Artificial neural networks (ANNs) and Brute Force algorithms (BF) are two of the most common and simplest techniques for modeling non-linear problems and linear search for an element. Very large data sets are actually compiled and fed into the ANN. An algorithm is run that iteratively makes billions of small adjustments to the weights and biases of millions of nodes. In this paper pilot-scale fermentation tests are carried out with mixtures of sewage sludge and food residues to investigate different process parameters that influence fermentation yields. A machine learning approach is used for data management and the development of a model capable of correlating process performance based on different inputs (operating parameters). To simulate the digester operation and estimate the Volatile Fatty Acid (VFA) outputs, a multi-layer ANN model with two hidden layers is developed. The ANN and BF are used to simulate and optimize the VFA from anaerobic digestion.
