Applied machine learning for prediction of waste plastic pyrolysis towards valuable fuel and chemicals production

Pyrolysis is a suitable conversion technology to address the severe ecological and environmental hurdles caused by waste plastics' ineffective pre- and/or post-user management massive landfilling. By using machine learning (ML) algorithms, present study developed models for predicting products of continuous non-catalytically processes pyrolysis plastics. Along with different input datasets, four including decision tree (DT), artificial neuron network (ANN), support vector (SVM), Gaussian process (GP), were compared select variables most accurate models. Among these DT model exhibited generalisable satisfactory accuracy (R2 > 0.99) training data. The dataset elemental composition plastics achieved better than that plastic-type liquid yields. These observations allow predictions data from ultimate analysis when inaccessible in unknown plastic wastes. Besides, combination also excellent gas predictions.