This article focuses on fuel quality in biomass power plants and describes an online prediction method based on image analysis and regression modeling. The main goal is to determine the mixture fraction from blends of two wood chip species with different qualities and properties. Starting from images of both fuels and different mixtures, we used two different approaches to deduce feature vectors. The first one relied on integral brightness values while the latter used spatial texture information. The features were used as input data for linear and non-linear regression models in nine training classes. This permitted the subsequent prediction of mixture ratios from prior unknown similar images. We extensively discuss the influence of model and image selection, parametrization, the application of boosting algorithms and training strategies. We obtained models featuring predictive accuracies of R² > 0.9 for the brightness-based model and R² > 0.8 for the texture based one during the validation tests. Even when reducing the data used for model training down to two or three mixture classes—which could be necessary or beneficial for the industrial application of our approach—sampling rates of n < 5 were sufficient in order to obtain significant predictions.

Differences in the densities of bed material and—especially biogenic—solid fuels prevent an ideal mixture within bubbling fluidised bed (BFB) combustors. So, the presence of fuel particles is usually observed mainly near the surface of the fluidised bed. During their thermal conversion, this leads to a release of unburnt pyrolysis products to the freeboard of the combustion chamber. Within the further oxidation, these species will not transfer their heat-of-reaction to the inert bed material in the way of a convective heat transfer, but rather increase the gas phase temperature providing probably some additional radiative heat transfer to the dense bed. In this case, the so-called heat release efficiency to the fluidised bed, being the ratio of transferred heat to the fuel input, will be reduced. This paper presents a methodology to quantify this heat release efficiency with lab-scale experiments and the observed effects of common operating parameters like bed temperature, fluidisation ratio and fuel-to-air ratio. Experimental results show that the air-to-fuel ratio dominates the heat release efficiency, while bed temperature and fluidisation ratio have minor influences.

Methods of computational intelligence show a high potential for short-term price forecasting of the energy market as they offer the possibility to cope with the complexity, multi-parameter dependency, and non-linearity of pricing mechanisms. While there is a large number of publications applying neural networks to the prediction of electricity prices, the analysis of natural gas and carbon prices remains scarce. Identifying a best practice from the literature, this study presents an iterative approach to optimize both the input values and network configuration of neural networks. We apply the approach to the natural gas and carbon market, sequentially testing autoregressive and exogenous explanatory variables as well as different neural network architectures. We subsequently discuss the influence of architectural properties, input parameters, data preparation, and the models’ resilience to singular events. Results show that the selection of appropriate lags of gas and carbon prices to account for autoregressive properties of the respective time series leads to a high degree of forecasting accuracy. Additionally, including ambient temperature data can slightly reduce errors of natural gas price forecasting whereas carbon price predictions benefit from electricity prices as a further explanatory input. The best configurations presented in this contribution achieve a root mean square error (RMSE) of 0.64 EUR/MWh (natural gas prices) corresponding to a normalized RMSE of 0.037 and 0.33 EUR/t_CO2 (carbon prices) corresponding to a normalized RMSE of 0.023.