Achieving effective control of parameters in the process of nitrate wastewater treatment is critical to electrochemical water treatment. The powerful nonlinear mapping ability, self-adaptation and self-learning ability of neural network technology can optimize the electrochemical processing. However, there are few researches in this direction. Hence, based on the test data of the electrochemical reduction of nitrate, an electrochemical prediction model was established by using the BP neural network algorithm. Considering the correlation of various parameters in the electrochemical process, the reaction time, initial nitrate nitrogen concentration, pH and current density were determined as the input layer of the BP neural network for model establishment. Results showed that the optimal network configuration of 4-7-1 was achieved by optimizing the hyperparameters of hidden layers number, and the numbers of neurons and epochs. The predicted value of nitrate nitrogen concentration was consistent with the measured value, and the R² value of 0.9095 was obtained. Meanwhile, the model predicts the effects of initial concentration, pH and current density on the removal efficiency of nitrate nitrogen. In the weak alkaline environment, the stability and reliability of nitrate electroreduction were higher than those in acidic and alkaline environments, and the predicted value of nitrate nitrogen is highly correlated to the true value (R²=0.9908). The initial concentration was negatively correlated to the removal rate, while the current density was positively correlated. Finally, the neural network model was used to control the electrochemical nitrate reduction process. Energy consumption tests were designed by optimizing current density, and 15% reduction energy consumption was obtained within the same processing time and processing efficiency. Also, through the prediction model, the effluent quality can be guaranteed by timely adjusting the parameter in the case of sudden water quality changes. The research results can provide a reference for the intelligent control in the electrochemical removal of nitrate. At the same time, combining the understanding of the electrochemical treatment system and artificial intelligence technology, several ideas are proposed for the application of artificial intelligence technology in the field of electrochemical water treatment.

Modification of electrode is vitally important for achieving high energy efficiency in aqueous quinone-based redox flow batteries (AQRFBs). The modification of graphite felt (GF) was carried out by means of urea hydrothermal reaction, and simultaneously, the effects of hydrothermal reaction time on the functional groups and surface structure of nitrogen-doped graphite felt were studied. The surface morphology and defect, element content and surface chemical state of the modified electrode were characterized by scanning electron microscopy (SEM), Brunauer-Emmett-Teller (BET) test, Raman spectroscopy, and X-ray photoelectron spectroscopy (XPS). The electrochemical performance of the modified electrodes was evaluated by cyclic voltammetry, electrochemical impedance spectroscopy and single cell test. These results indicate that the specific surface area, hydrophilicity and conductivity of GF have been improved by nitrogen doping. The nitrogen-doped graphite felt (NGF) demonstrates an outstanding electrochemical catalytic activity and less charge transfer resistance. With the NGF, the battery exhibited 8.0% increase in the energy efficiency of aqueous quinone redox flow batteries at 100 mA·cm^-2.

Solid oxide electrolysis cell (SOEC) is an efficient and clean energy conversion technology that can utilize electricity obtained from renewable resources, such as solar, wind, and geothermal energy to electrolyze water and produce hydrogen. The conversion of abundant intermittent energy to hydrogen energy would facilitate the efficient utilization of energy resources. SOEC is an all-ceramic electrochemical cell that operates in the intermediate to high temperature range of 500-750 °C. Compared with traditional low temperature electrolysis technology (e.g., alkaline or proton exchange membrane cells operating at ~100 °C), the high-temperature SOEC can increase the electrolysis efficiency from 80% to ~100%, providing a new way for energy saving.

The SOEC single cells with the nickel (Ni)-yttira-stabilized zirconia (YSZ) fuel electrode supported configuration have received most intensive research effort. This is due to the high catalytic activity and electronic conductivity of Ni, as well as good oxygen ionic conductivity of YSZ, promoting the electrochemical reduction of steam in fuel electrode. However, under the high steam partial pressures, the Ni in the electrode could be occasionally oxidized NiO at the high operation temperature, leading to volume expansion of the supporting layer. This phenomenon would induce internal stress in cell functional layers, resulting in cracking or even failure of the single cell.

To address the above mentioned issues, we propose a porous YSZ supported tubular single cell with a configuration of porous YSZ support, Ni-YSZ fuel electrode current collector, Ni-YSZ fuel electrode electrochemical functional layer, YSZ/Ce_0.8Sm_0.2O_1.9 bi-layer electrolyte, and La_0.6Sr_0.4Co_0.2Fe_0.8O_3-δ air electrode. As the porous YSZ substrate exhibits high chemical and structural stabilities in a wide range of oxygen and steam partial pressures under the SOEC operating conditions, employing the porous YSZ as the single cell support is expected to improve mechanical stability of the whole single cell. In this work, the porous YSZ supported tubular electrolysis cell has been fabricated by extrusion and dip-coating technique. The porosity, pore size and mechanical property of the YSZ support were investigated with respect to the amount of polymethyl methacrylate (PMMA) pore former. At the PMMA amount of 25wt.%, the porous YSZ support showed the optimum porosity of 40%-45% and good bending strength of ~20 MPa. Electrochemical performance of the single cell for steam electrolysis has been characterized under the H₂O-H₂ co-feeding condition. At the operation temperature of 750 °C, the H₂ production rate reached 3 mL·min^-1·cm^-2 and the cell maintained 95% of its initial performance during 10 thermal cycles, demonstrating the feasibility of the novel porous YSZ supported tubular cell design for solid oxide electrolysis cell.

The solid-electrolyte interphase (SEI) plays a key role in anodes for rechargeable lithium-based battery technologies. However, a thorough understanding in the mechanisms of SEI formation and evolution remains a major challenge, hindering the rapid development and wide applications of Li-based batteries. Here, we devise a borrowing surface-enhanced Raman scattering (SERS) activity strategy by utilizing a size optimized Ag nanosubstrate to in-situ monitor the formation and evolution of SEI, as well as its structure and chemistry in an ethylene carbonate-based electrolyte. To ensure a reliable in-situ SERS investigation, we designed a strict air-tight Raman cell with a three-electrode configuration. Based on the potential-dependent spectroscopic information, we revealed that the SEI formed in an EC-based electrolyte presents a double-layer structure, comprising a thin inorganic inner layer and an organic-rich outer layer. We also identified that LEMC, rather than LEDC, is the major component of EC reduction, and the critical role of metallic Li in the formation of stable SEI is preliminary explored. Nevertheless, identifying the SEI compositions is only feasible before Li deposition on the Ag surface. After the formation of Li-Ag alloys, the subsequent evolution of SEI could not be detected due to the change in the dielectric constant of Ag after the lithiation. Our work provides a real-time spectroscopic method for investigating interfacial processes of anodes, which is beneficial to the understanding of SEI formation and evolution and thus provides guidance for the development of rationally designed SEI in Li-based batteries.