论文部分内容阅读
针对常压塔复杂工况下的航煤干点估计困难的问题,本文提出一种基于PLS模糊多模型软测量建模方法:(FuzzyMulti-model based on PLS,FMM-PLS)。该方法:采用减法c-均值聚类进行数据划分,按隶属度最大原则,合理划分子空间,确定予空间个数为3个,然后利用PLS方法:建立3个子模型,并对各子模型的输出进行隶属度加权预测输出值。同时,也建立PLS、QPLS、RBF-PLS单模型,并与提出的FMM-PLS方法:相比较。PLS、QPLS、RBF-PLS和FMM-PLS的最大误差分别为4.9541、4.6282、4.7517、3.8040;均方根误差分别为1.8599、1.7025、1.7381、1.5327。研究结果:表明,与PLS、QPLS、RBF-PLS相比,在航煤干点的估计中本文提出的FMM-PLS方法:预测精度更高,泛化性能更好。
Aiming at the difficulty in estimating the dry spot of aviation coal under the complicated working conditions of atmospheric tower, this paper presents a modeling method of soft measurement based on PLS fuzzy multi-model: (Fuzzy Multi-model based on PLS, FMM-PLS). The method uses subtraction c-means clustering to divide the data, according to the principle of maximum membership, the sub-space is reasonably partitioned, and the number of space is determined to be three. Then PLS method is used to establish three sub-models, The output is weighted by membership degree. At the same time, PLS, QPLS, RBF-PLS single models are also established and compared with the proposed FMM-PLS method. The maximum errors of PLS, QPLS, RBF-PLS and FMM-PLS are 4.9541, 4.6282, 4.7517 and 3.8040, respectively. The root mean square errors are 1.8599, 1.7025, 1.7381 and 1.5327 respectively. The results show that compared with PLS, QPLS and RBF-PLS, the proposed FMM-PLS method in the estimation of dry coal ship points has higher prediction accuracy and better generalization performance.