Prediction of biochar yield from cattle manure pyrolysis via least squares support vector machine intelligent approach

• Intelligent approach is applied for predicting cattle manure biochar yield.
• Two intelligent models, ANN model and LS-SVM model, are developed.
• LS-SVM model has a better predicting accuracy and robustness than ANN model.

To predict conveniently the biochar yield from cattle manure pyrolysis, intelligent modeling approach was introduced in this research. A traditional artificial neural networks (ANN) model and a novel least squares support vector machine (LS-SVM) model were developed. For the identification and prediction evaluation of the models, a data set with 33 experimental data was used, which were obtained using a laboratory-scale fixed bed reaction system. The results demonstrated that the intelligent modeling approach is greatly convenient and effective for the prediction of the biochar yield. In particular, the novel LS-SVM model has a more satisfying predicting performance and its robustness is better than the traditional ANN model. The introduction and application of the LS-SVM modeling method gives a successful example, which is a good reference for the modeling study of cattle manure pyrolysis process, even other similar processes.