Fuel cells are promising devices to transform chemical energy into electricity; their behavior is described by principles of electrochemistry and thermodynamics, which are often difficult to model mathematically. One alternative to overcome this issue is the use of modeling methods based on artificial intelligence techniques. In this paper is proposed a hybrid scheme to model and control fuel cell systems using neural networks. Several feature selection algorithms were tested for dimensionality reduction, aiming to eliminate non-significant variables with respect to the control objective. Principal component analysis (PCA) obtained better results than other algorithms. Based on these variables, an inverse neural network model was developed to emulate and control the fuel cell output voltage under transient conditions. The results showed that fuel cell performance does not only depend on the supply of the reactants. A single neuro-proportional–integral–derivative (neuro-PID) controller is not able to stabilize the output voltage without the support of an inverse model control that includes the impact of the other variables on the fuel cell performance. This practical data-driven approach is reliably able to reduce the cost of the control system by the elimination of non-significant measures.

Wastewater treatment (WWT) is a priority around the world; conventional treatments are not widely used in rural areas owing to the high operating and maintenance costs. In Mexico, for instance, only 40% of wastewater is treated. One sustainable option for WWT is through the use of constructed wetlands (CWs) technology, which may remove pollutants using cells filled with porous material and vegetation that works as a natural filter. Knowing the optimal material and density of plants used per square meter in CWs would allow improving their WWT effect. In this study, the effect of material media (plastic/mineral) and plant density on the removal of organic/inorganic pollutants was evaluated. Low (three plants), medium (six plants) and high (nine plants) densities were compared in a surface area of 0.3 m² of ornamental plants (Alpinia purpurata, Canna hybrids and Hedychium coronarium) used in polycultures at the mesocosm level of household wetlands, planted on the two different substrates. Regarding the removal of contaminants, no significant differences were found between substrates (p ≥ 0.05), indicating the use of plastic residues (reusable) is an economical option compared to typical mineral materials. However, differences (p = 0.001) in removal of pollutants were found between different plant densities. For both substrates, the high density planted CWs were able to remove COD in a range of 86–90%, PO₄-P 22–33%, NH₄-N in 84–90%, NO₃-N 25–28% and NO₂-N 38–42%. At medium density, removals of 79–81%, 26–32, 80–82%, 24–26%, and 39–41%, were observed, whereas in CWs with low density, the detected removals were 65–68%, 20–26%, 79–80%, 24–26% and 31–40%, respectively. These results revealed that higher COD and ammonia were removed at high plant density than at medium or low densities. Other pollutants were removed similarly in all plant densities (22–42%), indicating the necessity of hybrid CWs to increase the elimination of PO₄-P, NO₃-N and NO₂-N. Moreover, high density favored 10 to 20% more the removal of pollutants than other plant densities. In addition, in cells with high density of plants and smaller planting distance, the development of new plant shoots was limited. Thus, it is suggested that the appropriate distance for this type of polyculture plants should be from 40 to 50 cm in expansion to real-scale systems in order to take advantage of the harvesting of species in these and allow species of greater foliage, favoring its growth and new shoots with the appropriate distance to compensate, in the short time, the removal of nutrients.

This article describes the use of the electrical conductivity for measuring bed expansion in a continuous anaerobic biofilm reactor in order to prevent the exit of support material from the reactor with the consequent loss of biomass. The substrate used for the tests is obtained from a two-stage anaerobic digestion (AD) process at the pilot scale that treats the liquid fraction of fruit and vegetable waste (FVW). Tests were performed with the raw substrate before anaerobic treatment (S1), the effluent from the hydrolysis reactor (S2), and the effluent from the methanogenic reactor (S3) to evaluate its effect on the electrical conductivity values and its interaction with colonized support material. The tests were carried out in a 32 L anaerobic inverse fluidized bed reactor (IFBR), which was inoculated with colonized support material and using two industrial electrodes at different column positions. The results with the previously digested samples (S2 and S3) were satisfactory to detect the presence of support material at the points where the electrodes were placed since the electrical conductivity values showed significant changes of up to 0.5 V, while with substrate S1 no significant voltage differences were appreciated. These results demonstrate that electrical conductivity can be used as an economic and simple mean for monitoring the support material expansion in order to avoid over expansion in the IFBR. It was also demonstrated that the conditions of the substrate in the methanogenic stage (pH and presence of volatile fatty acids) do not affect the operation of the electrical conductivity detection system.