Artificial neural network modelling approach for a biomass gasification process in fixed bed gasifiers

Mikulandrić, Robert; Lončar, Dražen; Böhning, Dorith; Böhme, Rene; Beckmann, Michael

doi:10.1016/j.enconman.2014.03.036

Cited by 110 publications

(43 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Injection frequency (the time from the last fuel injection) was also calculated to incorporate the dynamic behaviour (delays) of the process (instead of using a dynamic neural network modelling approach). A detailed description of the data analysis and motivation for this particular data analysis approach are presented in [26]. This could be due to different biomass quality, plant ageing, ash agglomeration or due to some other unwanted changes in the gasifier.…”

Section: Gasification Plant and Operating Conditionsmentioning

confidence: 99%

“…Dynamic neural networks with feedforward or recurrent feedback connections are used for systems with large delays like activated sludge processes [20], vapour-compression liquid chillers [21], chemical process systems [22] or energy related prediction processes [23]. Once trained ANN can predict process parameters in circulating and bubbling fluidised bed gasifiers [24], fluidised bed gasifiers with steam as gasifying agent [25] or in fixed bed gasifiers [26] with reasonable speed and accuracy. However, the prediction quality of trained ANN is highly dependent on the quantity and quality of training data related to the process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic modelling of biomass gasification in a co-current fixed bed gasifier

Mikulandrić

Böhning

Böhme

et al. 2016

Energy Conversion and Management

Self Cite

View full text Add to dashboard Cite

Existing technical issues related to biomass gasification process efficiency and environmental standards are preventing the technology to become more economically viable. In order to tackle those issues a lot of attention has been given to biomass gasification process predictive modelling. These models should be robust enough to predict process parameters during variable operating conditions. This could be accomplished either by changes of model input variables or by changes in model structure. This paper analyses the potential of neural network based modelling to predict process parameters during plant operation with variable operating conditions. Dynamic neural network based model for gasification purposes will be developed and its performance will be analysed based on measured data derived from a fixed bed biomass gasification plant operated by Technical University Dresden (TU Dresden). Dynamic neural network can predict process temperature with an average error less than 10% and in those terms performs better than multiple linear regression models. Average prediction error of syngas quality is lower than 30%. Developed model is applicable for online analysis of biomass gasification process under variable operating conditions. The model is automatically modified when new operating conditions occur.

show abstract

Section: Gasification Plant and Operating Conditionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dynamic modelling of biomass gasification in a co-current fixed bed gasifier

Mikulandrić

Böhning

Böhme

et al. 2016

Energy Conversion and Management

Self Cite

View full text Add to dashboard Cite

show abstract

“…Bu noktada dikkat edilmesi gereken en önemli noktalardan birisi de maliyettir; zira adsorpsiyon süreçlerinde kullanılan adsorbentlerin üretimi, süreç maliyetini doğrudan etkileyen önemli faktörlerden biridir. Örneğin; farkı biyokütlelere ait küspe ve kepekler, aktif ve/veya kırmızı çamur ve hatta aktif kömür gibi adsorbentlerin reaktif boyaların sulu çözeltilerden gideriminde kullanıldığı pek çok çalışma ilgili literatürde mevcuttur [14][15][16][17][18]. Bu bağlamda FK'nin bir adsorbent olarak kullanılması hem ilgili literature hem de ülkemiz katma değerine büyük bir katkı sunabilir.…”

Section: Gi̇ri̇ş (Introduction)unclassified

Fındık kabukları ile farklı model boyaların gideriminin kinetik ve termodinamik incelemesi

Büyükada

2019

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Hazelnut shell was found quite effective on removel of different model textile dyes  Adsorption process was controlled by both pseudo second order model and intra particular diffusion  It was determined that adsorption process was of endothermic and spontaneous  Hazelnut shell may be an eco-friendly solution for the treatment of effluents of industrial plants located in Turkey. The present study aimed at the utilization of hazelnut shells as a potential adsorbent for the treatment of synthetically prepared model textile dye solutions. Classical conventional adsorption procedure was followed to investigate the effects of initial dye concentration, adsorbent concentration, reaction time, initial pH, and temperature. The results showed that Langmuir isotherm identified the adsorption process of most of dyes better than Freundlich. Subsequently, kinetic calculations demonstrated that pseudo second order reaction model and intra particular diffusion model controlled the adsorption process for all dyes. Consequently, thermodynamic results showed that the adsorption process spontaneously occurred and it was of endothermic. Figure A. Effect ıf initial dye concentration on removal efficiency (%) Purpose: This study aims at the utilization of hazelnut shell for the treatment of industrial effluents to suggest an eco-friendly adsorbent. Theory and Methods: Classical batch adsorption process was performed to investigate the effects of initial dye concentration, adsorbent concentration, reaction time, initial pH, and temperature on removal efficiency. Results: This part can be divided into three groups as follows: (1) Isotherm studies showed that Langmuir model stated the adsorption process better than Freundlich model; (2) Kinetic studies showed that pseudo second order model and intra particular diffusion controlled the adsorption process; and (3) Thermodynamic studies showed that the adsorption process was of endothermic, spontaneous, and it had an increasing affinity with increasing temperature. Conclusion: Hazelnut shell was found quite effective on removal of synthetic model dye solutions. Given that Turkey has abundant sources of hazelnut, those shells can contribute to solution of problem coming from the industrial effluents.

show abstract

“…ANN have been applied to a number of chemical engineering problems [8]- [12] and even to kinetic model reduction [13], [14]. ANN have also been used in some other aspects of biomass pyrolysis modelling [15]- [18].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Prediction of Pyrolytic Conversion for Red Sea Seaweed

2017

Budapest 2017 International Conferences LEBCSR-17, ALHSSS-17, BCES-17, AET-17, CBMPS-17 &Amp; SACCEE-17

View full text Add to dashboard Cite

The complex and non-linear relationship between kinetic parameters and main biomass components is one of the major problem for model development. The application of non-linear modelling would be interesting to predict the behavior of such a complicated model. The machine learning approaches are widely used in many applications for modelling the non-linear relationship between input and output data. In this study, two machine learning tools, namely, Artificial Neural Network (ANN) and Support Vector Machine (SVM) are investigated in order to develop a prediction model for the pyrolytic conversion of Red Sea seaweed (Sargassum sp.). Pyrolysis of Sargassum sp. was carried out in a thermogravimetric analyzer (TGA) where the samples were nonisothermally heated at 10, 15, 20 and 25°C•min −1 from 40 to 900°C in an inert atmosphere. The obtained mass loss-time and temperature series data sets are used for the training, validation and testing the prediction model with ANN and SVM. The results show that ANN provide better accuracy than SVM. More importantly, higher R 2 and lower error rates renders machine learning based tools as reliable means for forecasting pyrolytic conversion.

show abstract

Artificial neural network modelling approach for a biomass gasification process in fixed bed gasifiers

Cited by 110 publications

References 41 publications

Dynamic modelling of biomass gasification in a co-current fixed bed gasifier

Dynamic modelling of biomass gasification in a co-current fixed bed gasifier

Fındık kabukları ile farklı model boyaların gideriminin kinetik ve termodinamik incelemesi

Machine Learning Based Prediction of Pyrolytic Conversion for Red Sea Seaweed

Contact Info

Product

Resources

About