Abstract
Anaerobic digestion technology is the most environmentally friendly approach to treat kitchen waste. Volatile fatty acid (VFA) is an essential quality monitoring indicator in the anaerobic digestion process of treating kitchen waste. In this paper, a soft measurement method of volatile fatty acid (VFA) concentration in the anaerobic digestion process is established based on stacked supervised auto-encoder combine kernel extreme learning machine algorithm (SSAE-KELM) to improve the real-time monitoring level and resource conversion efficiency of the anaerobic digestion process. Given the problems of poor feature extraction and low accuracy and efficiency of the model, a stack supervised autoencoder is proposed to realize nonlinear and deep feature extraction of process data. Simultaneously, using the idea of the extreme learning machine to train the network significantly improves the efficiency of the model. Then, the kernel extreme learning machine is used to realize regression modelling. Besides, a combined feature selection algorithm is presented to select auxiliary variables more accurately. The simulation results demonstrate that the soft sensor model can predict the concentration of volatile fatty acids (VFA) more efficiently and accurately.
Highlights
In recent years, kitchen waste treatment and resource reuse has become a new research hotspot
For the anaerobic digestion process of kitchen waste, a deep learning soft sensor model is established in this paper to achieve a more accurate and efficient prediction of volatile fatty acid concentration
Considering the anaerobic digestion process of kitchen waste, a soft sensing model of volatile fatty acid (VFA) concentration based on deep learning is established
Summary
Kitchen waste treatment and resource reuse has become a new research hotspot. Since data driven soft sensing modelling uses historical data to build the prediction model, it does not need a lot of prior knowledge nor complex mechanism analysis It has been well applied in complex industrial processes. With the help of the deep neural network, deep learning methods, such as deep belief network (DBN)[8] and stacked auto-encoder network (SAE)[9], can extract the original features into a more abstract high-level representation and effectively extract nonlinear potential variables It has strong nonlinear fitting ability and excellent feature learning ability, making the deep learning method suitable for soft sensor modelling of anaerobic digestion process with strong nonlinear characteristics. For the anaerobic digestion process of kitchen waste, a deep learning soft sensor model is established in this paper to achieve a more accurate and efficient prediction of volatile fatty acid concentration. The experimental results verify that the improved deep learning soft sensor algorithm can significantly improve the prediction accuracy and efficiency of the model
Sign-in/Register to view highlights & summary 
Published Version (
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