Artificial Neural Networks(ANNs)have emerged as a powerful tool in combustion simulations to replace memory-intensive tabulation of integrated chemical kinetics.Complex reaction mechanisms,however,present a challenge ...Artificial Neural Networks(ANNs)have emerged as a powerful tool in combustion simulations to replace memory-intensive tabulation of integrated chemical kinetics.Complex reaction mechanisms,however,present a challenge for standard ANN approaches as modeling multiple species typically suffers from inaccurate predictions on minor species.This paper presents a novel ANN approach which can be applied on complex reaction mechanisms in tabular data form,and only involves training a single ANN for a complete reaction mechanism.The approach incorporates a network architecture that automatically conserves mass and employs a particular loss weighting based on species depletion.Both modifications are used to improve the overall ANN performance and individual prediction accuracies,especially for minor species mass fractions.To validate its effectiveness,the approach is compared to standard ANNs in terms of performance and ANN complexity.Four distinct reaction mechanisms(H_(2),C_(7)H_(16),C_(12)H_(26),OME_(34))are used as a test cases,and results demonstrate that considerable improvements can be achieved by applying both modifications.展开更多
Solar radiation influences many and diverse fields like energy generation, agriculture and building operation.Hence, simulation models in these fields often rely on precise information about solar radiation. Measureme...Solar radiation influences many and diverse fields like energy generation, agriculture and building operation.Hence, simulation models in these fields often rely on precise information about solar radiation. Measurementsare often restricted to global irradiance, whereby measurements of its single components, direct and diffuseirradiance, are sparse. However, information on both, the direct and diffuse irradiance, is necessary forsimulation models to work reliably. In this study, solar separation models are developed using 10-min trainingdata from two different locations in Austria. Direct horizontal irradiance is predicted via regressing the directfraction using several objective functions. The models are first trained on a data set including data from bothlocations, and evaluated regarding root mean squared deviation (RMSD), mean bias deviation (MBD), andcoefficient of determination (R2) on measured and estimated direct normal irradiance. The two best performing models are then selected for further analysis. This analysis comprises of an evaluation of the models per season,transferability of trained modes between two locations in Austria, a transferability and generalisability studyconducted for four more locations in Central Europe, and a comparison with the trusted Engerer model. Thesolar separation model with polynomial terms up to order three and Ridge regularisation outperforms thesecond model based a logistic term in combination with mixed quadratic terms as well as the Engerer model.展开更多
文摘Artificial Neural Networks(ANNs)have emerged as a powerful tool in combustion simulations to replace memory-intensive tabulation of integrated chemical kinetics.Complex reaction mechanisms,however,present a challenge for standard ANN approaches as modeling multiple species typically suffers from inaccurate predictions on minor species.This paper presents a novel ANN approach which can be applied on complex reaction mechanisms in tabular data form,and only involves training a single ANN for a complete reaction mechanism.The approach incorporates a network architecture that automatically conserves mass and employs a particular loss weighting based on species depletion.Both modifications are used to improve the overall ANN performance and individual prediction accuracies,especially for minor species mass fractions.To validate its effectiveness,the approach is compared to standard ANNs in terms of performance and ANN complexity.Four distinct reaction mechanisms(H_(2),C_(7)H_(16),C_(12)H_(26),OME_(34))are used as a test cases,and results demonstrate that considerable improvements can be achieved by applying both modifications.
文摘Solar radiation influences many and diverse fields like energy generation, agriculture and building operation.Hence, simulation models in these fields often rely on precise information about solar radiation. Measurementsare often restricted to global irradiance, whereby measurements of its single components, direct and diffuseirradiance, are sparse. However, information on both, the direct and diffuse irradiance, is necessary forsimulation models to work reliably. In this study, solar separation models are developed using 10-min trainingdata from two different locations in Austria. Direct horizontal irradiance is predicted via regressing the directfraction using several objective functions. The models are first trained on a data set including data from bothlocations, and evaluated regarding root mean squared deviation (RMSD), mean bias deviation (MBD), andcoefficient of determination (R2) on measured and estimated direct normal irradiance. The two best performing models are then selected for further analysis. This analysis comprises of an evaluation of the models per season,transferability of trained modes between two locations in Austria, a transferability and generalisability studyconducted for four more locations in Central Europe, and a comparison with the trusted Engerer model. Thesolar separation model with polynomial terms up to order three and Ridge regularisation outperforms thesecond model based a logistic term in combination with mixed quadratic terms as well as the Engerer model.
