An integrated framework for diagnosing process faults with incomplete features

Handling missing values and large-dimensional features are crucial requirements for data-driven fault diagnosis systems. However, most intelligent diagnostic systems not able to handle data. The presence of high-dimensional feature sets can also further complicate the process diagnosis. This paper aims devise a data imputation unit along with dimensionality reduction in pre-processing module system. proposes novel pooling strategy (PSMI). simplify complex patterns missingness incrementally update pool. receives incomplete observations, PSMI estimates values, and, then, transforms completed observations onto lower-dimensional space. These transformed then fed as inputs classification decision making scheme makes use various state-of-the-art imputation, algorithms. enables comprehensive comparison allows find best techniques sake diagnosing faults Tennessee Eastman process. obtained results show effectiveness proposed indicate that principal component analysis heteroscedastic discriminant approaches outperform other this application.