Application of deep learning for informatics aided design of electrode materials in metal-ion batteries

To develop emerging electrode materials and improve the performances of batteries,the machine learning techniques can provide insights to discover,design and develop battery new materials in high-throughput way.In this paper,two deep learning models are developed and trained with two feature groups extracted from the Materials Project datasets to predict the battery electrochemical performances including average voltage,specific capacity and specific energy.The deep learning models are trained with the multilayer perceptron as the core.The Bayesian optimization and Monte Carlo methods are applied to improve the prediction accuracy of models.Based on 10 types of ion batteries,the correlation coefficients are maintained above 0.9 compared to DFT calculation results and the mean absolute error of the prediction results for voltages of two models can reach 0.41 V and 0.20 V,respectively.The electrochemical performance prediction times for the two trained models on thousands of batteries are only 72.9 ms and 75.7 ms.Besides,the two deep learning models are applied to approach the screening of emerging electrode materials for sodium-ion and potassium-ion batteries.This work can contribute to a high-throughput computational method to accelerate the rational and fast materials discovery and design.

Progress in efficient doping of Al-rich AlGaN

The development of semiconductors is always accompanied by the progress in controllable doping techniques.Taking AlGaN-based ultraviolet(UV)emitters as an example,despite a peak wall-plug efficiency of 15.3%at the wavelength of 275 nm,there is still a huge gap in comparison with GaN-based visible light-emitting diodes(LEDs),mainly attributed to the inefficient doping of AlGaN with increase of the Al composition.First,p-doping of Al-rich AlGaN is a long-standing challenge and the low hole concentration seriously restricts the carrier injection efficiency.Although p-GaN cladding layers are widely adopted as a compromise,the high injection barrier of holes as well as the inevitable loss of light extraction cannot be neglected.While in terms of n-doping the main issue is the degradation of the electrical property when the Al composition exceeds 80%,resulting in a low electrical efficiency in sub-250 nm UV-LEDs.This review summarizes the recent advances and outlines the major challenges in the efficient doping of Al-rich AlGaN,meanwhile the corresponding approaches pursued to overcome the doping issues are discussed in detail.

End-cloud collaboration method enables accurate state of health and remaining useful life online estimation in lithium-ion batteries

Though the lithium-ion battery is universally applied,the reliability of lithium-ion batteries remains a challenge due to various physicochemical reactions,electrode material degradation,and even thermal runaway.Accurate estimation and prediction of battery health conditions are crucial for battery safety management.In this paper,an end-cloud collaboration method is proposed to approach the track of battery degradation process,integrating end-side empirical model with cloud-side data-driven model.Based on ensemble learning methods,the data-driven model is constructed by three base models to obtain cloud-side highly accurate results.The double exponential decay model is utilized as an empirical model to output highly real-time prediction results.With Kalman filter,the prediction results of end-side empirical model can be periodically updated by highly accurate results of cloud-side data-driven model to obtain highly accurate and real-time results.Subsequently,the whole framework can give an accurate prediction and tracking of battery degradation,with the mean absolute error maintained below 2%.And the execution time on the end side can reach 261μs.The proposed end-cloud collaboration method has the potential to approach highly accurate and highly real-time estimation for battery health conditions during battery full life cycle in architecture of cyber hierarchy and interactional network.

Enabling dendrite-free charging for lithium batteries based on transport-reaction competition mechanism in CHAIN framework

Worldwide trends in mobile electrification will skyrocket demands for lithium-based battery production,driven by the popularity of electric vehicles.However,both lithium metal batteries and lithium ion batteries face severe safety issues due to dendrite nucleation and growth process.Li deposition is significantly influenced by interfacial factors and charging conditions.In this paper,an electrochemical model considering the internal and external factors is proposed based on Monte Carlo method.The influence of internal solid electrolyte interphase(SEI)porosity,thickness and the external conditions on dendrite growth process is systematically described.The simulation results support that the three factors investigated in this model could synergistically regulate the dendrite growth process.Three competition mechanisms are proposed to tailor lithium deposition for Li-based batteries and numerical solutions for variation pattern of dendrite growth with time are fitted.A three-step process describing kinetic process of lithium deposition is proposed.To achieve dendrite-free charging process,charging strategies and emerging materials design should be considered,including physicochemical materials engineering,artificial SEI,and design for dynamic safety boundary.This work could contribute to the foundation for insights of Li deposition mechanism,which is promising to provide guidelines for next-generation high-energy-density and safe batteries in CHAIN framework.

The Records of Anatomy in Ancient China

Through long-term observations and repeated practices of human body structure,anatomical knowledge in ancient China has gradually developed from the sprouting period when ancient Chinese hunted animals for survival,to anatomical exploration,which breaks the shackles of fear and religious rites.For example,Hua Tuo(华佗),a famous doctor in the period of The Three Kingdoms,did exquisite abdominal surgery;Yan Luozi(烟萝子),a Taoist priest in the period of The Five Dynasties,drew a map of human anatomy;Wang Weiyi(王唯一),a medical official in Northern Song dynasty,was responsible for casting acupuncture bronze figures,an anatomical mold for practicing acupuncture;Song Ci(宋慈),a forensic expert in Southern Song Dynasty,wrote Xi Yuan Ji Lu(《洗冤集录》Collected Cases of Injustice Rectified);Wang Qingren(王清任),a physician in Qing Dynasty wrote Yi Lin Gai Cuo(《医林改错》Correction on Errors in Medical Works).Ancient Chinese anatomy is far ahead of Western anatomy in understanding and describing human body structures.It has made great contributions to the emergence of Huang Di Nei Jing(《黄帝内经》Huangdi's Internal Classic)and laid a solid foundation for the establishment of visceral manifestation theory and meridian and collateral theory.Even now,it has served the basic theory of traditional Chinese medicine and clinical practices.Anatomical knowledges,such as relevant operation records,books,Atlas,models in ancient China,especially the names of Zangorgan and Fu-organ,bones and five sense organs,are still used in modern anatomy and modern medicine,making indelible contributions to the development of modern anatomy in China.

Improving the response of 2D COFs to the surface doping strategies through rational design of their chemical structure

The chemical structure of covalent organic frameworks(COFs)plays a key role in their response to the surface doping strategy used for tuning their electronic character,but it is still not fully understood.To explore a rational design proposal for their chemical structure,the electronic properties of three n-doped typical COFs,including boroncontaining(COF-1),triazine-based(CTF),and C–C bondlinked(GCOF)COFs,were investigated theoretically in this work.As expected,the chemical doping effects are different for these COFs.The dispersion of the frontier bands,the nuclear-independent chemical shift(NICS)aromaticity index results,distribution of the electron localization function(ELF),and Hirshfeld charge population plots show that part of the transferred electron from dopants will be offset by the intralayer charge transfer of COFs.Thus,chemical doping effects are more significant if the electron distribution in the COFs is more localized.This means the response of COFs to the surface doping strategy should be dominated by the conjugation degree of their chemical structure.Our results prove that the intrinsic conjugation degree of COFs plays a key role in such doping functionalization strategies,which are expected to provide more useful information for the initial structure design of COF materials and facilitate their practical applications as active electronic transport materials in nanoscale devices.

Ammonia fuel:A pathway for carbon-neutral of the transportation sector

Global warming is the most significant challenge to society due to the increasing carbon dioxide level in the atmosphere nowadays.Accelerating the deployment of zero-carbon fuel is imperative in the transportation field,one of the major sources of carbon emissions.The effort on clean energy represented by hydrogen has been made by showing good breakthroughs in some applications;however,many technical and economic challenges exist for large-scale commercial applications.Ammonia,as another zero-carbon fuel,is an efficient storage and transportation medium for hydrogen component and shows greater application potential.Compared to hydrogen,ammonia has more mature storage and transportation technologies,superior related infrastructure,and a further systematic transportation network.In the review,the current mainstream technology routes of ammonia synthesis,the storage and transportation,and the future development trends are summarized.Carbon emissions and costs for the processes are brought into focus.Additionally,the combustion and emission generation mechanisms with technical routes for ammonia as a direct fuel are discussed.The current opportunities and challenges are then analyzed for ammonia as a zero-carbon fuel.The prospect of utilizing ammonia both as a direct fuel and a carrier for hydrogen in transportation is being explored,along with an architecture of the zero-carbon energy system for transportation based on the ammonia fuel.

CHAINS:CHAIN-based fusion safety system framework for intelligent connected vehicle

Intelligent connected vehicles,as the focus of the global automotive industry,are currently at a critical stage of large-scale commercialization.However,during the development process of vehicles from mechanical systems with limited functions to mobile intelligence with complex and multiple functions,the issues of functional safety,cybersecurity,and safety of the intended functionality are the main challenges of the industrialization of intelligent connected vehicles,including multiple safety risks such as hardware and software failures,insufficient performance in edge scenarios,cyber-attacks and data leakage.In this paper,the safety and security issues of intelligent connected vehicles,the challenges posed by emerging technology applications,and related solutions are systematically reviewed and summarized.A fusion safety system framework with the safety cube as the core of protection and control is proposed innovatively based on a field-vehicle-human safety interactional model,realizing stereoscopic,deep,and comprehensive safety protection through end-cloud collaboration.Meanwhile,an X-shaped fusion safety development process based on CHAIN is proposed.Through the empowerment of digital twin and AI technologies,it could approach interaction between physical entities and digital twin models and the automation of the development process,thereby satisfying the demands of fusion safety system design,intelligent development,rapid delivery,and continuous iteration.The fusion safety system framework and X-shaped development process proposed in this paper can provide important insight into intelligent transportation vehicles and systems'safety and security design and development.

Research progress in the heat resistance, toughening and filling modification of PLA

Due to its high strength, high modulus, excellent clarity, good biodegradability and biocompatibility, poly(lactic acid)(PLA), a bio-based thermoplastic polyester, has evolved into a competitive commodity material with potential to replace conventional petrochemical-based polymers. However, the wide applications of PLA have been hampered by its native drawbacks, such as low heat distortion temperature(HDT), inherent brittleness and relatively high cost. In recent years, researchers have devoted to breaking above-mentioned bottleneck and attempted to extend the application of PLA. This review will summarize recent work about the modification of PLA, especially focusing on enhancing HDT, toughening and reducing cost.

Review of Abnormality Detection and Fault Diagnosis Methods for Lithium‑Ion Batteries

Electric vehicles are developing prosperously in recent years.Lithium-ion batteries have become the dominant energy storage device in electric vehicle application because of its advantages such as high power density and long cycle life.To ensure safe and efficient battery operations and to enable timely battery system maintenance,accurate and reliable detection and diagnosis of battery faults are necessitated.In this paper,the state-of-the-art battery fault diagnosis methods are comprehensively reviewed.First,the degradation and fault mechanisms are analyzed and common abnormal behaviors are summarized.Then,the fault diagnosis methods are categorized into the statistical analysis-,model-,signal processing-,and data-driven methods.Their distinctive characteristics and applications are summarized and compared.Finally,the challenges facing the existing fault diagnosis methods are discussed and the future research directions are pointed out.

Implementation for a cloud battery management system based on the CHAIN framework

An intelligent battery management system is a crucial enabler for energy storage systems with high power output,increased safety and long lifetimes.With recent developments in cloud computing and the proliferation of big data,machine learning approaches have begun to deliver invaluable insights,which drives adaptive control of battery management systems(BMS)with improved performance.In this paper,a general framework utilizing an end-edge-cloud architecture for a cloud-based BMS is proposed,with the composition and function of each link described.Cloud-based BMS leverages from the Cyber Hierarchy and Interactional Network(CHAIN)framework to provide multi-scale insights,more advanced and efficient algorithms can be used to realize the state-of-X es-timation,thermal management,cell balancing,fault diagnosis and other functions of traditional BMS system.The battery intelligent monitoring and management platform can visually present battery performance,store working-data to help in-depth understanding of the microscopic evolutionary law,and provide support for the development of control strategies.Currently,the cloud-based BMS requires more effects on the multi-scale inte-grated modeling methods and remote upgrading capability of the controller,these two aspects are very important for the precise management and online upgrade of the system.The utility of this approach is highlighted not only for automotive applications,but for any battery energy storage system,providing a holistic framework for future intelligent and connected battery management.

Simultaneously Constructing Asymmetrically Coordinated Cobalt Single Atoms and Cobalt Nanoclusters via a Fresh Potassium Hydroxide Clipping Strategy toward Efficient Alkaline Oxygen Reduction Reaction

Single-atom catalysts based on metal-N-C constituents facilitate oxygen reduction reaction kinetics due to super-high atomic utilization efficiency.However,conventional isolated atoms suffer from coordination symmetry and make less use of electron interaction between adjacent metal sites,which severely impedes its electrocatalytic activity.In response,we creatively issue a feasible potassium hydroxide clipping strategy through breaking up partial Co-N bonding and reconstructing Co-Co coordination,thus simultaneously implanting abundant Co atomic clusters and Co single atoms(SAs)on the surface of covalent organic framework(COF)-derived N-doped carbon nanospheres,which are intertwined by surrounding carbon nanotube(CNT)networks.This elaborately designed Co_(AC-SAs)/N-C@CNT catalyst combines the benefits of the asymmetrically coordinated Co-N_(2) configuration and Co-Co electronic interaction,which exert great influence on local atomic microenvironment of metal sites and,thus,efficiently modulate the electronic structure.Then,the optimized d-band center of Co centers contributes to weakening oxygen intermediate adsorption and to reducing the rate-determining step energy barrier.Meanwhile,because of the unique surface chelation mechanism between COF matrix and Co cations,the as-optimized Co centers are homogenously stabilized on the carbon outermost shell,further maximizing active sites efficiency.As expected,the CoAC-SAs/N-C@CNT catalyst harvests superior oxygen reduction reaction catalytic kinetics in alkaline medium,surpassing the commercial Pt/C catalyst.

Novel utilization exploration for the dephosphorization waste of Ca-modified biochar:enhanced removal of heavy metal ions from water

Phosphorus-modified biochar has been proven to enhance the precipitation and complexation of heavy metal ions from wastewater.However,the current modification methods require large amounts of exogenous P and have high energy consumption.Hence,this study proposes and analyzes a strategy integrating biochar production,phosphorus wastewater treatment,dephosphorization waste recovery,and heavy metal removal.“BC-Ca-P”was derived from Ca-modified biochar after phosphorus wastewater treatment.The adsorption of Pb(II)by BC-Ca-P followed the Langmuir isotherm and pseudo-second-order kinetic models.The maximum adsorption capability of 361.20 mg·g^(−1)at pH 5.0 for 2 h was markedly greater than that of external phosphorous-modified biochar.The adsorption mechanisms were dominated by chemical precipitation and complexation.Furthermore,density functional theory calculations indicated that oxygen-containing functional groups(P-O and C-O)contributed the most to the efficient adsorption of Pb(II)onto BC-Ca-P.To explore its practical feasibility,the adsorption performance of BC-Ca-P recovered from an actual environment was evaluated.The continuous-flow adsorption behavior was investigated and well-fitted utilizing the Thomas and Yoon-Nelson models.There was a negligible P leakage risk of BC-Ca-P during heavy metal treatment.This study describes a novel and sustainable method to utilize dephosphorization waste for heavy metal removal.