论文部分内容阅读
由于化工过程的复杂性,数据往往存在动态以及序列之间具有相关性特点,传统的支持向量数据描述(Support Vector Data Description,SVDD)方法,很难保证故障监测的准确性和实时性,提出一种基于加权的动态SVDD(WDSVDD)在线实时故障监测方法,引入动态方法,考虑了数据之间的序列相关性,利用加权的方法把有用的信息突出显示,利用SVDD方法建立模型,实现了在线实时故障监测。该方法不仅克服了过程数据非高斯、非线性特性对故障监测带来的影响,并且考虑了数据的动态特性和序列之间的关系,通过在数值仿真和TE过程实例中的应用验证了方法的有效性。
Due to the complexity of the chemical process, the data tend to be dynamic and there is a correlation between the sequences. The traditional Support Vector Data Description (SVDD) method can hardly guarantee the accuracy and real-time performance of fault monitoring. Based on weighted dynamic SVDD (WDSVDD) online real-time fault monitoring method, the dynamic method is introduced, the sequence correlation between data is considered, the useful information is highlighted by weighted method, and the model is built by SVDD method, Fault monitoring. The method not only overcomes the influence of non-Gaussian and nonlinear characteristics of process data on fault monitoring, but also considers the relationship between the dynamic characteristics of data and the sequence. The application of numerical simulation and TE process is verified by the proposed method. Effectiveness.