欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对复杂工业过程存在的多变量、相关性和非线性问题，提出一种新的基于非线性偏最小二乘（partial least squares，pts）回归的软测量建模方法。该方法利用PLS作为模型的外部框架来提取输入输出主成分变量，同时消除变量间的相关性，然后用最小二乘支持向量机（1ean squares suppor tvector machine，LSSVM）作为内部函数来描述主成分变量之间的非线性关系，并引入基于误差最小化的权值更新策略，来改进模型的预测精度。以pH中和过程的Benchmark模型来验证该方法的性能，并与其他建模方法比较，结果表明该方法预测精度较高，而且具有较强的泛化能力。将该方法应用于某电站燃煤锅炉的NO2排放软测量建模之中，取得了较好的于页测效果。
英文摘要：
A novel soft-sensing method based on nonlinear partial least squares （PLS） regression was proposed to deal with the modeling problem of complex industrial process with characteristics of multivariate, correlation and nonlinearity. Firstly PLS was applied as the outer framework to extract the input and output latent components while eliminating the correlation, then we employed least squares support vector machine （LSSVM） to describe the nonlinear relation between pairs of latent variables. Moreover, the weights updating strategy based on errors minimization was also involved to improve the prediction accuracy. The pH neutralization process was taken as a benchmark to validate the performance and some comparisons were also made. The results showed that the novel method proposed in this paper exhibited a perfect prediction accuracy and had a strong generalization ability. Finally this method was applied in the NO2 emission modeling of a coal-fired boiler and an effective prediction result was achieved.
同期刊论文项目
同项目期刊论文
Consensus analysis of continuous-time second-order multi-agent systems with nonuniform time-delays a
Minimizing neighborhood evidential decision error for feature evaluation and selection based on evid
Convenient T-S fuzzy model with enhanced performance using a novel swarm intelligent fuzzy clusterin
Sliding mode H-infinity control design for uncertain nonlinear stochastic state-delayed Markovian ju
Stabilization of interconnected nonlinear stochastic Markovian jump systems via dissipativity approa
期刊信息
位置：