LSTM and 1-D Convolutional Neural Networks for Predictive Monitoring of the Anaerobic Digestion Process

Abstract

Anaerobic digestion is a natural process that transforms organic substrates to methane and other products. Under controlled conditions the process has been widely applied to manage organic wastes. Improvements in process control are expected to lead to improvements in the technical and economic efficiency of the process. This paper presents and compares 3 different neural network model architectures for use as anaerobic digestion process predictive models. The models predict the future biogas production trend from measured physical and chemical parameters. The first model features an LSTM layer, the second model features a 1-D convolutional layer and the third model combines 2 separate inputs and parallel treatment using LSTM and 1-D convolutional layers followed by merging to produce a single prediction. The predictions can be used to adaptively adjust the substrate feeding rate in accordance with the transient state of the digestion process as defined by liquid feeding rate, the organic acid and ammonium ion concentrations and the pH of the digester liquid phase. The training and testing data were obtained during 1 year of continuous operation of a pilot-plant treating restaurant wastes. PLS regression and ICA were used to select the most relevant process parameters from the data. The 1-D Convolutional based model comprising 272 trainable parameters predicted the future biogas flow rate changes with accuracy as high as 89% and an average accuracy of 58%. The work-flow can be applied to optimize the control of the study digester and to control bioreactors in general.

A New Comprehensive Indicator for Monitoring Anaerobic Digestion: A Principal Component Analysis Approach

“…Nonetheless, it is worth noting that this method has outstanding adaptability and utility in diagnosing the instability of anaerobic digestion. Recent years have seen notable advancements in techniques for monitoring operational full-scale digesters, including the use of deep learning and electrochemical sensors [14,38,48]. These technologies enable the prediction of state and performance variables and offer alternatives to traditional wet analysis, thus simplifying the monitoring process.…”

“…For instance, electrochemical sensors provide real-time data on crucial parameters including pH, electric conductivity, and oxidation-reduction potential [1,19]. Further, datadriven models, such as a combined model of convolutional neural network as well as longand short-term memory, can be used to process sensor data to extract meaningful insights about the state of anaerobic digestion [1,48]. The combination of these technologies with PCA-based diagnostics could lead to comprehensive indicators that not only offer real-time monitoring but also serve as early warning systems to help prevent failures in anaerobic digestion processes.…”

Dark Web: E-Commerce Information Extraction Based on Name Entity Recognition Using Bidirectional-LSTM

“…In the early layers examined during the experiment, Conv1D outperforms with an Elmo embedding BiLSTM layer, followed by multiple filters and a fully-connected layer with activation of Softmax in later layers. To maintain the dimensions and sequence information of the data set, Conv1D [71] without a pooling layer was utilized. By doubling the weights of each kernel and embedded values, the Conv1D layer generates new representative data.…”

Review of Soft Sensors in Anaerobic Digestion Process

“…This suggests that the target variable is affected by the auxiliary variable in the current state, the changes in the operating conditions, and production conditions at the last moment, as well as the target variable in the current state. Therefore, Mccormick proposed a dynamic soft sensor based on long short-term memory (LSTM) network to predict biogas yield [105]. The LSTM structure is exhibited in Figure 6.…”