[go: up one dir, main page]
Scribd
Upload
97 views18 pages

7 - Developing Models For Optimization

This document discusses process modeling, simulation, and optimization. It covers topics such as developing models for optimization, classification of models, how to build a model, dealing with under-specified, over-specified and just-specified models, data regression including graphical and analytical methods, introduction to regression analysis, multivariable linear regression, and solving examples during a practical session. The document contains chapter headings and content related to modeling techniques.

Uploaded by

niral
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
97 views18 pages

7 - Developing Models For Optimization

This document discusses process modeling, simulation, and optimization. It covers topics such as developing models for optimization, classification of models, how to build a model, dealing with under-specified, over-specified and just-specified models, data regression including graphical and analytical methods, introduction to regression analysis, multivariable linear regression, and solving examples during a practical session. The document contains chapter headings and content related to modeling techniques.

Uploaded by

niral
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 18

Process Modeling,

Simulation & Optimization


2180503

Presentation-II

Developing Models for Optimization

KJS 1
CHAPTER-I

CHAPTET-2

CHAPTER-3

KJS 2
CHAPTER-4

CHAPTET-5

KJS 3
CHAPTER-6

CHAPTET-7

CHAPTER-8

KJS 4
Classification of Model

• Model based on Physical theory Vs Strictly empirical description


• Linear Vs Nonlinear model
• Steady Vs Unsteady model
• Distributed Vs Lumped model
• Continuous Vs Discrete model

KJS 5
How to build a model

Formulate model
Experience Management
objective, Evaluate
reality Objectives
criteria & Cost
Problem
Definition Phase
Select Key Variables, Physical
principles to be applied, test
plan to be used
------------------------------------------------------------------------------------------------------------------------------------------------------------

Computer simulation, Develop Model Observations,


Software development data
Estimate Design Phase
Parameters

------------------------------------------------------------------------------------------------------------------------------------------------------------
Evaluate and
verify model
Evaluation Phase

Apply Model 6
KJS
No. of Variable > No. of Eqn.
Underspecified
No. of Variable = No. of Eqn.
DoF = 0
No. of Variable < No. of Eqn.
Over specified

KJS 7
KJS 8
KJS 9
Data Regression (Curve fitting)
1. Graphical Methods
2. Analytical Methods:
a) Method of averages
b) Method pf least square

KJS 10
Introduction to Regression analysis

In statistical modeling, regression analysis is a statistical process for estimating the


relationships among variables. It includes many techniques for modeling and analyzing
several variables, when the focus is on the relationship between a dependent variable
and one or more independent variables (or 'predictors')
• yi, is called the regressand, response variable, measured variable, criterion variable,
or dependent variable
• xi, xi , …. , xin are called regressors, input variables or independent variables

KJS 11
KJS 12
Ln (P) Ln (V)
Y = mx + C -0.6931 0.4824
0.0000 0.0000
γ Ln (V) + Ln (P) = Ln (K) 0.4055 -0.2877
Ln (P) = Ln (K) - γ Ln (V) 0.6931 -0.4780
0.9163 -0.6539
1.0986 -0.7765
Plot Ln (P) vs Ln (V)
0.5596 -0.1883

KJS 13
Ln (P) vs Ln (V)
1.5
Y = mx + C
Ln (P) = Ln (K) - γ Ln (V) 1
Slope = - γ = - 1.4534
γ = 1.4534 0.5
& Ln (K) = 0
Therefore; K = e0
0
K=1 -1 -0.8 -0.6 -0.4 -0.2 0 0.2 0.4 0.6

-0.5

y = -1.4534x
R² = 0.9621
γ = 1.4534
-1

K=1
KJS 14
Multivariable Linear Regression
The extension to multiple and/or vector-valued predictor variables (denoted with a capital
X) is known as multiple linear regression, also known as multivariable linear regression.
Nearly all real-world regression models involve multiple predictors, and basic descriptions
of linear regression are often phrased in terms of the multiple regression model.

KJS 15
KJS 16
May 2012

Will solve it during practical session


Practical-VIII
KJS 17
Thank you

You might also like