Abstract:Biomass is an important primary source of renewable energy source. Producer gas, a derivative of Biomass, comprises of tar and particulate content which is harmful and critical parameter for IC engine application, which influences the design of filter. Numerous researchers have developed various types of filter for gas cleaning system in order to reduce the tar content and particulate in producer gas. In this work, an experimental investigation has been carried out on the newly developed hybrid compact filter … Show more
“…Compared to the literature, high coefficients of determination with R 2 higher than 0.90 and 0.98 were found by different authors [28,66] by using artificial networks ANN to predict tar from biomass gasification. Despite the essence of this model is the same that PLS, the ANN has also got limitations related to an oversimplified approach, where some parameters are assumed to be constant.…”
Section: Partial Least Square Regression For Collected Tarmentioning
confidence: 83%
“…It requires a very large number of samples and it has got 'black box' nature in comparison with other models. Other authors have mainly proposed models based on kinetic models finding overestimation of the tar content or even the models are not able to foresee the tar content in the product gas [35,[66][67][68][69]. The lack of kinetic data and the theoretical comprehension of the tar reaction during gasification point out the difficult task of modelling this variable.…”
Section: Partial Least Square Regression For Collected Tarmentioning
Gasification represents a potential technology for the conversion of biomass into usable energy. The influence of the main gasification parameters, i.e. the type of biomass used and its composition, as well as the composition of the outlet gas, were studied by a multivariate statistical analysis based on principal component analysis (PCA) and partial least square (PLS) regression models in order to identify the main correlations between them and to the contents of methane, ethylene and tar in the outlet gas. In this work, the experimental data used as input for the multivariate statistical analysis came from a TRL-4 gasification plant running under sorption enhanced conditions, i.e. using steam as the gasifying agent and CaO as the bed material. The composition of the biomass feed played an important role in the quality of the outlet gas composition. In fact, biomasses with high ash and sulphur contents (municipal solid waste) increased ethylene content, while those with high-volatile matter content and fixed C content (wood pellets, straw pellets and grape seeds) mainly increased CO and CO2 formation. By increasing the gasification bed temperature and the CaO/C ratio, it was possible to reduce the methane and the collected tar contents in the outlet gas. Other light hydrocarbons could also be reduced by controlling the Treactor and TFB. Methane, ethylene and tar contents were modelled, cross-validated and tested with a new set of samples by PLS obtaining results with an average overall error between 8 and 26%. The statistically significant variables to predict methane and ethylene content were positively associated to the thermal input and negatively to the CaO/C ratio. The biomass composition was also remarkable for both variables, as mentioned in the PCA analysis. As far as the tar content, which is undesirable in all gasification processes, the decrease in the tar content was favoured by high bed temperature, low thermal input and biomass with high-volatile matter content. In order to produce an outlet gas with adequate quality (e.g. low tar content), a compromise should be found to balance average bed temperature, sorbent-to-mass ratio, and ultimate and proximate analyses of the biomass feed.
Graphical abstract
“…Compared to the literature, high coefficients of determination with R 2 higher than 0.90 and 0.98 were found by different authors [28,66] by using artificial networks ANN to predict tar from biomass gasification. Despite the essence of this model is the same that PLS, the ANN has also got limitations related to an oversimplified approach, where some parameters are assumed to be constant.…”
Section: Partial Least Square Regression For Collected Tarmentioning
confidence: 83%
“…It requires a very large number of samples and it has got 'black box' nature in comparison with other models. Other authors have mainly proposed models based on kinetic models finding overestimation of the tar content or even the models are not able to foresee the tar content in the product gas [35,[66][67][68][69]. The lack of kinetic data and the theoretical comprehension of the tar reaction during gasification point out the difficult task of modelling this variable.…”
Section: Partial Least Square Regression For Collected Tarmentioning
Gasification represents a potential technology for the conversion of biomass into usable energy. The influence of the main gasification parameters, i.e. the type of biomass used and its composition, as well as the composition of the outlet gas, were studied by a multivariate statistical analysis based on principal component analysis (PCA) and partial least square (PLS) regression models in order to identify the main correlations between them and to the contents of methane, ethylene and tar in the outlet gas. In this work, the experimental data used as input for the multivariate statistical analysis came from a TRL-4 gasification plant running under sorption enhanced conditions, i.e. using steam as the gasifying agent and CaO as the bed material. The composition of the biomass feed played an important role in the quality of the outlet gas composition. In fact, biomasses with high ash and sulphur contents (municipal solid waste) increased ethylene content, while those with high-volatile matter content and fixed C content (wood pellets, straw pellets and grape seeds) mainly increased CO and CO2 formation. By increasing the gasification bed temperature and the CaO/C ratio, it was possible to reduce the methane and the collected tar contents in the outlet gas. Other light hydrocarbons could also be reduced by controlling the Treactor and TFB. Methane, ethylene and tar contents were modelled, cross-validated and tested with a new set of samples by PLS obtaining results with an average overall error between 8 and 26%. The statistically significant variables to predict methane and ethylene content were positively associated to the thermal input and negatively to the CaO/C ratio. The biomass composition was also remarkable for both variables, as mentioned in the PCA analysis. As far as the tar content, which is undesirable in all gasification processes, the decrease in the tar content was favoured by high bed temperature, low thermal input and biomass with high-volatile matter content. In order to produce an outlet gas with adequate quality (e.g. low tar content), a compromise should be found to balance average bed temperature, sorbent-to-mass ratio, and ultimate and proximate analyses of the biomass feed.
Graphical abstract
“…Nevertheless, as highlighted by the authors, the models are not able to foresee the tar content in the product gas, resulting in a negative R 2 value. The model proposed et al [55]; ► Hejazi et al [56]; ○ Rameshkumar and Mayilsamy [58]. Dotted and dashed lines correspond with a relative error of 10 and 20 %, respectively.…”
Section: Comparison Of Ann Modelling With Existing Literature Modelsmentioning
“…Kumar et al used FNN to determine optimal operating conditions based on the ultimate analysis data of biomass feedstock (Kumar et al, 2018). Rameshkumar et al trained an ANFIS model to predict the tar content after gasification to improve the syngas quality (Rameshkumar & Mayilsamy, 2014).…”
Section: Applications Of Artificial Intelligence To Bioenergy Systemsmentioning
Bioenergy is widely considered a sustainable alternative to fossil fuels. However, large‐scale applications of biomass‐based energy products are limited due to challenges related to feedstock variability, conversion economics, and supply chain reliability. Artificial intelligence (AI), an emerging concept, has been applied to bioenergy systems in recent decades to address those challenges. This paper reviewed 164 articles published between 2005 and 2019 that applied different AI techniques to bioenergy systems. This review focuses on identifying the unique capabilities of various AI techniques in addressing bioenergy‐related research challenges and improving the performance of bioenergy systems. Specifically, we characterized AI studies by their input variables, output variables, AI techniques, dataset size, and performance. We examined AI applications throughout the life cycle of bioenergy systems. We identified four areas in which AI has been mostly applied, including (1) the prediction of biomass properties, (2) the prediction of process performance of biomass conversion, including different conversion pathways and technologies, (3) the prediction of biofuel properties and the performance of bioenergy end‐use systems, and (4) supply chain modeling and optimization. Based on the review, AI is particularly useful in generating data that are hard to be measured directly, improving traditional models of biomass conversion and biofuel end‐uses, and overcoming the challenges of traditional computing techniques for bioenergy supply chain design and optimization. For future research, efforts are needed to develop standardized and practical procedures for selecting AI techniques and determining training data samples, to enhance data collection, documentation, and sharing across bioenergy‐related areas, and to explore the potential of AI in supporting the sustainable development of bioenergy systems from holistic perspectives.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.