Utilizing machine learning techniques for data-driven diagnosis of high temperature PEM fuel cells is beneficial and meaningful to the system durability. Nevertheless, ensuring the robustness of diagnosis remains a cr...
详细信息
Utilizing machine learning techniques for data-driven diagnosis of high temperature PEM fuel cells is beneficial and meaningful to the system durability. Nevertheless, ensuring the robustness of diagnosis remains a critical and challenging task in real application. To enhance the robustness of diagnosis and achieve a more thorough evaluation of diagnostic performance, a robust diagnostic procedure based on electrochemical impedance spectroscopy (EIS) and a new method for evaluation of the diagnosis robustness was proposed and investigated in this work. To improve the diagnosis robustness: (1) the degradation mechanism of different faults in the high temperature PEM fuel cell was first analyzed via the distribution of relaxation time of EIS to determine the equivalent circuit model (ECM) with better interpretability, simplicity and accuracy;(2) the feature extraction was implemented on the identified parameters of the ECM and extra attention was paid to distinguishing between the long-term normal degradation and other faults;(3) a Siamese Network was adopted to get features with higher robustness in a new embedding. The diagnosis was conducted using 6 classic classification algorithms—support vector machine (SVM), K-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), random forest (RF), and Naive Bayes employing a dataset comprising a total of 1935 collected EIS. To evaluate the robustness of trained models: (1) different levels of errors were added to the features for performance evaluation;(2) a robustness coefficient (Roubust_C) was defined for a quantified and explicit evaluation of the diagnosis robustness. The diagnostic models employing the proposed feature extraction method can not only achieve the higher performance of around 100% but also higher robustness for diagnosis models. Despite the initial performance being similar, the KNN demonstrated a superior robustness after feature selection and re-embedding by triplet-loss method, which sug
The mechanochemical effects of elasticity and plasticity are introduced into a peridynamic (PD) corrosion model. A PD equation that couples the mechanics and kinetics of electrochemistry is proposed for the first time...
详细信息
This study investigates the influence of waste characteristics,especially zeta potential,on the properties of cement pastes and *** focus is to evaluate the impact of the zeta potential of cement particles and waste m...
详细信息
This study investigates the influence of waste characteristics,especially zeta potential,on the properties of cement pastes and *** focus is to evaluate the impact of the zeta potential of cement particles and waste materials on the sedimentation speed,rheology,and hardening time of stabilized cement *** Cement II F 40,retarder additive,silica,and fly ash were used in the *** pastes were prepared,and during the stabilization period,their rheological properties and pH were *** zeta potential and sedimentation speed of the cement and waste particles were measured at the pH that the pastes presented during the entire stabilization *** the stabilization period,the pastes were subjected to the hardening time *** zeta potential analyses revealed diverse values for the different powder types,with the cement particles exhibiting a zeta potential of−3.0 mV,the silica particles exhibiting−10.5 mV,and the fly ash particles exhibiting−20.3 *** influence of the high zeta potential modulus was observed on the sedimentation speed,with the solution containing fly ash exhibiting a speed of 40.01μm/s,whereas the solution containing only cement exhibited a speed of 99.38μm/*** the pastes,the results indicate that the presence of fly ash particles with a significantly negative zeta potential led to a 16%reduction in hardening time compared to particles with a lower modulus of zeta *** tests showed that the inclusion of fly ash particles prevented the formation of *** the zeta potential influenced agglomerate formation and hardening time,it was found to have no effect on yield stress or viscosity.
Electrochemical CO_(2)reduction is a sustainable approach in green chemistry that enables the production of valuable chemicals and fuels while mitigating the environmental impact associated with CO_(2)*** its several ...
详细信息
Electrochemical CO_(2)reduction is a sustainable approach in green chemistry that enables the production of valuable chemicals and fuels while mitigating the environmental impact associated with CO_(2)*** its several advantages,this technology suffers from an intrinsically low CO_(2)solubility in aqueous solutions,resulting in a lower local CO_(2)concentration near the electrode,which yields lower current densities and restricts product *** diffusion electrodes(GDEs),particularly those with tubular architectures,can solve these issues by increasing the local CO_(2)concentration and triple-phase interface,providing abundant electroactive sites to achieve superior reaction *** this study,robust and self-supported Cu flow-through gas diffusion electrodes(FTGDEs)were synthesized for efficient formate production via electrochemical CO_(2)*** were further compared with traditional Cu electrodes,and it was found that higher local CO_(2)concentration due to improved mass transfer,the abundant surface area available for the generation of the triple-phase interface,and the porous structure of Cu FTGDEs enabled high formate Faradaic efficiency(76%)and current density(265 mA¸cm^(−2))at–0.9 V *** hydrogen electrode(RHE)in 0.5 mol·L^(−1)*** combined phase inversion and calcination process of the Cu FTGDEs helped maintain a stable operation for several *** catalytic performance of the Cu FTGDEs was further investigated in a non-gas diffusion configuration to demonstrate the impact of local gas concentration on the activity and performance of electrochemical CO_(2)*** study demonstrates the potential of flow-through gas-diffusion electrodes to enhance reaction kinetics for the highly efficient and selective reduction of CO_(2),offering promising applications in sustainable electrochemical processes.
Mg alloys have the defects of low stiffness,low strength,and high coefficient of thermal expansion(CTE).The composites strategy and its architecture design are effective approaches to improve the comprehensive perform...
详细信息
Mg alloys have the defects of low stiffness,low strength,and high coefficient of thermal expansion(CTE).The composites strategy and its architecture design are effective approaches to improve the comprehensive performance of materials,but the processing difficulty,especially in ceramics forming,limits the control and innovation of material ***,combined with 3D printing and squeeze infiltration technology,two precisely controllable architectures of AZ91/Al_(2)O_(3)interpenetrating phase composites(IPC)with ceramic scaffold were *** interface,properties and impact of different architecture on IPC performance were studied by experiments and finite element *** metallurgical bonding of the interface was realized with the formation of MgAl_(2)O_(4)reaction *** IPC with 1 mm circular hole scaffold(1C-IPC)exhibited significantly improved elastic modulus of 164 GPa,high compressive strength of 680 MPa,and good CTE of 12.91×10^(-6)K^(−1),which were 3.64 times,1.98 times and 55%of the Mg matrix,*** elastic modulus,compressive strength,and CTE were superior to the vast majority of Mg alloys and Mg based *** reinforcement and matrix were bicontinuous and interpenetrating each other,which played a critical role in ensuring the potent strengthening effect of the Al_(2)O_(3)reinforcement by efficient load *** the same volume fraction of reinforcements,compared to IPC with 1 mm hexagonal hole scaffold(1H-IPC),the elastic modulus and compressive strength of 1C-IPC increased by 15%and 28%,respectively,which was due to the reduced stress concentration and more uniform stress distribution of *** shows great potential of architecture design in improving the performance of *** study provides architectural design strategy and feasible preparation method for the development of high performance materials.
This study investigates the effect of graphene oxide(GO)on the mechanical and corrosion behavior,antibacterial performance,and cell response of Mg–Zn–Mn(MZM)***/GO nanocomposites with different amounts of GO(i.e.,0....
详细信息
This study investigates the effect of graphene oxide(GO)on the mechanical and corrosion behavior,antibacterial performance,and cell response of Mg–Zn–Mn(MZM)***/GO nanocomposites with different amounts of GO(i.e.,0.5 wt%,1.0 wt%,and1.5 wt%)were fabricated by the semi-powder metallurgy *** influence of GO on the MZM nanocomposite was analyzed through the hardness,compressive,corrosion,antibacterial,and cytotoxicity *** experimental results showed that,with the increase in the amount of GO(0.5 wt%and 1.5 wt%),the hardness value,compressive strength,and antibacterial performance of the MZM nanocomposite increased,whereas the cell viability and osteogenesis level decreased after the addition of 1.5 wt%***,the electrochemical examination results showed that the corrosion behavior of the MZM alloy was significantly enhanced after encapsulation in 0.5 wt%*** summary,MZM nanocomposites reinforced with GO can be used for implant applications because of their antibacterial performance and mechanical property.
We propose an approach for data-driven automated discovery of material laws,which we call EUCLID(Efficient Unsupervised Constitutive Law Identification and Discovery),and we apply it here to the discovery of plasticit...
详细信息
We propose an approach for data-driven automated discovery of material laws,which we call EUCLID(Efficient Unsupervised Constitutive Law Identification and Discovery),and we apply it here to the discovery of plasticity models,including arbitrarily shaped yield surfaces and isotropic and/or kinematic hardening *** approach is unsupervised,i.e.,it requires no stress data but only full-field displacement and global force data;it delivers interpretable models,i.e.,models that are embodied by parsimonious mathematical expressions discovered through sparse regression of a potentially large catalog of candidate functions;it is one-shot,i.e.,discovery only needs one *** material model library is constructed by expanding the yield function with a Fourier series,whereas isotropic and kinematic hardening is introduced by assuming a yield function dependency on internal history variables that evolve with the plastic *** selecting the most relevant Fourier modes and identifying the hardening behavior,EUCLID employs physics knowledge,i.e.,the optimization problem that governs the discovery enforces the equilibrium constraints in the bulk and at the loaded boundary of the *** promoting regularization is deployed to generate a set of solutions out of which a solution with low cost and high parsimony is automatically *** virtual experiments,we demonstrate the ability of EUCLID to accurately discover several plastic yield surfaces and hardening mechanisms of different complexity.
Molecular dynamics simulations were performed to understand the mechanical properties of Ni-10Cu alloy with pre-existing faceted Σ3 [111] 60° {11 8 5} grain boundary under uniaxial tensile loading at various str...
详细信息
High-performance batteries are poised for electrification of vehicles and therefore mitigate greenhouse gas emissions,which,in turn,promote a sustainable ***,the design of optimized batteries is challenging due to the...
详细信息
High-performance batteries are poised for electrification of vehicles and therefore mitigate greenhouse gas emissions,which,in turn,promote a sustainable ***,the design of optimized batteries is challenging due to the nonlinear governing physics and *** advancements have demonstrated the potential of deep learning techniques in efficiently designing batteries,particularly in optimizing electrodes and *** review provides comprehensive concepts and principles of deep learning and its application in solving battery-related electrochemical problems,which bridges the gap between artificial intelligence and *** also examine the potential challenges and opportunities associated with different deep learning approaches,tailoring them to specific battery ***,we aim to inspire future advancements in both fundamental scientific understanding and practical engineering in the field of battery ***,we highlight the potential challenges and opportunities for different deep learning methods according to the specific battery demand to inspire future advancement in fundamental science and practical engineering.
暂无评论