Immune principle for RBF network and its application on Carrousel oxidation ditch system prediction

doi:10.3778/j.issn.1002-8331.2009.26.072

Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (26): 240-242.DOI: 10.3778/j.issn.1002-8331.2009.26.072

• 工程与应用 • Previous Articles Next Articles

Immune principle for RBF network and its application on Carrousel oxidation ditch system prediction

XU Chang-zhu，DENG Wei

School of Computer Science & Technology，Soochow University，Suzhou，Jiangsu 215006，China

Received:2008-05-15 Revised:2008-07-28 Online:2009-09-11 Published:2009-09-11
Contact: XU Chang-zhu

基于免疫原理的RBF网络Carrousel氧化沟系统预报

徐常祝，邓伟

苏州大学计算机科学与技术学院，江苏苏州 215006

通讯作者: 徐常祝

Abstract

Abstract: To improve stimulating precision of water quality for Carrousel oxidation ditch system，immune arithmetic and RBF neural network are combined together in this model.Furthermore，using k-means algorithm as pretreatment step.In the end，doing experiment with a waste water treatment center’s data，the forecasting error of TN is 0.195 6，and the forecasting error of TP is 0.145 6，the precision improves much compared with RBF network.It proves well that this method can be used in online real time forecasting of Carrousel oxidation ditch system.

Key words: immune arithmetic, RBF neural network, k-means algorithm, oxidation ditch system

摘要： 为提高Carrousel氧化沟系统水质模拟的精度，利用免疫算法结合RBF神经网络进行建模，并加入k-means聚类对样本进行预处理。以某污水处理中心两年生产数据进行实验，测得出水TN的预报误差0.195 6，出水TP的预报误差0.145 6，较仅用RBF网络均有很大提高，证明该方法可以应用于Carrousel氧化沟系统的在线实时预测。

关键词: 免疫算法, RBF神经网络, k-means算法, 氧化沟系统

CLC Number:

TP183

XU Chang-zhu，DENG Wei. Immune principle for RBF network and its application on Carrousel oxidation ditch system prediction[J]. Computer Engineering and Applications, 2009, 45(26): 240-242.

徐常祝，邓伟. 基于免疫原理的RBF网络Carrousel氧化沟系统预报[J]. 计算机工程与应用, 2009, 45(26): 240-242.

[1]	PAN Chengsheng, ZHANG Bin, LYU Yana, DU Xiuli, QIU Shaoming. K-Means Text Clustering Based on Improved Gray Wolf Optimization Algorithm [J]. Computer Engineering and Applications, 2021, 57(1): 188-193.
[2]	SU Jiali, WU Zhongdong, DING Longbin, LIU Feifei. Research on LTE-R Handover Algorithm Based on IGWO-RBF [J]. Computer Engineering and Applications, 2020, 56(8): 74-80.
[3]	WANG Zilong, LI Jin, SONG Yafei. Improved K-means Algorithm Based on Distance and Weight [J]. Computer Engineering and Applications, 2020, 56(23): 87-94.
[4]	ZHANG Zhen, LI Haofang, LI Mengzhou. Research on YOLO Algorithm in Abnormal Security Images [J]. Computer Engineering and Applications, 2020, 56(21): 187-193.
[5]	LI Feng, LI Mingxiang, ZHANG Yujing. Partial Iterative Fast K-means Clustering Algorithm [J]. Computer Engineering and Applications, 2020, 56(13): 63-71.
[6]	WANG Jianren, MA Xin, DUAN Ganglong. Improved K-means Clustering k-Value Selection Algorithm [J]. Computer Engineering and Applications, 2019, 55(8): 27-33.
[7]	WANG Yanyan1, WANG Hongwei1，2. Post-Partial Polynomial RBF Neural Network Algorithm Based on Particle Swarm Optimization [J]. Computer Engineering and Applications, 2019, 55(12): 72-76.
[8]	CHEN Qinghu, ZHOU Xiaodan, YAN Yuchen. Recognition of print file based on character image segmentation [J]. Computer Engineering and Applications, 2018, 54(7): 170-175.
[9]	ZHOU Benjin, TAO Yizheng, JI Bin, XIE Yonghui. Optimizing k-means initial clustering centers by minimizing sum of squared error [J]. Computer Engineering and Applications, 2018, 54(15): 48-52.
[10]	WANG Binyu1, LIU Wenfen2, HU Xuexian1, WEI Jianghong1. Research on text clustering for selecting initial cluster center based on Cosine distance [J]. Computer Engineering and Applications, 2018, 54(10): 11-18.
[11]	WANG Zhaofeng, SHAN Ganlin . k-means based method for dynamically selecting DBSCAN algorithm parameters [J]. Computer Engineering and Applications, 2017, 53(3): 80-86.
[12]	YAN Xuelong, DING Peng, MA Jun. Analog circuit diagnosis based on wolf pack algorithm radical basis function network [J]. Computer Engineering and Applications, 2017, 53(19): 152-156.
[13]	BAI Shuren1，2, CHEN Long2. Particle clustering algorithm with adaptive K values [J]. Computer Engineering and Applications, 2017, 53(16): 116-120.
[14]	ZHOU Hui, ZHANG Yousai, LI Yuanjiang. Design of multi-dimensional transfer function for volume rendering based on RBF neural network [J]. Computer Engineering and Applications, 2016, 52(22): 180-184.
[15]	QIU Yunfei, ZHAO Bin, LIN Mingming, WANG Wei. Improved K-means clustering algorithm combined semantic similarity of short text [J]. Computer Engineering and Applications, 2016, 52(19): 78-83.

Immune principle for RBF network and its application on Carrousel oxidation ditch system prediction

基于免疫原理的RBF网络Carrousel氧化沟系统预报

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics