Abstract
In industrial processes, some important process variables cannot be measured directly by hardware sensors for technical or economic reasons. Soft sensors estimate these key variables using some other easily measured variables by building a mathematical model. A novel knowledge- and data-driven soft sensor is proposed in this paper to predict the deformation of an air preheater rotor in a thermal power plant boiler. Two submodels were constructed, including the knowledge-driven submodel, derived from all the available domain knowledge, and the data-driven submodel, constructed solely from the data. The two submodels were integrated with a mass balance model. A mathematical model based on technical expertise in predicting rotor deformation, named the Lab model, was used as the knowledge-driven submodel, and a deep learning model based on stacked autoencoders (SAE) was used as the data-driven submodel. To improve the performance of the model, the limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm was adopted to optimize the SAE parameters. The experimental results demonstrate that, compared with the common knowledge-driven (KDM) and data-driven (DDM) models, the proposed Lab-stacked autoencoders (L-SAE) model is able to provide a higher predictive accuracy for the air preheater rotor deformation and inherits the advantages of both the KDM and DDM.
Highlights
In industrial processes, there are some variables that play an important role in improving efficiency and product quality
The most common knowledge-driven models (KDMs) for calculating the rotor deformation, the Lab model, was used as the knowledge-driven submodel, and a deep neural network based on stacked autoencoders (SAE) was used as the data-driven submodel
In our previous research [36], we established a soft sensor based on SAE with an support vector machine regression (SVR) method to estimate the rotor deformation, which was a typical data-driven models (DDMs) based on deep learning
Summary
There are some variables that play an important role in improving efficiency and product quality. A new knowledge- and data-driven soft sensor, named the Lab-stacked autoencoders (L-SAE) model is proposed, inspired by the idea of combining the advantages of the two abovementioned methods to estimate the rotor deformation of an air preheater rotor in a thermal power plant boiler. The most common KDM for calculating the rotor deformation, the Lab model, was used as the knowledge-driven submodel, and a deep neural network based on stacked autoencoders (SAE) was used as the data-driven submodel. The established model is introduced to estimate the rotor deformation of an air preheater This is the first application of the knowledge- and data-driven model in this aspect from a review of the searchable literature.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
