Open access

A Multi-Agent Expert System for Steel Grade Classification Using Adaptive Neuro-fuzzy Systems

Written By

Mohammad Hossein Fazel Zarandi, Milad Avazbeigi, Mohammad Hassan Anssari and Behnam Ganji

Published: 01 January 2010

DOI: 10.5772/7077

From the Edited Volume

Expert Systems

Edited by Petrica Vizureanu

Chapter metrics overview

2,893 Chapter Downloads

View Full Metrics

1. Introduction

Iron and steel industry is a crucial basic section for most of the industrial activities. This industry provides the primary materials for construction, automobile, machinery and many other businesses. Furthermore, the iron and steel manufacturing is highly energy consuming. The influence of an efficient process control on the cost and energy reduction and environmental effects in iron and steel industry makes the process control one of the main issues of this industry.

Iron and steel industry should mainly rely on the new integrated production processes to improve productivity, reduce energy consumption, and maintain competitiveness in the market. Without rational process controlling systems, the potential benefits of new production processes can’t be fully realized. Process control is the key function in the production management. Furthermore, a high degree of real-time operation and dynamic adjustment capabilities is required. In particular, the coordination of different production stages must be considered so as to achieve overall goals of the entire production processes.

In most steel companies, the principal production planning and scheduling techniques have been essentially manual techniques with little computerized decision support. These manual techniques are mainly based on the know-how and the experiences of those experts who have worked in a plant for years. Considering the above mentioned characteristics of a steel manufacturing, some important characteristics of this area can be summarized as:

  • Steel manufacturing is a multi-stage process, logically and geographically distributed, involving a variety of production processes (Ouelhadj et al., 2004);

  • In a steel grade classification, an operator has to determine the amount of additive materials in steel-making process. This is mainly based on the know-how and the professional experience of experts who have worked in the plant for years;

  • A high degree of real-time operation and dynamic adjustment capabilities is required;

  • The output of some stages is usually the input of some other stages, so integration is mandatory;

  • The percentage of elements in steel-making usually has a fuzzy nature

According to the above characteristics of the steel manufacturing, a steel automation system is needed to represent distribution and integration existing in this industry. A fuzzy multi-agent expert system can provide such capabilities.

In the literature, there are only a few scientific papers and technical reports which are related directly to the design and development of intelligent expert systems for iron and steel industry. Perez De La Cruz et al. (1994) presents an expert system which is designed for the problem of identifying a steel or cast iron from a microphotograph. However, the essential aim of the implemented system is to help metallography students in the task of learning the concepts relevant for identifying and classifying steels and cast irons. Kim et al. (1998) presents an application of neural networks to the supervisory control of a reheating furnace in the steel industry. Also there are some papers concentrating on the scheduling of different steel making processes like casting, rolling, scrap charge using fuzzy multi-agent systems (Cowling et al., 2003, Cowling et al., 2004, Lahdelma & Rong, 2006, Ouelhadj et al., 2004). Finally, Fazel Zarandi and Ahmadpour (2009) present a fuzzy multi-agent system for steel making process. Each process of electric arc furnace steel making is assigned to be an agent, which works independently whilst coordinates and cooperates with other acquaintance agents. Adaptive neuro-fuzzy inference system (ANFIS) is used to generate agents’ knowledge bases.

Most of the previous researches are related to the scheduling and coordination of steel making processes while our attempt is mainly about the steel grade classification. This chapter presents a new multi-agent expert system based on adaptive neuro-fuzzy inference system to help an operator to determine the amount of additive materials in steel-making process. Since the percentage of elements in steel-making usually has a fuzzy nature, the fuzzy rule sets and adaptive neuro-fuzzy systems are more accurate and robust to model this complex problem.

In the design of the adaptive neuro-fuzzy systems, determination of the appropriate number of the rules is critical. In other words, large number of rules increases the complexity of the systems exponentially. In this research, to estimate the optimal number of rules, first a clustering algorithm is presented based on the historical data of steel grade process. Moreover, appropriate values for the parameters of clustering algorithm including the number of rules and membership functions of fuzzy rule set are determined using an iterative procedure.

Here, an agent named “Clustering Agent” carries clustering procedure using the initial random membership functions obtained by another agent named “Initiator Agent”.

The output of the “Clustering Agent” is cluster centers and the initial values of membership functions in fuzzy rule set. This output is used as the input to the adaptive neuro-fuzzy agents. These agents apply ANFIS to tune the obtained fuzzy rule set generated by clustering agent. ANFIS combines the advantages of fuzzy rule sets and neural networks capability of learning and hence provide a powerful tool of modeling fuzzy systems. In the proposed multi-agent system, five agents are responsible for implementation of ANFIS for different additives, each of which is responsible for each additive.

The cooperation of agents forms a fuzzy expert system which can help the operator to determine the suitable amount of additive materials in steel-making process.

The multi-agent expert system is programmed and simulated using Matlab. For three grade of steel including CK45, C67 and 70CR2 historical data are applied first for extraction of fuzzy rules using the “Clustering Agent” and “Initiator Agent”, and then for tuning the ANFIS agents.

Advertisement

2. Steel making process

Iron and steel plants and their components are usually large-scale and very complex. In order to improve quality and productivity, many techniques have been developed combining the computer system and control theory and expert system. To overcome the complexity, the problem can be divided into some small sub-problems. In this chapter a model for steel grade classification in pneumatic steel making method (converter) is proposed. In this section, first the steel making process is briefly presented and then, in the next sections our proposed model is explained.

The steel manufacturing involves many processing stages and diverse technologies. In Fig. 1 the sub-processes of steel making process are shown (Council on Wage and Price Stability, 1977).

  • Coke production: Coke is produced independently and is charged to blast furnace as one of the raw materials.

  • Sintering plant: Iron ore is roasted with coke and limestone to produce a clinker.

  • Blast Furnace: In the blast furnace the sintered ore is converted into the pig iron. With blowing hot air and fuel from bottom of furnace and charging sintered iron ore, and coke from top of furnace pig iron produce in the bottom of furnace. Pig iron transported in open ladles to metal mixers.

  • Steel Production: Pig iron is smelted to steel. Steel in LD steel works. The steelmaking processes consist of three stages: steel-making, refining, and continuous casting.

In steel making stage, carbon, sulphur, silicon, and other impurity contents of molten iron are reduced to desirable levels by burning with oxygen in a converter or Electric Arc Furnace. The output from the stage is molten steel with the main alloy elements. To obtain the different grades of steel, some materials are charged in LD or EAF. These materials are called additives of alloying metals. These alloying metals tune the percentage of the elements such as carbon, manganese, aluminium, and etc. For fine-tuning the molten steel from the steel-making process is poured into ladle furnace (LF) by a crane. The operator at this stage further refines the chemicals and eliminates impurities in molten steel or adds the required alloy ingredients.

After refining, molten steel is poured into a tandish for casting. In the casting stage, molten steel flows down from a hole at the bottom of the tandish into the crystallizer. The last process is rolling.

Alloying in steel-making process and grade classification is a very important stage. In order to omitting human errors, an expert system is proposed to help an operator to determine the amount of additives.

Advertisement

3. Proposed multi-agent system

The proposed multi agent system has three types of agents including:

  • Initiator agent which provides the input for the clustering agents. The output of the initiator agent is a set of the initial membership functions generated randomly.

  • Clustering agent which carries clustering procedure using the initial random membership functions obtained by another agent named initiator agent.

  • ANFIS agents apply ANFIS to tune the obtained fuzzy rule set generated by clustering agent. ANFIS combines the advantages of fuzzy rule sets and neural networks capability of learning and hence provide a powerful tool of modeling fuzzy systems. In the proposed multi-agent system, five agents are responsible for implementation of ANFIS for different additives, each of which is responsible for each additive.

Figure 1.

Overview of steel making Process

The cooperation of agents forms a fuzzy expert system which can help the operator to determine the suitable amount of additive materials in steel-making process.

3.1. Initiator and clustering agents

The basic objective of the cluster analysis is to partition optimally the n unlabeled data points into c clusters base on a similarity measure. In crisp clustering, the separation of the clusters is sharp. However, in the real world problems, the separation of the clusters is usually fuzzy. Fuzzy clustering analysis has been extensively studied by many researchers (Bezdek & Pal, 1992, Huntsberger et Al., 1993, Moghaddam Zadeh & Bourbakis, 1997, Nguyen & Cohen, 1997, Pal & Ghosh, 1992). The most commonly used fuzzy clustering algorithm is fuzzy C-means (FCM), developed by Bezdek (1993). The objective function of FCM is defined as:

J ( U , V ; X ) = i = 1 c u i j m d i j 2 E1

where, u i j is membership function of element j in cluster i:

i = 1 c u i j = 1, j = 1,..., n E2

where, V i is the cluster center of fuzzy cluster i, d i j = x j v i is the Euclidean distance between i-th cluster center and j-th data point; and m is a weighting exponent that determines the degree of fuzziness. The necessary conditions for equation (1) to reach its minimum are:

v i = i = 1 n u i j m x j j = 1 n u i j m E3
u i j = [ k = 1 c ( d i j d k j ) 2 ( m 1 ) ] 1 E4

In a batch-mode operation, FCM determines the cluster center v i and the membership matrix U using the following steps (Bezdek, 1993):

Step 1: Initialize the membership matrix U with random values between 0 and 1 such that the constraints in Equation (2) are satisfied.Step 2: Calculate c fuzzy cluster center v i , i=1,…,c, using Equation (3).Step 3: Compute the Cost Function according to Equation (1).

Stop if either it is below a certain tolerance value or its improvement over previous iteration.

Step 4: Compute a new U using Equation (4). Go to step 2.

FCM suffers from some challenging problems such as unknown number of clusters, noise contaminated data and supervisory determining the u:

  1. The first is that the number c of clusters must be pre-defined and the resulting structure for the specified number of clusters is assumed to be the best. This is seldom the case in practice. Thus, the difficult problem encountered is the cluster validity, which is required to evaluate the quality of the c-partitions resulting from the algorithms.

  2. The second is that the FCM algorithm is sensitive to noise in the data. To solving this problem in many algorithms based on FCM, the m parameter is fixed in a predefined value (Bezdek, 1993).

To improve the performance of clustering various clustering validity indices have been proposed. However, most of them focus on improving robustness or extending the function of FCM (Krishnapuram & Keller, 1993; Pedrycz, 1996, Nasraoui & Krishnapuram, 1996, Fazel Zarandi et al., 2009). In this book chapter, an unsupervised clustering is proposed which allows initializing the u, automatic setting of optimal cluster number, and finding the most appropriate m.

The objective function of penalized Fuzzy c-means proposed by Yang and Su (1994) is defined as follows:

J = 1 2 i = 1 c j = 1 n ( u i j ) m d i j 2 1 2 ν i = 1 c j = 1 n ( u i j ) m L n α i E5

where u ij is the membership degree of the j-th data point Xj in the i-th cluster, d ij is their distance, N is the total number of data and c the number of clusters to be found, α i is a proportional constant for class j and v >= 0 is a constant. When v equals zero, we will have J FCM .

Now consider the problem of minimizing J with respect to u ij fuzzy, subject to m>1 and the constraints (2).

As we know:

0 u i j 1 E6

and this constraint many be eliminated by setting u i j = S i j 2 with S i j real. We adjoin the constraints (2) and (6) to J with a set of Lagrange multipliers ( λ i ) to give:

J = i = 1 c j = 1 n ( u i j ) m d i j ν j = 1 c j = 1 ( u i j ) m ln α i + j = 1 n λ i ( i = 1 c u i j 1 ) E7
u i j = S i j 2 E8
then:
J S i j = 2 m ( d i j ν ln α i ) S i j 2 m 1 + 2 S i j λ i E9
J S i j = 0 t h e n : S i j 2 ( m 1 ) = λ i m ( d i j ν ln α i ) E10

By summing over j and using (2) the necessary conditions for Equation (7) to reach its minimum are:

α i = j = 1 n u i j m i = 1 c j = 1 n u i j m E11
v i = j = 1 n u i j m x j j = 1 n u i j m E12
u i j = [ l = 1 c ( d i j 2 ν L n α i ) 1 / ( m 1 ) ( d i l 2 ν L n α l ) 1 / ( m 1 ) ] 1 E13

The objective function (5) has two main components. The first component is similar to the FCM objective function and has a global minimum when each data point is in a separate cluster. The global minimum of the second component can be achieved when all points are in the same cluster such that it controls the number of clusters.

According to (10), (11), (12) an iterative procedure is proposed for obtaining the optimal cluster centers. In this procedure, an unsupervised method is used for finding the membership matrix U, m and . The program for finding the initial U is shown in Fig. 2.

Clusters can be found easier and with less number of iterations using the initial agent’s program. The pseudocode of the clustering agent combining the initial agent’s program is also shown in Fig. 3.

Figure 2.

Pseudocode of the initial agent’s program

Figure 3.

Pseudocode of the clustering agent’s program

So from algorithm we can find the cluster centers with optimal location and number. After running the algorithm we can merge some cluster center that they are the same or very near each other, but in our model we want to use these cluster centers for training, so we don’t eliminate any of them and train our model with some repetitive data.

3.2. ANFIS agents

Neuro-fuzzy models have played an important role in the design of the fuzzy expert systems. However in most situations, the proper selection of the number, the type, and the parameters of the fuzzy membership function and rules are crucial for achieving the desired performance. The desired performance has yet been achieved through the trial and error. This fact highlights the significance of tuning of the fuzzy systems.

ANFIS is a fuzzy Sugeno network in the framework of adaptive systems facilitating learning and adaptation. Such a framework makes models more systematic and less relying on expert knowledge. To understand the ANFIS architecture, consider the following fuzzy system which has two rules and is a first order Sugeno model:

Rule 1:

i f ( x i s A 1 ) a n d ( y i s B 1 ) t h e n ( f 1 = p 1 x + q 1 y + r 1 ) E14

Rule 2:

i f ( x i s A 2 ) a n d ( y i s B 2 ) t h e n ( f 2 = p 2 x + q 2 y + r 2 ) E15

Figure 4.

Flowchart of the initiator and clustering agents’ procedures (part I)

Figure 5.

Flowchart of the initiator and clustering agents’ procedures (part II)

Several types of fuzzy reasoning have been proposed in the literature (Lee, 1990a and 1990b). Depending on the type of fuzzy reasoning and fuzzy if-then rules employed, most fuzzy inference systems can be classified into three types:

  1. The overall output is the weighted average of each rule’s crisp output induced by the rule’s firing strength (the product or minimum of the degrees of match with the premise part) and output membership functions. The output membership functions used in this scheme must be monotonic functions (Tsukamoto, 1979).

  2. The overall fuzzy output is derived by applying “max” operation to the qualified fuzzy outputs (each of which is equal to the minimum of firing strength and the output membership function of each rule). Various schemes have been proposed to choose the final crisp output based on the overall fuzzy output; some of them are centroid of area, bisector of area, mean of max, maximum criterion, etc (Lee, 1990a and 1990b).

  3. Takagi and Sugeno’s fuzzy if-the rules are used (Sugeno, 1985, Takagi and Sugeno, 1985). The output of each rule is a linear combination of input variables plus a constant term, and the final output is the weighted average of each rule’s output. A possible ANFIS architecture to implement these two rules is shown in Fig. 5. Note that a Circle indicates a fixed node whereas a square indicates an adaptive node (the parameters are changed during training). Here, O l i denotes the output of node i in layer l.

Figure 6.

ANFIS architecture

The explanation of the layers of ANFIS is as follows:

Layer 1: All the nodes in this layer are adaptive nodes. The output of each node is the degree of membership of the input of the fuzzy membership functions represented by the node:
O 1, i = μ A i ( x ) i = 1,2 E16
O 1, i = μ B i ( x ) i = 3,4 E17

where, A i and B i are any appropriate fuzzy sets in parametric form, and O 1, i is the output of the node in the i th layer. This study uses bell shape membership functions. A bell shape membership function can be shown as follows:

μ A i ( x ) = 1 1 + [ ( x c i a i ) 2 ] b i E18

Here, a i , b i and c i are the parameter for the membership functions.

Layer 2: The nodes in this layer are fixed (not adaptive). They are labelled by M to indicate that they play the role of a simple multiplier. The outputs of these nodes are given by:
O 2, i = w i = μ A i ( x ) μ B i ( y ) i = 1,2 E19

The output of each node in this layer represents the firing strength of the rule.

Layer 3: Nodes in this layer are also fixed nodes. They are labelled by N to indicate that they perform a normalization of the firing strength from the previous layer. The Output of each node in this layer is given by:
O 3, i = W i ¯ = W i W 1 + W 2 i = 1,2 E20
Layer 4: All the nodes in this layer are adaptive nodes. The output of each node in this layer is simply the product of the normalized firing strength and a first order polynomial (for first order Sugeno model):
O 4, i = W ¯ i f i = W ¯ i ( P i x + q i y + r i ) i = 1,2 E21

where p i , q i and r i are design parameters (referred to as consequent parameters since they deal with the then-part of the fuzzy rule).

Layer 5: This layer has only one node labelled by S to indicate that it performs the function of a simple summation. The output of this single node is given by:
O 5, i = i W ¯ i f i = i W i f i i W i i = 1,2 E22

The ANFIS architecture is not unique. Some layers can be combined and still produce the same output. In this ANFIS architecture, there are two adaptive layers (Layers 1 and 4). Layer 1 has three modifiable parameters ( a i , b i and C i ) pertaining to the input MFs. These parameters are called premise parameters. Layer 4 has also three modifiable parameters ( p i , q i and r i ) pertaining to the first order polynomial. These parameters are consequent parameters.

The task of the training or learning algorithm for this architecture is to tune all the modifiable parameters to make the ANFIS output match the training data. It should be noted that a i , b i and c i describe the sigma, slope and center of the bell shape membership functions. If these parameters are fixed, the output of the network becomes:

f = W 1 W 1 + W 2 f 1 + W 2 W 1 + W 2 f 2 = W ¯ 1 f 1 + W ¯ 2 f 2 = W ¯ 1 ( P 1 x + q 1 y + r 1 ) + W 2 ¯ ( P 2 x + q 2 y + r 2 ) = ( W ¯ 1 x + ) P 1 + ( W 1 ¯ y ) q 1 ( W 1 ¯ ) r 1 + ( W ¯ 2 x ) P 2 + ( W 2 ¯ y ) q 2 + ( W 2 ) r 2 ¯ E23

which is a linear combination of modifiable parameters. Therefore, a combination of gradient descent and the least-squares method (hybrid learning rule as in Jang, 1991) can easily identify the optimal values for the parameters p i , q i are r 1 . If the membership functions are not fixed and are allowed to vary, the search space becomes large and consequently, the convergence of the training algorithm becomes slower.

3.3. Merging ANFIS with clustering

Clustering techniques are primarily used in conjunction with radial basis function or fuzzy modeling to determine the initial location of the radial bases functions or fuzzy if-then rules.

For this purpose, clustering techniques are validated on the basis of two assumptions:

  1. The similar inputs to the target system which have to be modeled should produce the similar outputs.

  2. These similar input-output pairs are bundled into clusters in the training data set.

First assumption states that the target system to be modeled should be a smooth input-output mapping; this is generally true for the real-world systems. Second assumption requires that the data set has to conform to some specific type of statistical distribution functions. However, this is not always true and therefore clustering techniques used for structure identification in neural networks or fuzzy modelings are highly heuristic. That’s why heuristic methods are widely used to overcome the problem.

Fuzzy or neuro-fuzzy systems define a rule for every inputs and outputs. For instance, in an ANFIS model with 10 inputs which every input is mapped to two membership functions, 2^10=1024 rules can be formed, and with further inputs, and mapping to further MFs the number of rules increases exponentially. Hence, a data set can be partitioned into several groups with the similar properties and later these groups can be used as the training data for ANFIS. In our case we could develop a model with fewer rules than ANFIS.

Advertisement

4. Implementation, verification and validation of the multi-agent expert system for the steel grade classification problem

The basic oxygen process is characterized by three things:

  1. The use of gaseous oxygen as the sole refining agent.

  2. A metallic charge composed largely of blast furnace iron in a molten condition, thus greatly reducing the thermal requirements of the process.

  3. -Chemical reactions that proceed quite in bath of comparatively low surface –to-volume ratio, thus minimizing external heat losses.

A schematic representation of progress of refining in top-blown vessel is shown in figure Fig. 6.

As the Fig. 6 shows the percent of elements are not crisp and they can be better modelled using fuzzy numbers. This is also valid for the final steel. That’s why in this research the fuzzy methods are used for the clustering. The cluster centers are then used for training the ANFIS model.

Figure 7.

Schematic representation of the progress of refining in top-blown vessel

About 200 data were collected in a matrix, named with the mark of steel. A sample of the collected data is shown bellow:

Steel Analyze in LD Steel Analyze in LF Amount of Additives
C% *100 Mn% *100 P% *1000 Temp. C% *100 Mn% *100 Si% *1000 P% *1000 S% *1000 Temp. FeMn Kg FeSi Kg Al Kg Granol Kg SiCa Kg
12 37 31 1675 45 63 16 20 16 1670 770 290 06 590 190
16 20 24 1680 46 67 30 28 25 1675 850 539 15 540 440
14 23 26 1670 44 70 33 32 28 1665 845 593 18 540 490
12 19 28 1673 68 73 37 30 24 1670 970 665 14 650 565
15 25 26 1682 47 55 20 28 24 1678 540 360 14 580 260
11 21 28 1680 46 63 27 25 20 1675 760 485 10 630 385
09 21 27 1679 50 68 32 31 26 1674 845 575 16 740 475
10 21 24 1671 45 74 30 32 27 1668 953 540 17 700 440
08 15 28 1682 48 72 29 20 15 1677 1030 520 05 720 421
10 14 18 1677 43 53 25 21 17 1672 700 450 07 590 350
10 15 20 1673 47 58 28 27 20 1674 770 500 10 660 400
09 14 19 1674 45 62 22 28 22 1671 863 395 12 650 295
12 16 22 1670 44 67 33 29 21 1665 920 595 11 575 495
16 18 22 1680 46 69 38 30 30 1675 920 683 20 539 583
12 20 27 1671 50 73 20 32 18 1670 950 360 08 680 260
10 20 20 1679 49 72 21 30 19 1674 935 377 09 700 277

Table 1.

Sample of collected data for CK45

According to the proposed algorithm the collected data are clustered and then the cluster centers (C=10) are saved in a matrix.

The values of the fuzzification parameters for 10 clusters are shown below. These parameters are related to the objective function of the clustering method.

m1 m2 m3 m4 m5 m6 m7 m8 m9 m10 m11 m12 m13 m14 m15
3.2 3.27 2.53 2.63 3.12 2.41 2.27 3.23 2.38 2.21 3.17 3.15 3.54 2.78 2.7

Table 2.

Fuzzification parameters value

Vi .098, i=1,…,15.

All of these parameters are obtained by an unsupervised mode. If v equals zero, the cost function converts to Fuzzy c-mean’s cost function. After the clustering, the cluster centers are used as the inputs for the ANFIS training. The number of rules in knowledge base and the running time decrease considerably by using the output of the clustering method as the input of the ANFIS.

C% 16.9959 15.0000 14.0000 16.9994 10.0091 9.0010 10.0005 14.8235 16.0000 16.9999
Mn% 20.9999 16.3357 21.0000 18.0000 14.0000 15.9940 16.0000 15.5730 15.0040 16.0000
P% 24.0020 28.0000 24.0000 29.8114 23.0002 28.2872 25.0000 30.0000 20.0128 25.0008
Temp. 73.0000 74.0003 78.7339 80.0000 80.0000 74.0047 73.4254 71.5233 74.0000 80.0000
C% 46.0120 42.0007 47.0000 48.9922 43.0278 44.9913 45.0000 43.0000 43.0000 48.0000
Mn% 73.0000 68.5728 65.8806 53.0642 69.0523 71.1385 71.4639 60.0000 66.0000 69.0000
Si% 27.0000 21.0000 30.0000 29.1963 20.0000 25.9769 21.0058 25.9270 23.0000 33.6949
P% 31.0000 30.9995 25.0000 29.8779 25.6069 24.0000 25.0000 25.0000 29.0000 26.0002
S% 28.0000 28.0000 27.0000 27.9538 28.0000 31.9940 25.0000 22.8422 22.1667 19.8773
Temp. 71.0000 74.9999 73.9558 70.0000 73.9979 70.0000 74.2199 77.4732 72.0974 72.0000
FeMn 92.4316 85.0000 85.0009 76.0001 82.9576 82.0001 95.0000 84.0000 86.4096 84.0000
FeSi 40.0000 54.0000 50.6572 53.9992 37.5990 58.1757 51.7653 49.6328 38.0000 53.9912
Al 20.0000 20.0000 6.2156 17.9602 23.9869 16.0000 18.0000 14.9998 3.0289 19.6295
Gran. 52.1006 63.9593 56.5167 66.0000 52.0000 55.5068 66.9999 69.9870 69.9992 61.3691
SiCa 26.0001 38.4433 58.2097 49.0000 49.0000 55.0000 31.6977 49.0000 40.6215 40.2289

Table 3.

Input, Output, and Additive Elements Cluster matrix for CK45.

We use the training data in the following form:

y 1 = [ F e M n ] , U = [ C % , M n % , P % , T , Steel Analyze in LF C % , M n % , S i % , P % , S % , T  Steel Analyze in LD ] y 2 = [ F e S i ] , U y 3 = [ A l ] , U y 4 = [ G r a m o l ] , U y 5 = [ S i C a ] , U

U is the input and y i (i=1… 5) are the outputs (Additives). For simplicity the model is designed in multi-input single-output form (see Fig. 7-11 ANFIS training and test for 5 additives).

Figure 8.

Comparision of the training data output and the ANFIS Output and the architecture of the FeMn ANFIS agent

Figure 9.

Comparision of the training data output and the ANFIS Output and the architecture of the FeSi ANFIS agent

Figure 10.

Comparision of the training data output and the ANFIS Output and the architecture of the Al ANFIS agent

Figure 11.

Comparision of the training data output and the ANFIS Output and the architecture of the Granule ANFIS agent

Figure 12.

Comparision of the training data output and the ANFIS Output and the architecture of the SiCa ANFIS agent

To show the performance of the designed multi-agent expert system, the system is applied to determine the value of the additives for CK45. The model has ten inputs according to table 4. As explained before, each additive amount is determined by a specialized agent. Each agent first uses the ouput of the initiator agent and the clustering agent to train its ANFIS. Then, it applies the trained ANFIS to determine the amount of the related additives. The Amounts of the additives are summarized in table 5.

C% Mn% P% Temp. C% Mn% Si% P% S% Temp.
*100 *100 *1000 -1600 *100 *100 *1000 *1000 *1000 -1600
8.000 15.025 25.257 76.799 47.999 74.989 20.002 31.980 27.000 75.000

Table 4.

Input parameters values for determintion the additives of CK45

FeMn FeSi Al Granule SiCa
Kg Kg Kg Kg Kg
939.082 497.827 15.312 633.155 448.793

Table 5.

Output values of the additives of CK45

Advertisement

5. Conclusion

Iron and steel manufacturing is a crucial basic industry for most of the industrial activities. The influence of an efficient process control on the cost and energy reduction has made the process control one of the main issues of this industry. Iron and steel manufacturing should mainly rely on the new integrated production processes to improve productivity, reduce energy consumption, and maintain competitiveness in the market.

In the most steel companies, the principal production planning and scheduling techniques are essentially manual techniques with little computerized decision support. These manual techniques are mainly based on the know-how and the experiences of those experts who have worked in the plant for years. Moreover, steel production is a multi-stage process, logically and geographically distributed, involving a variety of production processes. Also, in a steel grade classification, an operator has to determine the amount of additive materials in steel-making process. Because of the above reasons, a steel automation system is needed to represent distribution and integration existing in this industry. A fuzzy multi-agent expert system can enable such capabilities.

This chapter proposes a multi-agent expert system includes three different types of agents:

  1. Initiator Agent: Provides the initial membership functions and cluster centers for the clustering agent.

  2. Clustering Agent: Produces the initial cluster centers for training of the ANFIS agents

  3. ANFIS Agents: By using ANFIS we can refine fuzzy if-then rules obtained from human expert to describe the input-output behaviour of a complex system. However, if human expertise is not available we can still set up reasonable membership functions and start the learning process to generate a set up fuzzy if-then rules to approximate a desired data set.

The results show that the proposed system can identify the amounts of the additives for different classes of steel grade. Also the results show that the Multi-agent expert systems can be applied effectively in the steel-making.

References

  1. 1. Bezdek J. C. 1993 Fuzzy mathematics in pattern classification, Ph.D. dissertation. Cornell University, Ithaca, NY.
  2. 2. Bezdek J. C. Pal S. K. 1992 Fuzzy Models for pattern Recognition, IEEE press, New York.
  3. 3. Council on Wage and Price Stability 1977 Report to the President on Prices and Costs in the United States Steel Industry. October. Washington, D.C.: U.S. Government Printing Office.
  4. 4. Cowling P. I. Ouelhadj D. Petrovic S. 2003 A Multi-agent architecture for dynamic scheduling of steel hot rolling, Journal of Intelligent Manufacturing, 14 page numbers 457-470.
  5. 5. Cowling P. I. Ouelhadj D. Petrovic S. 2004 Dynamic scheduling of steel casting and milling using multi-agents, Production Planning and Control, 15 page numbers 1-11.
  6. 6. Fazel Zarandi. M. H. Ahmadpour P. 2009 Fuzzy agent-based expert system for steel making process, Expert Systems with Applications, 36 page numbers 9539-9547.
  7. 7. Fazel Zarandi. M. H. Avazbeigi M. Turksen I. B. 2009 A new Fuzzy Noise-rejection Data Partitioning Algorithm with Revised Mahalanobis Distance, proceeding of IFSA09.
  8. 8. Huntsberger T. L. Jacobs C. L. Cannon R. L. 1993 Iterative fuzzy image segmentation, Pattern Recognition, 18 page numbers 131-138.
  9. 9. Jang J. S. R. 1991 Fuzzy modeling using generalized neural networks and kalman filter algorithm, Proceedings of Ninth Nat. conf-Artificial Intell. (AAAI-91), 762 767 .
  10. 10. Kim Y. I. Moon K. C. Kang B. S. Han C. Chang K. S. 1998 Application of neural network to the supervisory control of a reheating furnace in the steel industry, Control Engineering Practice, 6 page numbers 1009-1014.
  11. 11. Krishnapuram R. Keller J. M. 1993 A Possibilistic Approach to Clustering, IEEE TRANSACTIONS ON FUZZY SYSTEMS, 1 2
  12. 12. Lahdelma R. Rong A. 2006 Scrap charge optimization using fuzzy chance constrained linear programming, In New developments in artificial intelligence and the semantic web proceedings of the 12th Finnish artificial intelligence conference STeP.
  13. 13. Lee C.C. 1990a Fuzzy logic in control systems: Fuzzy logic controller-parti. IEEE Trans. Syst. Man, cybern., 20 page numbers 404-418.
  14. 14. Lee C. C. 1990b Fuzzy logic in control systems: Fuzzy logic controller-parti. IEEE Trans. Syst. Man, cybern., 20 page numbers 419-435.
  15. 15. Moghaddam Zadeh. A. Bourbakis N. 1997 A fuzzy region growing approach for segmentation of color images, Pattern Recognition, 30 page numbers 867-881.
  16. 16. Nasraoui O. Krishnapuram R. 1996 An improved possibilistic C-Means algorithm with finite rejection and robust scale estimation, proceeding of NAFIPS Biennial Conference of the North American.
  17. 17. Nguyen H. H. Cohen P. 1993 Gibbs random field, fuzzy clustering and the unsupervised segmentation of textured images, CVGIP Graphical Models Image Processing, 55 page numbers 1-19.
  18. 18. Ouelhadj D. Petrovic S. Cowling P. I. Meisels A. 2004 Inter-agent cooperation and communication for agent-based robust dynamic scheduling in steel production, Advanced Engineering Informatics, 18 page numbers 161-172.
  19. 19. Pal S. K. Ghosh A. 1992 Image segmentation using fuzzy Correlation, Inform. Sce., 62 page numbers 232-250.
  20. 20. Pedrycz W. 1996 Conditional Fuzzy C- Means, Pattern Recognition Letters, 17, page numbers 625 632 .
  21. 21. Perez La Cruz. J. L. Marti M. J. Conejo R. Morales-Bueno R. Fernandez T. 1994 An Expert System for Identifying Steels and Cast Irons, Engng Applic. Artif. lntell., 7 4 page numbers 455-459.
  22. 22. Sugeno M. 1985 Ed. Industrial Applications of Fuzzy control, New York Elsevier.
  23. 23. Takagi T. Sugeno M. 1985 Fuzzy identification of system and its applications to modeling and control. IEEE Trans. Syst., Man, Cybern., 15 page numbers 116-132.
  24. 24. Tsukamoto Y. 1979 An approach to fuzzy reasoning method, In Madan M. Gupta, Rammohan K. Ragade and R. Yager edts. Advances in fuzzy set theory and applications, North-Holland, Amsterdam, page numbers 137 149 .
  25. 25. Yang M.S. Su C. F. 1994 On parameter estimation for normal mixtures based on fuzzy clustering algorithms, Fuzzy sets and systems, 68 page numbers 13-28.

Written By

Mohammad Hossein Fazel Zarandi, Milad Avazbeigi, Mohammad Hassan Anssari and Behnam Ganji

Published: 01 January 2010