Nonlinear Dynamic Soft Sensor Modeling With Supervised Long Short-Term Memory Network

By Xiaofeng Yuan, Lin Li, Yalin Wang. IEEE Transactions on Industrial Informatics, 2020

450 citations recorded by the source corpus.

Soft sensor has been extensively utilized in industrial processes for prediction of key quality variables. To build an accurate virtual sensor model, it is very significant to model the dynamic and nonlinear behaviors of process sequential data properly. Recently, a long short-term memory (LSTM) network has shown great modeling ability on various time series, in which basic LSTM units can handle data nonlinearities and dynamics with a dynamic latent variable structure. However, the hidden variables in the basic LSTM unit mainly focus on describing the dynamics of input variables, which lack representation for the quality data. In this paper, a supervised LSTM (SLSTM) network is proposed to learn quality-relevant hidden dynamics for soft sensor application, which is composed of basic SLSTM unit at each sampling instant. In the basic SLSTM unit, the quality and input variables are simultaneously utilized to learn the dynamic hidden states, which are more relevant and useful for quality prediction. The effectiveness of the proposed SLSTM network is demonstrated on a penicillin fermentation process and an industrial debutanizer column.

Subfields: Artificial Intelligence, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/6a4e6329a336e7bb4ba569e71ea59622771328ce

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhiqiang Ge
2. Qingqiang Sun
3. Xiaofeng Yuan
4. Yuri A. W. Shardt
5. Lin Li
6. Yalin Wang
7. Chunhua Yang

In Control and Systems Engineering

1. Zhiqiang Ge
2. Qingqiang Sun
3. Chunhua Yang

Citations in the corpus

• A Survey on Deep Learning for Data-Driven Soft Sensors (2021, methodology): “[126] proposed a supervised LSTM network, which used both the input and quality variables to learn dynamic hidden states, and the method was proved to be effective on a penicillin fermentation process and an industrial debutanizer column.”
• Deep Learning With Spatiotemporal Attention-Based LSTM for Industrial Soft Sensor Model Development (2020, background): “…memory cells and three nonlinear gates are used to replace the basic activation unit in RNN. LSTM can not only forget the useless information in the past, but also judge the current information and store useful information in the memory cell [34], [35].”