摘要
提出了一种解决批处理过程多种工作模式故障检测问题的方法。该方法从多种工作模式中提取各个模式相类似的信息,解决了该工作模式下故障检测建模问题;将核函数应用到算法中,利用核技术提高算法处理非线性数据故障检测的能力;将在每种工作模式下的数学模型进行分解,将反映相似信息和各个模式不同的信息进行分离,并分别建立故障检测模型,通过分析可以辨别出当前所处的工作模式,并且有效地检测故障的发生。
A new online monitoring approach is proposed for handling the muhimode fault detection in the industrial batch processes. The method for extracting the common characteristics from different modes is proposed; The kernel method is used to solve the nonlinear data problem; A new model analysis method is proposed. There are both similarity and dissimilarity in the underlying correlations of different modes. By an adequate decomposition, one part of the underlying variations in each subspace stay invariable over subspaces while the other part changes with the alternation of subspaces. After that two different subspaces are separated, the common and specific subspace modles are established respectively. The common subspace and specific subspace are analyzed respectively, and the monitoring process is carried out in each subspace. The corresponding confidence regions are constructed according to their models respectively. Then the online monitoring system is set up, which can track different types of variations closely.
出处
《南京航空航天大学学报》
EI
CAS
CSCD
北大核心
2011年第B07期36-40,共5页
Journal of Nanjing University of Aeronautics & Astronautics