Multi-period intermittent process soft measurement modeling method based on FF-RVM

Abstract

The invention discloses a multi-period intermittent process soft measurement modeling method based on FF-RVM. The method comprises the following steps: firstly, carrying out period division on an intermittent process by utilizing an SCFCM clustering method; then, respectively utilizing KPCA and SSAE to carry out feature extraction on original process data of each time period; achieving feature dimension reduction processing based on KPCA and feature dimension expansion processing based on SSAE, adopting a feature selection method based on minimum errors to screen out SSAE features having highcorrelation with quality variables, and conducting feature fusion on the screened-out SSAE features and the extracted KPCA features; and finally, establishing an RVM-based time period soft measurementmodel by taking the process data subjected to feature fusion as time period training data, thereby realizing online prediction of the quality variable. According to the method, the amount of information contained in the process data is effectively expanded, a large amount of effective training data is provided for establishing an intermittent process soft measurement model, and online predictionof the intermittent process quality variable is realized.

Description

technical field [0001] The invention belongs to the technical field of intermittent process soft sensing, and in particular relates to a multi-period intermittent process soft sensing modeling method based on Fusion Features-Relevant Vector Machine (FF-RVM). Background technique [0002] As one of the main production methods of modern production, batch process has been widely used in chemical industry, food, semiconductor processing and biopharmaceutical fields. In order to ensure its efficient, reliable and safe operation, online measurement of quality variables is urgently needed. Soft sensor technology is a technology that uses process data to establish a mathematical model between auxiliary variables and quality variables to realize online prediction of quality variables. It has been widely used in online measurement of quality variables in batch processes. [0003] The data-driven soft-sensing modeling method of batch process uses the collected process data to carry out...

AI Technical Summary

Problems solved by technology

However, in the actual batch production process, due to the multi-period characteristics, dynamic characteristics, nonlinearity, and high complexity of the process, the collected batch process data is less, and it is difficult to meet the data-driven batch process soft sensor modeling data. In addition, the soft sensor model established by using the original process data ignores the nonlinear characteristics and inherent deep features of the process data, which leads to poor prediction performance of the established soft sensor model and reduces the online prediction accuracy of quality variables

Images