Blast Furnace Analysis with Neural Networks

Size: px
Start display at page:

Download "Blast Furnace Analysis with Neural Networks"

Transcription

1 Blast Furnace Analysis with Neural Networks Joachim Angstenberger MIT - Management Intelligenter Technologien GmbH Promenade Aachen, Germany Phone: Fax: jang@mitgmbh.de Abstract: Nowadays blast furnace operation is supervised by extensive measurements and controlled accordingly. Characteristic indications concerning process quality are given by the analysis of the radial temperature profile in the upper part of the furnace. Optimising this temperature distribution would lead to considerable savings of input material. To achieve an optimisation, quantitative relations between furnace parameters are needed. As those relationships are unknown, a process model can be provided using neural networks and fuzzy methods. In this paper we show the application of fuzzy clustering and neural networks to classify temperature profiles and to build a model of the interdependence between process operation parameters and the resulting temperature profiles. These investigations have been carried out in a plant of a German steel producer. Keywords: blast furnace, process analysis, fuzzy clustering, multilayer perceptron, identification of temperature profiles 1 Introduction During the blast furnace process, ferric oxides contained in the input materials ore and sinter are reduced and melted. The output material is liquid pig-iron. Figure 1 shows a schematic overview of this process. The furnace is charged from its top. The input materials are sinking downwards while gas is flowing upwards through the furnace. The melting heat is supplied by this gas stream and by coke (which is also charged from above). Although studies have been made about the internal operating conditions of the furnace [Omori, 1987], the blast furnace operating personnel relies mainly upon measurements at the inputs and outputs of the process. A wide range of measuring data is acquired at the blast furnace. Blast furnace engineers check Vertical probe Profile meter Layer thickness meter Lumpy zone Horizontal probe Fig. 1: Schematic view of the blast furnace Cohesive zone Dripping zone Belly probe Raceway Hearth

2 these data in order to find out if the change of a controllable furnace parameter is necessary. This inspection is done by expert knowledge, i.e. control of the blast furnace is based on the experience of the operating personnel. Quantitative knowledge of functional dependencies between furnace parameters is not absolutely required for that purpose.however, experience has shown that missing knowledge of quantitative functional interdependencies makes an optimised furnace operation almost impossible.the operation is considered to be optimal, if the fuel consumption (coke and coal) is minimised (cost savings) and the furnace shows a steady cycle without greater fluctuations of some parameters. One of these essential parameters is the radial temperature distribution in the upper part of the blast furnace. According to the experts' knowledge, this magnitude is the most important parameter to judge the condition of the furnace. The temperature profile should show a determined characteristic shape: Maximal value in the centre of the furnace, fall off reaching the wall with a minimum briefly after the half radius and again rising reaching the wall. Past has shown that at the considered blast furnace among all of these profiles one specific shape is always connected with the best furnace operation (in the above-mentioned sense). The question indeed is how to receive such a shape and how to maintain it in the long run? For that purpose the shape influencing quantities have to be known as well as the order of magnitude of their quantitative influence on the furnace process. Due to the large number of furnace parameters and their highly non-linear coupling the identification of these influencing factors is difficult, which thus also holds for the modelling of the process itself. As there is no possibility to generate an adequate physical model of the blast furnace, the relationship between these influencing parameters on one hand and the resulting temperature profile on the other hand were modelled using a neural network By interviewing blast furnace experts the characteristics of the input materials sinter (iron supply) and coke (energy supply) as well as the charging program were identified as the main influence factors on the temperature profile. The charging program determines the order and the amount of the input materials brought into the furnace, thereby producing a series of sinter and coke layers. The thickness and the structure of these layers (shown at the upper left side of figure 1 as different hatchings) have great influence on the rising gas streams in the furnace and therefore determine indirectly the measured temperature profile. The two objectives of this analysis were: 1. A classification of the temperature profiles with the objective to assess how much the current state of the furnace corresponds to determined quality criteria. 2. The determination of the quantitative dependency of the cross-sectional temperature profile on the decisive magnitudes that constitute this profile (i.e. modelling the blast furnace). These two parts of the analysis can later on be combined into a complete blast furnace control system. In a first step the classification of the temperature profile gives

3 information about the current state of the blast furnace. A suitable influencing of the profile can then be carried out using the furnace model. All examinations have been carried out with the help of the data analysis software DataEngine, which includes methods for fuzzy clustering as well as neural networks. Together with its data pre-processing, statistics and visualisation facilities this tool enables a complete solution of the whole task. 2 Classification of Temperature Profiles in the Blast Furnace by Fuzzy Clustering For splitting the temperature profiles into classes 143 data records, each containing a profile of 8 temperature values recorded previously have been used. At the beginning, the number of different classes of profiles included in the data material was unknown, so the optimum number of classes had to be determined first. For the purpose of classification the fuzzy c-means algorithm was used, a fuzzy clustering procedure that allows gradual association of the considered objects (here: temperature profiles) to the respective classes [Bezdek 1981]. The essential information this algorithm produces are the centres of the clusters found during clustering. Each cluster centre represents a (fictitious) sample that characterises the respective class best. Here, fuzzy clustering results in typical temperature profiles that can be interpreted as prototypes of the respective classes. To determine the optimal number of classes, cluster validity measures can be used [Windham 1981]. The analysis of the given data records leads to an optimal partition of five clusters, whose centres are displayed in the following diagrams (Figure 2). In each diagram the temperature is plotted against the measuring position (seen from the centre of the furnace). 8 Cla ss 1 8 Cla ss Te m p 4 Te m p Te m p Cla ss Te m p 4 2 Cla ss

4 Temp Class 5 Position 41 Fig. 2: Types of temperature profiles (classification into 5 classes) Using the criteria mentioned in the introduction above, it can be recognised that the profiles of classes 1, 2 and, with certain reservations, class 4 represent good furnace states, whereas classes 3 and 5 characterise undesired states of the furnace. The received class partition was validated by blast furnace experts. It turned out to represent a good characterisation of typical states of the furnace (cf. also [Bulsari, Saxen 1995]). 3 Modelling of the Dependency Between Temperature Profiles and Input Parameters by Neural Networks The available data records for modelling the blast furnace comprised the charging program, the distributions of the grain sizes of coke and sinter as well as several parameters of the material strength. As the grain spectrum of coke covers a relatively narrow area, the evaluation considered only the medium grain diameter. The distribution of the grain size of sinter plays an essential part for the furnace process, as it bears strongly upon the gas flow in the furnace. For that reason the distribution of the sinter grain size was used completely as an input parameter. Altogether 1 input parameters were used. Because of material transportation time and other effects the material parameters affect the temperature profile with a delay of approximately 24 hours. On the other hand, the charging program bears on the temperature profile with a delay of 8 hours due to process characteristics. An appropriate synchronisation of the data had to be carried out. After further pre-processing (scaling, etc.) these data were used as inputs of a multilayer perceptron. Some data records were extracted from the total amount of data in order to be used for validation of the network performance. The output of the network consists of 8 values modelling the temperature at the respective measurement positions of the measuring system. Figure 3 represents a schematic view of the neural network's structure.

5 Fig. 3: Schematic structure of the neural network for blast furnace modelling Several network configurations (number of hidden layers, number of hidden neurons, learning parameters) have been trained and tested with regard to their efficiency. The neural network is able to approximate the temperature profiles with good precision. This is proven by the comparisons shown in figure 4. The diagrams show the temperature profiles calculated by the neural network (indicated as "Network" in figure 4) as opposed to the actually measured profiles ("" in figure 4) for four data records. The cases shown in figure 4 have not been used for training the neural network. The neural network proved to be able to recognise relatively unusual temperature profiles as well (like the one displayed in figure 4 on the lower right) Fig. 4: Comparison of measured and calculated temperature profiles However, the test results made clear as well that there are certain situations where the neural network is not able to achieve a reasonable result. Therefore, additional examinations have to be performed to quantify the influence of several additional magnitudes that have not been considered yet. In particular, these are magnitudes influencing the gas flow in the furnace and more detailed information about the input material. With inclusion of this information modelling and optimisation of the blast furnace process can be largely improved.

6 4 Conclusions In this contribution modelling of a blast furnace by neural networks and fuzzy logic has been investigated. The neural network model achieved a high correlation between actual and estimated temperature profiles. Based on these results an improved process control with respect to input material savings and quality of the produced steel can be implemented. 5 References [Bezdek 1981] Bezdek, J. C.: Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press, New York London, [Bulsari, Saxen 1995] Bulsari, A., Saxen, B.: Classification of blast furnace probe temperatures using neural networks. Steel Research 66, 1995, No. 6, pp [Omori 1987] Omori, Y. (ed.): Blast Furnace Phenomena and Modelling. The Iron and Steel Institute of Japan. Elsevier, London, [Windham 1981] Windham, M.P.: Cluster Validity for Fuzzy Clustering Algorithms. Fuzzy Sets and Systems 5, 1981, pp

SUCCESSFUL PREDICTION OF HORSE RACING RESULTS USING A NEURAL NETWORK

SUCCESSFUL PREDICTION OF HORSE RACING RESULTS USING A NEURAL NETWORK SUCCESSFUL PREDICTION OF HORSE RACING RESULTS USING A NEURAL NETWORK N M Allinson and D Merritt 1 Introduction This contribution has two main sections. The first discusses some aspects of multilayer perceptrons,

More information

INTELLIGENT ENERGY MANAGEMENT OF ELECTRICAL POWER SYSTEMS WITH DISTRIBUTED FEEDING ON THE BASIS OF FORECASTS OF DEMAND AND GENERATION Chr.

INTELLIGENT ENERGY MANAGEMENT OF ELECTRICAL POWER SYSTEMS WITH DISTRIBUTED FEEDING ON THE BASIS OF FORECASTS OF DEMAND AND GENERATION Chr. INTELLIGENT ENERGY MANAGEMENT OF ELECTRICAL POWER SYSTEMS WITH DISTRIBUTED FEEDING ON THE BASIS OF FORECASTS OF DEMAND AND GENERATION Chr. Meisenbach M. Hable G. Winkler P. Meier Technology, Laboratory

More information

Effect of Magnesium Oxide Content on Final Slag Fluidity of Blast Furnace

Effect of Magnesium Oxide Content on Final Slag Fluidity of Blast Furnace China Steel Technical Report, No. 21, pp. 21-28, (2008) J. S. Shiau and S. H. Liu 21 Effect of Magnesium Oxide Content on Final Slag Fluidity of Blast Furnace JIA-SHYAN SHIAU and SHIH-HSIEN LIU Steel and

More information

CONTENTS. ZVU Engineering a.s., Member of ZVU Group, WASTE HEAT BOILERS Page 2

CONTENTS. ZVU Engineering a.s., Member of ZVU Group, WASTE HEAT BOILERS Page 2 WASTE HEAT BOILERS CONTENTS 1 INTRODUCTION... 3 2 CONCEPTION OF WASTE HEAT BOILERS... 4 2.1 Complex Solution...4 2.2 Kind of Heat Exchange...5 2.3 Heat Recovery Units and Their Usage...5 2.4 Materials

More information

Maximization versus environmental compliance

Maximization versus environmental compliance Maximization versus environmental compliance Increase use of alternative fuels with no risk for quality and environment Reprint from World Cement March 2005 Dr. Eduardo Gallestey, ABB, Switzerland, discusses

More information

6.2.8 Neural networks for data mining

6.2.8 Neural networks for data mining 6.2.8 Neural networks for data mining Walter Kosters 1 In many application areas neural networks are known to be valuable tools. This also holds for data mining. In this chapter we discuss the use of neural

More information

EFFICIENT DATA PRE-PROCESSING FOR DATA MINING

EFFICIENT DATA PRE-PROCESSING FOR DATA MINING EFFICIENT DATA PRE-PROCESSING FOR DATA MINING USING NEURAL NETWORKS JothiKumar.R 1, Sivabalan.R.V 2 1 Research scholar, Noorul Islam University, Nagercoil, India Assistant Professor, Adhiparasakthi College

More information

Quality and Operation Management System for Steel Products through Multivariate Statistical Process Control

Quality and Operation Management System for Steel Products through Multivariate Statistical Process Control , July 3-5, 2013, London, U.K. Quality and Operation Management System for Steel Products through Multivariate Statistical Process Control Hiroyasu Shigemori, Member, IAENG Abstract A new quality and operation

More information

Corporate Financial Evaluation and Bankruptcy Prediction Implementing Artificial Intelligence Methods

Corporate Financial Evaluation and Bankruptcy Prediction Implementing Artificial Intelligence Methods Corporate Financial Evaluation and Bankruptcy Prediction Implementing Artificial Intelligence Methods LOUKERIS N. (1), MATSATSINIS N. (2) Department of Production Engineering and Management, Technical

More information

Performance of the Boiler and To Improving the Boiler Efficiency Using Cfd Modeling

Performance of the Boiler and To Improving the Boiler Efficiency Using Cfd Modeling IOSR Journal of Mechanical and Civil Engineering (IOSR-JMCE) e-issn: 2278-1684,p-ISSN: 2320-334X, Volume 8, Issue 6 (Sep. - Oct. 2013), PP 25-29 Performance of the Boiler and To Improving the Boiler Efficiency

More information

Pulverized Coal Pipe Testing and Balancing

Pulverized Coal Pipe Testing and Balancing Pulverized Coal Pipe Testing and Balancing By Richard F. (Dick) Storm, PE The first step in optimizing combustion system performance is balancing the air and fuel flowing through each of the plant's coal

More information

Effect of Magnesium and Aluminum Oxides on Fluidity of Final Blast Furnace Slag and Its Application

Effect of Magnesium and Aluminum Oxides on Fluidity of Final Blast Furnace Slag and Its Application Materials Transactions, Vol. 53, No. 8 (2012) pp. 1449 to 1455 2012 The Japan Institute of Metals Effect of Magnesium and Aluminum Oxides on Fluidity of Final Blast Furnace Slag and Its Application Jia-Shyan

More information

Verification Experiment on Cooling and Deformation Effects of Automatically Designed Cooling Channels for Block Laminated Molds

Verification Experiment on Cooling and Deformation Effects of Automatically Designed Cooling Channels for Block Laminated Molds International Journal of Engineering and Advanced Technology (IJEAT ISSN: 2249 8958 Volume-4 Issue-5 June 2015 Verification Experiment on Cooling and Deformation Effects of Automatically Designed Cooling

More information

Iranian J Env Health Sci Eng, 2004, Vol.1, No.2, pp.51-57. Application of Intelligent System for Water Treatment Plant Operation.

Iranian J Env Health Sci Eng, 2004, Vol.1, No.2, pp.51-57. Application of Intelligent System for Water Treatment Plant Operation. Iranian J Env Health Sci Eng, 2004, Vol.1, No.2, pp.51-57 Application of Intelligent System for Water Treatment Plant Operation *A Mirsepassi Dept. of Environmental Health Engineering, School of Public

More information

FRAUD DETECTION IN ELECTRIC POWER DISTRIBUTION NETWORKS USING AN ANN-BASED KNOWLEDGE-DISCOVERY PROCESS

FRAUD DETECTION IN ELECTRIC POWER DISTRIBUTION NETWORKS USING AN ANN-BASED KNOWLEDGE-DISCOVERY PROCESS FRAUD DETECTION IN ELECTRIC POWER DISTRIBUTION NETWORKS USING AN ANN-BASED KNOWLEDGE-DISCOVERY PROCESS Breno C. Costa, Bruno. L. A. Alberto, André M. Portela, W. Maduro, Esdras O. Eler PDITec, Belo Horizonte,

More information

Overview of Integrated Coal Gasification Combined-cycle Technology Using Low-rank Coal

Overview of Integrated Coal Gasification Combined-cycle Technology Using Low-rank Coal 19 Overview of Integrated Coal Gasification Combined-cycle Technology Using Low-rank Coal TAKAO HASHIMOTO *1 KOICHI SAKAMOTO *2 YOSHIKI YAMAGUCHI *3 KOJI OURA *4 KENICHI ARIMA *5 TAKESHI SUZUKI *6 Mitsubishi

More information

Predictive Dynamix Inc

Predictive Dynamix Inc Predictive Modeling Technology Predictive modeling is concerned with analyzing patterns and trends in historical and operational data in order to transform data into actionable decisions. This is accomplished

More information

THE ELEMENT C. Introduction graphite and carbon Lattice Classification of grain size. Properties of graphite and carbon

THE ELEMENT C. Introduction graphite and carbon Lattice Classification of grain size. Properties of graphite and carbon THE ELEMENT C Introduction graphite and carbon Lattice Classification of grain size Fine-grained graphite Coarse-grained graphite Properties of graphite and carbon High temperature properties Introduction

More information

Piotr Tofiło a,*, Marek Konecki b, Jerzy Gałaj c, Waldemar Jaskółowski d, Norbert Tuśnio e, Marcin Cisek f

Piotr Tofiło a,*, Marek Konecki b, Jerzy Gałaj c, Waldemar Jaskółowski d, Norbert Tuśnio e, Marcin Cisek f Available online at www.sciencedirect.com Procedia Engineering 57 (2013 ) 1156 1165 11th International Conference on Modern Building Materials, Structures and Techniques, MBMST 2013 Expert System for Building

More information

D A T A M I N I N G C L A S S I F I C A T I O N

D A T A M I N I N G C L A S S I F I C A T I O N D A T A M I N I N G C L A S S I F I C A T I O N FABRICIO VOZNIKA LEO NARDO VIA NA INTRODUCTION Nowadays there is huge amount of data being collected and stored in databases everywhere across the globe.

More information

How To Use Neural Networks In Data Mining

How To Use Neural Networks In Data Mining International Journal of Electronics and Computer Science Engineering 1449 Available Online at www.ijecse.org ISSN- 2277-1956 Neural Networks in Data Mining Priyanka Gaur Department of Information and

More information

A New Approach For Estimating Software Effort Using RBFN Network

A New Approach For Estimating Software Effort Using RBFN Network IJCSNS International Journal of Computer Science and Network Security, VOL.8 No.7, July 008 37 A New Approach For Estimating Software Using RBFN Network Ch. Satyananda Reddy, P. Sankara Rao, KVSVN Raju,

More information

High Flux Steam Reforming

High Flux Steam Reforming High Flux Steam Reforming by Thomas Rostrup-Nielsen Haldor Topsoe A/S, Lyngby, Denmark Abstract Topsøe has introduced the High Flux Steam Reformer (HFR), with lower cost than conventional side fired reformers.

More information

COKE PRODUCTION FOR BLAST FURNACE IRONMAKING

COKE PRODUCTION FOR BLAST FURNACE IRONMAKING COKE PRODUCTION FOR BLAST FURNACE IRONMAKING By Hardarshan S. Valia, Scientist, Ispat Inland Inc INTRODUCTION A world class blast furnace operation demands the highest quality of raw materials, operation,

More information

COMBINING THE METHODS OF FORECASTING AND DECISION-MAKING TO OPTIMISE THE FINANCIAL PERFORMANCE OF SMALL ENTERPRISES

COMBINING THE METHODS OF FORECASTING AND DECISION-MAKING TO OPTIMISE THE FINANCIAL PERFORMANCE OF SMALL ENTERPRISES COMBINING THE METHODS OF FORECASTING AND DECISION-MAKING TO OPTIMISE THE FINANCIAL PERFORMANCE OF SMALL ENTERPRISES JULIA IGOREVNA LARIONOVA 1 ANNA NIKOLAEVNA TIKHOMIROVA 2 1, 2 The National Nuclear Research

More information

Open Access Research on Application of Neural Network in Computer Network Security Evaluation. Shujuan Jin *

Open Access Research on Application of Neural Network in Computer Network Security Evaluation. Shujuan Jin * Send Orders for Reprints to reprints@benthamscience.ae 766 The Open Electrical & Electronic Engineering Journal, 2014, 8, 766-771 Open Access Research on Application of Neural Network in Computer Network

More information

HEAVY OIL FLOW MEASUREMENT CHALLENGES

HEAVY OIL FLOW MEASUREMENT CHALLENGES HEAVY OIL FLOW MEASUREMENT CHALLENGES 1 INTRODUCTION The vast majority of the world s remaining oil reserves are categorised as heavy / unconventional oils (high viscosity). Due to diminishing conventional

More information

T U R B I N E G A S M E T E R

T U R B I N E G A S M E T E R TURBINE GAS METER TURBINE GAS METER CGT 1 2 3 4 5 6 7 Design and function page 2 General technical data page 3 Measurement outputs page 4 Dimensions and weights page 5 Performance page 7 Pressure loss

More information

The Second Law of Thermodynamics

The Second Law of Thermodynamics The Second aw of Thermodynamics The second law of thermodynamics asserts that processes occur in a certain direction and that the energy has quality as well as quantity. The first law places no restriction

More information

Experimental investigation of golf driver club head drag reduction through the use of aerodynamic features on the driver crown

Experimental investigation of golf driver club head drag reduction through the use of aerodynamic features on the driver crown Available online at www.sciencedirect.com Procedia Engineering 00 (2013) 000 000 www.elsevier.com/locate/procedia The 2014 conference of the International Sports Engineering Association Experimental investigation

More information

Sound Quality Evaluation of Hermetic Compressors Using Artificial Neural Networks

Sound Quality Evaluation of Hermetic Compressors Using Artificial Neural Networks Purdue University Purdue e-pubs International Compressor Engineering Conference School of Mechanical Engineering 2006 Sound Quality Evaluation of Hermetic Compressors Using Artificial Neural Networks Claudio

More information

Optimizing the prediction models of the air quality state in cities

Optimizing the prediction models of the air quality state in cities Air Pollution XV 89 Optimizing the prediction models of the air quality state in cities J. Skrzypski, E. Jach-Szakiel & W. Kamiński Faculty of Process and Environmental Engineering, Technical University

More information

Gerard Mc Nulty Systems Optimisation Ltd gmcnulty@iol.ie/0876697867 BA.,B.A.I.,C.Eng.,F.I.E.I

Gerard Mc Nulty Systems Optimisation Ltd gmcnulty@iol.ie/0876697867 BA.,B.A.I.,C.Eng.,F.I.E.I Gerard Mc Nulty Systems Optimisation Ltd gmcnulty@iol.ie/0876697867 BA.,B.A.I.,C.Eng.,F.I.E.I Data is Important because it: Helps in Corporate Aims Basis of Business Decisions Engineering Decisions Energy

More information

Thermocline Management of Stratified Tanks for Heat Storage

Thermocline Management of Stratified Tanks for Heat Storage Thermocline Management of Stratified Tanks for Heat Storage M.R.W. Walmsley, M. J. Atkins, J. Riley Energy Research Group, Department of Engineering, University of Waikato Hamilton, NZ Stratified tanks

More information

The Combination Forecasting Model of Auto Sales Based on Seasonal Index and RBF Neural Network

The Combination Forecasting Model of Auto Sales Based on Seasonal Index and RBF Neural Network , pp.67-76 http://dx.doi.org/10.14257/ijdta.2016.9.1.06 The Combination Forecasting Model of Auto Sales Based on Seasonal Index and RBF Neural Network Lihua Yang and Baolin Li* School of Economics and

More information

Thermal Control of the Extrusion Press Container

Thermal Control of the Extrusion Press Container Thermal Control of the Extrusion Press Container Prepared by -- Dennis Van Dine, Nazmi Gilada, Paul Robbins, Castool Tooling Solutions, Dr. V.I. (Mike) Johannes, BENCHMARKS, Shigeyoshi Takagi, Techno-Consul

More information

Summary of specified general model for CHP system

Summary of specified general model for CHP system Fakulteta za Elektrotehniko Eva Thorin, Heike Brand, Christoph Weber Summary of specified general model for CHP system OSCOGEN Deliverable D1.4 Contract No. ENK5-CT-2000-00094 Project co-funded by the

More information

DYNAMIC FUZZY PATTERN RECOGNITION WITH APPLICATIONS TO FINANCE AND ENGINEERING LARISA ANGSTENBERGER

DYNAMIC FUZZY PATTERN RECOGNITION WITH APPLICATIONS TO FINANCE AND ENGINEERING LARISA ANGSTENBERGER DYNAMIC FUZZY PATTERN RECOGNITION WITH APPLICATIONS TO FINANCE AND ENGINEERING LARISA ANGSTENBERGER Kluwer Academic Publishers Boston/Dordrecht/London TABLE OF CONTENTS FOREWORD ACKNOWLEDGEMENTS XIX XXI

More information

Chapter 27: Taxation. 27.1: Introduction. 27.2: The Two Prices with a Tax. 27.2: The Pre-Tax Position

Chapter 27: Taxation. 27.1: Introduction. 27.2: The Two Prices with a Tax. 27.2: The Pre-Tax Position Chapter 27: Taxation 27.1: Introduction We consider the effect of taxation on some good on the market for that good. We ask the questions: who pays the tax? what effect does it have on the equilibrium

More information

It simply works! Safe process monitoring.

It simply works! Safe process monitoring. It simply works! Safe process monitoring. A solution that simply works. It simply works: BK Mikro All safely under control: In automated manu facturing there is an enormous range of possible uses for the

More information

Simulation of Transient Temperature Field in the Selective Laser Sintering Process of W/Ni Powder Mixture

Simulation of Transient Temperature Field in the Selective Laser Sintering Process of W/Ni Powder Mixture Simulation of Transient Temperature Field in the Selective Laser Sintering Process of W/Ni Powder Mixture Jiwen Ren,Jianshu Liu,Jinju Yin The School of Electromechanical Engineering, East China Jiaotong

More information

Analecta Vol. 8, No. 2 ISSN 2064-7964

Analecta Vol. 8, No. 2 ISSN 2064-7964 EXPERIMENTAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN ENGINEERING PROCESSING SYSTEM S. Dadvandipour Institute of Information Engineering, University of Miskolc, Egyetemváros, 3515, Miskolc, Hungary,

More information

Chapter 10. Key Ideas Correlation, Correlation Coefficient (r),

Chapter 10. Key Ideas Correlation, Correlation Coefficient (r), Chapter 0 Key Ideas Correlation, Correlation Coefficient (r), Section 0-: Overview We have already explored the basics of describing single variable data sets. However, when two quantitative variables

More information

Data Mining Analysis of a Complex Multistage Polymer Process

Data Mining Analysis of a Complex Multistage Polymer Process Data Mining Analysis of a Complex Multistage Polymer Process Rolf Burghaus, Daniel Leineweber, Jörg Lippert 1 Problem Statement Especially in the highly competitive commodities market, the chemical process

More information

Completion of SCR System for Ninghai Power Plant Unit 4 in China

Completion of SCR System for Ninghai Power Plant Unit 4 in China Hitachi Review Vol. 57 (2008), No. 6 293 Completion of SCR System for Ninghai Power Plant 4 in China Yoshiro Inatsune Yoshiyuki Takeuchi Masafumi Ishizaki OVERVIEW: The SCR system installed on Ninghai

More information

Data Mining mit der JMSL Numerical Library for Java Applications

Data Mining mit der JMSL Numerical Library for Java Applications Data Mining mit der JMSL Numerical Library for Java Applications Stefan Sineux 8. Java Forum Stuttgart 07.07.2005 Agenda Visual Numerics JMSL TM Numerical Library Neuronale Netze (Hintergrund) Demos Neuronale

More information

Segmentation of stock trading customers according to potential value

Segmentation of stock trading customers according to potential value Expert Systems with Applications 27 (2004) 27 33 www.elsevier.com/locate/eswa Segmentation of stock trading customers according to potential value H.W. Shin a, *, S.Y. Sohn b a Samsung Economy Research

More information

SINTERING AND PELLETISATION OF INDIAN IRON ORES

SINTERING AND PELLETISATION OF INDIAN IRON ORES SINTERING AND PELLETISATION OF INDIAN IRON ORES By SURESH KUMAR* & T.M. SRINIVASAN** 1 * Vice President, Mineral Enterprises Limited, Bangalore ** Managing Director, FerroGreen Technologies Pvt. Ltd. Bangalore

More information

APPLICATION OF DATA MINING TECHNIQUES FOR BUILDING SIMULATION PERFORMANCE PREDICTION ANALYSIS. email paul@esru.strath.ac.uk

APPLICATION OF DATA MINING TECHNIQUES FOR BUILDING SIMULATION PERFORMANCE PREDICTION ANALYSIS. email paul@esru.strath.ac.uk Eighth International IBPSA Conference Eindhoven, Netherlands August -4, 2003 APPLICATION OF DATA MINING TECHNIQUES FOR BUILDING SIMULATION PERFORMANCE PREDICTION Christoph Morbitzer, Paul Strachan 2 and

More information

www.optimumheat.co.uk

www.optimumheat.co.uk The modern wood pellet boiler with built-in flexibility and remote fingertip control Up to 98% efficient Wide output range Simple touch-panel control Remote control & maintenance Extremly low emissions

More information

Essential Components of an Integrated Data Mining Tool for the Oil & Gas Industry, With an Example Application in the DJ Basin.

Essential Components of an Integrated Data Mining Tool for the Oil & Gas Industry, With an Example Application in the DJ Basin. Essential Components of an Integrated Data Mining Tool for the Oil & Gas Industry, With an Example Application in the DJ Basin. Petroleum & Natural Gas Engineering West Virginia University SPE Annual Technical

More information

Diagrams and Graphs of Statistical Data

Diagrams and Graphs of Statistical Data Diagrams and Graphs of Statistical Data One of the most effective and interesting alternative way in which a statistical data may be presented is through diagrams and graphs. There are several ways in

More information

Infrastructure & Cities Sector

Infrastructure & Cities Sector Technical Article Infrastructure & Cities Sector Building Technologies Division Zug (Switzerland), October 18, 2011 Saving Energy in a Data Center A Leap of Faith? New guidelines from ASHRAE (American

More information

2. IMPLEMENTATION. International Journal of Computer Applications (0975 8887) Volume 70 No.18, May 2013

2. IMPLEMENTATION. International Journal of Computer Applications (0975 8887) Volume 70 No.18, May 2013 Prediction of Market Capital for Trading Firms through Data Mining Techniques Aditya Nawani Department of Computer Science, Bharati Vidyapeeth s College of Engineering, New Delhi, India Himanshu Gupta

More information

Chapter 1.3 Energy management & audit

Chapter 1.3 Energy management & audit Chapter 1.3 Energy management & audit Part I: Objective type questions and answers 1. The judicious and effective use of energy to maximise profits and enhance competitive positions. This can be the definition

More information

Characteristics of an Integrated Germanium Detector Based Gamma-Ray Spectrometer for Monitoring Systems

Characteristics of an Integrated Germanium Detector Based Gamma-Ray Spectrometer for Monitoring Systems Characteristics of an Integrated Germanium Detector Based Gamma-Ray Spectrometer for Monitoring Systems Ronald M. Keyser, Timothy R. Twomey, Sam Hitch ORTEC 801 South Illinois Avenue Oak Ridge, TN, 37831

More information

Michael Montgomery Marketing Product Manager Rosemount Inc. Russ Evans Manager of Engineering and Design Rosemount Inc.

Michael Montgomery Marketing Product Manager Rosemount Inc. Russ Evans Manager of Engineering and Design Rosemount Inc. ASGMT / Averaging Pitot Tube Flow Measurement Michael Montgomery Marketing Product Manager Rosemount Inc. Russ Evans Manager of Engineering and Design Rosemount Inc. Averaging Pitot Tube Meters Introduction

More information

Optimization of Steel and Methanol Production in an Integrated

Optimization of Steel and Methanol Production in an Integrated Optimization of Steel and Methanol Production in an Integrated H. Ghanbari, H. Helle, M. Helle, F. Pettersson and H. Saxen Åbo Akademi University Heat Engineering Laboratory Åbo / Turku, Finland tel. +358

More information

Improving Steam Methane Reformer Performance with the ZoloSCAN-SMR

Improving Steam Methane Reformer Performance with the ZoloSCAN-SMR Improving Steam Methane Reformer Performance with the SCAN-SMR The global demand for hydrogen continues to increase as heavier crudes are processed and stricter governmental mandates require reductions

More information

Business Policy of CEZ Group and ČEZ, a. s.

Business Policy of CEZ Group and ČEZ, a. s. Business Policy of CEZ Group and ČEZ, a. s. Contents: Introduction 1. CEZ Group mission and vision 2. Scope of business of CEZ Group 3. Business concept Guiding principles Trade Generation Electricity

More information

ENERGY EFFICIENCY ENHANCEMENT IN THE HOT ROLLING MILL

ENERGY EFFICIENCY ENHANCEMENT IN THE HOT ROLLING MILL Materials Science and Engineering, Volume 3, No. 2. (2014), pp. 43 50. ENERGY EFFICIENCY ENHANCEMENT IN THE HOT ROLLING MILL ERIKA KUN 1 TAMÁSNÉ SZEMMELVEISZ 2 Hungarian steel producer ISD Dunaferr Ltd.

More information

POURING THE MOLTEN METAL

POURING THE MOLTEN METAL HEATING AND POURING To perform a casting operation, the metal must be heated to a temperature somewhat above its melting point and then poured into the mold cavity to solidify. In this section, we consider

More information

Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches

Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches PhD Thesis by Payam Birjandi Director: Prof. Mihai Datcu Problematic

More information

PRESSBLOWER Injection Blow Moulder

PRESSBLOWER Injection Blow Moulder PRESSBLOWER Injection Blow Moulder PRESSBLOWER DSE 140 PRESSBLOWER DSE 250 Tasks Solutions C. V. Joint Boots Bellows used in automobiles are subject to permanent stress. Under quality aspects this means

More information

Environment Protection Engineering APPROXIMATION OF IMISSION LEVEL AT AIR MONITORING STATIONS BY MEANS OF AUTONOMOUS NEURAL MODELS

Environment Protection Engineering APPROXIMATION OF IMISSION LEVEL AT AIR MONITORING STATIONS BY MEANS OF AUTONOMOUS NEURAL MODELS Environment Protection Engineering Vol. 3 No. DOI: 1.577/epe1 SZYMON HOFFMAN* APPROXIMATION OF IMISSION LEVEL AT AIR MONITORING STATIONS BY MEANS OF AUTONOMOUS NEURAL MODELS Long-term collection of data,

More information

Geometry and dimensional tolerances of engine bearings

Geometry and dimensional tolerances of engine bearings Geometry and dimensional tolerances of engine bearings Dr. Dmitri Kopeliovich (Research & Development Manager.) 1. Hydrodynamic lubrication Engine bearings operate mostly in the hydrodynamic regime of

More information

Safety Storage Cabinets

Safety Storage Cabinets Safety Storage Cabinets Safe storage of flammables? The workplace without a fire resistant Safety Storage Cabinet Dangers, risks and your disadvantages... STORAGE ROOM Transport/working time - Increased

More information

SPPA-D3000 Plant Monitor Technical Description

SPPA-D3000 Plant Monitor Technical Description SPPA-D3000 Plant Monitor Technical Description Model-based monitoring and early fault detection for components and processes May 2008 Answers for energy. 1 Siemens AG 2008. All Rights Reserved Contents

More information

CFD SIMULATION OF SDHW STORAGE TANK WITH AND WITHOUT HEATER

CFD SIMULATION OF SDHW STORAGE TANK WITH AND WITHOUT HEATER International Journal of Advancements in Research & Technology, Volume 1, Issue2, July-2012 1 CFD SIMULATION OF SDHW STORAGE TANK WITH AND WITHOUT HEATER ABSTRACT (1) Mr. Mainak Bhaumik M.E. (Thermal Engg.)

More information

Data Mining and Visualization

Data Mining and Visualization Data Mining and Visualization Jeremy Walton NAG Ltd, Oxford Overview Data mining components Functionality Example application Quality control Visualization Use of 3D Example application Market research

More information

John KW Hou, Ph.D. World- Wide Director, Industry Solutions Member of IBM Industry Academy IBM Corporation. José R. Favilla Jr

John KW Hou, Ph.D. World- Wide Director, Industry Solutions Member of IBM Industry Academy IBM Corporation. José R. Favilla Jr 1 A Big Data Approach to Optimize Energy Efficiency in the Steel Industry John KW Hou, Ph.D. Manager, IBM Center of Competence, Metals IBM Corporation José R. Favilla Jr World- Wide Director, Industry

More information

MODELLING COUPLED HEAT AND AIR FLOW: PING-PONG VS ONIONS

MODELLING COUPLED HEAT AND AIR FLOW: PING-PONG VS ONIONS MODELLING COUPLED HEAT AND AIR FLOW: PING-PONG VS ONIONS Jan Hensen University of Strathclyde Energy Systems Research Unit 75 Montrose Street, GLASGOW G1 1XJ, Scotland Email: jan@esru.strath.ac.uk SYNOPSIS

More information

A Framework for Intelligent Online Customer Service System

A Framework for Intelligent Online Customer Service System A Framework for Intelligent Online Customer Service System Yiping WANG Yongjin ZHANG School of Business Administration, Xi an University of Technology Abstract: In a traditional customer service support

More information

Stabilization by Conceptual Duplication in Adaptive Resonance Theory

Stabilization by Conceptual Duplication in Adaptive Resonance Theory Stabilization by Conceptual Duplication in Adaptive Resonance Theory Louis Massey Royal Military College of Canada Department of Mathematics and Computer Science PO Box 17000 Station Forces Kingston, Ontario,

More information

Numerical Algorithms Group

Numerical Algorithms Group Title: Summary: Using the Component Approach to Craft Customized Data Mining Solutions One definition of data mining is the non-trivial extraction of implicit, previously unknown and potentially useful

More information

DESIGN AND SIZING OF SCREW FEEDERS. By Marco Bortolamasi Johannes Fottner

DESIGN AND SIZING OF SCREW FEEDERS. By Marco Bortolamasi Johannes Fottner DESIGN AND SIZING OF SCREW FEEDERS By Marco Bortolamasi Johannes Fottner International Congress for Particle Technology Abstract Screw devices and other systems. This paper is concerned with the design

More information

About the NeuroFuzzy Module of the FuzzyTECH5.5 Software

About the NeuroFuzzy Module of the FuzzyTECH5.5 Software About the NeuroFuzzy Module of the FuzzyTECH5.5 Software Ágnes B. Simon, Dániel Biró College of Nyíregyháza, Sóstói út 31, simona@nyf.hu, bibby@freemail.hu Abstract: Our online edition of the software

More information

Data Mining for Manufacturing: Preventive Maintenance, Failure Prediction, Quality Control

Data Mining for Manufacturing: Preventive Maintenance, Failure Prediction, Quality Control Data Mining for Manufacturing: Preventive Maintenance, Failure Prediction, Quality Control Andre BERGMANN Salzgitter Mannesmann Forschung GmbH; Duisburg, Germany Phone: +49 203 9993154, Fax: +49 203 9993234;

More information

PROPERTIES AND MIX DESIGNATIONS 5-694.200

PROPERTIES AND MIX DESIGNATIONS 5-694.200 September 1, 2003 CONCRETE MANUAL 5-694.200 5-694.210 PROPERTIES OF CONCRETE PROPERTIES AND MIX DESIGNATIONS 5-694.200 Inspectors should familiarize themselves with the most important properties of concrete:

More information

Contents. Dedication List of Figures List of Tables. Acknowledgments

Contents. Dedication List of Figures List of Tables. Acknowledgments Contents Dedication List of Figures List of Tables Foreword Preface Acknowledgments v xiii xvii xix xxi xxv Part I Concepts and Techniques 1. INTRODUCTION 3 1 The Quest for Knowledge 3 2 Problem Description

More information

NEURAL networks [5] are universal approximators [6]. It

NEURAL networks [5] are universal approximators [6]. It Proceedings of the 2013 Federated Conference on Computer Science and Information Systems pp. 183 190 An Investment Strategy for the Stock Exchange Using Neural Networks Antoni Wysocki and Maciej Ławryńczuk

More information

Big Data: Rethinking Text Visualization

Big Data: Rethinking Text Visualization Big Data: Rethinking Text Visualization Dr. Anton Heijs anton.heijs@treparel.com Treparel April 8, 2013 Abstract In this white paper we discuss text visualization approaches and how these are important

More information

Blood Vessel Classification into Arteries and Veins in Retinal Images

Blood Vessel Classification into Arteries and Veins in Retinal Images Blood Vessel Classification into Arteries and Veins in Retinal Images Claudia Kondermann and Daniel Kondermann a and Michelle Yan b a Interdisciplinary Center for Scientific Computing (IWR), University

More information

Intelligent Agents Serving Based On The Society Information

Intelligent Agents Serving Based On The Society Information Intelligent Agents Serving Based On The Society Information Sanem SARIEL Istanbul Technical University, Computer Engineering Department, Istanbul, TURKEY sariel@cs.itu.edu.tr B. Tevfik AKGUN Yildiz Technical

More information

Data Mining Algorithms Part 1. Dejan Sarka

Data Mining Algorithms Part 1. Dejan Sarka Data Mining Algorithms Part 1 Dejan Sarka Join the conversation on Twitter: @DevWeek #DW2015 Instructor Bio Dejan Sarka (dsarka@solidq.com) 30 years of experience SQL Server MVP, MCT, 13 books 7+ courses

More information

Natural Convection. Buoyancy force

Natural Convection. Buoyancy force Natural Convection In natural convection, the fluid motion occurs by natural means such as buoyancy. Since the fluid velocity associated with natural convection is relatively low, the heat transfer coefficient

More information

Application of Building Energy Simulation to Air-conditioning Design

Application of Building Energy Simulation to Air-conditioning Design Hui, S. C. M. and K. P. Cheung, 1998. Application of building energy simulation to air-conditioning design, In Proc. of the Mainland-Hong Kong HVAC Seminar '98, 23-25 March 1998, Beijing, pp. 12-20. (in

More information

2. Simple Linear Regression

2. Simple Linear Regression Research methods - II 3 2. Simple Linear Regression Simple linear regression is a technique in parametric statistics that is commonly used for analyzing mean response of a variable Y which changes according

More information

Brown Hills College of Engineering & Technology Machine Design - 1. UNIT 1 D e s i g n P h i l o s o p h y

Brown Hills College of Engineering & Technology Machine Design - 1. UNIT 1 D e s i g n P h i l o s o p h y UNIT 1 D e s i g n P h i l o s o p h y Problem Identification- Problem Statement, Specifications, Constraints, Feasibility Study-Technical Feasibility, Economic & Financial Feasibility, Social & Environmental

More information

Examples of Data Representation using Tables, Graphs and Charts

Examples of Data Representation using Tables, Graphs and Charts Examples of Data Representation using Tables, Graphs and Charts This document discusses how to properly display numerical data. It discusses the differences between tables and graphs and it discusses various

More information

Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks

Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks Ph. D. Student, Eng. Eusebiu Marcu Abstract This paper introduces a new method of combining the

More information

HEINRICH FRINGS INFORMATION

HEINRICH FRINGS INFORMATION THE MODERN PRODUCTION OF ALCOHOL VINEGAR FRINGS offers a number of fermentation processes for the production of just that individual product which suits your market needs. The main difference between these

More information

A Simple Feature Extraction Technique of a Pattern By Hopfield Network

A Simple Feature Extraction Technique of a Pattern By Hopfield Network A Simple Feature Extraction Technique of a Pattern By Hopfield Network A.Nag!, S. Biswas *, D. Sarkar *, P.P. Sarkar *, B. Gupta **! Academy of Technology, Hoogly - 722 *USIC, University of Kalyani, Kalyani

More information

Knowledge Based Descriptive Neural Networks

Knowledge Based Descriptive Neural Networks Knowledge Based Descriptive Neural Networks J. T. Yao Department of Computer Science, University or Regina Regina, Saskachewan, CANADA S4S 0A2 Email: jtyao@cs.uregina.ca Abstract This paper presents a

More information

FURNACEPHOSPHORUS AND PHOSPHORICACID PROCESS ECONOMICS PROGRAM. Report No. 52. July 1969. A private report by. the

FURNACEPHOSPHORUS AND PHOSPHORICACID PROCESS ECONOMICS PROGRAM. Report No. 52. July 1969. A private report by. the Report No. 52 FURNACEPHOSPHORUS AND PHOSPHORICACID by GEORGE E. HADDELAND July 1969 A private report by. the PROCESS ECONOMICS PROGRAM STANFORD RESEARCH INSTITUTE MENLO PARK, CALIFORNIA CONTENTS 1 INTRODUCTION........................

More information

Variable Capacity Compressors, a new dimension for refrigeration engineers to explore

Variable Capacity Compressors, a new dimension for refrigeration engineers to explore Variable Capacity Compressors, a new dimension for refrigeration engineers to explore By: Marcos G. Schwarz, VCC Group Leader Corporate Research & Development, EMBRACO SA Abstract: This paper presents

More information

Up/Down Analysis of Stock Index by Using Bayesian Network

Up/Down Analysis of Stock Index by Using Bayesian Network Engineering Management Research; Vol. 1, No. 2; 2012 ISSN 1927-7318 E-ISSN 1927-7326 Published by Canadian Center of Science and Education Up/Down Analysis of Stock Index by Using Bayesian Network Yi Zuo

More information

Data Quality Mining: Employing Classifiers for Assuring consistent Datasets

Data Quality Mining: Employing Classifiers for Assuring consistent Datasets Data Quality Mining: Employing Classifiers for Assuring consistent Datasets Fabian Grüning Carl von Ossietzky Universität Oldenburg, Germany, fabian.gruening@informatik.uni-oldenburg.de Abstract: Independent

More information

Short Term Electricity Price Forecasting Using ANN and Fuzzy Logic under Deregulated Environment

Short Term Electricity Price Forecasting Using ANN and Fuzzy Logic under Deregulated Environment Short Term Electricity Price Forecasting Using ANN and Fuzzy Logic under Deregulated Environment Aarti Gupta 1, Pankaj Chawla 2, Sparsh Chawla 3 Assistant Professor, Dept. of EE, Hindu College of Engineering,

More information

Coal-To-Gas & Coal-To-Liquids

Coal-To-Gas & Coal-To-Liquids Located in the Energy Center at Discovery Park, Purdue University Coal-To-Gas & Coal-To-Liquids CCTR Basic Facts File #3 Brian H. Bowen, Marty W. Irwin The Energy Center at Discovery Park Purdue University

More information