scholarly journals Surrogate Models for Performance Prediction of Axial Compressors Using through-Flow Approach

Energies ◽  
2019 ◽  
Vol 13 (1) ◽  
pp. 169
Author(s):  
Xiaoxiong Wu ◽  
Bo Liu ◽  
Nathan Ricks ◽  
Ghader Ghorbaniasl
Keyword(s):  
Experimental Data ◽  
Total Pressure ◽  
Surrogate Models ◽  
Empirical Models ◽  
Bayesian Optimization ◽  
Support Vector ◽  
Flow Angle ◽  
Flow Calculation ◽  
Transonic Compressor ◽  
Through Flow

Two-dimensional design and analysis issues on the meridional surface, which is important in the preliminary design procedure of compressors, are highly dependent on the accuracy of empirical models, such as the prediction of total pressure loss model and turning flow angle. Most of the widely used models are derived or improved from experimental data of some specific cascades with low-loading and low-speed airfoil types. These models may work for most conventional compressors but are incapable of accurately estimating the performance for some specific cases like transonic compressors. The errors made by these models may mislead the final design results. Therefore, surrogate models are developed in this work to reduce the errors and replace the conventional empirical models in the through-flow calculation procedure. A group of experimental data considering a two-stage transonic compressor is used to generate the airfoils database for training the surrogate models. Sensitivity analysis is applied to select the most influential features. Two supervised learning approaches including support vector regression (SVR) and Gaussian process regression (GPR) are used to train the models with a Bayesian optimization algorithm to obtain the optimal hyper parameters. The trained models are integrated into the through-flow code based on streamline curvature method (SLC) to predict the overall performance and internal flow field of the transonic compressor on five rotational speed lines for validation. The predictions are compared with the experimental data and the results of conventional empirical models. The comparison shows that SVR and GPR respectively reduce the predicted error of empirical models by 62.2% and 55.2% for the total pressure ratio and 48.4% and 50.1% for adiabatic efficiency on average. This suggests that the surrogate models constitute an alternative way to predict the performance of airfoils in through-flow calculation where empirical models are inefficient.

scholarly journals Application of Artificial Intelligence (AI) for Sustainable Highway and Road System

Symmetry ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 60
Author(s):  
Md Arifuzzaman ◽  
Muhammad Aniq Gul ◽  
Kaffayatullah Khan ◽  
S. M. Zakir Hossain
Keyword(s):  
Experimental Data ◽  
High Performance ◽  
Adhesion Force ◽  
Model Development ◽  
Real Life ◽  
Bayesian Optimization ◽  
Support Vector ◽  
Adhesive Properties ◽  
Bayesian Optimization Algorithm ◽  
The Mean

There are several environmental factors such as temperature differential, moisture, oxidation, etc. that affect the extended life of the modified asphalt influencing its desired adhesive properties. Knowledge of the properties of asphalt adhesives can help to provide a more resilient and durable asphalt surface. In this study, a hybrid of Bayesian optimization algorithm and support vector regression approach is recommended to predict the adhesion force of asphalt. The effects of three important variables viz., conditions (fresh, wet and aged), binder types (base, 4% SB, 5% SB, 4% SBS and 5% SBS), and Carbon Nano Tube doses (0.5%, 1.0% and 1.5%) on adhesive force are taken into consideration. Real-life experimental data (405 specimens) are considered for model development. Using atomic force microscopy, the adhesive strength of nanoscales of test specimens is determined according to functional groups on the asphalt. It is found that the model predictions overlap with the experimental data with a high R2 of 90.5% and relative deviation are scattered around zero line. Besides, the mean, median and standard deviations of experimental and the predicted values are very close. In addition, the mean absolute Error, root mean square error and fractional bias values were found to be low, indicating the high performance of the developed model.

Scaling of Incidence Variations With Inlet Distortion for a Transonic Axial Compressor

2020 ◽  
Vol 142 (2) ◽  
Author(s):  
D. J. Hill ◽  
J. J. Defoe
Keyword(s):  
Total Pressure ◽  
Incidence Angle ◽  
Computational Cost ◽  
Force Model ◽  
Flow Angle ◽  
Total Enthalpy ◽  
Transonic Compressor ◽  
Inlet Distortion ◽  
Scaling Relationships ◽  
The Impact

Abstract This paper numerically explores the manner in which blade row inlet incidence variation scales with various distortion patterns and intensities. The objectives are to (1) identify the most appropriate parameter whose circumferential variation can be used to assess scaling relationships of a transonic compressor and (2) use this parameter to evaluate two types of non-uniform inflow patterns, vertically stratified total pressure distortions and radially stratified total enthalpy and total pressure distortions. A body force model of the blade rows is employed to reduce computational cost; the approach has been shown to capture distortion transfer and to be able to predict upstream flow redistribution with inlet distortion. Diffusion factor is shown to be an inadequate proxy for streamline loss generation in non-uniform flow, leading to the choice of incidence angle variations as the metric for which we assess scaling relationships. Posteriori scaling of circumferential flow angle variation based on the maximum incidence excursion for varying distortion intensity yields an accurate method for prediction of the impact for other distortion intensities; linear regression of the maximum variation in incidence around the annulus as a function of distortion intensity had R2 > 0.97 for all spanwise locations examined in both the rotor and stator for both vertically and radially stratified distortions. However, changes to far upstream distortion shape yield highly non-linear incidence variation scaling; the results suggest that the pitchwise gradients of far upstream total pressure govern the degree of linearity for incidence variation scaling.

Oxy-Fuel Turbine Through-Flow Design

2014 ◽  
Author(s):  
Majed Sammak ◽  
Srikanth Deshpande ◽  
Magnus Genrup
Keyword(s):  
Mach Number ◽  
Total Pressure ◽  
Tangential Velocity ◽  
Flow Angle ◽  
Power Turbine ◽  
Through Flow ◽  
The Mean ◽  
Line Design ◽  
Reaction Degree ◽  
Relative Flow

The objective of the paper is to present the through-flow design of a twin-shaft oxy-fuel turbine. The through-flow design is the subsequent step after the turbine mean-line design. The through-flow phase analyses the flow in both axial and radial directions, where the flow is computed from hub to tip and along streamlines. The parameterization of the through-flow is based on the mean-line results, so principal features such as blade angles at the mean-line into the through-flow phase should be retained. Parameters such as total inlet pressure and temperature, mass flow, rotation speed and turbine geometries are required for the through-flow modelling. The through-flow study was performed using commercial software — AxCent(™) from Concepts NREC. The rotation speed of the twin-shaft power turbine was set to 7200 rpm, while the power turbine was set to 4800 rpm. The mean-line design determined that the twin-shaft turbine should be designed with two compressor turbine stages and three power turbine stages. The through-flow objective was to study the variations in the thermodynamic parameters along the blade. The power turbine last-stage design was studied because of the importance of determining exit Mach number distribution of the rotor tip. The last stage was designed with damped forced condition. The term ‘damped’ is used because the opening from the tip to the hub is limited to a certain value rather than maintaining the full concept of forced vortex. The study showed the parameter distribution of relative Mach number, total pressure and temperature, relative flow angle and tangential velocity. Through-flow results at 50% span and mean-line results showed reasonable agreement between static pressure, total pressure, reaction degree and total efficiency. Other parameters such as total temperature and relative Mach number showed some difference which can be attributed to working fluid in AxCent being pure CO2. The relative tip Mach number at rotor exit was 1.03, which is lower than the maximum typically allowed value of 1.2. The total pressure distribution was smooth from hub to tip which minimizes the spanwise gradient of total pressure and thus reduces the strength of secondary vortices. The reaction degree distribution was presented in the paper and no problems were revealed in the reaction degree at the hub. Rotor blades were designed to produce a smooth exit relative flow angle distribution. The relative flow angle varied by approximately 5° from hub to tip. The tangential velocity distribution was proportional to blade radius, which coincided with forced vortex design. Through-flow design showed that the mean-line design of a twin-shaft oxy-fuel turbine was suitable.

scholarly journals Design, Optimization, and Analysis of a High-Turning Transonic Tandem Compressor Cascade

1997 ◽  
Author(s):  
Anton Weber ◽  
Wolfgang Steinert
Keyword(s):  
Mach Number ◽  
Total Pressure ◽  
Side Wall ◽  
Design Flow ◽  
Basic Question ◽  
Compressor Cascade ◽  
Flow Angle ◽  
Transonic Compressor ◽  
Blade Row ◽  
Transonic Cascade

As a feasibility study for a stator guide vane a highly loaded transonic compressor stator blade row was designed, optimized, and tested in a transonic cascade facility. The flow entering the turning device with an inlet Mach number of 1.06 has to be turned by more than 60° and diffused extremely to leave the blade row without swirl. Therefore, the basic question was: Is it feasible to gain such a high amount of flow turning with an acceptable level of total pressure losses? The geometric concept chosen is a tandem cascade consisting of a transonic blade row with a flow turning of 10° followed by a subsequent high-turning subsonic cascade. The blade number ratio of the two blade rows was selected to be 1:2 (transonic: subsonic). Design and optimization have been performed using a modern Navier-Stokes flow solver under 2D assumptions by neglecting side wall boundary-layer effects. In the design process it was found to be necessary to guide the wake of the low turning transonic blade near the suction surface of the subsonic blade. Furthermore, it is advantageous to enlarge the blade spacing of the ‘wake’ passage in relation to the neighbouring one of the high turning part. The optimized design geometry of the tandem cascade was tested in the transonic cascade windtunnel of the DLR in Cologne. At design flow conditions the experiments confirmed the design target in every aspect. A flow turning of more than 60°, a static pressure ratio of 1.75, and a total pressure loss coefficient of 0.15 was measured. The working range at design inlet Mach number of 1.06 is about 3.5° in terms of the inlet flow angle. A viscous analysis of various operating points showed excellent agreement with the experimental results.

scholarly journals Unsteady Numerical Simulations of Radial Temperature Profile Redistribution in a Single-Stage Turbine

1995 ◽  
Author(s):  
Daniel J. Dorney ◽  
John R. Schwab
Keyword(s):  
Experimental Data ◽  
Temperature Profile ◽  
Total Pressure ◽  
Three Dimensional ◽  
Temperature Gradients ◽  
Single Stage ◽  
Angle Distribution ◽  
Pressure Gradients ◽  
Flow Angle ◽  
Radial Temperature

Experimental data taken from gas turbine combustors indicate that the flow exiting the combustor can contain both circumferential and radial temperature gradients. A significant amount of research recently has been devoted to studying turbine flows with inlet temperature gradients, but no total pressure gradients. Less attention has been given to flows containing both temperature and total pressure gradients at the inlet. The significance of the total pressure gradients is that the secondary flows and the temperature redistribution process in the vane blade row can be significantly altered. Experimental data previously obtained in a single-stage turbine with inlet total temperature and total pressure gradients indicated a redistribution of the warmer fluid to the pressure surface of the airfoils, and a severe underturning of the flow at the exit of the stage. In a concurrent numerical simulation, a steady, inviscid, three-dimensional flow analysis was able to capture the redistribution process, but not the exit flow angle distribution. In the current research program, a series of unsteady two- and three-dimensional Navier-Stokes simulations have been performed to study the redistribution of the radial temperature profile in the turbine stage. The three-dimensional analysis predicts both the temperature redistribution and the flow underturning observed in the experiments.

scholarly journals Estimation and Optimization of Tool Wear in Conventional Turning of 709M40 Alloy Steel Using Support Vector Machine (SVM) with Bayesian Optimization

Materials ◽  
2021 ◽  
Vol 14 (14) ◽  
pp. 3773
Author(s):  
Mahdi S. Alajmi ◽  
Abdullah M. Almeshal
Keyword(s):  
Artificial Intelligence ◽  
Experimental Data ◽  
Tool Wear ◽  
Alloy Steel ◽  
Bayesian Optimization ◽  
Research Trend ◽  
Support Vector ◽  
Machining Parameters ◽  
Svm Model ◽  
Data Points

Cutting tool wear reduces the quality of the product in production processes. The optimization of both the machining parameters and tool life reliability is an increasing research trend to save manufacturing resources. In the present work, we introduced a computational approach in estimating the tool wear in the turning process using artificial intelligence. Support vector machines (SVM) for regression with Bayesian optimization is used to determine the tool wear based on various machining parameters. A coated insert carbide tool 2025 was utilized in turning tests of 709M40 alloy steel. Experimental data were collected for three machining parameters like feed rate, depth of cut, and cutting speed, while the parameter of tool wear was calculated with a scanning electron microscope (SEM). The SVM model was trained on 162 experimental data points and the trained model was then used to estimate the experimental testing data points to determine the model performance. The proposed SVM model with Bayesian optimization achieved a superior accuracy in estimation of the tool wear with a mean absolute percentage error (MAPE) of 6.13% and root mean square error (RMSE) of 2.29%. The results suggest the feasibility of adopting artificial intelligence methods in estimating the machining parameters to reduce the time and costs of manufacturing processes and contribute toward greater sustainability.

scholarly journals Improvement of Flow Field in Vaned Diffuser for Centrifugal Compressor Through Flow Field Calculation

1999 ◽  
Author(s):  
Hideakl Tamaki ◽  
Hidefumi Nakao
Keyword(s):  
Flow Field ◽  
Total Pressure ◽  
Field Calculation ◽  
Peak Efficiency ◽  
Vaned Diffuser ◽  
Flow Angle ◽  
Pressure Surface ◽  
Through Flow ◽  
Oil Flow ◽  
Oil Flow Visualization

Flow field in the vaned diffuser was calculated with CFD code. In order to take the large flow angle difference of the impeller discharged flow between hub and shroud into account, measured total pressure and flow angle downstream of the impeller with vaneless diffuser were used as the inlet boundary condition. Calculated results were compared with the measured total pressure distribution at the exit of the vaned diffuser and the results of oil flow visualization at hub and shroud. According to the results of the calculation and measurements, the possibility of existence of the separated region near pressure surface at hub was shown from the compressor choke to peak efficiency. In order to reduce this separated region, the vaned diffuser whose shroud wall was pinched from just downstream of the diffuser throat to vaned diffuser exit was calculated and tested. The improvement of flow field and the pressure recovery in the vaned diffuser was confirmed with the measurement of the static pressure and the total pressure at the vaned diffuser exit. The efficiency of the compressor was also improved from the compressor choke to peak efficiency. This study shows that the reduction of separation near pressure side at hub is effective way to improve the vaned diffuser performance.

Unsteady Numerical Simulations of Radial Temperature Profile Redistribution in a Single-Stage Turbine

1996 ◽  
Vol 118 (4) ◽  
pp. 783-791 ◽  
Author(s):  
D. J. Dorney ◽  
J. R. Schwab
Keyword(s):  
Experimental Data ◽  
Temperature Profile ◽  
Total Pressure ◽  
Three Dimensional ◽  
Temperature Gradients ◽  
Single Stage ◽  
Angle Distribution ◽  
Pressure Gradients ◽  
Flow Angle ◽  
Radial Temperature

Experimental data taken from gas turbine combustors indicate that the flow exiting the combustor can contain both circumferential and radial temperature gradients. A significant amount of research recently has been devoted to studying turbine flows with inlet temperature gradients, but no total pressure gradients. Less attention has been given to flows containing both temperature and total pressure gradients at the inlet. The significance of the total pressure gradients is that the secondary flows and the temperature redistribution process in the vane blade row can be significantly altered. Experimental data previously obtained in a single-stage turbine with inlet total temperature and total pressure gradients indicated a redistribution of the warmer fluid to the pressure surface of the airfoils, and a severe underturning of the flow at the exit of the stage. In a concurrent numerical simulation, a steady, inviscid, three-dimensional flow angle distribution, In the current research program, a series of unsteady two-and three-dimensional Navier–Stokes simulations have been performed to study the redistribution of the radial temperature profile in the turbine stage. The three-dimensional analysis predicts both the temperature redistribution and the flow underturning observed in the experiments.

scholarly journals Smart Design Nano-Hybrid Formulations by Machine Learning

Proceedings ◽  
2020 ◽  
Vol 78 (1) ◽  
pp. 5
Author(s):  
Raquel de Melo Barbosa ◽  
Fabio Fonseca de Oliveira ◽  
Gabriel Bezerra Motta Câmara ◽  
Tulio Flavio Accioly de Lima e Moura ◽  
Fernanda Nervo Raffin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Water Solubility ◽  
Inorganic Materials ◽  
Fine Tuning ◽  
Support Vector ◽  
Drug Solubility ◽  
Physical Behavior ◽  
Best Fit

Nano-hybrid formulations combine organic and inorganic materials in self-assembled platforms for drug delivery. Laponite is a synthetic clay, biocompatible, and a guest of compounds. Poloxamines are amphiphilic four-armed compounds and have pH-sensitive and thermosensitive properties. The association of Laponite and Poloxamine can be used to improve attachment to drugs and to increase the solubility of β-Lapachone (β-Lap). β-Lap has antiviral, antiparasitic, antitumor, and anti-inflammatory properties. However, the low water solubility of β-Lap limits its clinical and medical applications. All samples were prepared by mixing Tetronic 1304 and LAP in a range of 1–20% (w/w) and 0–3% (w/w), respectively. The β-Lap solubility was analyzed by UV-vis spectrophotometry, and physical behavior was evaluated across a range of temperatures. The analysis of data consisted of response surface methodology (RMS), and two kinds of machine learning (ML): multilayer perceptron (MLP) and support vector machine (SVM). The ML techniques, generated from a training process based on experimental data, obtained the best correlation coefficient adjustment for drug solubility and adequate physical classifications of the systems. The SVM method presented the best fit results of β-Lap solubilization. In silico tools promoted fine-tuning, and near-experimental data show β-Lap solubility and classification of physical behavior to be an excellent strategy for use in developing new nano-hybrid platforms.

Sign in / Sign up

Export Citation Format

Share Document