=Paper=
{{Paper
|id=Vol-2608/paper9
|storemode=property
|title=Intelligence analysis method of automation control system archive database for controlling hot blast stove block
|pdfUrl=https://ceur-ws.org/Vol-2608/paper9.pdf
|volume=Vol-2608
|authors=Oleksiy Koyfman,Oleksandr Simkin,Kseniia Serdiuk
|dblpUrl=https://dblp.org/rec/conf/cmis/KoyfmanSS20
}}
==Intelligence analysis method of automation control system archive database for controlling hot blast stove block==
https://ceur-ws.org/Vol-2608/paper9.pdf
Intelligence Analysis Method of Automation Control
System Archive Database for controlling Hot Blast Stove
Block
Oleksiy Koyfman 1 [0000-0003-2075-7417], Oleksandr Simkin 2 [0000-0002-9939-7866]
Kseniia Serdiuk 3 [0000-0002-4598-0562]
Pryazovskyi State Technical University, str. Universytets’ka 7, Mariupol, 87555, Ukraine,
1
koifman_o_o@pstu.edu, 2 simkin@pstu.edu
3
serdiuk.xen@gmail.com
Abstract. In automated process control systems the data from the archive data-
base are used in most cases in a graphic form for analyzing the technological
process history. Frequently, the controlling of а hot blast stove block occurs in
the conditions of incomplete information. The method of data mining of the ar-
chive database was developed and implemented in the form of computer pro-
grams to obtain new interconnections between the main technological parame-
ters of the blast air heating process in a hot blast stove block. The developed al-
gorithm allows to determine the functional dependence of the base parameter on
two other parameters with fixing the third parameter in a certain range. The ob-
tained analytical dependencies allow us to make decisions about changes in
control algorithms for a hot blast stove block.
Keywords: intelligence analysis, data mining, method, approximation, hot blast
stove, HBS, flow-chart, computer application
1 Introduction
Nowadays, all the basic technological processes of metallurgical production are au-
tomated by Automated Control Systems (ACS) of various levels of complexity, in
which the technological parameters measured by the sensors, the values of the calcu-
lated variables enter the visualization systems and are stored in current databases.
This information is used both for process control and for informing personnel about
the process condition. Current databases are stored forming an archive database of the
technological process (ADB). Unfortunately, in most cases ADB information is used
to display the process flow in a graph form and, if necessary, to evaluate the operation
of the unit in the past.
The software of ACS includes programs that implement mathematical models – in-
formational or controlling. During the operation of the technological facility, such
Copyright © 2020 for this paper by its authors. Use permitted under Creative
Commons License Attribution 4.0 International (CC BY 4.0).
tuning coefficients of these programs must be adjusted due to aging or a change in the
state of equipment and structural elements.
To solve this problem, some ACS are used data mining in recent years.
The goal of the research: the development and application of new methods of data
mining to obtain new interconnections between the technological parameters of blast
air heating in hot blast stove block (HBSB) in order to configure control algorithms
for HBSB.
2 Formal problem statement
In many cases HBSB consists of three or four hot blast stoves (HBS). The block is
designed to heat blast air (air enriched with oxygen up to 25-30%) to a temperature of
1000 - 1200 °C, which enters a blast furnace (BF).
HBS is a unit of discontinuous operation. The main two modes of operation are the
checkerwork heating (on-gas period) and the blast heating (on-blast period). In on-gas
period in the combustion chamber a fuel gas is burned (blast furnace gas (BFG) or a
mixture of BFG and natural or coke gas). Then the hot combustion products heat the
block refractory checkerwork, giving it the heat. In on-blast period, BF air passes
through the hot checkerwork in the direction opposite to the combustion products,
taking the heat from the checkerwork. In case of operation of HBSB, which includes
4 units, in sequential mode, three HBS operate in on-gas period, and one operates in
on-blast period. As soon as one of HBS ends on-blast period, it is switched to the on-
gas period, and the heated HBS is switched to on-blast period.
HBSB is controlled by an automation system that also includes a subsystem for
maintaining a database of process parameters for each HBS. In modern ACS, there is
a system for controlling the dome temperature, the fuel-air ratio and a monitoring
system for a fuel gas flow, an air for combustion flow, a flue gases temperature,
chemical analysis of the flue gases composition and fuel value.
In the studied system, there is a system for controlling the dome temperature and a
system for monitoring the fuel gas flow and the temperature of the flue gases. Such
number of parameters does not allow a clear understanding of process quality, i.e. in
practice, ACS operates in the conditions of incomplete information.
Thus, the objective of the research aims at by using ADB that contains the above-
mentioned minimum set of parameter values for the long-term operation of HBSB to
find the interconnections between these parameters in order to their further use to
correct the existing mathematical models of HBS operation and in block control algo-
rithms.
3 Literature review
The article [1] describes various methods used in data analysis and approaches to the
implementation of these methods.
Liu Y. et al. [2] use accumulated production data to compensate for the lack of
technological information for the gas flow and conclude that the obtained sufficient
accuracy of reproducing the missing data provides powerful support for the operation
of gas blast furnace facilities.
The quality and accuracy of the technological information stored in the current and
archive databases are very important for the decision-making process in order to save
resources. Unfortunately, due to design errors, instability and vulnerability of the
Supervisory Control and Data Acquisition (SCADA), these anomalies usually exist in
practice. This usually leads to a negative impact on the accuracy and stability of data-
driven methodologies. The authors of [3] proposed two methods for searching for
anomalies in the data presented in the current database.
Methodology, problems and solutions in the field of using multivariate polynomial
regression are described in [4]. According to the authors, descriptive data analysis is a
process of evaluating values based on a given data set, which can be achieved by
regression analysis on this data set. In real time, data can include various data sets
with different properties. Predictive (intelligent) Data Mining is the process of evalu-
ating or predicting future values from an available set of values, uses the concept of
regression to evaluate future values.
An example of the use of quadratic multiparametric polynomial regression is [5],
where the authors performed an analysis to determine the relationships between the
parameters (gas temperature, wall thickness) of heat exchange during drying with
infrared convection. By analyzing the dispersion, the authors evaluate the order of
influence of the significance of all factors on the temperature of hot air.
As indicated above, both the blast furnace itself and the hot blast stoves are units
operating in conditions of incomplete information. For such objects, according to
various authors, the only real opportunity for implementing management functions is
data analysis.
The standard approach to the analysis of BF process is based on a detailed study of
its individual phenomena (heat and mass transfer, gas and hydrodynamics, etc.) with
the subsequent use of the identified patterns for determination of possible and desired
trends in the development of processes and management. The authors of [6] proposed
a thermochemical model of BF smelting, allowing the operator to apply corrective
actions, based on an analysis of data from an archive database for 6 months. The cal-
culation results obtained on the basis of the model were compared with real data.
The success of cluster data analysis primarily depends on the controllability of BF
processes based on existing sets of measured parameters and control factors [7]. The
uncertainty of the control of BF process is determined by uncontrolled parameters,
which determine the spread of the values of the output parameters of the process. An
analysis of the controllability of BF processes, carried out in this work on the basis of
existing statistics of BF smelting, shows that setting specific values of control factors
determine the productivity of BF with a certain accuracy. This fact justifies the man-
agement technique proposed in this paper. It is based on real data as applied to the
calculation of the theoretical combustion temperature.
According to the authors of [8], measurements of technological parameters of BF
smelting usually have non-Gaussian characteristics. This problem can be solved if we
do not stick to the analytical solution, but use the empirical method to determine the
control limit. In the general case, if the distribution of the measurement data is uni-
modal and the detection index value is constant for the data under normal conditions.
To diagnose disturbances in the operation of BF, the authors of the article used multi-
variate statistical analysis, the purpose of which was to monitor disturbances associ-
ated with switching HBS to detect anomalies.
To monitor the process of cast iron production in BF, the authors of [9] use the
Principal Component Analysis (PCA) method of analysis of the main components - a
statistical procedure that orthogonally converts the initial n coordinates of the data set
into a new set of n coordinates called the main components. The work shows that the
distribution is not normal for the following reasons: peak-like interference caused by
HBS switching; periodic loading of coke and tapping of cast iron, etc. Before detect-
ing abnormalities, outliers are removed from the original database, the size of the
training sample and the number of main components are selected.
In article [10] an approach is proposed to control BF process to increase the effi-
ciency of process, based on modeling the operation of BF and on-line stabilization of
parameters on the basis of the obtained mathematical models. Using machine learning
methods, dependencies are determined to specify the controlled parameters at the
output and coke speed. Intelligent data analysis for BF operation was performed to
identify models of distribution and subsequent melting of materials. Based on the
developed models an expert system was developed and implemented.
In practice, operators of BF make decisions on controlling the unit based on a vis-
ual assessment of the graphic profiles of key variables, and not through a complex
calculation of the exact numerical values. Zhou, B. et al. [11] proposed a new qualita-
tive trend analysis algorithm (QTA) based on piecewise linear polynomial approxima-
tion. Using the first and second derivatives, the rate of change and the direction of the
trend are determined. The effectiveness of the algorithm is shown by testing on vari-
ous models and real data of blast furnaces.
An analysis of the existing quality control systems performed by the author [12]
showed that currently there are practically no systems that could be used for opera-
tional control of the dynamics of the quality of cast iron during the smelting process
in real time. In this regard, the article presents a system for collecting and analyzing
data on the controlled parameters of the BF process with the aim of real-time monitor-
ing of the quality of cast iron during smelting. Data on the current values of the tech-
nological parameters are sent to a server from the controllers every 3 seconds and are
smoothed using an exponential algorithm with the choice of the optimal parameter.
The work [13] describes the operation of a BF automation system based on the use
of an archive database in the mode of an operator advisor. The author outlines a
methodology for analyzing and optimizing the volume of the operational database in
order to predict the course of BF smelting in real time and offers a method for analyz-
ing data of the technological parameters, which allows you to obtain additional infor-
mation about the smelting process. When designing the system, hierarchical cluster-
ing (the Lance-Williams method) was used, which allows them to be found in the
process of performing the clustering procedure.
The main goal of [14] is to show the potential of modern intelligent technologies
based on self-organizing neural networks for clustering operating modes and model-
predictive control of the BF process. The method uses a prediction model of control
technology. Moreover, the construction of a model of the BF process includes data
obtained in real time. The authors propose to use two approaches to clustering the
effective values of parameters using the criteria for the efficiency of a blast furnace:
using elliptical surfaces and a self-organizing Kohonen network.
A sufficient amount of research also applies to the use of modeling, solving opti-
mization problems, multivariate statistical analysis, cluster analysis and data mining
for the operation of automation systems for HBS.
For example, Nose, K. et al. [15] formulated and solved using modeling the non-
linear optimization problem by using the generalized reduced gradient (GRG) meth-
od.
For a HBS control system the authors of [16] proposed a sequential procedure for
improving process control based on multivariate methods of statistical analysis. In
order to take advantage of a large amount of historical data, a combination of the
hierarchical clustering method and statistical process control methods is used to detect
and analyze key factors that significantly affect process performance. This technique
consists of four successive stages: data collection and multivariate statistical analysis,
hierarchical clustering and detection of the operating mode, the selection of dominant
variables, a new operational benchmark and its verification.
The authors of [17] confirm that with intelligent data processing the Six Sigma
Methodology increases the processing speed and the quality of the “gained” data.
4 Statement of Basic Materials
The procedure for obtaining the desired information from the archive database is
shown in Fig. 1.
Fig. 1. Stages of information conversion
At one of the iron and steel plants of Ukraine, the values of 194 technological pa-
rameters of HBS in ACS for cast iron smelting are recorded in ADB (file with the
extension * .dbf) with a frequency of 5 seconds, and the file is generated for every 24
hours and, accordingly, one file contains 3352320 records.
The ADB file structure is shown in Fig. 2, where Date and Time columns corre-
spond to the date and time the parameter was written to the database, TagIndex is the
index corresponding to the technological parameter, Value is the value of the techno-
logical parameter; Tagname – the name of the technological parameter in the data-
base.
The studied ADB has a form that is inconvenient for its further analysis and use
due to its structure (outdated recording format) and accordingly due to its size.
a) b)
Fig. 2. ADB structure: a) file with values, b) tag table
Therefore, firstly, it is necessary to transform the database into a form convenient
for further analysis. The authors developed and implemented an ADB processing
algorithm taking into account the following provisions:
1. The operation of each HBS will be described with the characteristics (values of
technological parameters) of two periods – on-gas and on-blast including:
a) for on-gas period: time of the beginning and end of the period ( H _ Gbeg ,
M _ Gbeg , S _ Gbeg , H _ Gend , M _ Gend ; S _ G end ); the duration of the period; the
beginning and end values of the dome temperature ( TDG_HBS1beg , TDG_HBS1end );
the beginning and end values of the flue gases temperature ( TFG_HBS1beg ,
TFG_HBS1end ); the average integral value of the dome temperature ( TDG_HBS1avg );
the average integral value of the flue gases temperature ( TFG_HBS1avg ); dome heat-
ing rate; the rate of heating of the flue gases; the beginning and end consumption of
the BFG ( FG_HBS1beg , FG_HBS1end ); volume of the consumed BFG ( VG_HBS1 );
the average integral flow rate of the BFG during the period ( FG_HBS1end );
b) for on-blast period: time of the beginning and end of the period ( H _ Bbeg ,
M _ Bbeg , S _ Bbeg , H _ Bend , M _ Bend ; S _ Bend ); the duration of the period; the
beginning and end values of the dome temperature ( TDB_HBS1beg , TDB_HBS1end );
the beginning and end values of the temperature of the blast air ( TBB_HBS1beg ,
TBB_HBS1end ); the average integral value of the dome temperature ( TDB_HBS1avg );
the average integral value of the blast temperature at the inlet to HBS
( TBB_HBS1avg ); the cooling rate of the dome temperature during the period.
2. Divide ADB into 8 parts (files), each of which will contain data on on-gas and
on-blast periods for each HBS of the block.
Let us consider in details the proposed algorithm (Fig. 3) for converting the ADB
into a form convenient for analysis of HBS #1 in particular.
When the program is initialized, a directory in which the ADB files are located and
a directory in which the processing results will be written are selected.
Fig. 3. Flow-chart of algorithm of ADB conversion in а form convenient for analysis
Step 1. Beginning of reading of information subprogrammе from the database.
Step 2. Resetting variables: M – mode of operation of HBS, M 1 – on-gas pe-
riod, M 2 – on-blast period, n – number of parameters values recorded over
on-gas period; k – number of parameters values recorded over on-blast period.
Step 3. Loop No. 1 starting, it operates until all ADB files from the folder are proc-
essed.
Step 4. Opening the next ADB file.
Step 5. Resetting variable: i – number of records in a file.
Step 6. Loop No. 2 starting, it operates until the end of a file is reached.
Step 7. Reading data from ADB file using SQL-queries: i ; VN1 \ Di – on-blast pe-
riod; VN1 \ N i – on-gas period; VN1 \ TKFi – dome temperature; VN1 \ TDi – flue gas
temperature; VN1 \ RSGi – BFG flow.
Step 8. Mode checking: VN1 \ Di 0 AND VN1 \ N i 1 ? If YES – on-gas period,
transition to step 9, if NOT – transition to step 16.
Step 9. Mode change checking: M 1 ? If YES – mode changing from on-blast
period to on-gas period, transition to step 10; if NOT – transition to step 14.
Step 10. Assigning initial values for on-gas period beginning: TDG_HBS1beg ,
TFG_HBS1beg , FG_HBS1beg , H _ Gbeg , M _ Gbeg , S _ Gbeg .
Step 11: Assigning finite values for on-blast period end: TDB_HBS1end ,
TBB_HBS1end , H _ Bend , M _ Bend , S _ Bend
Step 12. Calculating for on-blast period: TDB_HBS1avg , TBB_HBS1avg .
Resetting for on-gas period: TDG_HBS1avg , TFG_HBS1avg , FG_HBS1avg ,
VG_HBS1 .
Step 13: Assigning initial values: M 1 – on-gas period; k 1 – beginning of
new on-gas period; n 0 – end of on-blast period.
Step 14. Calculating: TDG_HBS1avg , TFG_HBS1avg , FG_HBS1avg , VG_HBS1 .
Step 15. Incrementing number of parameters values k k 1 .
Step 16. Mode checking: VN1 \ Di 1 AND VN1 \ Di 0 ? If YES – on-blast pe-
riod, transition to step 17, if NOT – transition to step 24.
Step 17. Mode change checking: M 2 ? If YES – mode changing from on-gas
period to on-blast period, transition to step 18; if NOT – transition to step 22.
Step 18. Assigning initial values for on-blast period beginning: TDB_HBS1beg ,
TBB_HBS1beg , H _ Bbeg , M _ Bbeg , S _ Bbeg .
Step 19. Assigning finite values for on-gas period ending: TDG_HBS1end ,
TFG_HBS1end , FG_HBS1end , H _ Gend , M _ Gend ; S _ G end .
Step 20. Calculating for on-gas period: TDG_HBS1avg , TFG_HBS1avg ,
FG_HBS1avg .
Resetting for on-gas period: TDB_HBS1avg , TBB_HBS1avg .
Step 21. Assigning initial values: M 2 – on-blast period; k 0 – ending of new
on-gas period; n 1 – beginning of on-blast period.
Step 22. Calculating: TDB_HBS1avg , TBB_HBS1avg .
Step 23. Incrementing number of parameters values n n 1 .
Step 24. Incrementing number of records i i 1 .
Step 25. Exiting from the loop No. 2.
Step 26. Exiting from the loop No. 1.
Step 27. End.
The results of processing ADB are written to an Excel file (Fig. 4). Each row of
eight tables represents one on-gas period or one on-blast period.
Fig. 4. ADB conversion results
The next second processing step is the analysis of the obtained periods and the
comparison of on-gas periods with the corresponding subsequent on-blast periods.
The following ADB processing results were obtained, which included 7 months of
operation of HBSB in on-gas periods / on-blast periods: for HBS1 696 / 761; for
HBS2 773 / 763; for HBS3 306 / 718; HBS4 207 / 237. For the next 3 months: for
HBS1 155 / 152; for HBS2 166 / 167; for HBS3 59 / 81; for HBS4 173 / 173. For
example, inconsistencies in the number of periods can be in the case when the re-
cording of the technological parameters values in the ADB is incorrect (absence or
failure of the sensor) and there is a mismatch between the values of the tags responsi-
ble for the periods and these periods.
In addition the operating values of time of on-gas and on-blast periods are known
from the operating map of HBS block, so periods that are known to be small or long
in duration are initially removed.
Then a search is made for on-blast periods, which correspond to the current on-gas
period. After processing the following number of full cycles was obtained: for HBS1
– 641, for HBS2 – 736, for HBS3 – 135, for HBS4 – 201. Thus, for example, for
HBS1 there were 851 entries in ADB, and only 641 full cycles fell into the table, i.e.
approximately 25% of records are filtered.
At the third processing step, localization and removal of anomalies of the obtained
values for each of the columns is performed using descriptive statistics: calculation of
the maximum and minimum values, average values, standard deviation ( ): elements
that do not belong to the range 3 ;3 are removed from the selection. It can be
seen from Fig. 5 that the initial distribution of the parameter values is processed in
such a way that the resulting distribution is close to normal.
Fig. 5. Result of processing in steps 3
As a result, the final version of the database was obtained with a breakdown into
full HBS operation cycles database (hereinafter referred to as FCDB).
In the fourth processing step we get the data from FCDB. At this stage, the oppor-
tunity is realized using FCDB and the algorithm developed by the authors (Fig.6) to
determine the functional dependence of the base parameter on two other parameters
with fixing the third parameter in a certain range.
Below is an algorithm that implements this possibility, using the example of ob-
taining the dependence of on-gas duration dur ( Z ) on the average dome temperature
TDG_HBS avg ( X ) and the volume of consumed BFG VG_HBS ( Y ) within the range
of BFG flow FG_HBS ( F ) from FG_HBS1min to FG_HBS1max ( Fmin to Fmax ):
Z f X , Y within F Fmin , Fmax . (1)
Let us consider in details the proposed algorithm (Fig. 6):
Step 1. Beginning of the subprogram.
Step 2. Opening FCDB file.
Step 3. Reading k - the number of records in FCDB file.
Step 4. Reading data from FCDB file to X , Y , Z , F .
Step 5. Calculating the values of average, minimum, maximum, standard deviation
for X and Y arrays: X min , X max , X avg , X ds , Ymin , Ymax , Yavg , Yds .
Step 6. Input Fmin , Fmax .
Step 7. Input range values in which the X and Y data will be processed: beg ,
end , step . By default : beg 2 , end 2 , step 1 .
Step 8. Assigning initial values beg , m 0 .
Step 9. Loop No. 1 starting, it operates until end .
Step 10. Calculating values of convX m and convYm arrays.
Step 11. Incrementing and m .
Step 12. Exiting from the loop No. 2
Step 13. Resetting Xrez array.
Step 14. Loop No. 2 starting, it operates until i m 1 .
Step 15. Resetting Yrez array elements to zero.
Step 16. Loop No. 3 starting, it operates until j m 1 .
Step 17. Resetting Zrez array elements to zero; n=0.
Fig. 6. Flow-chart of algorithm for determining the functional dependence
Step 18. Loop No. 4 starting, it operates until l k .
Step 19. Checking condition: Fmin F1 Fmax ? If YES – transition to step 20, if
NOT – transition to step 23.
Step 20. Checking condition:
if convX i X l convX i 1 AND convY j Yl convY j 1 ? If YES – transition to
step 21, if NOT – transition to step 23.
Step 21. Calculating: Zrezi , j , Xrezi , j , Yrezi , j .
Step 22. Incrementing n .
Step 23. Exiting from the loop No. 4
Step 24. Checking condition: if n 0 ? If YES – transition to step 25, if NOT –
transition to step 26.
Step 25. Calculating of average values: Zrezi , j , Xrezi , j , Yrezi , j .
Step 26. Exiting from the loop No. 3
Step 27. Exiting from the loop No. 2
Step 28. Averaging Xrez and Yrez values – getting a one-dimensional array from
a two-dimensional array.
Step 29. Output Xrez , Yrez , Zrez .
Step 30. Regression analysis of the obtained results Xrez , Yrez , Zrez with multi-
variate approximation.
Step 31. Output Xrez , Yrez , appZrez .
Step 32. End.
5 Assessment of the research results
Based on the above algorithms, the following programs have been developed: for the
implementation of the first and second stages (Fig. 1); for the implementation of the
third and fourth stages (Fig. 1).
Below are the results of the programs.
To analyze the operation of HBS #4, the dependence (1) was obtained (Fig.7) with
the following samples: 3 ; 3 , step (Fig. 7, a, b); 2,5 ; 2,5 , step 0,5
(Fig. 7, c, d, e); 2,5 ; 2,5 , step 0,25 (Fig. 7, f, g, h).
It can be seen from the graphs that when using a step of 0,5 and especially
0,25 (Fig. 7, c, f), the problem of the lack of input data in FCDB that simultane-
ously satisfy the set of specified parameters values (dome temperature and gas vol-
ume) arises. This is determined by the presence of zero values of heating time. In this
case, the program replaces these points using an approximation based on nonzero
values, which is visually seen by the presence of flat sections on the surface of the
graphs (Fig. 7, d, g).
Thus using an interval equal to eliminates the problems that arise in the absence
of values in the database (Fig. 7, a).
It should be noted that the most optimal sampling range is the range from 2 to
2 with an interval equal to .
The obtained results (Fig 7, a, d, g) in terms of the totality of values are unsuitable
for subsequent use in control algorithms of HBS. Using the multi-parameter approxi-
mation, we obtain these dependencies in the form of analytical expressions (R2> 0.8),
the graphs of which are shown in Fig. 7 (b, e, h). Examples of such expressions are
given in Table 1.
Earlier [18], the authors developed and implemented a mathematical model of the
thermal operation of HBS of BF, which was identified on the basis of ADB used in
this research. For this purpose, the averaged basic operation parameters of each HBS
of the block ([18], Fig. 4) were used. Thus, for example, for HBS4, the average dome
temperature corresponds to 1275 °C, and the average on-gas period duration is 230
minutes, which fully corresponds to the calculated value in accordance with the ana-
lytical expression (Tab. 1).
a) b)
c) d) e)
f) g) h)
Fig. 7. The dependence (1) for HBS #4 for different range of
Table 1. Analytical expressions
Range Analytical expressions R2
3 ; 3 , step 0.0001 V BFG 0.5 t Dome 471.3 0.8939
2,5 ; 2,5 , step 0,5 0.0001 V BFG 0.6 t Dome 511 .6 0.8578
2,5 ; 2,5 , step 0,25 0.00005 VBFG 0.6 t Dome 534.3 0.8281
Fig. 8 graphically presents the dependences of on-gas duration on the average dome
temperature and the BFG volume for various average BFG flow for each HBS of the
block obtained as a result of the research.
Such data presentation (Fig.8) makes it possible to change in real time the parame-
ters of the mode map of the blast heating of HBSB in case of production need or sig-
nificant changes in the production situation.
6 Conclusion
1. The methods of data mining and their use, including in control systems for blast
furnace production, which allows one to extract new opportunities from a minimum
set of values of technological parameters, have been analyzed. The authors concluded
that there is no information on the use of data mining in automation systems of
HBSB.
2. For the first time, a method and algorithm for processing an archive database
which includes 4 stages is proposed.
3. The specified algorithm is implemented in the form of two software modules de-
veloped using Visual Studio 2019.
Fig. 8. Dependence of on-gas duration on the average dome temperature and the volume of
consumed BFG within the range of BFG flow for each HBS of block
4. As a result of the research, analytical dependencies have been obtained, they al-
low to make decisions about changes in the heating flow chart and implement control
algorithms for HBSB and each HBS of the block.
References
1. Qin, S. J.: Process data analytics in the era of big data. AIChE Journal, Vol. 60(9):
pp. 3092-3100 (2014). doi: 10.1002/aic.14523
2. Liu, Y., Lv, Z., Wang, W.: An Improved Generalized-Trend-Diffusion-Based Data Impu-
tation for Steel Industry. Mathematical Problems in Engineering, Vol. 2013: pp. 1-10
(2013). doi: 10.1155/2013/136241
3. Zhao, J., Liu, K., Wang, W., Liu, Y.: Adaptive fuzzy clustering based anomaly data detec-
tion in energy system of steel industry. Information Sciences, Vol. 259: pp. 335-345
(2014). doi: 10.1016/j.ins.2013.05.018
4. Sinha, P. Multivariate polynomial regression in data mining: methodology, problems and
solutions. International Journal of Scientific and Engineering Research, Vol. 4(12):
pp. 962-965 (2013).
5. Liu, C., Chen, S., Hai, Y., et al.: Experimental study and analysis on heat transfer hot air
temperature of far infrared convection combined drying. In 2018 International Conference
on Robots & Intelligent System (ICRIS): pp. 552-555. IEEE (2018).
doi: 10.1109/ICRIS.2018.00142
6. Gasparini, V. M., de Castro, L. F. A., et. al.: Thermo-chemical model for blast furnace
process control with the prediction of carbon consumption. Journal of Materials Research
and Technology. Vol. 6(3): pp. 220-225 (2017). doi:10.1016/j.jmrt.2016.12.001
7. Kazarinov, L.S., Barbasova, T.A., Mohsen, H.M.: An efficient control method for furnace
process based on cluster analysis. Bulletin of the South Ural State University. Ser. Com-
puter Technologies, Automatic Control, Radio Electronics. Vol. 16 (2): pp. 164–169
(2016). (In Russian) doi: 10.14529/ctcr160220
8. Shang, J., Chen, M., Zhang, et al.: Increment-based recursive transformed component sta-
tistical analysis for monitoring blast furnace iron-making processes: An index-switching
scheme. Control Engineering Practice. Vol. 77, pp. 190–200 (2018).
doi: 10.1016/j.conengprac.2018.05.012
9. Zhou, B., Ye, H., Zhang, H., Li, M.: Process monitoring of iron-making process in a blast
furnace with PCA-based methods. Control Engineering Practice. Vol. 47, pp. 1–14.
(2016). doi: 10.1016/j.conengprac.2015.11.006
10. Barbasova, T., Zagoskina, E.: Blast-Furnace Melting Blast Control. 2019 IEEE Russian
Workshop on Power Engineering and Automation of Metallurgy Industry: Research &
Practice (PEAMI), Magnitogorsk, Russia, pp. 13-17. (2019).
doi: 10.1109/peami.2019.8915284
11. Zhou, B., Ye, H., Zhang, H., Li, M.: A new qualitative trend analysis algorithm based on
global polynomial fit. AIChE Journal, Vol. 63(8): pp. 3374-3383. (2017).
doi: 10.1002/aic.15706
12. Vorotnikova, Z.J., Novoselzev, M.A.: Cast iron fusion quality control functional monitor-
ing. Reporter of Priazovskyi State Technical University: Collection of scientific papers.
Vol. 26: pp. 221-227 (2013). (In Russian)
13. Vorotnikova, Z.Ye.: Forming and use of an archived database in the system “Adviser of a
blast furnace operator”. Scientific works of Donetsk National Technical University. Vol. 1
(26): pp.14-23 (2014) (In Russian).
14. Shnayder, D. A., Kazarinov, L. S., Barbasova, T. A., Lipatnikov, A. V.: Data mining and
model-predictive approach for blast furnace thermal control. In 2017 Intelligent Systems
Conference (IntelliSys), pp. 653-660 (2017). doi: 10.1109/IntelliSys.2017.8324364
15. Nose, K., Takemura, M., Morita, T.: Systems engineering approach to the optimization of
hot blast stoves. IFAC Proceedings Volumes. Vol.: 16(15), pp. 47-54. (1983).
doi: 10.1016/S1474-6670(17)64255-1/
16. Lee, Y.-H., Min, K. G., Han, C., Chang, K. S., Choi, T. H.: Process improvement method-
ology based on multivariate statistical analysis methods. Control Engineering Practice.
Vol. 12(8), pp. 945–961 (2004). doi:10.1016/j.conengprac.2003.11.004
17. Jang, G.-S., Jeon, J.-H.: A Six Sigma Methodology Using Data Mining: A Case Study on
Six Sigma Project for Heat Efficiency Improvement of a Hot Stove System in a Korean
Steel Manufacturing Company. Cutting-Edge Research Topics on Multiple Criteria Deci-
sion Making. MCDM 2009. Communications in Computer and Information Science.
Vol. 35: pp. 72-80 (2009). doi: 10.1007/978-3-642-02298-2_12
18. Koifman, A., Simkin, A.: Development and Software Implementation of the Hot Blast
Stove Computer Model. CEUR Workshop Proceedings, Vol. 2353: pp. 440-454 (2019).
Online http://ceur-ws.org/Vol-2353/paper35.pdf.