Comparison of various regression models for predicting compressor and turbine performance parameters

Yazar, Işıl; Yavuz, Hasan Serhan; Yavuz, Arzu Altin

doi:10.1016/j.energy.2017.05.061

Cited by 24 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regression analysis is one of the most ordinarily utilized statistical modelling methods for modelling relationships between a dependent variable (often called the 'response variable') and independent variables (often called 'predictors', 'covariates', or 'features') (Yazar et al, 2017). It employs several models and methods (linear and non-linear) for fitting the relationships between the response variable and two or more predictor variables, which can potentially be used for predicting the response variable given a set of predictor variables.…”

Section: Development Of Regression Modelsmentioning

confidence: 99%

“…Conversely, non-linear regression is a powerful alternative to linear regression, since it offers the most flexible functionality for curve fitting. Linear regression analysis may be inadequate in some instances to describe experimental data, and in these instances, non-linear regression offers the best performance for system description (Yazar et al, 2017). This paper considers five regression models, both linear (MLR, GLM,) and non-linear (QR, GAM, SVR), to relate the IGS final ZTDs (response variable) and the site-wise VMF3-ZTD products including P, T, e, and ZTD as well as the stations' latitudes φ, longitudes λ, and ellipsoidal heights (h) (predictor variables) using R studio statistical computing software.…”

Section: Development Of Regression Modelsmentioning

confidence: 99%

“…This is to check whether the quadratic model fits the data better than the linear model. The quadratic model takes the form (Yazar et al, 2017):…”

Section: Quadratic Regression Model (Qrm)mentioning

confidence: 99%

See 2 more Smart Citations

Regression models for predicting daily IGS zenith tropospheric delays in West Africa: Implication for GNSS meteorology and positioning applications

Osah

Acheampong

Fosu

et al. 2021

Meteorological Applications

View full text Add to dashboard Cite

The ability to precisely and accurately model and predict tropospheric delay is essential for precise global navigation satellite system (GNSS) and meteorological applications. The International GNSS Service (IGS) provides highly accurate and highly reliable daily time series zenith tropospheric delay (ZTD) products for all its member sites using data from each IGS site. Nevertheless, if for reasons such as poor internet connectivity, equipment failure, and power outages the IGS station is inaccessible, gaps are created in the data archive, resulting in degrading the quality of the ZTD estimation, as well as inhibits the quality of precipitable water vapour (PWV) estimation, needed for precise positioning applications, meteorological studies, and weather forecasting. To address this challenge, five regression models are proposed in this study to model and predict daily ZTDs using daily datasets from four IGS stations in West Africa over a period of 5 years (2015)(2016)(2017)(2018)(2019). The site-specific Vienna Mapping Functions 3 (VMF3) products (ZTD, pressure, temperature, water vapour partial pressure) and stations' coordinates (latitudes and longitudes) are used as the predictors, while the IGS final ZTD product as the response variable in fitting the models. Several performance measures are calculated to compare the predictive performance of the models.The results show that the five regression models performed outstandingly and agree very well with the IGS-ZTD data, and hence provide a useful alternative for ZTD predictions and also in the event the West African IGS stations' ZTD data are unavailable. Nonetheless, the support vector regression model outperformed the remaining four models.

show abstract

Section: Development Of Regression Modelsmentioning

confidence: 99%

Section: Development Of Regression Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Regression models for predicting daily IGS zenith tropospheric delays in West Africa: Implication for GNSS meteorology and positioning applications

Osah

Acheampong

Fosu

et al. 2021

Meteorological Applications

View full text Add to dashboard Cite

show abstract

“…Further, El-Gammal [4] provided a transformation matrix of axes to preserve internal behaviour and crosscoupling. Also, the regression structure, such as third-order polynomial [5], logarithm [6], rotated elliptical curve [7,8], and Chebyshev polynomial [9] will affect the result of fitting, which has been reported by many authors. However, these structures mainly depend on the mathematical analysis and the physical property in maps and can hardly be reflected.…”

Section: Introductionmentioning

confidence: 98%

Performance Prediction of the Centrifugal Compressor Based on a Limited Number of Sample Data

Jiang

Dong

Liu

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Centrifugal compressor is widely used in various engineering domains, and predicting the performance of a centrifugal compressor is an essential task for its conceptual design, optimization, and system simulation. For years, researchers seek to implement this mission through various kinds of methods, including interpolation, curve fitting, neural network, and other statistics-based algorithms. However, these methods usually need a large amount of data, and obtaining data may cost considerable computing or experimental resources. This paper focuses on constructing the performance maps of pressure ratio and isentropic efficiency using a limited number of sample data while maintaining accuracy. Firstly, sample data are generated from simulation using Vista CCD. Then, corrected flow rate and corrected rotational speed are used as independent variables, and the regression expressions with physical meaning of pressure ratio and isentropic efficiency are derived and simplified through thermodynamic analysis and loss analysis of centrifugal compressor, resulting in two loss-analysis-based models. Meanwhile, kriging models based on a second-order polynomial and neural network models are built. Results show that, when predicting inside data boundary, the loss-analysis-based model and the kriging model produce higher accuracy prediction even in a small data set, and the predicting result is stable, while the neural network model provides better results only in a more extensive data set with more speed lines. For the prediction outside the data boundary, the loss-analysis-based model can provide relatively accurate results. Besides, it takes less time to train and utilize a loss-analysis-based model than other models.

show abstract

Low‐Emission Propulsive Technologies in Transport Aircraft

Ranasinghe,

Guan,

Gardi

et al. 2023

Sustainable Aviation Technology and Operations

View full text Add to dashboard Cite

Comparison of various regression models for predicting compressor and turbine performance parameters

Cited by 24 publications

References 18 publications

Regression models for predicting daily IGS zenith tropospheric delays in West Africa: Implication for GNSS meteorology and positioning applications

Regression models for predicting daily IGS zenith tropospheric delays in West Africa: Implication for GNSS meteorology and positioning applications

Performance Prediction of the Centrifugal Compressor Based on a Limited Number of Sample Data

Low‐Emission Propulsive Technologies in Transport Aircraft

Contact Info

Product

Resources

About