ANN coupled with Monte Carlo simulation for predicting the concentration of acids

Highlights: • The ANN model was trained by the simulation data and was validated by the experimental data. • The trained ANN model is capable of accurately predicting the percentage concentration of acids. • The relative deviations between predicted and reference concentrations are under 3.5% for all investigated samples. The present study proposes a new approach for determining the concentration of acids. The method is based on the combination of Monte Carlo simulation and artificial neural network (ANN) technique for predicting the concentration of acids. Firstly, a Monte Carlo simulation model is validated based on the comparison of simulation data with experimental data. Then, the whole data derived from the Monte Carlo simulation using the MCNP code was used to train the ANN model. The trained ANN model was used to predict the percentage concentrations of 14 acid samples, which yields the maximum relative deviation between the predicted and the reference concentrations is less than 3.5%.