The Experts below are selected from a list of 3699 Experts worldwide ranked by ideXlab platform

Peter Holubar - One of the best experts on this subject based on the ideXlab platform.

  • Prediction of trace compounds in biogas from anaerobic digestion using the MATLAB Neural Network Toolbox
    Environmental Modelling & Software, 2005
    Co-Authors: David P.b.t.b. Strik, A.m. Domnanovich, L. Zani, Rudolf Braun, Peter Holubar
    Abstract:

    Abstract The outlook to apply the highly energetic biogas from anaerobic digestion into fuel cells will result in a significantly higher electrical efficiency and can contribute to an increase of renewable energy production. The practical bottleneck is the fuel cell poisoning caused by several gaseous trace compounds like hydrogen sulfide and ammonia. Hence artificial Neural Networks were developed to predict these trace compounds. The experiments concluded that ammonia in biogas can indeed be present up to 93 ppm. Hydrogen sulfide and ammonia concentrations in biogas were modelled successfully using the MATLAB Neural Network Toolbox. A script was developed which made it easy to search for the best Neural Network models' input/output-parameters, settings and architectures. The models were predicting the trace compounds, even under dynamical conditions. The resulted determination coefficients ( R 2 ) were for hydrogen sulfide 0.91 and ammonia 0.83. Several model predictive control tool strategies were introduced which showed the potential to foresee, control, reduce or even avoid the presence of the trace compounds.

  • Short Communication Prediction of trace compounds in biogas from anaerobic digestion using the MATLAB Neural Network Toolbox
    2005
    Co-Authors: A.m. Domnanovich, L. Zani, Rudolf Braun, Peter Holubar
    Abstract:

    The outlook to apply the highly energetic biogas from anaerobic digestion into fuel cells will result in a significantly higher electrical efficiency and can contribute to an increase of renewable energy production. The practical bottleneck is the fuel cell poisoning caused by several gaseous trace compounds like hydrogen sulfide and ammonia. Hence artificial Neural Networks were developed to predict these trace compounds. The experiments concluded that ammonia in biogas can indeed be present up to 93 ppm. Hydrogen sulfide and ammonia concentrations in biogas were modelled successfully using the MATLAB Neural Network Toolbox. A script was developed which made it easy to search for the best Neural Network models’ input/output-parameters, settings and architectures. The models were predicting the trace compounds, even under dynamical conditions. The resulted determination coefficients (R 2 ) were for hydrogen sulfide 0.91 and ammonia 0.83. Several model predictive control tool strategies were introduced which showed the potential to foresee, control, reduce or even avoid the presence of the trace compounds.

Yu Zhao - One of the best experts on this subject based on the ideXlab platform.

David P.b.t.b. Strik - One of the best experts on this subject based on the ideXlab platform.

  • Prediction of trace compounds in biogas from anaerobic digestion using the MATLAB Neural Network Toolbox
    Environmental Modelling & Software, 2005
    Co-Authors: David P.b.t.b. Strik, A.m. Domnanovich, L. Zani, Rudolf Braun, Peter Holubar
    Abstract:

    Abstract The outlook to apply the highly energetic biogas from anaerobic digestion into fuel cells will result in a significantly higher electrical efficiency and can contribute to an increase of renewable energy production. The practical bottleneck is the fuel cell poisoning caused by several gaseous trace compounds like hydrogen sulfide and ammonia. Hence artificial Neural Networks were developed to predict these trace compounds. The experiments concluded that ammonia in biogas can indeed be present up to 93 ppm. Hydrogen sulfide and ammonia concentrations in biogas were modelled successfully using the MATLAB Neural Network Toolbox. A script was developed which made it easy to search for the best Neural Network models' input/output-parameters, settings and architectures. The models were predicting the trace compounds, even under dynamical conditions. The resulted determination coefficients ( R 2 ) were for hydrogen sulfide 0.91 and ammonia 0.83. Several model predictive control tool strategies were introduced which showed the potential to foresee, control, reduce or even avoid the presence of the trace compounds.

Wu Jun - One of the best experts on this subject based on the ideXlab platform.

Yanbo Xue - One of the best experts on this subject based on the ideXlab platform.

  • Development of A New Recurrent Neural Network Toolbox (RNN-Tool) ⁄
    2006
    Co-Authors: Le Yang, Yanbo Xue
    Abstract:

    In this report, we developed a new recurrent Neural Network Toolbox, including the recurrent multilayer perceptron structure and its companying extended Kalman fllter based training algorithms: BPTT-GEKF and BPTT-DEKF. Besides, we also constructed programs for designing echo state Network with single reservoir, together with the o†ine linear regression based training algorithm. We name this Toolbox as the RNN-Tool. Within the Toolbox, we implement the RMLP and ESN as MATLAB structures, which are used throughout the processes of Network generation, training and testing. Finally we study a predictive modeling case of a phase-modulated sinusoidal function to test this Toolbox. Simulation results show that ESN can outperform the BPTT-GEKF and BTPP-DEKF methods both on computational load and prediction accuracy.

  • development of a new recurrent Neural Network Toolbox rnn tool
    2006
    Co-Authors: Le Yang, Yanbo Xue
    Abstract:

    In this report, we developed a new recurrent Neural Network Toolbox, including the recurrent multilayer perceptron structure and its companying extended Kalman fllter based training algorithms: BPTT-GEKF and BPTT-DEKF. Besides, we also constructed programs for designing echo state Network with single reservoir, together with the o†ine linear regression based training algorithm. We name this Toolbox as the RNN-Tool. Within the Toolbox, we implement the RMLP and ESN as MATLAB structures, which are used throughout the processes of Network generation, training and testing. Finally we study a predictive modeling case of a phase-modulated sinusoidal function to test this Toolbox. Simulation results show that ESN can outperform the BPTT-GEKF and BTPP-DEKF methods both on computational load and prediction accuracy.