: Exploration, Exploitation, and Reclamation

Minerals ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 148
Author(s):  
Dahee Jung ◽  
Yosoon Choi
Keyword(s):  
Machine Learning ◽  
Mineral Exploration ◽  
Mining Industry ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Research Papers ◽  
Recent Developments ◽  
Machine Learning Applications ◽  
Exploration Exploitation ◽  
Mining Exploration

Recent developments in smart mining technology have enabled the production, collection, and sharing of a large amount of data in real time. Therefore, research employing machine learning (ML) that utilizes these data is being actively conducted in the mining industry. In this study, we reviewed 109 research papers, published over the past decade, that discuss ML techniques for mineral exploration, exploitation, and mine reclamation. Research trends, ML models, and evaluation methods primarily discussed in the 109 papers were systematically analyzed. The results demonstrated that ML studies have been actively conducted in the mining industry since 2018, mostly for mineral exploration. Among the ML models, support vector machine was utilized the most, followed by deep learning models. The ML models were evaluated mostly in terms of their root mean square error and coefficient of determination.

scholarly journals Evaluation of Printing Parameters on 3D Extrusion Printing of Pluronic Hydrogels and Machine Learning Guided Parameter Recommendation

2021 ◽  
Vol 7 (4) ◽  
pp. 343
Author(s):  
Zhouquan Fu ◽  
Vincent Angeline ◽  
Wei Sun
Keyword(s):  
Machine Learning ◽  
Three Dimensional ◽  
Pluronic F127 ◽  
Support Vector ◽  
Machine Model ◽  
Machine Learning Applications ◽  
Nozzle Temperature ◽  
Extrusion Printing ◽  
Future Work ◽  
Printing Parameters

Bioprinting is an emerging technology for the construction of complex three-dimensional (3D) constructs used in various biomedical applications. One of the challenges in this field is the delicate manipulation of material properties and various disparate printing parameters to create structures with high fidelity. Understanding the effects of certain parameters and identifying optimal parameters for creating highly accurate structures are therefore a worthwhile subject to investigate. The objective of this study is to investigate high-impact print parameters on the printing printability and develop a preliminary machine learning model to optimize printing parameters. The results of this study will lead to an exploration of machine learning applications in bioprinting and to an improved understanding between 3D printing parameters and structural printability. Reported results include the effects of rheological property, nozzle gauge, nozzle temperature, path height, and ink composition on the printability of Pluronic F127. The developed Support Vector Machine model generated a process map to assist the selection of optimal printing parameters to yield high quality prints with high probability (>75%). Future work with more generalized machine learning models in bioprinting is also discussed in this article. The finding of this study provides a simple tool to improve printability of extrusion-based bioprinting with minimum experimentations.

scholarly journals Predicting Delayed Neurocognitive Recovery After Non-cardiac Surgery Using Resting-State Brain Network Patterns Combined With Machine Learning

2021 ◽  
Vol 13 ◽  
Author(s):  
Zhaoshun Jiang ◽  
Yuxi Cai ◽  
Xixue Zhang ◽  
Yating Lv ◽  
Mengting Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Clinical Trial ◽  
Cardiac Surgery ◽  
Prefrontal Cortex ◽  
Random Forest ◽  
Resting State ◽  
Brain Network ◽  
Support Vector ◽  
Whole Brain ◽  
The Right

Delayed neurocognitive recovery (DNR) is a common subtype of postoperative neurocognitive disorders. An objective approach for identifying subjects at high risk of DNR is yet lacking. The present study aimed to predict DNR using the machine learning method based on multiple cognitive-related brain network features. A total of 74 elderly patients (≥ 60-years-old) undergoing non-cardiac surgery were subjected to resting-state functional magnetic resonance imaging (rs-fMRI) before the surgery. Seed-based whole-brain functional connectivity (FC) was analyzed with 18 regions of interest (ROIs) located in the default mode network (DMN), limbic network, salience network (SN), and central executive network (CEN). Multiple machine learning models (support vector machine, decision tree, and random forest) were constructed to recognize the DNR based on FC network features. The experiment has three parts, including performance comparison, feature screening, and parameter adjustment. Then, the model with the best predictive efficacy for DNR was identified. Finally, independent testing was conducted to validate the established predictive model. Compared to the non-DNR group, the DNR group exhibited aberrant whole-brain FC in seven ROIs, including the right posterior cingulate cortex, right medial prefrontal cortex, and left lateral parietal cortex in the DMN, the right insula in the SN, the left anterior prefrontal cortex in the CEN, and the left ventral hippocampus and left amygdala in the limbic network. The machine learning experimental results identified a random forest model combined with FC features of DMN and CEN as the best prediction model. The area under the curve was 0.958 (accuracy = 0.935, precision = 0.899, recall = 0.900, F1 = 0.890) on the test set. Thus, the current study indicated that the random forest machine learning model based on rs-FC features of DMN and CEN predicts the DNR following non-cardiac surgery, which could be beneficial to the early prevention of DNR.Clinical Trial Registration: The study was registered at the Chinese Clinical Trial Registry (Identification number: ChiCTR-DCD-15006096).

Sign in / Sign up

Export Citation Format

Share Document