Performance Of Polymer Electrolyte Membrane Research Articles

Study on the effect mechanism of functional graphene oxide on the performance of polymer electrolyte membrane for fuel cells

In this paper, amino-phosphate bifunctionalized graphene oxide (PA-GO) was successfully synthesized by amination reaction of graphene oxide followed by acid modification with hypophosphorous acid. A series of composite proton exchange membranes were successfully prepared by adding modified GO to sulfonated poly (aryl ether ketone sulfone) matrices containing carboxyl groups (C-SPAEKS). The prepared composite membranes were performed by a series of tests. The C-SPAEKS@1%PA-GO had the best performance, which was able to achieve the tensile strength of 42 MPa while possessing the high proton conductivity of 128.23 mS cm−1 at 80 °C. In addition, the peak power density of C-SPAEKS@1%PA-GO reached 677.67 mW cm−2 at a current density of 2082.8 mA cm−2, which was almost four times that of the pure membrane (166 mW cm−2). And after 44 h at a constant current density of 0.1 A cm−2, the C-SPAEKS@1%PA-GO membrane could still maintain 54.1 % of the original voltage. It can be seen that our work has achieved certain results, and the functionalized modification of graphene oxide could greatly improve the comprehensive performance of proton exchange membranes (PEMs).

Acid-Doping Induced Phase Separation for Shaping Phase Morphology and Enhancing Performance of Polymer Electrolyte Membranes

Acid-Doping Induced Phase Separation for Shaping Phase Morphology and Enhancing Performance of Polymer Electrolyte Membranes

Experimental investigation on the effect of channel geometry on performance heterogeneity in hydrogen PEM fuel cell

Straight parallel graphite-based flow fields are experimentally assessed to evaluate the effect of geometrical parameters on the performance of polymer electrolyte membrane fuel cell. A 1+1D fuel cell model is exploited to evaluate the local operating conditions occurring along various positions of the flow field channel for different load requirements. The estimated operating conditions are implemented in a zero-gradient hardware to perform a broad experimental campaign, conducting tests under controlled and uniform operating conditions. The achieved experimental results depict the impact of the flow field geometry along different positions of the flow field channel under real operating conditions, identifying the individual contributions of the geometric parameters on water transport, oxygen transport and electrical resistance. The proposed methodology provides detailed information on the local operation of a large-area bipolar plate using a small-area sample, demonstrating the effect of rib and channel geometrical parameters on real-world operation of a PEMFC.

Investigating the Role of Flow Plate Surface Roughness in Polymer Electrolyte Membrane Fuel Cells with the Use of Multiphysics Simulations

This study investigates the influence of surface roughness on the performance of polymer electrolyte membrane fuel cells (PEMFCs) through computational simulations using COMSOL Multiphysics. Two distinct gas flow channel (GFC) models of serpentine and parallel GFC structures were analysed, featuring various surface roughness levels to examine their impact on gas pressure and velocity dynamics. Rough surfaces are modeled using trigonometric functions to replicate machining-induced variations. Finite element simulations were conducted, assessing the time-dependent relationship between gas pressure and velocity while considering different electrode phase potentials as a function of surface roughness. Rough surfaces generally enhance mass transport, water management, and current distribution compared to smooth surfaces. The results indicated that a surface roughness of approximately 1 µm optimizes PEMFC performance by balancing pressure and velocity, enhancing electrochemical reactions, and reducing excessive pressure drops within the cell. Notably, the 0.7 V operating voltage was found to be the most efficient, achieving rapid stabilization of pressure and velocity levels swiftly. The findings underscore the importance of precise control over GFC roughness to enhance PEMFC performance gains in commercial applications, especially when multiple cells are stacked to achieve high power outputs.

Study on the Application Performance of Polymer Electrolyte Membrane Functionalized with Triethyl Phosphite-Modified Graphene Oxide in Fuel Cells.

In this paper, we successfully synthesize phosphoric acid functionalized graphene oxide (PGO) based on acid modification of graphene oxide. The composite membrane is further prepared by adding PGO into sulfonated poly(aryl ether ketone sulfone) containing carboxyl groups matrix (C-SPAEKS). The PGO as well as the composite membranes were characterized by a series of tests. The prepared composite proton exchange membranes (PEMs) have good mechanical and electrochemical properties. Compared to the C-SPAEKS membrane, the best composite membrane has a tensile strength of 40.7 MPa while exhibiting superior proton conductivity (110.17 mS cm-1 at 80 °C). In addition, the open-circuit voltage and power density of C-SPAEKS@1% PGO are 0.918 V and 792.17 mW cm-2, respectively. Compared with C-SPAEKS (0.867 V and 166 mW cm-2), it can be seen that our work has a certain effect on the improvement of the single cell performance. The above results demonstrate that the functionalized graphene oxide has greatly improved the electrochemical performance and even the overall performance of PEMs.

Humidity impact on polarization dynamics in polymer electrolyte membrane fuel cells through distribution of relaxation times analysis

The interaction among relative humidity, current density, and internal polarization plays a crucial role in optimizing the performance of polymer electrolyte membrane fuel cells (PEMFCs). However, achieving swift analysis and feedback on the internal humidity status of PEMFCs through on-vehicle impedance spectroscopy measurements remains a significant challenge. Conducting a series of impedance spectra under operating conditions of 30 %, 50 %, and 80 % relative humidity sheds light on the impact of humidity on performance. Correlations between specific distribution of relaxation times (DRT) peaks and internal polarization are established. Through DRT analysis, four polarization dynamics related to proton transfer at the proton exchange membrane interface, proton transport in the cathode catalyst layer, charge transfer, and the oxygen diffusion process are effectively identified based on characteristic frequencies and peaks. The rate-determining step of the polarization varies under idling, rated, and overload conditions, providing valuable insights. This study contributes analytical models and strategic guidance for tailoring relative humidity conditions to mitigate polarization, thereby enabling real-time control and enhancement of PEMFC performance.

Conduction mechanism analysis and modeling of different gas diffusion layers for PEMFC to improve their bulk conductivities via microstructure design

Increasing the conductivity of gas diffusion layers (GDLs) is an important way to improve the output performance of polymer electrolyte membrane fuel cells (PEMFCs). However, the complex porous fiber structures of GDLs significantly enhances the difficulty of quantitatively altering their conductivity which is determined by the carbon fibers and the conduction characteristics between fibers. In addition, the microstructures of various types of GDLs are different. Thus, it is a considerable challenge to explore the conductive mechanisms of these porous materials and optimize their structures to reduce their bulk resistances. In this work, a mathematical graph theory model that applies to the through-plane (T-P) bulk resistance prediction of two types of commonly used GDLs, carbon paper and carbon felt, is established to explain their different micro conduction mechanisms in depth. In addition to the number of fiber contact points, their distribution, as well as the resistance of the carbon fibers, are all important factors affecting the T-P conductivity. Optimizing fiber density and fiber diameter can significantly improve the T-P conductivity of carbon paper. In comparison, making the structure of carbon felt more compact so that the distribution of its contact points in the T-P direction can be more uniform will be more effective for the reduction of its T-P bulk resistance. Meanwhile, the T-P bulk resistance of carbon paper can also be effectively improved by optimizing the content and distribution of the binders. A method to decline the bulk resistance of carbon paper by aggregating the binders in the in-plane (IP) direction is proposed. The simulation results show that it can reduce the T-P bulk resistance of carbon paper by about 19.9% at a compressive stress of 1.5 MPa. This study provides further guidance for optimizing the structural designs of GDLs to optimize their conduction performance.

Effects of cathode gas diffusion layer porosity and contact angle distributions along through-plane direction on the performance of polymer electrolyte membrane fuel cell

In the present work, a numerical model for polymer electrolyte membrane fuel cell (PEMFC) has been employed to investigate the effects of porosity and contact angle distributions of the porous layer on the performance of PEMFC. The three-dimensional, two-phase, and non-isothermal flow solver considers heat transfer, electrochemical reaction, and liquid water saturation. Various cases with different cathode gas diffusion layer (GDL) porosities are performed. The results showed that a better performance is achieved when the GDL porosity is increased because of the reduced mass transport resistance of oxygen. The effects of the porosity distributions on the PEMFC performance were examined by comparing the predictions from the cases with non-uniform porosity and uniform porosity in the cathode GDL. It was shown that the current density of the cases with non-uniform porosity is higher than that of the uniform porosity case when the operation voltage is low. This is due to the fact that non-uniform porosity distributions in the cathode GDL enhance the reactant transport. When the operation voltage is high, the current densities of the cases with non-uniform porosity and uniform porosity are almost the same. Moreover, the influence of contact angle distributions in cathode GDL was explored. Various cases with gradient-decreasing, gradient-increasing, and uniform constant contact angles from GDL/channel interface to GDL/catalyst layer interface were studied. It was found that the case with gradient-increasing contact angle has a better performance due to the larger capillary pressure difference to remove more water. The poor performance of the case with gradient-decreasing contact angle is related to the phenomenon of flooding in the catalyst layer.

Structural optimization study on porous transport layers of sintered titanium for polymer electrolyte membrane electrolyzers

An effective way to improve the performance of polymer electrolyte membrane (PEM) electrolyzers is to optimize the structural design of porous transport layers. This paper uses mirco-computed tomography (μ-CT) to study the three-dimensional microstructure distribution characteristics of commercial sintered titanium powder-based porous transport layers (PTL). A three-dimensional PTLs model with different porosity, pore diameter and thickness was established by Stochastic reconstruction model method. In addition, lattice Boltzmann method is used to study the influence of PTL structural parameters and single-phase permeability. The results show that the large compression thickness not only can significantly improve the PTL single-phase permeability, but also has little effect on the interface contact area. In addition, an increase in pore size and porosity will increase the transport performance while reducing interface contact. It is recommended that the average pore size of PTL should be greater than 10 μm, and the porosity should be greater than 30%. This work can be used to guide the preparation technology of PTL in order to improve the performance of PEM electrolyzer.

Air Mass Flow and Pressure Optimization of a PEM Fuel Cell Hybrid System for a Forklift Application

The air compressor holds paramount importance due to its significant energy consumption when compared to other Balance of Plant components of polymer electrolyte membrane (PEM) fuel cells. The air supply system, in turn, plays a critical role in ensuring the stable and efficient operation of the entire fuel cell system. To enhance system efficiency, the impact of varying the stoichiometric ratio of air and air pressure was observed. This investigation was carried out under real loading conditions, replicating the conditions experienced by the power module when fuel cells are in use within a forklift. The air compressor can be operated at different pressure and excess air ratios, which in turn influence both the fuel cell’s performance and the overall efficiency of the power module system. Our research focused on assessing the performance of PEM fuel cells under different load cycles, adhering to the VDI60 requirements for forklift applications. This comprehensive examination encompassed the system’s minimum and maximum load scenarios, with the primary goal of optimizing excess air and pressure ratio parameters, especially under dynamic load conditions. The results revealed that higher air pressures and lower excess air ratios were conducive to increasing system efficiency, shedding light on potential avenues for enhancing the performance of PEM fuel cell systems in forklift applications.

Impedance Study of the Effect of Cell Compression on PEMFC Under Various Oxygen Supply Conditions

Cell compression impacts the performance of polymer electrolyte membrane fuel cells (PEMFCs). A previous study has reported a trade-off between mass transport and contact resistances from cell compression [1]. Our study focuses on how the compression pressure affects polarization resistance under various oxygen partial pressure conditions. Without hot pressing the gas diffusion layers, a membrane electrode assembly with an electrode area of 1 cm2 was set in a housing in which the compression pressure could be adjusted [2]. Impedance spectra were measured at 0.7 A/cm2 under various oxygen partial pressure conditions. Figure 1 shows that polarization resistance decreases with increasing compression pressure under low compression pressure conditions, and conversely increases under high compression pressure conditions. The change in polarization resistance is more pronounced under low oxygen partial pressure conditions. In this contribution, the effect of cell compression on the different polarization processes will be discussed, considering the impact of compression pressure on catalyst layer thickness and porosity.

A Numerical Assessment of Mitigation Strategies to Reduce Local Oxygen and Proton Transport Resistances in Polymer Electrolyte Fuel Cells

The optimized design of the catalyst layer (CL) plays a vital role in improving the performance of polymer electrolyte membrane fuel cells (PEMFCs). The need to improve transport and catalyst activity is especially important at low Pt loading, where local oxygen and ionic transport resistances decrease the performance due to an inevitable reduction in active catalyst sites. In this work, local oxygen and ionic transport are analyzed using direct numerical simulation on virtually reconstructed microstructures. Four morphologies are examined: (i) heterogeneous, (ii) uniform, (iii) uniform vertically-aligned, and (iv) meso-porous ionomer distributions. The results show that the local oxygen transport resistance can be significantly reduced, while maintaining good ionic conductivity, through the design of high porosity CLs (ε≃ 0.6–0.7) with low agglomerated ionomer morphologies. Ionomer coalescence into thick films can be effectively mitigated by increasing the uniformity of thin films and reducing the tortuosity of ionomer distribution (e.g., good ionomer interconnection in supports with a vertical arrangement). The local oxygen resistance can be further decreased by the use of blended ionomers with enhanced oxygen permeability and meso-porous ionomers with oxygen transport routes in both water and ionomer. In summary, achieving high performance at low Pt loading in next-generation CLs must be accomplished through a combination of high porosity, uniform and low tortuosity ionomer distribution, and oxygen transport through activated water.

Contribution of zeolitic imidazolate framework-8 in improving the performance of polymer electrolyte membrane for direct methanol fuel cell

Introducing ZIF-8 into the PES-cSMM membranes played a pivotal role in the development of proton-conducting pathways and an effective methanol barrier. We employed dry-wet phase inversion techniques to fabricate PES-cSMM, finding that a 3 wt% cSMM content yielded optimal results. The resulting PES-cSMM exhibits impressive performance, with a 38% higher selectivity and a 95% greater methanol barrier compared to Nafion® 117. The imidazole-N-H linker in the terminal PES-cSMM/ZIF-8 promotes proton transport through a hydrogen bond chain, while the hydrophobic backbone acts as an effective methanol filter. As a result, PES-cSMM/ZIF-8 boasts a 13-fold higher water uptake than Nafion® 117 and achieves a 99% improvement in methanol sieving performance, a highly promising breakthrough for DMFC systems. Proton conductivity for the PES-cSMM/ZIF-8 immersion membrane reaches 19.5 × 10-3 Scm-1, comparable to Nafion® 117, which is 20.4 × 10-3 Scm-1. The structural flexibility of ZIF-8 within PES-cSMM facilitates efficient proton conduction, while the ZIF-8 cage acts as a robust methanol barrier. Computational analysis revealed covalent bonding within the PES-cSMM system. We characterized the chemical interactions in PES-cSMM/ZIF-8 using topology analysis, specifically the Atom in Molecules/Non-covalent analysis (AIM/NCI) technique.

Density functional theory investigation of the role of Fe doped in boron carbide nanotube as an electro-catalyst for oxygen reduction reaction in fuel cells

A critical issue in enhancing the performance of polymer electrolyte membrane fuel cells (FCs) is the slow kinetics of the cathodic oxygen reduction reaction (ORR). The development of electrocatalysts with selectivity toward the four-electron (4e) pathway and high electrochemical activity to ORR reaction is important for fuel cell applications. Within the present study, it was found that boron carbide nanotube (BC3NT) is an encouraging ORR-EC based on density functional theory computations. In the pristine BC3NT, the neighboring B atoms with positive charges on the surface of the material surface were incapable of providing active sites for the dissociation of O. However, the ORR catalytic activity of BC3NT improved under the ligand effect due to the replacement of Fe atom, where there was a slight over-potential that was similar or lower than that of platinum (111), which demonstrated its superior ORR activity. The results suggest that BC-based materials are considered promising for ORR catalysis and for designing highly efficient ORR-ECs as alternatives to platinum-based catalysts.

Adsorption/Desorption Behaviors of Sulfur Species at Pt Single Crystal Surfaces

Platinum is an excellent electrocatalyst for polymer electrolyte membrane (PEM) fuel cells because it drives hydrogen oxidation and oxygen reduction with very high efficiency. However, when sulfur species contained as a trace amount of impurity in hydrogen fuel and/or pollutant in air adsorb on platinum surfaces, power output significantly decrease because of reduced electrochemically active surface area. Such negative effect caused by the adsorption of sulfur species, so-called sulfur poisoning, is a serious problem because interaction between sulfur species and platinum surfaces is very strong. Thus, understanding and control of adsorption behavior of sulfur species at platinum surfaces are very important to maintain the cell performance of PEM fuel cells. In the present study, adsorption/desorption behaviors of sulfur species at well-defined platinum single crystal surfaces in acidic aqueous solutions are studied by electrochemical measurements, x-ray photoelectron spectroscopy (XPS), and surface x-ray diffraction (SXRD).Prior to each experiment, platinum single crystal surfaces were annealed by induction heating method [1, 2, 3] at 1600°C more than 1 h under the flowing of Ar and H2 mixed gas, followed by cooling under the Ar and H2 flow for 7 min. The surface was immersed in a 1 mM Na2S aqueous solution saturated with Ar and H2 mixed gas, for 1 h. After rinsing with ultrapure water, electrochemical measurements were carried out in an aqueous solution of 0.1 M HClO4 or H2SO4 deaerated with pure N2 gas.At the bare Pt(111) surface, characteristic current responses such as adsorption/desorption of hydrogen and hydroxyl group were observed. After immersing in the sulfur-containing solution, however, those characteristic current responses disappeared, confirming the adsorption of sulfur species and decrease of electrochemically active surface area. XPS in the S 2p region of the Pt(111) surface immersed in the sulfur-containing solution showed three major adsorbed species; adsorbed hydrosulfide ion (Pt-HS- ad) at 161.8 eV, adsorbed sulfur (Pt-Sad) at162.7 eV, and adsorbed polysulfide (Pt-Sn) at 164.3 eV. While Pt-HS- ad reductively desorbed from the surface by the potential sweeping up to -0.2 V vs. Ag/AgCl, Pt-Sad and Pt-Sn oxidatively desorbed by the potential sweeping up to the potential more positive than 0.7 V vs. Ag/AgCl. SXRD showed that the sulfur species adsorbed at the Pt(111) surface in the (√3×√3)R30° structure.At the Pt(100) surface, the oxidative desorption of sulfur species occurred at more positive potential than that at the Pt(111) surface. This indicates that the recovery from sulfur poisoning at the Pt(100) surface is more difficult than that at the Pt(111) surface. Unlike the Pt(111)-(√3×√3)R30° structure, SXRD showed that the sulfur species adsorbed at the Pt(100) surface in the (√2×√2)R45° structure. While the sulfur species occupies a three-fold hollow site of the Pt(111)-(√3×√3)R30° structure, it occupies a four-fold hollow site of the Pt(100)-(√2×√2)R45° structure. The different coordination number of adsorbed sulfur species is considered as the origin of different oxidative desorption behaviors.

A parametric numerical study on the performance of polymer electrolyte membrane fuel cell with intermediate‐blocked interdigitated flow field designs

AbstractFlow field design is crucial for achieving higher performance in polymer electrolyte membrane fuel cells (PEMFCs). This study uses a two‐phase, multi‐component, and three‐dimensional model to simulate the performance of PEMFCs that use interdigitated flow field design with intermediate blocks on the cathode side. A detailed parametric study is presented to investigate the effects of various geometric and operational parameters. Of the parameters studied, inlet mass flow rate, relative humidity, and rib width had the greatest impact on cell performance. The results show that increasing the cathode stoichiometric ratio resulted in higher fuel cell performance for blocked interdigitated designs compared to parallel designs. In addition, using cathode channels with higher height values resulted in lower PEMFC performance for all flow fields. Higher values of rib/channel width ratio resulted in lower cell performance due to liquid water accumulation in the rib regions. However, at higher rib/channel width ratios, the positive effect of using interdigitated flow designs was more pronounced. Moreover, at a low relative humidity of RH = 25%, a 10.4% higher performance was obtained for the interdigitated type II compared to cases with RH = 100%, due to more effective over‐rib convection and higher water removal.

Modified polymer electrolyte membrane for microbial fuel cell: Performance analysis, investigation on anti-biofouling effect, and microbial community analysis on biofouled membrane

Sulphonation is limited in Sulphonated Polyether Ether Ketone (SPEEK) due to its solubility in water beyond an extent. However, to enhance performance of polymer electrolyte membrane (PEM) in microbial fuel cell (MFC), more functional groups are required. To facilitate effective proton transfer, styrene sulphonic acid (SSA) is grafted onto SPEEK, resulting in SPEEK/SSA, to increase the number of functional groups. Based on membrane properties, 5 wt% SSA is found to be the optimum grafting for further filler addition. Copper oxide doped reduced graphene oxide (CuO@rGO) is used as membrane filler at various concentrations to enhance anti-biofouling effect. Swelling is excessive in SPEEK/SSA (30.2%), whereas it is only 17.3% in SPEEK/SSA+1.5 wt%CuO@rGO. As evidenced by the zone of inhibition assay, biofilm inhibition test, and Bradford protein assay, the membrane's anti-biofouling impact is improved by the inherent hydrophilicity of SPEEK/SSA and antibacterial activity of CuO@rGO. The MFC with 1.5 wt% CuO@rGO membrane shows highest maximum power density of 186 ± 5 mW m−2 and Chemical Oxygen Demand removal of 81.23%. Phylogenetic analysis on biofouled membrane shows the predominance of Pseudomonas, Acidovorax and Flavobacterium. The research demonstrates that despite biofouling, the synthesized grafted PEM exhibits high resistance to it and hence performs better.

Investigating the effect of solvent composition on ink structure and crack formation in polymer electrolyte membrane fuel cell catalyst layers

To improve the performance of polymer electrolyte membrane fuel cells (PEMFCs), controlling the microstructure of the membrane electrode assembly (MEA) catalyst layer is crucial. Ink design, which includes a catalyst, an ionomer, and a solvent, serves as the starting point for controlling the microstructure of the catalyst layer. However, there is a significant lack of understanding of the ink structure required for this purpose. In this study, we investigated the effect of the solvent, a key component that determines the ink structure. The ink comprises 20 wt% Pt/C, short-side-chain (SSC) Aquivion ionomer, and a solvent mixture of 1-propanol (NPA) and water. Three types of inks with different compositions of NPA and water are manufactured, and their stability and rheological properties were measured to infer and compare the ink structures. Furthermore, the crack characteristics of the catalyst layer were compared by directly coating the ink onto the electrolyte membrane using the doctor-blade method. In the ink with a high water content, we observed a gel-like elastic behavior dominated by network structures formed by ionomers adsorbed between catalyst particles. In contrast, the ink with a high NPA content exhibited a liquid-like viscous behavior dominated by well-dispersed catalyst particles and ionomers. These properties of the inks directly influence the crack formation characteristics after coating. Specifically, the strong liquid properties of the NPA-rich ink were found to suppress crack formation in the catalyst layer. These findings provide important insights into how the solvent composition affects ink structure and how it, in turn, influences crack formation in the catalyst layer, which can help optimize the ink design to improve the performance of PEMFCs.

Enhancing electrochemical performance and membrane stability evaluation of carrageenan/polyvinyl alcohol-graphene oxide membrane in passive DEFCs

A good electrochemical performance of polymer electrolyte membranes (PEMs) is achieving high membrane selectivity, which is a result of low ethanol permeability and high proton conductivity. Reducing the thickness of PEMs is beneficial for high proton conductivity due to the short distance of proton diffusion. Unfortunately, it results in high ethanol permeability. Thus, achieving high membrane selectivity for good electrochemical performance by balancing the requirements of ethanol permeability and proton conductivity is a critical parameter of PEMs. In this paper, the thickness of the carrageenan/polyvinyl alcohol-graphene oxide membrane was varied from 15 μm – 30 μm to identify the optimum thickness for good electrochemical performance. With a 25 μm membrane thickness, the highest membrane selectivity was performed at 1.609 × 104 S s cm−3, and maximum power density in passive direct ethanol fuel cells was achieved at 14.5 mW cm−2, using 2.0 mg cm−2 anode catalyst loading and 2 M ethanol concentration at 70 °C, respectively. Furthermore, this membrane has sustained electrochemical performance for 1000 h at 70 °C without degrading the membrane stability.

Predicting optimal membrane hydration and ohmic losses in operating fuel cells with machine learning

The absence of proper membrane hydration in membrane electrode assembly (MEA)-based electrochemical energy conversion technologies can lead to disastrous effects, such as reactant crossover, material degradation, and cell failure. In this work, we are the first to apply machine learning to predict if the optimal membrane hydration has been reached in polymer electrolyte membrane (PEM) fuel cells. We evaluate the ability of machine and deep learning algorithms to predict the high frequency resistance (HFR) and whether the optimal hydration current density (OHCD) has been reached via parameters measured from electrochemical impedance spectroscopy (EIS). We accurately predict the HFR using a long short-term memory recurrent neural network model (3.11% mean absolute percentage error and over 0.95 R2). We also accurately predict OHCD with precision and recall values over 98% using deep learning and a k-nearest neighbours model. Furthermore, our models provide a powerful tool for real-time parameter estimation and control systems to monitor and improve the performance of PEM fuel cells and other electrochemical energy devices, such as water and carbon dioxide electrolyzers.