doi:10.16186/j.cnki.1673-9787.2020050008

Received:2020/05/06

Revised:2020/05/29

Published:2021/07/15

Monitoring model of gasification process parameter instability based onBA-RBFNN control chart pattern recognition

ZHANG Zichuan, ZHANG Jinchun

School of Energy Science and Engineering， Henan Polytechnic University ，Jiaozuo 454000 ， Henan， China

Abstract:To identify variation patterns in the process of gasification of solid， a monitering model based on bees algorithm-radial basis function neural network（ RBFNN） was proposed to conduct pattern recognition of the parameters of gasification process. The model consisted of four modules ： feature description， feature extraction， classifier and training method. Shape feature and statistical feature were selected to describe gasification process parameters. Association rule（ AR） algorithm was nsed to select the best feature set. Radial basis function neural network（ RBFNN） was selected as classifier. Bees algorithm（ BA） was used as the training method of the model. In order to test the performance of the model. The simulation data and the gasifier field data were used to test the model respectively， and the pnodel was compared with the traditional method. The results showed that the proposed model had a better recognition effect on the abnormal patterns in the gasifier parameters.

Key words:gasification process parameter;pattern recognition;radial basis functions neural network;bees al gorithm;association rule algorithm

 基于BA_RBFNN控制图模式识别的气化过程参数失稳监控模型_张自川.pdf