Data imputation and dimensionality reduction using deep learning in industrial data
Zhihong Zhou, Jiao Mo, Yijie Shi · 2017
Due to human errors, noise during transmission and other interference, some data collected from industrial process system might be lost in the collection process, which would affect the whole quality of data. In addition, the data collected by the industrial control system are generally composited of a large number of high-dimensional data. To facilitate the follow-up processing like anomaly detection, the “the curse of dimensionality” need to be solved, to obtain useful and meaningful content from massive high-dimensional data. The features obtained from DBNs (Deep Belief Networks) are usually not on the low-dimensional surface, and they can well express high-dimensional nonlinear function with a variety of variables. Therefore, in this paper, the DBNs are used to solve the data processing problem in industrial control system. Moreover, some experiments have been done to reveal that the DBNs algorithm can improve the filling accuracy, and the reduction of dimensions of data is good for effective information extraction.