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.

Machine learning design of 400 MPa grade biodegradable Zn-Mn based alloys with appropriate corrosion rates

The commonly used trial-and-error method of biodegradable Zn alloys is costly and blindness.In this study,based on the self-built database of biodegradable Zn alloys,two machine learning models are established by the first time to predict the ultimate tensile strength(UTS)and immersion corrosion rate(CR)of biodegradable Zn alloys.A real-time visualization interface has been established to design Zn-Mn based alloys;a representative alloy is Zn-0.4Mn-0.4Li-0.05Mg.Through tensile mechanical properties and immersion corrosion rate tests,its UTS reaches 420 MPa,and the prediction error is only 0.95%.CR is 73μm/a and the prediction error is 5.5%,which elevates 50 MPa grade of UTS and owns appropriate corrosion rate.Finally,influences of the selected features on UTS and CR are discussed in detail.The combined application of UTS and CR model provides a new strategy for synergistically regulating comprehens-ive properties of biodegradable Zn alloys.

Ab Initio Design of Ni-Rich Cathode Material with Assistance of Machine Learning for High Energy Lithium-Ion Batteries

With the widespread use of lithium-ion batteries in electric vehicles,energy storage,and mobile terminals,there is an urgent need to develop cathode materials with specific properties.However,existing material control synthesis routes based on repetitive experiments are often costly and inefficient,which is unsuitable for the broader application of novel materials.The development of machine learning and its combination with materials design offers a potential pathway for optimizing materials.Here,we present a design synthesis paradigm for developing high energy Ni-rich cathodes with thermal/kinetic simulation and propose a coupled image-morphology machine learning model.The paradigm can accurately predict the reaction conditions required for synthesizing cathode precursors with specific morphologies,helping to shorten the experimental duration and costs.After the model-guided design synthesis,cathode materials with different morphological characteristics can be obtained,and the best shows a high discharge capacity of 206 mAh g^(−1)at 0.1C and 83%capacity retention after 200 cycles.This work provides guidance for designing cathode materials for lithium-ion batteries,which may point the way to a fast and cost-effective direction for controlling the morphology of all types of particles.

Machine-Learning-Assisted Design of Deep Eutectic Solvents Based on Uncovered Hydrogen Bond Patterns

Non-ionic deep eutectic solvents(DESs)are non-ionic designer solvents with various applications in catalysis,extraction,carbon capture,and pharmaceuticals.However,discovering new DES candidates is challenging due to a lack of efficient tools that accurately predict DES formation.The search for DES relies heavily on intuition or trial-and-error processes,leading to low success rates or missed opportunities.Recognizing that hydrogen bonds(HBs)play a central role in DES formation,we aim to identify HB features that distinguish DES from non-DES systems and use them to develop machine learning(ML)models to discover new DES systems.We first analyze the HB properties of 38 known DES and 111 known non-DES systems using their molecular dynamics(MD)simulation trajectories.The analysis reveals that DES systems have two unique features compared to non-DES systems:The DESs have①more imbalance between the numbers of the two intra-component HBs and②more and stronger inter-component HBs.Based on these results,we develop 30 ML models using ten algorithms and three types of HB-based descriptors.The model performance is first benchmarked using the average and minimal receiver operating characteristic(ROC)-area under the curve(AUC)values.We also analyze the importance of individual features in the models,and the results are consistent with the simulation-based statistical analysis.Finally,we validate the models using the experimental data of 34 systems.The extra trees forest model outperforms the other models in the validation,with an ROC-AUC of 0.88.Our work illustrates the importance of HBs in DES formation and shows the potential of ML in discovering new DESs.

Transformer for the Design of Automatic Control Systems with Prefilters

A machine learning model, using the transformer architecture, is used to design a feedback compensator and prefilter for various simulated plants. The output of the transformer is a sequence of compensator and prefilter parameters. The compensator and prefilter are linear models, preserving the ability to analyze the system with linear control theory. The input to the network is a window of recent reference and output samples. The goal of the transformer is to minimize tracking error at each time step. The plants under consideration range from simple to challenging. The more difficult plants contain closely spaced, lightly damped, complex conjugate pairs of poles and zeros. Results are compared to PID controllers tuned for a similar crossover frequency and optimal phase margin. For simple plants, the transformer converges to solutions which overly rely on the prefilter, neglecting the maximization of negative feedback. For more complex plants, the transformer designs a compensator and prefilter with more desirable qualities. In all cases, the transformer can start with random model parameters and modify them to minimize tracking error on the step reference.

Recent progress in the machine learning-assisted rational design of alloys

Alloys designed with the traditional trial and error method have encountered several problems,such as long trial cycles and high costs.The rapid development of big data and artificial intelligence provides a new path for the efficient development of metallic materials,that is,machine learning-assisted design.In this paper,the basic strategy for the machine learning-assisted rational design of alloys was introduced.Research progress in the property-oriented reversal design of alloy composition,the screening design of alloy composition based on models established using element physical and chemical features or microstructure factors,and the optimal design of alloy composition and process parameters based on iterative feedback optimization was reviewed.Results showed the great advantages of machine learning,including high efficiency and low cost.Future development trends for the machine learning-assisted rational design of alloys were also discussed.Interpretable modeling,integrated modeling,high-throughput combination,multi-objective optimization,and innovative platform building were suggested as fields of great interest.

Kansei Engineering Applied to the Form Design of Injection Molding Machines

This study investigated the relationship between a subject’s evaluation of injection molding machines (IMMs) and formal design features using Kansei engineering. This investigation used 12 word pairs to evaluate the IMM configurations and employed the semantic differential method to explore the perception of 60 interviewees of 12 examples. The relationship between product feature design and corresponding words was derived by multiple regression analysis. Factor analysis reveals that the 12 examples can be categorized as two styles—advanced style and succinct style. For the advanced style, an IMM should use a rectangular form for the clamping-unit cover and a full-cover for the injection-unit. For the succinct style, the IMM configuration should use a beveled form for the safety cover and a vertical rectangular form for the clamping-unit cover. Quantitative data and suggested guidelines for the relationship between design features and interviewee evaluations are useful to product designers when formulating design strategies.

The Influence of a User-Centred Design Focus on the Effectiveness of a User Interface for an Agricultural Machine

As agricultural machines become more complex, it is increasingly critical that special attention be directed to the design of the user interface to ensure that the operator will have an adequate understanding of the status of the machine at all times. A user-centred design focus was employed to develop two conceptual designs (UCD1 & UCD2) for a user interface for an agricultural air seeder. The two concepts were compared against an existing user interface (baseline condition) using the metrics of situation awareness (Situation Awareness Global Assessment Technique), mental workload (Integrated Workload Scale), reaction time, and subjective feedback. There were no statistically significant differences among the three user interfaces based on the metric of situation awareness;however, UCD2 was deemed to be significantly better than either UCD1 or the baseline interface on the basis of mental workload, reaction time and subjective feedback. The research has demonstrated that a user-centred design focus will generate a better user interface for an agricultural machine.

Performance Evaluation and Comparison of Multi - Objective Optimization Algorithms for the Analytical Design of Switched Reluctance Machines

This paper systematically evaluates and compares three well-engineered and popular multi-objective optimization algorithms for the design of switched reluctance machines.The multi-physics and multi-objective nature of electric machine design problems are discussed,followed by benchmark studies comparing generic algorithms(GA),differential evolution(DE)algorithms and particle swarm optimizations(PSO)on a 6/4 switched reluctance machine design with seven independent variables and a strong nonlinear multi-objective Pareto front.To better quantify the quality of the Pareto fronts,five primary quality indicators are employed to serve as the algorithm testing metrics.The results show that the three algorithms have similar performances when the optimization employs only a small number of candidate designs or ultimately,a significant amount of candidate designs.However,DE tends to perform better in terms of convergence speed and the quality of Pareto front when a relatively modest amount of candidates are considered.

Accelerated design of high-performance Mg-Mn-based magnesium alloys based on novel bayesian optimization

Magnesium(Mg),being the lightest structural metal,holds immense potential for widespread applications in various fields.The development of high-performance and cost-effective Mg alloys is crucial to further advancing their commercial utilization.With the rapid advancement of machine learning(ML)technology in recent years,the“data-driven''approach for alloy design has provided new perspectives and opportunities for enhancing the performance of Mg alloys.This paper introduces a novel regression-based Bayesian optimization active learning model(RBOALM)for the development of high-performance Mg-Mn-based wrought alloys.RBOALM employs active learning to automatically explore optimal alloy compositions and process parameters within predefined ranges,facilitating the discovery of superior alloy combinations.This model further integrates pre-established regression models as surrogate functions in Bayesian optimization,significantly enhancing the precision of the design process.Leveraging RBOALM,several new high-performance alloys have been successfully designed and prepared.Notably,after mechanical property testing of the designed alloys,the Mg-2.1Zn-2.0Mn-0.5Sn-0.1Ca alloy demonstrates exceptional mechanical properties,including an ultimate tensile strength of 406 MPa,a yield strength of 287 MPa,and a 23%fracture elongation.Furthermore,the Mg-2.7Mn-0.5Al-0.1Ca alloy exhibits an ultimate tensile strength of 211 MPa,coupled with a remarkable 41%fracture elongation.

A REVIEW OF THE HISTORY OF CHINA'S MACHINE DESIGN METHODS AND THE PROSPECT

This paper examines the history of China’s machine design methods and its status quo. First of all, it discusses machine design methods in ancient China. (1)The design idea of creation by the intelligent and exposition by the ingenious. (2)The design principle of the dependence of workmanship on criteria. (3)A macroscopic view of the object of design. (4)The design method of manufacture emphasizing shape. (5)Technological requirements on excellent material and consummate skill. Second, it discusses machine design ideas in ancient China. (1)The system idea in machine design, (2)The idea of machine design.(3)The idea of standardization in machine design. (4)The idea of automation in machine design. Finally, it discusses the status quo and a look ahead of the theory of machine design in China.

Machine learning for membrane design and discovery

Membrane technologies are becoming increasingly versatile and helpful today for sustainable development.Machine Learning(ML),an essential branch of artificial intelligence(AI),has substantially impacted the research and development norm of new materials for energy and environment.This review provides an overview and perspectives on ML methodologies and their applications in membrane design and dis-covery.A brief overview of membrane technologies isfirst provided with the current bottlenecks and potential solutions.Through an appli-cations-based perspective of AI-aided membrane design and discovery,we further show how ML strategies are applied to the membrane discovery cycle(including membrane material design,membrane application,membrane process design,and knowledge extraction),in various membrane systems,ranging from gas,liquid,and fuel cell separation membranes.Furthermore,the best practices of integrating ML methods and specific application targets in membrane design and discovery are presented with an ideal paradigm proposed.The challenges to be addressed and prospects of AI applications in membrane discovery are also highlighted in the end.

NEW INSIGHTS INTO PRINCIPLES FOR DESIGNING ARCHITECTURE OF ENVIRONMENT SYSTEM FOR TOOL INTEGRATION ─IN THE CASE OF PRODUCTION MACHINES DESIGN

CAD/CAM integration is broadly viewed as tool integration. From this point of view, both CAD/CAM software and hardware are considered as tools. A great advantage of this view point is that a very flexible paradigm is introduced, in which the CAD/CAM system for a particular industrial application can be customized and built by selecting a set of tools. This paper intends to shed some lights on the principles for designing the architecture of such a tool integration environment. Although such an environment is no more than a computer program sys. tem itself, its particular characteristics arising from its unique role, i.e., tool integration, make the discussion on the designing of an environment architecture nontrivial. The paper externalizes the author's experiences in implementing an tool integration environment for production machines.In particular, the discussion renders some insights into the concepts such as tool integration models, various views of an environment architecture, classification of data into tool-data and environment data, and employment of the information relativity principle in making an environment architecture flexible. The paper will take production machines design as a target application that an environment system is developed for, owing to its extreme complexity and thus make sense of coverage of other engineering applications.

A graph neural network approach to the inverse design for thermal transparency with periodic interparticle system

Recent years have witnessed significant advances in utilizing machine learning-based techniques for thermal metamaterial-based structures and devices to attain favorable thermal transport behaviors.Among the various thermal transport behaviors,achieving thermal transparency stands out as particularly desirable and intriguing.Our earlier work demonstrated the use of a thermal metamaterial-based periodic interparticle system as the underlying structure for manipulating thermal transport behavior and achieving thermal transparency.In this paper,we introduce an approach based on graph neural network to address the complex inverse design problem of determining the design parameters for a thermal metamaterial-based periodic interparticle system with the desired thermal transport behavior.Our work demonstrates that combining graph neural network modeling and inference is an effective approach for solving inverse design problems associated with attaining desirable thermal transport behaviors using thermal metamaterials.

Convergence Analysis of the Numerical Solution for Cathode Design of Aero-engine Blades in Electrochemical Machining

As a main difficult problem encountered in electrochemical machining （ECM）, the cathode design is tackled, at present, with various numerical analysis methods such as finite difference, finite element and boundary element methods. Among them, the finite element method presents more flexibility to deal with the irregularly shaped workpieces. However, it is very difficult to ensure the convergence of finite element numerical approach. This paper proposes an accurate model and a finite element numerical approach of cathode design based on the potential distribution in inter-electrode gap. In order to ensure the convergence of finite element numerical approach and increase the accuracy in cathode design, the cathode shape should be iterated to eliminate the design errors in computational process. Several experiments are conducted to verify the machining accuracy of the designed cathode. The experimental results have proven perfect convergence and good computing accuracy of the proposed finite element numerical approach by the high surface quality and dimensional accuracy of the machined blades.

Big Data Creates New Opportunities for Materials Research: A Review on Methods and Applications of Machine Learning for Materials Design

Materials development has historically been driven by human needs and desires, and this is likely to con- tinue in the foreseeable future. The global population is expected to reach ten billion by 2050, which will promote increasingly large demands for clean and high-ef ciency energy, personalized consumer prod- ucts, secure food supplies, and professional healthcare. New functional materials that are made and tai- lored for targeted properties or behaviors will be the key to tackling this challenge. Traditionally, advanced materials are found empirically or through experimental trial-and-error approaches. As big data generated by modern experimental and computational techniques is becoming more readily avail- able, data-driven or machine learning (ML) methods have opened new paradigms for the discovery and rational design of materials. In this review article, we provide a brief introduction on various ML methods and related software or tools. Main ideas and basic procedures for employing ML approaches in materials research are highlighted. We then summarize recent important applications of ML for the large-scale screening and optimal design of polymer and porous materials, catalytic materials, and energetic mate- rials. Finally, concluding remarks and an outlook are provided.

A Finite and Instantaneous Screw Based Approach for Topology Design and Kinematic Analysis of 5-Axis Parallel Kinematic Machines

Unifying the models for topology design and kinematic analysis has long been a desire for the research of parallel kinematic machines(PKMs). This requires that analytical description, formulation and operation for both finite and instantaneous motions are performed by the same mathematical tool. Based upon finite and instantaneous screw theory, a unified and systematic approach for topology design and kinematic analysis of PKMs is proposed in this paper. Using the derivative mapping between finite and instantaneous screws built in the authors’ previous work, the finite and instantaneous motions of PKMs are analytically described by the simple and non?redundant screws in quasi?vector and vector forms. And topological and parametric models of PKMs are algebraically formulated and related. These related topological and parametric models are ready to do type synthesis and kinematic analysis of PKMs under the unified framework of screw theory. In order to show the validity of the proposed approach, a kind of two?translational and three?rotational(2T3R)5?axis PKMs is taken as example. Numerous new structures of the 2T3R PKMs are synthe?sized as the results of topology design, and their Jacobian matrix is obtained easily for parameter optimization and performance evaluation. Some of the synthesized PKMs have outstanding capabilities in terms of large workspaces and flexible orientations, and have great potential for industrial applications of machining and manufacture. Among them, METROM PKM is a typical example which has attracted a lot of attention from global companies and already been developed as commercial products. The approach is a general and unified approach that can be used in the innovative design of different kinds of PKMs.

RESEARCH ON THE GENERALIZED MODULAR DESIGN METHOD WITH FLEXIBLE MODULES OF PRODUCT STRUCTURES

A new generalized modular design (GMD) method is proposed based on designpractice of frame structure of hydraulic press machines. By building a series of flexible modules(FMs), design knowledge and structure features are integrated into parametric models. Then,parametric design and variational analysis methods for GMD are presented according to user defineddesign objectives and customized product characteristics. A FM-centered GMD system is developed andsuccessfully used in the rapid design of relevant products.

ADAPTABLE DESIGN OF MACHINE TOOLS STRUCTURES

Adaptable design aims to extend the utilities of design and product. The specific methods are developed for practical applications of adaptable design in the design of mechanical structures, including adaptable platform, interface and module designs. Adaptable redesign problems are formulated as adaptable platform design under adaptability bound constraints. Analysis tools are then suggested for the implementation of the redesign of machine tool structures, including variation techniques based sensitivity analysis, similarity-based commonality analysis, performance improvement, and adaptability measures. The specific measure of adaptability for machine tool structures is measured through the quantification of the structural similarity and performance improvement gained from adaptable design. The method provides designers with an approach that brings adaptability into the design process, with considering the cost and benefits of such adaptability. The redesign of CNC spiral bevel gear cutting machine structures has been included to illustrate these concepts and methods.

KINEMATIC DESIGN OF A RECONFIGURABLE MINIATURE PARALLEL KINEMATIC MACHINE

The kinematic design of a reconfigurable miniature parallel kinematic machineis dealt with. It shows that the reconfigurability may be realized by packaging a tripod-basedparallel mechanism with fixed length struts into a compact and rigid frame with which the differentconfigurations can be formed. Utilizing a dual parameter model, the influences of the geometricalparameters on the dexterous performance and the workspace/machine volume ratio are investigated. Anovel global performance index for the dimensional synthesis is proposed and optimized, resulting ina set of dimensionless geometrical parameters.