Predictive modeling of bacterial growth in anaerobic biogas digester using artificial neural networks (original) (raw)
Related papers
The anaerobic digestion (AD) has been long an object of mathemati-cal modelling with deterministic means. However, the parameter estimation of these nonlinear models is a very hard problem. That is why, recently, the Artificial Neural Networks approach was used for AD modelling. In the paper, this approach was used for modelling the processes of AD of cattle dung. Mul-tiple experimental studies were done on the laboratory-scale continuous biogas plant, applying appropriate step-or pulse-wise actions with acetate as a stimu-lating substance. On the basis of the experimental data, comparatively simple input-output neural models of AD dynamics are developed, where the dilution rate and the concentration of acetate are control inputs, the biogas flow rate is the measured output. All neural models are recurrent with one hidden layer of six neurons. Validating the models with another set of experimental data, very good results were obtained with practically no static error and an insignif...
2017
The modelling of anaerobic co-digestion of household food solid wastes and wastewater are complex and this is due to the rigorous processes that take place during the digestion process. The development of a predictive model that is capable of the simulation of anaerobic digester (AD) performances can go a long way in helping the operation of the AD processes and the optimization for biogas yield. The artificial neural networks (ANNs) approach is considered to be suitable and straightforward modelling method for AD process. In this research work, a multi-layer ANNs model with six input layer, ten hidden layers was trained using Lavenberg-Marquardt back propagation algorithm to simulate the digester operation and to predict the outcome of biogas yield. The performance of the developed ANNs models was validated and the results obtained from the research work reveal the effectiveness of the model to predict biogas yield with a mean squared error (MSE) of best validation performance of 5...
Artificial Neural Network Modelling for Biogas Production in Biodigesters
Chemical Engineering Transactions, 2019
The use of the biodigestion is considered promising for the energetic valorization of agriculture biomass such as swine farm sewage and lignocelulosic residues. The understanding of biodigesters operation and the control of their main operational variables are of great importance to improve the performance of anaerobic digestion process in order to increase biogas production. In this context, mathematical modelling can be used as a tool to increase process efficiency. This work presents the development of Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) to predict volume of biogas. The variables from process were temperature (ºC), pH, FOS/TAC ratio and type of biodigesters. A database was constructed with the information of the experiments, dividing them into groups of training (67 %) and test (33 %). The models were obtained using MATLAB R2018b toolbox. In the developed neural models, the data obtained from process were used as neurons in the input ...
2020
The anaerobic digestion process is a technology that recovers energy in form of biogas and nutrients from biodegradable waste streams in useable forms in the absence of oxygen. It is sustainable, renewable and a zero-carbon form of energy supply. In this research work, modelling of biogas yield from co-digestion of food waste and animal manure using artificial neural networks was carried out. An experimental three stage continuous anaerobic digestion plant was used to co-digest food waste and animal manure. The composition of food waste and animal manure used include fufu, eba, starch, rice, beans, yam, fish, meat, moi moi, pig and cow dung. The feedstock was ground into fine particles to increase its surface area, and then mixed with water in a ratio of 1:2. The actual biogas yield was compared to the predicted biogas yield using artificial neural networks model. The performance of the developed artificial neural networks model was validated, and the results obtained from the resea...
The performance of a laboratory-scale anaerobic bioreactor was investigated in the present study to determine methane (CH 4) content in biogas yield from digestion of organic fraction of municipal solid waste (OFMSW). OFMSW consists of food waste, vegetable waste and yard trimming. An organic loading between 40 and 120 kg VS/m 3 was applied in different runs of the bioreactor. The study was aimed to focus on the effects of various factors, such as pH, moisture content (MC), total volatile solids (TVS), volatile fatty acids (VFAs), and CH 4 fraction on biogas production. OFMSW witnessed high CH 4 yield as 346.65 L CH 4 /kg VS added. A target of 60–70% of CH 4 fraction in biogas was set as an optimized condition. The experimental results were statistically optimized by application of ANN model using free forward back propagation in MATLAB environment.
Prediction of Biogas Generation Profiles in Wastewater Treatment Plants Using Neural Networks
Journal of Clean Energy Technologies, 2014
The great potential of Waste Activated Sludge (WAS) to produce methane as renewable bio-resource energy has always been of engineers' interest. The evaluation of the rate of methane generation and its ultimate value is a crucial step to predict the performance of anaerobic digesters degrading wide ranges of raw and pre-treated WAS. Biochemical methanogenic potential (BMP) test is known as the most common assay in this context. However, it is known as a time consuming, equipment-intensive and consequently expensive tool. The objectives of this research are to identify key WAS properties required to estimate biodegradability of raw and pretreated sludge and accordingly generate a proper model for predicting sludge biodegradability, utilizing Artificial Neural Networks (ANN). Earlier attempts to identify such key indicators and generating a proper model representing sludge biodegradability using typical mathematical approaches were unsuccessful. However, the results of this research proved ANN effective in modeling sludge biodegradability.
Renewable and Sustainable Energy Reviews , 2020
An anaerobic fermentation process for biogas production integrated with wastewater purification in a modern wastewater treatment plant (WWTP) of designed nominal capacity 27,000 m 3 /day was modelled using artificial neural networks (ANNs). Neural models were trained, validated, and tested based on real-scale industrial data (covering three years of continuous plant operation), considering both technological aspects of the process and treated wastewater quality. An innovative approach addressing the simultaneous effect of seven adjustable main plant operation parameters together with wastewater characteristics (five parameters) on biogas production is reported for the first time in the literature. A parameter sensitivity analysis indicated clearly the higher importance of the operation process parameters on the biogas yield compared to the wastewater quality (COD, BOD 5 , TSS, P g , N g). The operation process parameters were the subject of modelling and analysis in respect to new, innovative possibilities, and technological strategies for biogas yield enhancement. The ANN model presented can be used as a predictive tool, an important element in such complex processes as steering/control strategies or for their optimisation procedures, as well as in the testing of other promising process intensification and optimisation scenarios.
Modeling anaerobic process for wastewater treatment: new trends and methodologies
ipcbee.net
Anaerobic digestion is a multistep process involving the action of multiple microbes. In order to be able to design and operate anaerobic digestion systems efficiently, appropriate models need to be developed. Several Mathematical models have been introduced which suffer from lack of knowledge on constants, complexity and weak generalization. Novel techniques to provide correlation between the affecting factors and production criteria of reactors have been reported to be robust, simple and fast enough for control applications and on-line industrial implementations. In this paper, artificial neural networks (ANN), genetic algorithms (GA) and Fuzzy systems are reviewed. ANN models have been extensively used and gained a considerable attention among the researchers. However, integration of GA and Fuzzy systems looks extremely promising for the industrial fields in future. In addition, the advantageous and practical applications of these models for wastewater treatment are also fully discussed.
The Global Environmental Engineers, 2014
The processes of anaerobic digestion and co-digestion are complicated and the development of computational models that are capable of simulation and prediction of anaerobic digester performances can assist in the operation of the anaerobic digestion processes and the optimization for methane production. The artificial neural network approach is considered to be an appropriate and uncomplicated modelling approach for anaerobic digestion applications. This study developed neural network models to predict the outcomes of anaerobic co-digestion of leachate with pineapple peel using experimental data. The multilayered feed forward neural network model proposed was capable of predicting the outcomes of biogas production from the anaerobic co-digestion processes with a mean squared error for validation of 2.67 x 10-2 and a R value for validation of 0.9942. The approach was found to be effective, flexible and versatile in coping with the non-linear relationships using available information.