Soft Measurement for VFA Concentration in Anaerobic Digestion for Treating Kitchen Waste Based on Improved DBN

Abstract

Anaerobic digestion is a new method for treating kitchen waste, which can reduce waste, protect the environment, and create clean energy. Because the concentration of volatile fatty acids (VFA) in kitchen waste anaerobic digestion process cannot be measured in real time online, a soft measurement method based on deep belief network (DBN) is applied to the measurement of VFA. In this paper, the extreme learning machine (ELM) is applied to the training of DBN. The adaptive learning rate is introduced to increase the convergence speed of the network, which is different from traditional DBF. The data from a real plant is classified and decomposed using a Gaussian mixture model (GMM) and ensemble empirical mode analysis (EEMD) before training the network firstly. A DBN is used to perform numerical analysis of original data to extract features. Then, the extracted features are input into the extreme learning machine for training to obtain a soft measurement model. The experimental verification shows that this method is more precise than traditional methods and pure DBN model.