A Review of Enhancement of Biohydrogen Productions by Chemical Addition Using a Supervised Machine Learning Method

Abstract

In this work, the impact of chemical additions, especially nano-particles (NPs), was quantitatively analyzed using our constructed artificial neural networks (ANNs)-response surface methodology (RSM) algorithm. Fe-based and Ni-based NPs and ions, including Mg2+, Cu2+, Na+, NH4+, and K+, behave differently towards the response of hydrogen yield (HY) and hydrogen evolution rate (HER). Manipulating the size and concentration of NPs was found to be effective in enhancing the HY for Fe-based NPs and ions, but not for Ni-based NPs and ions. An optimal range of particle size (86–120 nm) and Ni-ion/NP concentration (81–120 mg L−1) existed for HER. Meanwhile, the manipulation of the size and concentration of NPs was found to be ineffective for both iron and nickel for the improvement of HER. In fact, the variation in size of NPs for the enhancement of HY and HER demonstrated an appreciable difference. The smaller (less than 42 nm) NPs were found to definitely improve the HY, whereas for the HER, the relatively bigger size of NPs (40–50 nm) seemed to significantly increase the H2 evolution rate. It was also found that the variations in the concentration of the investigated ions only statistically influenced the HER, not the HY. The level of response (the enhanced HER) towards inputs was underpinned and the order of significance towards HER was identified as the following: Na+ > Mg2+ > Cu2+ > NH4+ > K+.

Keywords

• biohydrogen (BioH₂)
• nanoparticles
• quantitative assessment
• artificial neuron networks
• process intensifications