Integrating Taguchi method and artificial neural network for predicting and maximizing biofuel production via torrefaction and pyrolysis

Artificial neural network (ANN) is one kind of artificial intelligence in the computing system that aims to process information as the way neurons in the human brain. In this study, the combination of the Taguchi method and ANN are used to maximize and predict biofuel yield from spent mushroom substrate torrefaction and pyrolysis via microwave irradiation. The Taguchi method is utilized to design the multiple factors (particle size, catalyst, power, and magnetic agent) and levels of experiment parameters. The highest total biofuel yield (biochar + bio-oil) is 99.42%, accomplished by a combination of 355 mn particle size, 300 mg.g-SMS(-1 )catalyst, 900 W power, and 300 mg.g-SMS-1 magnetic agent. ANN with one hidden layer shows the outstanding linear regression predictions for the highest biofuel yields (biochar 0.9999 and bio-oil 0.9998). This high linear regression indicates that ANN with a quick propagation algorithm is an appropriate approach for predicting biofuel conversion.

Automated summary

In this study, a combination of the Taguchi method and ANN was used to optimize and predict biofuel yield from spent mushroom substrate torrefaction and pyrolysis. By designing experiment parameters, the highest total biofuel yield was achieved and showed outstanding linear regression predictions for the highest biofuel yields. The high linear regression indicates that ANN with a quick propagation algorithm is an appropriate approach for predicting biofuel conversion.