﻿ 基于FSVM锅炉烟气含氧量软测量 Boiler Flue Gas Oxygen Content Soft Sensor Based on FSVM

Modeling and Simulation
Vol.05 No.04(2016), Article ID:19117,5 pages
10.12677/MOS.2016.54026

Boiler Flue Gas Oxygen Content Soft Sensor Based on FSVM

Zhen Liu, Yuguo Zhou, Shilong Xie

Qingdao University of Technology, Qingdao Shandong

Received: Nov. 12th, 2016; accepted: Nov. 27th, 2016; published: Nov. 30th, 2016

ABSTRACT

For power plant boiler combustion process of a high degree of complexity and nonlinear problem, fuzzy support vector machine (FSVM) is adopted to establish the prediction models of oxygen forecast in different fuel quantity, total air volume and total yield, total steam flow under the influence of factors such as flue gas oxygen content. We select fuzzy c-means algorithm (FCM) as a design method of membership function, then select the radial basis kernel function (RBF) and ε-SVR model structure, and choose the penalty factor and the optimum parameter value of slack variable to use cross validation method. Matlab simulation experiment results show that this method can effectively shorten the training time, improve the prediction precision and the model of noise resistance; and its performance is superior to the general support vector machine forecasting model.

Keywords:FSVM, Flue Gas Oxygen Content, Soft Measurement, Prediction Model

1. 引言

2. 基于模糊支持向量机的预测模型

(1)

(1) 式中为输入空间到特征空间的映射函数；为权值向量，偏置量。

(2)

(2) 式中，为松弛变量，为预算误差的惩罚系数用于调节误差所取的作用，它能够使训练误差和模型复杂度之间取一个折衷，以便使所求的函数具有较好的泛化能力，并且值越大，模型的回归误差 [4] 越小。FSVM是近几年提出的一种新方法，是对传统SVM的改进和完善。为了提高SVM的抗噪能力，对每一个样本引入模糊隶属度则优化问题改进为：

(3)

(4)

(5)

(6)

3. FSVM模型建立

3.1. 模糊隶属度函数的计算

3.2. 核函数和初级参数的选取

3.3. 基于FSVM软测量模型的流程图

3.4. 仿真实验结果及分析

Figure 1. Flow chart of FSVM soft meas- urement model

Figure 2. FSVM model predicted results compared with the actual oxygen

Table 1. FSVM compared with SVM experimental results

4. 结束语

Boiler Flue Gas Oxygen Content Soft Sensor Based on FSVM[J]. 建模与仿真, 2016, 05(04): 205-209. http://dx.doi.org/10.12677/MOS.2016.54026

1. 1. 马芳芳. 模糊支持向量机算法及其在一次风量测量中的应用[D]: [硕士学位论文]. 北京: 华北电力大学, 2013: 11-40.

2. 2. 张捷夫. 电站锅炉烟气含氧量软测量方法研究[D]: [硕士学位论文]. 北京: 华北电力大学, 2014: 20-33.

3. 3. 王勇, 刘保军, 李琛. 软测量技术的新进展及其在火电厂热工过程中应用[J]. 长春工程学院学报(自然科学版), 2006, 7(4): 55-57.

4. 4. 徐艳芳. 改进支持向量回归机及其在过程建模与控制中的应用[D]: [博士学位论文]. 上海: 华东理工大学, 2004.

5. 5. 傅永峰. 软测量建模方法研究及其工业应用[D]: [博士学位论文]. 杭州: 浙江大学, 2007.

6. 6. 杨庆柏, 厉鹏. 氧气传感器及其在火电厂的应用[J]. 传感器世界, 2001, 7(9): 22-24.

7. 7. 程启明, 郭瑞青, 杜许峰, 郑勇. 火电厂烟气含氧量测量的现状与发展[J]. 电站系统工程, 2008, 24(6): 1-4.

8. 8. 于振亚, 王闻侠, 潘丰. 模糊支持向量机在青霉素发酵中的应用[J]. 微计算机信息, 2007, 23(19): 300-302.

9. 9. Han, P., Q, H., W, D.F. and Zhai, Y.J. (2007) Development and Current Status of Thermal Parameter Soft-Sensing Technique in Power Plant. Chinese Journal of Scientific Instrument, 28, 1139-1146.

10. 10. Niu, D.X., Wang, Y.L. and Ma, X.Y. (2010) Optimization of Support Vector Machine Power Load Forecasting Model Based on Data Mining and Lyapunov Exponents. Journal of Central South University of Technology, 17, 406-412.