scholarly journals Nonlinear Factor‐Augmented Predictive Regression Models with Functional Coefficients

2020 ◽  
Vol 41 (3) ◽  
pp. 367-386
Author(s):  
Degui Li ◽  
Jiraroj Tosasukul ◽  
Wenyang Zhang
Keyword(s):  
Regression Models ◽  
Predictive Regression ◽  
Nonlinear Factor

Influence of alloying systems on the properties of single crystal nickel-based superalloys

2021 ◽  
Vol 112 (10) ◽  
pp. 794-799
Author(s):  
Alexander Glotka ◽  
Vadim Ol’shanetskii
Keyword(s):  
Single Crystal ◽  
Regression Models ◽  
Strength Properties ◽  
Term Limits ◽  
Alloying Elements ◽  
Structure Stability ◽  
Plastic Properties ◽  
Crystal Lattices ◽  
Predictive Regression ◽  
First Time

Abstract The purpose of the investigation was to obtain the predictive regression models that help correct the calculation of the mechanical properties of single crystal nickel-based superalloys without conducting prior experiments. The paper considers the influence of alloying elements on their tendency to form phases in foundry nickel-based superalloys. Using the elements influence on the phase formation, the coefficient Kc’ of the ratio of alloying elements for this class of alloys was set for the first time. We have revealed the short correlation of the ratio Kc’ with the dimensional misfit of γ and γ’ crystal lattices. Also, a high probability to predict the misfit for multicomponent nickel systems is shown, which significantly affected the strength properties. The regression models of correlation dependencies on the dimensional γ/γ’- misfit were offered to predict the short-term and long-term limits of the strength of alloys. We determined the operating temperature at which the misfit value should decrease to zero. The structure stability should increase because of the structural stresses minimizing. This has a positive effect on strength and plastic properties.

scholarly journals Properties of nickel-based superalloys of equiaxial crystallization

2021 ◽  
pp. 19-23
Author(s):  
O. Glotka ◽  
V. Olshanetskii
Keyword(s):  
Mechanical Properties ◽  
Chemical Composition ◽  
Regression Models ◽  
Computational Prediction ◽  
Integrated Approach ◽  
Experimental Data Processing ◽  
Predictive Regression ◽  
Heat Resistant ◽  
First Time ◽  
Thermodynamic Processes

Purpose. The aim of the work is to obtain predictive regression models, with the help of which, it is possible to adequately calculate the mechanical properties of nickel-based superalloys of equiaxial crystallization, without carrying out preliminary experiments. Research methods. To find regularities and calculate  the latest CALPHAD method was chosen, and modeling of thermodynamic processes of phase crystallization was performed. Results. As a result of experimental data processing, the ratio of alloying elements Kg¢ was proposed for the first time, which can be used to assess the mechanical properties, taking into account the complex effect of the main alloy components. The regularities of the influence of the composition on the properties of heat-resistant nickel alloys of equiaxial crystallization are established. The analysis of the received dependences in comparison with practical results is carried out. The relations well correlated with heat resistance, mismatch and strength of alloys are obtained. Scientific novelty. It is shown that for multicomponent nickel systems it is possible with a high probability to predict a mismatch, which significantly affects the strength characteristics of alloys of this class. The regularities of the influence of the chemical composition on the structure and properties of alloys are established. A promising and effective direction in solving the problem of predicting the main characteristics of heat-resistant materials based on nickel is shown Practical value. On the basis of an integrated approach for multicomponent heat-resistant nickel-based alloys, new regression models have been obtained that make it possible to adequately predict the properties of the chemical composition of the alloy, which made it possible to solve the problem of computational prediction of properties from the chemical composition of the alloy. This allows not only to design new nickel-based alloys, but also to optimize the composition of existing brands.

scholarly journals The effect of sugar on the processing behaviour of palm oil: from confectionery fundamentals to predictive regression models

2021 ◽  
Author(s):  
Ryan West
Keyword(s):  
Palm Oil ◽  
Regression Models ◽  
Crystal Morphology ◽  
Milk Powder ◽  
Bulk Oil ◽  
Process Maps ◽  
Predictive Regression ◽  
Dispersion Effects ◽  
Increased Sensitivity ◽  
The Impact

This dissertation explores the impact of confectioner’s sugar and processing on key physical characteristics of palm oil. Though bulk oils such as palm oil have been well-studied, fat-continuous dispersions that include other ingredients such as sugar, cocoa solids, or milk powder are much more complex due to ingredient interactions and the resulting changes in properties such as fat crystal morphology and crystallization pathway. These implications restrict the ability to extrapolate responses from bulk oils towards multi-ingredient systems. This is particularly important given that palm oil in foods rarely exists in bulk but is usually mixed with multiple ingredients. The effects of processing on both bulk oil and oil-sugar blends were explored over four weeks of storage and clearly demonstrated that the existence of a dispersion resulted in large differences in rheology and texture compared to the bulk. Adding sugar significantly increased storage modulus and firmness of the oils while exhibiting increased sensitivity towards processing conditions. Predictive models were generated through multiple regression analysis that overcame limitations derived from extrapolation and corrected for these behavioural differences using a single binary variable accounting for the presence of confectioner’s sugar. As a result, the contributions of sugar to the rheology and texture of oil-sugar blends were modelled, a first in such systems. The results contained within this dissertation are of great industrial relevance as they: i) limit the dependence on anecdote and empiricism to explain results, ii) generate detailed process maps, iii) identify optimal process values to attain desirable rheological and textural responses, and iv) open the door for further investigation into dispersion effects.

scholarly journals Highly predictive regression model of active cases of COVID-19 in a population by screening wastewater viral load

2020 ◽  
Author(s):  
Juan Vallejo ◽  
Soraya Rumbo-Feal ◽  
Kelly Conde ◽  
Ángel López-Oriona ◽  
Javier Tarrío ◽  
...  
Keyword(s):  
Viral Load ◽  
Regression Models ◽  
Treatment Plant ◽  
Statistical Regression ◽  
Nw Spain ◽  
Infected People ◽  
Predictive Regression ◽  
The World ◽  
Asymptomatic Individuals ◽  
High Degree

Abstract The quantification of the SARS-CoV-2 load in wastewater has emerged as a useful method to monitor COVID-19 outbreaks in the community. This approach was implemented in the metropolitan area of A Coruña (NW Spain), where wastewater from the treatment plant of Bens was analyzed to track the epidemic’s dynamic in a population of 369,098 inhabitants. We developed statistical regression models that allowed us to estimate the number of infected people from the viral load detected in the wastewater with a reliability close to 90%. This is the first wastewater-based epidemiological model that could potentially be adapted to track the evolution of the COVID-19 epidemic anywhere in the world, monitoring both symptomatic and asymptomatic individuals. It can help to understand with a high degree of reliability the true magnitude of the epidemic in a place at any given time and can be used as an effective early warning tool for predicting outbreaks.

Forecasting Economic Indicators of Transport Activity

2021 ◽  
pp. 70-78
Author(s):  
D. Biryukov ◽  
O. Rod'kina ◽  
Ruslan Vakulenko ◽  
D. Lapaev
Keyword(s):  
Correlation Analysis ◽  
Economic Activity ◽  
Regression Models ◽  
Economic Indicators ◽  
Transport Sector ◽  
Linear Regression Models ◽  
Transport Activity ◽  
Statistical Accuracy ◽  
Predictive Regression ◽  
And Storage

The article discusses the methodological and practical aspects of forecasting the economic indicators of the transport sector at the level of a transport company and the type of economic activity. The development of forecasting methodology at the present time is analyzed. The necessity, features and main directions of development of the forecasting methodology for the type of economic activity are revealed. The methodological basis for forecasting the development of the transport sector is investigated and characterized. A method for forecasting transportation and storage as a type of economic activity under conditions of uncertainty is proposed and tested. Based on the results of the correlation analysis, subsets of predicted indicators and factors were formed that were optimal for constructing the corresponding linear regression models. Predictive regression models have been developed, their significance and statistical accuracy have been confirmed.

scholarly journals Selection of Credibility Regression Models

1999 ◽  
Vol 29 (2) ◽  
pp. 245-270 ◽  
Author(s):  
Peter Bühlmann ◽  
Hans Bühlmann
Keyword(s):  
Regression Models ◽  
Simulation Experiment ◽  
Decision Rules ◽  
Model Parameters ◽  
Shrinkage Estimation ◽  
Asymptotic Results ◽  
Usual Model ◽  
Predictive Regression ◽  
Squared Error ◽  
Selection Of

AbstractWe derive some decision rules to select best predictive regression models in a credibility context, that is, in a “random effects’ linear regression model with replicates. In contrast to usual model selection techniques on a collective level, our proposal allows to detect individual structures, even if they disappear in the collective.We give exact, non-asymptotic results for the expected squared error loss for a predictor based on credibility estimation in different models. This involves correct accounting of random model parameters and the study of expected loss for shrinkage estimation. We support the theoretical properties of the new model selectors by a small simulation experiment.

Sign in / Sign up

Export Citation Format

Share Document