Back to Search
Start Over
Physically Consistent Soft-Sensor Development Using Sequence-to-Sequence Neural Networks
- Source :
- IEEE Transactions on Industrial Informatics. 16:2829-2838
- Publication Year :
- 2020
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2020.
-
Abstract
- Soft sensors attempt to predict the key quality variables that are infrequently available using the sensor and manipulated variables that are readily available. Since only limited amount of labeled data are available, there is always the concern whether the underlying physics were captured so that the model can be reasonably extrapolated. A sequence-to-sequence model in the form of a nonlinear state-observer/encoder and predictor/decoder was proposed. The observer can be trained using a large amount of unlabeled data, but in a supervised manner in which the process dynamics is tracked. The encoder output and manipulated variables are used to train the quality predictor. The model is applied to the product impurity predictions of an industrial column. Results show that good predictions and excellent consistency in the sign of estimated gains can be achieved even with limited amount of data. These findings indicated that the proposed sequence-to-sequence data-driven approach is able to capture the underlying physics of the process.
- Subjects :
- Observer (quantum physics)
Artificial neural network
020208 electrical & electronic engineering
Process (computing)
02 engineering and technology
Soft sensor
Computer Science Applications
Data modeling
Nonlinear system
Control and Systems Engineering
Consistency (statistics)
0202 electrical engineering, electronic engineering, information engineering
Electrical and Electronic Engineering
Algorithm
Encoder
Information Systems
Subjects
Details
- ISSN :
- 19410050 and 15513203
- Volume :
- 16
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Industrial Informatics
- Accession number :
- edsair.doi...........edde7c3928a2267e96b51f3f3cfaf161