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：
由于水压试验机机理建模的复杂性，很难从机理方面对其生产过程进行故障诊断，因此利用钢管水压试验系统过程变量多、打压速度快、短时间内能够产生大批数据信息的特点，采用基于数据的多向Fisher判别分析（MFDA）方法对其进行故障诊断。在建立MFDA模型之前，先采取多向独立成分分析（MICA）方法去除变量之间的相关性，并且提取少数驱动过程本身的关键变量，经过MICA变换后的数据用以建立MFDA模型可以提高故障诊断精度。综上，本文提出了一种基于MICA-FDA的方法用于水压试验机打压过程的故障诊断。采用水压试验机生产过程的几类故障数据对该方法进行验证，结果表明该方法具有很好的故障诊断性能。
英文摘要：
Due to the complexity of hydraulic tube tester modelling, it is difficult to diagnose the production process fault from the mechanism. Considering that hydraulic tube tester process can be characterized as a data-rich process and it can generate a large number of process measurement data on many variables in short time, a data mining based muhiway independent component analysis and multiway fisher discriminant analysis （MICA-FDA） method is devel- oped for the fault diagnosis in hydraulic tube tester process, where MICA models are adopted to find the underlying components from normal process data and remove the collinearity of the variables, and then MFDA models are built for fault diagnosis from the various known fault data. The proposed method was applied to a hydraulic tube tester production process to verify its effectiveness in fault diagnosis.
同期刊论文项目
同项目期刊论文
Batch-to-Batch Iterative Learning Control of a Batch Polymerization Process Based on Online Sequenti
期刊信息
位置：