Deep Learning of Semisupervised Process Data With Hierarchical Extreme Learning Machine and Soft Sensor Application

TLDR

Data‑driven soft sensors are widely used in industry, but low sampling rates leave most process data unlabeled, limiting prediction accuracy. This study aims to fully exploit all available process data for soft‑sensor development. A semisupervised deep‑learning model, the hierarchical extreme learning machine, first extracts features with autoencoders on all samples, then uses an extreme learning machine for regression and manifold regularization for semi‑supervised training. The method deepens feature extraction, leverages unlabeled data, and achieves markedly better carbon monoxide predictions in a high‑low transformer than conventional approaches.

Abstract

Data-driven soft sensors have been widely utilized in industrial processes to estimate the critical quality variables which are intractable to directly measure online through physical devices. Due to the low sampling rate of quality variables, most of the soft sensors are developed on small number of labeled samples and the large number of unlabeled process data is discarded. The loss of information greatly limits the improvement of quality prediction accuracy. One of the main issues of data-driven soft sensor is to furthest exploit the information contained in all available process data. This paper proposes a semisupervised deep learning model for soft sensor development based on the hierarchical extreme learning machine (HELM). First, the deep network structure of autoencoders is implemented for unsupervised feature extraction with all the process samples. Then, extreme learning machine is utilized for regression through appending the quality variable. Meanwhile, the manifold regularization method is introduced for semisupervised model training. The new method can not only deeply extract the information that the data contains, but learn more from the extra unlabeled samples as well. The proposed semisupervised HELM method is applied in a high-low transformer to estimate the carbon monoxide content, which shows a significant improvement of the prediction accuracy, compared to traditional methods.