Prediction model of biogas production for anaerobic digestion process of food waste based on LM-BP neural network and particle swarm algorithm optimization

This paper presents a prediction model to predict biogas production for anaerobic digestion process of food waste. There exist sophisticated biogas production models in published literature, but the application of these models in anaerobic digestion process of food waste is often impractical because of its high complexity. Considering the shortcomings of the accuracy of these biogas production prediction models, the BP neural network based on LM algorithm is researched to build biogas production prediction model. The LM algorithm is a combination of gradient descent method and Gauss-Newton method which is a more efficient optimization algorithm. And the Particle Swarm Optimization algorithm (PSO) is introduced to optimize the parameters of the model to get better prediction effect. The results show that the prediction model based on PSO-LM-BP has higher prediction accuracy compared with standard BP neural network.