A Dynamic Recurrent Neural Network for Predicting Higher Heating Value of Biomass

The higher heating value (HHV) is the main property showing the energy amount of biomass samples. Several linear correlations based on either the proximate or the ultimate analysis have already been proposed for predicting biomass HHV. Since the HHV relationship with the proximate and ultimate analyses is not linear, nonlinear models might be a better alternative. Accordingly, this study employed the Elman recurrent neural network (ENN) to anticipate the HHV of different biomass samples from both the ultimate and proximate compositional analyses as the model inputs. The number of hidden neurons and the training algorithm were determined in such a way that the ENN model showed the highest prediction and generalization accuracy. The single hidden layer ENN with only four nodes, trained by the Levenberg–Marquardt algorithm, was identified as the most accurate model. The proposed ENN exhibited reliable prediction and generalization performance for estimating 532 experimental HHVs with a low mean absolute error of 0.67 and a mean square error of 0.96. In addition, the proposed ENN model provides a ground to clearly understand the dependency of the HHV on the fixed carbon, volatile matter, ash, carbon, hydrogen, nitrogen, oxygen, and sulfur content of biomass feedstocks.

Thermodynamic Characteristics Study with Pyrolysis Steam Coupled Multi-Stage Condensers

A four-stage condensers in series system was adopted to solve the problems of insufficient condensation of high-temperature pyrolysis steam and difficulty in the classification and recovery of pyrolysis oil, where the internal fluids conducted countercurrent convection heat exchange. A steady-state physical and mathematical model of a single condenser was established to clarify the discipline of heat transfer between the internal fluids. Meanwhile, the model of pyrolysis steam coupled multi-stage condensers was proposed with the help of the model compound firstly. A numerical simulation was carried out and the results showed that when the number of condensers in series was four, the heat transfer process of the system reached saturation, and the heat exchange of the cold and hot fluids was completely realized, and it was of little significance to continue to connect more condensers in series for the condensation of pyrolysis steam. To quickly condense the hot fluid, the key was to increase the mass flow rate of the cold fluid in the first-stage condenser. Compared with the experimental values, the calculated values of hot fluid outlet temperature were not higher than 10%, indicating that the model was highly reliable.