Research of Machine Vision Based Recognition of Burning through Point of Sintering

The accurate prediction and control of burning through point are the keys of improving the quantity and quality of sinter. The position of burning through point can be determined by identifying the flame image features of the tail through the sinter. How to effectively segment the image of the flame is the key to identify the characteristics of the flame. By using the approach of the c-means clustering flame image segmentation based on particle-pair optimizer, the flame image of the sintering machine plant-tail section will be segmented in this paper. Frequently, the standard c-means clustering algorithm may easily immerse in partial minimum and slow converging speed. However, this new calculation method can overcome these shortcomings. Besides, the results of the experiment also show that this method has many other advantages, such as effectively removing the halo of the sintering machine plant-tail section, high segmenting speed and obvious segmenting effects. This approach will lay a good foundation for the extraction and identification of image features in the following stages.

Intelligent Control of the Complex Technology Process Based on Adaptive Pattern Clustering and Feature Map

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.