A kind of fuzzy neural networks (FNNs) based on adaptive pattern clustering and feature map (APCFM) is proposed to improve the property of the large delay and time varying of the sintering process. By using the density clustering and learning vector quantization (LVQ), the sintering process is divided automatically into subclasses which have similar clustering center and labeled fitting number. Then these labeled subclass samples are taken into fuzzy neural network (FNN) to be trained; this network is used to solve the prediction problem of the burning through point (BTP). Using the 707 groups of actual training process data and the FNN to train APCFM algorithm, experiments prove that the system has stronger robustness and wide generality in clustering analysis and feature extraction.

Sintering
is the most widely used agglomeration process for
iron ores and is a very
important chain of iron making. In general, the process of sintering includes
three major phases. First, it involves blending all the ores thoroughly according
to certain proportions and adding water to the ore mix to produce particles.
Second, the actual sintering operation is initiated by the ignition of the
cokes as the raw mix passes under gas ignition. Finally, after traveling the
length of the strand, the finished sinter is broken up, cooled, and screened
[

According to the chemical/physical characteristics for sintering, a model was formulated as a series of differential equations to describe the relation between the thick martial, the ignition temperature, and the bellows temperature at the tail of the machine. For the time varying and randomness of the sintering process, many mechanisms have still not been understood. Although the dynamic model is tenable at a certain boundary condition, it is difficult to cover the whole process.

For the fast approach of neural network, a model can be established rapidly from the given input and output data, and it can also solve the problem of this long-time delay system. In general, genetic algorithm is used to optimize the parameters of the network and improve the generalization of the system, but it has still not been reported to be used in real-time control.

The rule base,
acknowledge, database,
and inference machine can be constructed by the technology and operation experts’ experience
[

In general, the dynamic behavior of a fuzzy logical
controller is characterized by a set of linguistic control rules based on the knowledge
of an expert [

Consider the fuzzy controller with Gaussian MFs and multiplication
implication; the topology structure of fuzzy neural network is shown in
Figure

The topology structure of fuzzy neural network.

The fuzzy rule is as follows:

The first
layer is input variable layer. In this layer, the

The second
layer is membership layer. In this layer, each node performs the Gaussian function;
the function is adopted as a membership function. The membership function of the
input is defined as

The third layer is rule layer. The layer is used to implement the antecedent matching. The matching operation or the fuzzy and aggregation operation is chosen as the simple product operation. In this layer, summing is finished by neuron.

In addition to

The fifth layer is output of the fuzzy neural network.

Thus,
the entire fuzzy neural network
[

According to technology character and
equipment requirement, density sintering speed and burning temperature are
selected as input vectors; the temperature and pressure of 18 windboxes and the waste
gas temperature are chosen as output vectors. The input space scatter diagram
is obtained by using the input sample to do three-vector space map, and the
clustering center

Feature map network developed by
Kohonen is an unsupervised competitive learning cluster network in which only
one neuron is on at any time. The map is an artificial system that emulates the
brain in the visual system, and which includes three major phases
[

Competitive
phase: the inputs of the network can be written as vector by

Cooperative
phase: the winner neuron is
located in the center of the cooperation neuron’s topology neighborhood.
We supposed that

The trend of topology neighborhood coast line.

Self-adjusting phase: it includes self-ordering and
converging stages; self-ordering formula is

The equation
is in converging stage; learning rate

The
learning vector
quantification (LVQ) algorithm is used to adjust fine weight vector to improve
quality in decision area by utilizing supervisor learning skill. The foundation
method is first to find the average value of the attribute of
every subclass on the
basis of clustering, second to make a comparison
between the average value of the subclass and the whole
vector, and last to label the up-arrowhead tag with the larger values and the
down-arrowhead with the smaller values. The set of every labeled
subclasses may be expressed as the
direction of its weight shifting. For this purpose, let the

If

Passing through a period of time iteratively, the subclasses with the same property may be converged together, and the other subclasses with different properties may be departed from each other.

In this paper, we use the actual data as the samples from sintering process. The input vectors are density, velocity, and ignition temperature, and the output vectors are the temperature and pressure of 18 windboxes and the temperature of waste gas.

The distributing diagram of the two-year input samples
in three-dimensional space is shown in Figure

The distributing diagram of samples.

The topology structure of clustering.

Computing
the average value of every property for each subclass, respectively, such as
density (

The setting of subclass property.

Subclass | Num | Compare results | |||
---|---|---|---|---|---|

1 | 65 | 0.6643 | 0.7986 | 0.8039 | |

2 | 29 | 0.6659 | 0.7893 | 0.6781 | |

3 | 40 | 0.6462 | 0.7208 | 0.3900 | |

4 | 92 | 0.7039 | 0.7779 | 0.8215 | |

5 | 17 | 0.6471 | 0.6775 | 0.6662 | |

6 | 32 | 0.6149 | 0.5921 | 0.5671 | |

7 | 95 | 0.7549 | 0.7505 | 0.8696 | |

8 | 27 | 0.6987 | 0.6771 | 0.8178 | |

9 | 96 | 0.6067 | 0.5184 | 0.7202 | |

10 | 75 | 0.7558 | 0.6892 | 0.8749 | |

11 | 34 | 0.6468 | 0.5361 | 0.7817 | |

12 | 105 | 0.5993 | 0.4557 | 0.7410 |

In this table, we can find 5 different large classes.
Row 1 is a class, rows 2, 3, 5 are a class, rows 4, 7, 8, 10 are a class, rows
6, 9, 12 are a class, and row 11 is a class.
Figure

(a) The results of fuzzy neural network training (FNN). (b) The results of adaptive pattern clustering and feature map (APCFM).

According
to the characters of process and performance of equipments, we can get the property
of each class in Figure

Class
1 (

Class
2 (

Class
3 (

Class
4 (

Class 5 (

According
to the analysis above, 12 subclasses have been readjusted into 5 classes. Now,
retraining the whole input samples by using the LVQ network, the network is a
characteristic studying of having teacher. The
training network with the LVQ can improve the hitting accuracy of feature map
that is proved by [

The
testing results are shown in Figures

In this paper, in order to predict the BTP, an
APCFM reference and FNN system have
been proposed to solve the challenging problem of the sinter production
process, which is a typical nonlinear, time-varying, and multimode process, and
is very difficult to solve using traditional methods. In our approach, a
density clustering is used to determine the number of the initial input vectors
consciously, and a feature map algorithm is used to extract data relevance
property from different subclasses and improve the confidence of the vector. By using the
teacher’s instruction, LQV network can herd effectively feature categories together on
this basis FNN algorithm. The constructed system has been trained with input
sample consisting of 707 technology
groups and measuring apparatus of two-year actual process and has obtained very
good performance; especially, comparing APCFM+FNN with FNN
[

This work is supported by the National Nature Science Foundation of China (Project no. 60274031).