Advancements in machine learning for material design and process optimization in the field of additive manufacturing

Additive manufacturing technology is highly regarded due to its advantages,such as high precision and the ability to address complex geometric challenges.However,the development of additive manufacturing process is constrained by issues like unclear fundamental principles,complex experimental cycles,and high costs.Machine learning,as a novel artificial intelligence technology,has the potential to deeply engage in the development of additive manufacturing process,assisting engineers in learning and developing new techniques.This paper provides a comprehensive overview of the research and applications of machine learning in the field of additive manufacturing,particularly in model design and process development.Firstly,it introduces the background and significance of machine learning-assisted design in additive manufacturing process.It then further delves into the application of machine learning in additive manufacturing,focusing on model design and process guidance.Finally,it concludes by summarizing and forecasting the development trends of machine learning technology in the field of additive manufacturing.

论UI扁平化设计体验感的实现——以Material Design为例

互联网行业的飞速发展推动了UI设计领域的不断进步。近年来,UI设计风格主流趋势逐渐由靠近真实的拟物化设计发展为如今的扁平化设计,随着大众审美的改变和对用户体验标准的提升,扁平化设计也在逐步拓展。在各种拓展中,Material Design遵从了设计美学原则、视觉语言原则和功能表达原则,创造了全新的扁平化UI交互体验,这样的交互体验是如何实现的,值得深思。

An Expert System in FRP Composite Material Design

An expert system prototype for fibre-reinforced plastic matrix (FRP) composite material design, ESFRP, has been developed. The system consists of seven main functional parts: a general inference engine, a set of knowledge bases, a material properties algorithm base, an explanation engine, various data bases, several function models and the user interface. The ESFRP can simulate human experts to make design scheme for fibre-reinforced plastics design, FRP layered plates design and FRP typical engineering components design. It can also predict the material properties and make strength analysis according to the micro and macro mechanics of composite materials. A satisfied result can be gained through the reiterative design.

TOPOLOGY DESCRIPTION FUNCTION BASED METHOD FOR MATERIAL DESIGN

The purpose of this paper is to investigate the application of topology description function （TDF） in material design. Using TDF to describe the topology of the microstructure, the formulation and the solving technique of the design problem of materials with prescribed mechanical properties are presented. By presenting the TDF as the sum of a series of basis functions determined by parameters, the topology optimization of material microstructure is formulated as a size optimization problem whose design variables are parameters of TDF basis functions and independent of the mesh of the design domain. By this method, high quality topologies for describing the distribution of constituent material in design domain can be obtained and checkerboard problem often met in the variable density method is avoided. Compared with the conventional level set method, the optimization problem can be solved simply by existing optimization techniques without the process to solve the ＇Hamilton-Jacobi-type＇ equation by the difference method. The method proposed is illustrated with two 2D examples. One gives the unit cell with positive Poisson＇s ratio, the other with negative Poisson＇s ratio. The examples show the method based on TDF is effective for material design.

GMA material design and construction quality control for asphalt pavement of steel box girder: Case study of the Hong Kong–Zhuhai–Macao Bridge

To improve the quality of the Hong Kong–Zhuhai–Macao Bridge paving project,a new paving layer material,Guss-mastic asphalt(GMA),was proposed in this paper by combining the advantages of two types of cast asphalt mixtures:mastic asphalt(MA)and Guss asphalt(GA).Based on the characteristics of GMA,to simulate its actual production process,this study developed a small-simulated cooker mixing equipment.Moreover,the flow degree,60C dynamic stability,and impact toughness were proposed to be used to evaluate the construction and ease,high temperature stability,and fatigue resistance of GMA cast asphalt mixtures,respectively.Moreover,the quality control standards for GMA paving materials by indoor tests,field trial mix GMA material performance tests,and accelerated loading tests were finalized.The study showed that the developed simulated cooker yielded consistent mixing results in the same working environment as the engineering cooker device.Increasing the coarse aggregate incorporation rate,coarsening the mastic epure(ME)gradation composition,and using a smaller oil to stone ratio can reduce the flowability of the GMA materials to varying degrees.The four-point bending fatigue life and impact toughness of the different GMA materials are correlated well.A mobility of<20 s,60C dynamic stability of 400–800 times/mm,15C impact toughness of400 N⋅mm,and cooker car mixing temperature control standard of 210C–230C form an appropriate control index system for the design and production of GMA cast asphalt mixtures.Simultaneously,accelerated loading tests verified the accuracy and reliability of the quality control index system that has been used in the GMA paving project of the Hong Kong–Zhuhai–Macao Bridge deck and has achieved good application results.

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.

Impacts of thermal and electric contact resistance on the material design in segmented thermoelectric generators

Segmented thermoelectric generators(STEGs)can exhibit present superior performance than those of the conventional thermoelectric generators.Thermal and electrical contact resistances exist between the thermoelectric material interfaces in each thermoelectric leg.This may significantly hinder performance improvement.In this study,a five-layer STEG with three pairs of thermoelectric(TE)materials was investigated considering the thermal and electrical contact resistances on the material contact surface.The STEG performance under different contact resistances with various combinations of TE materials were analyzed.The relationship between the material sequence and performance indicators under different contact resistances is established by machine learning.Based on the genetic algorithm,for each contact resistance combination,the optimal material sequences were identified by maximizing the electric power and energy conversion efficiency.To reveal the underlying mechanism that determines the heat-to-electrical performance,the total electrical resistance,output voltage,ZT value,and temperature distribution under each optimized scenario were analyzed.The STEG can augment the heat-to-electricity performance only at small contact resistances.A large contact resistance significantly reduces the performance.At an electrical contact resistance of RE=10^(-3) K⋅m^(2)⋅W^(-1) and thermal contact resistance of RT=10-8Ω⋅m^(2),the maximum electric power was reduced to 5.71 mW(90.86 mW without considering the contact resistance).And the maximum energy conversion efficiency is lowered to 2.54%(12.59%without considering the contact resistance).

Optimizing design of lattice materials based on finite element simulation

The optimized design of simple cross-truss and column lattice structures was carried out by the SolidWorks simulation module.The effective density of the structure was calculated according to the weight reduction requirements proposed by the project.Then,the vari-ation curve between the maximum bearing stress of the unit structure and the structural variables was obtained by simulation.Meanwhile,the mathematical equation between the maximum bearing stress and the structural variables could be obtained through MATLAB fitting.The results indicated that with the decrease in the number of cells,the compressive strength of the prepared column lattice increased(400 to 4 cells,compressive strength 29 MPa to 160 MPa).However,the yield strength increased with the number of cells.The compression strength of the simple cross-truss lattice samples indicated an increase trend with the decrease of the pillar size(an increase of the number of units),reaching 91 MPa(pillar diameter 0.52 mm,number of units 25).While the yield strength increased with the increasing of the number of units.In addition,the additive manufacturing processes of simple cubic lattice and simple cross-pillar lattice were investigated using selective laser melting.The compression performance obtained from the experiment is compared with the simulation results,which are in good agreement.The results of this paper can provide an important reference for optimizing design of lattice materials.

Designing high-efficiency light-to-thermal conversion materials for solar desalination and photothermal catalysis

Light-to-thermal conversion materials(LTCMs)have been of great interest to researchers due to their impressive energy conversion capacity and wide range of applications in biomedical,desalination,and synergistic catalysis.Given the limited advances in existing materials(metals,semiconductors,π-conjugates),researchers generally adopt the method of constructing complex systems and hybrid structures to optimize performance and achieve multifunctional integration.However,the development of LTCMs is still in its infancy as the physical mechanism of light-to-thermal conversion is unclear.In this review,we proposed design strategies for efficient LTCMs by analyzing the physical process of light-tothermal conversion.First,we analyze the nature of light absorption and heat generation to reveal the physical processes of light-to-thermal conversion.Then,we explain the light-to-thermal conversion mechanisms of metallic,semiconducting andπ-conjugated LCTMs,and propose new material design strategies and performance improvement methods.Finally,we summarize the challenges and prospects of LTCMs in emerging applications such as solar water evaporation and photothermal catalysis.

Advances in data-assisted high-throughput computations for material design

Extensive trial and error in the variable space is the main cause of low efficiency and high cost in material development.The experimental tasks can be reduced significantly in the case that the variable space is narrowed down by reliable computer simulations.Because of their numerous variables in material design,however,the variable space is still too large to be accessed thoroughly even with a computational approach.High-throughput computations(HTC)make it possible to complete a material screening in a large space by replacing the conventionally manual and sequential operations with automatic,robust,and concurrent streamlines.The efficiency of HTC,which is one of the pillars of materials genome engineering,has been verified in many studies,but its applications are still limited by demanding computational costs.Introduction of data mining and artificial intelligence into HTC has become an effective approach to solve the problem.In the past years,many studies have focused on the development and application of HTC and data combined approaches,which is considered as a new paradigm in computational materials science.This review focuses on the main advances in the field of data-assisted HTC for material research and development and provides our outlook on its future development.

The design and engineering strategies of metal tellurides for advanced metal-ion batteries

Owning various crystal structures and high theoretical capacity,metal tellurides are emerging as promising electrode materials for high-performance metal-ion batteries(MBs).Since metal telluride-based MBs are quite new,fundamental issues raise regarding the energy storage mechanism and other aspects affecting electrochemical performance.Severe volume expansion,low intrinsic conductivity and slow ion diffusion kinetics jeopardize the performance of metal tellurides,so that rational design and engineering are crucial to circumvent these disadvantages.Herein,this review provides an in-depth discussion of recent investigations and progresses of metal tellurides,beginning with a critical discussion on the energy storage mechanisms of metal tellurides in various MBs.In the following,recent design and engineering strategies of metal tellurides,including morphology engineering,compositing,defect engineering and heterostructure construction,for high-performance MBs are summarized.The primary focus is to present a comprehensive understanding of the structural evolution based on the mechanism and corresponding effects of dimension control,composition,electron configuration and structural complexity on the electrochemical performance.In closing,outlooks and prospects for future development of metal tellurides are proposed.This work also highlights the promising directions of design and engineering strategies of metal tellurides with high performance and low cost.

Advances in the structure design of substrate materials for zinc anode of aqueous zinc ion batteries

Aqueous zinc ion batteries(AZIBs) demonstrate tremendous competitiveness and application prospects because of their abundant resources,low cost, high safety, and environmental friendliness. Although the advanced electrochemical energy storage systems based on zinc ion batteries have been greatly developed, many severe problems associated with Zn anode impede its practical application, such as the dendrite formation,hydrogen evolution, corrosion and passivation phenomenon. To address these drawbacks, electrolytes, separators, zinc alloys, interfacial modification and structural design of Zn anode have been employed at present by scientists. Among them, the structural design for zinc anode is relatively mature, which is generally believed to enhance the electroactive surface area of zinc anode, reduce local current density, and promote the uniform distribution of zinc ions on the surface of anode. In order to explore new research directions, it is crucial to systematically summarize the structural design of anode materials. Herein, this review focuses on the challenges in Zn anode, modification strategies and the three-dimensional(3D) structure design of substrate materials for Zn anode including carbon substrate materials, metal substrate materials and other substrate materials. Finally, future directions and perspectives about the Zn anode are presented for developing high-performance AZIBs.

Inverse design for material anisotropy and its application for a compact X-cut TFLN on-chip wavelength demultiplexer

Inverse design focuses on identifying photonic structures to optimize the performance of photonic devices.Conventional scalar-based inverse design approaches are insufficient to design photonic devices of anisotropic materials such as lithium niobate(LN).To the best of our knowledge,this work proposes for the first time the inverse design method for anisotropic materials to optimize the structure of anisotropic-material based photonics devices.Specifically,the orientation dependent properties of anisotropic materials are included in the adjoint method,which provides a more precise prediction of light propagation within such materials.The proposed method is used to design ultra-compact wavelength division demultiplexers in the X-cut thin-film lithium niobate(TFLN)platform.By benchmarking the device performances of our method with those of classical scalar-based inverse design,we demonstrate that this method properly addresses the critical issue of material anisotropy in the X-cut TFLN platform.This proposed method fills the gap of inverse design of anisotropic materials based photonic devices,which finds prominent applications in TFLN platforms and other anisotropicmaterial based photonic integration platforms.

Application of machine learning in perovskite materials and devices:A review

Metal-halide hybrid perovskite materials are excellent candidates for solar cells and photoelectric devices.In recent years,machine learning(ML)techniques have developed rapidly in many fields and provided ideas for material discovery and design.ML can be applied to discover new materials quickly and effectively,with significant savings in resources and time compared with traditional experiments and density functional theory(DFT)calculations.In this review,we present the application of ML in per-ovskites and briefly review the recent works in the field of ML-assisted perovskite design.Firstly,the advantages of perovskites in solar cells and the merits of ML applied to perovskites are discussed.Secondly,the workflow of ML in perovskite design and some basic ML algorithms are introduced.Thirdly,the applications of ML in predicting various properties of perovskite materials and devices are reviewed.Finally,we propose some prospects for the future development of this field.The rapid devel-opment of ML technology will largely promote the process of materials science,and ML will become an increasingly popular method for predicting the target properties of materials and devices.

Databases of 2D material-substrate interfaces and 2D charged building blocks

Discovery of materials using“bottom-up”or“top-down”approach is of great interest in materials science.Layered materials consisting of two-dimensional(2D)building blocks provide a good platform to explore new materials in this respect.In van der Waals(vdW)layered materials,these building blocks are charge neutral and can be isolated from their bulk phase(top-down),but usually grow on substrate.In ionic layered materials,they are charged and usually cannot exist independently but can serve as motifs to construct new materials(bottom-up).In this paper,we introduce our recently constructed databases for 2D material-substrate interface(2DMSI),and 2D charged building blocks.For 2DMSI database,we systematically build a workflow to predict appropriate substrates and their geometries at substrates,and construct the 2DMSI database.For the 2D charged building block database,1208 entries from bulk material database are identified.Information of crystal structure,valence state,source,dimension and so on is provided for each entry with a json format.We also show its application in designing and searching for new functional layered materials.The 2DMSI database,building block database,and designed layered materials are available in Science Data Bank at https://doi.org/10.57760/sciencedb.j00113.00188.

Hybrid Data-Driven and Mechanistic Modeling Approaches for Multiscale Material and Process Design

The world’s increasing population requires the process industry to produce food,fuels,chemicals,and consumer products in a more efficient and sustainable way.Functional process materials lie at the heart of this challenge.Traditionally,new advanced materials are found empirically or through trial-and-error approaches.As theoretical methods and associated tools are being continuously improved and computer power has reached a high level,it is now efficient and popular to use computational methods to guide material selection and design.Due to the strong interaction between material selection and the operation of the process in which the material is used,it is essential to perform material and process design simultaneously.Despite this significant connection,the solution of the integrated material and process design problem is not easy because multiple models at different scales are usually required.Hybrid modeling provides a promising option to tackle such complex design problems.In hybrid modeling,the material properties,which are computationally expensive to obtain,are described by data-driven models,while the well-known process-related principles are represented by mechanistic models.This article highlights the significance of hybrid modeling in multiscale material and process design.The generic design methodology is first introduced.Six important application areas are then selected:four from the chemical engineering field and two from the energy systems engineering domain.For each selected area,state-ofthe-art work using hybrid modeling for multiscale material and process design is discussed.Concluding remarks are provided at the end,and current limitations and future opportunities are pointed out.

Design of Structural Left-handed Material based on Topology Optimization

An effective method to design structural Left-handed material（LHM） was proposed. A commercial finite element software HFSS and S-parameter retrieval method were used to determine the effective constitutive parameters of the metamaterials, and topology optimization technique was introduced to design the microstructure configurations of the materials with desired electromagnetic characteristics. The material considered was a periodic array of dielectric substrates attached with metal film pieces. By controlling the arrangements of the metal film pieces in the design domain, the potential microstructure with desired electromagnetic characteristics can be obtained finally. Two different LHMs were obtained with maximum bandwidth of negative refraction, and the experimental results show that negative refractive indices appear while the metamaterials have simultaneously negative permittivity and negative permeability. Topology optimization technique is found to be an effective tool for configuration design of LHMs.

Discovery and design of lithium battery materials via high-throughput modeling

This paper reviews the rapid progress in the field of high-throughput modeling based on the Materials Genome Initiative, and its application in the discovery and design of lithium battery materials. It offers examples of screening, optimization and design of electrodes, electrolytes, coatings, additives, etc. and the possibility of introducing the machine learning method into material design. The application of the material genome method in the development of lithium battery materials provides the possibility to speed up the upgrading of new candidates in the discovery of lots of functional materials.

Time-varying clustering for local lighting and material design

This paper presents an interactive graphics processing unit （GPU）-based relighting system in which local lighting condition, surface materials and viewing direction can all be changed on the fly. To support these changes, we simulate the lighting transportation process at run time, which is normally impractical for interactive use due to its huge computational burden. We greatly alleviate this burden by a hierarchical structure named a transportation tree that clusters similar emitting samples together within a perceptually acceptable error bound. Furthermore, by exploiting the coherence in time as well as in space, we incrementally adjust the clusters rather than computing them from scratch in each frame. With a pre-computed visibility map, we are able to efficiently estimate the indirect illumination in parallel on graphics hardware, by simply summing up the radiance shoots from cluster representatives, plus a small number of operations of merging and splitting on clusters. With relighting based on the time-varying clusters, interactive update of global illumination effects with multi-bounced indirect lighting is demonstrated in applications to material animation and scene decoration.

ELT Materials Design of a Speaking Unit based on Needs Analysis

In this article,the authors design a speaking unit based on needs analysis following Hutchinson and Waters'(1987) model.First,the rationale in designing this unit is introduced,which involves the teaching approach adopted and relevant theories in organizing the materials.Then,the teaching plan of this speaking unit is provided and some activities are designed to create an authentic and optimal situation for students to practice their speaking skill.