Loading in 5 sec....

Artificial Neural Networks for Decision Support in Copper Smelting ProcessPowerPoint Presentation

Artificial Neural Networks for Decision Support in Copper Smelting Process

- By
**colby** - Follow User

- 91 Views
- Uploaded on

Download Presentation
## PowerPoint Slideshow about ' Artificial Neural Networks for Decision Support in Copper Smelting Process' - colby

**An Image/Link below is provided (as is) to download presentation**

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript

Ivan S. Živković

Mathematical Institute of the Serbian Academy of Sciences and Arts

Artificial Neural Networks for Decision Support in Copper Smelting ProcessIvan S. Živković

1. Introduction

Considerable development of pyrometallurgical copper smelting process

Enlargement of production plants capacities

Increase of entirecopper production in the world

Increasing problems due to environmental pollution

1. Introduction

Smelting plants with old technologies emit PM10 and SO2 far above the limited values

World Health Organization (WHO, 2001) has prescribed limited values of SO2, PM10 content and heavy metals' content in the air

EU standardized limits of these polluters in the air by their regulations

1. Introduction

Multi-Criteria Decision Making (MCDM)methods in the analysis of problems of air pollution and soil

The integration of the analysis:

technological criteria

social criteria

environmental criteria

economicalcriteria

2. The blending problem

K1,...,Kmconcentrates

Determining the amount of each of the available raw materials (concentrates) K1,...,Km which will be used for obtaining the useful products

GOAL:achieve the greatest difference betweenprofit from useful products salesand costs for obtaining specified quantities of raw materials.

2. The blending problem

Take into account :

interactive relations between the quality of raw materials,

economical criteria,

the influence of the environmental criteria in the production process.

2. The blending problem

3. Neural network model

F(x1,...,xn) = ?

F(x1,...,xn) = Artificial Neural Network (ANN)

4. Neural network training

Generate training data

Combination of concentrate amount in mixture (x1,...,x14)

Calculate profit for combination

Back propagation algorithm

The trained network stores the nonlinear relationships between amounts of concentrates in mixture

5. Optimization

Complex Method for Constrained Optimization (Richardson and Kuester)

Sequential search technique

No derivatives are required

The initial set of points is randomly scattered throughout the feasible region

5. Optimization

x1 = 0.0011503862654742391

x2 = 0.0000044659968334488122

x3 = 0.33686567686323504

x4 = 0.000065479997370932846

x5 = 0.000005457597151501704

x6 = 0.14504843643625098

x7 = 0.0031948514922107056

x8 = 0.073478464846484792

x9 = 0.00043238651034418812

x10 = 0.00046832857651410561

x11 = 0.00011146905884013261

x12 = 0.43769285709204886

x13 = 0.00043421539040961333

x14 = 0.000063306618389357238

Profit = 581.19142562842535

6. Advantage

- No need for explicit form of the goal function
- No derivatives are required
- Network can learn nonlinear relationships between amounts of concentrates in mixture
- Easy to implement

Download Presentation

Connecting to Server..