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.

A HybridManufacturing ProcessMonitoringMethod Using Stacked Gated Recurrent Unit and Random Forest

This study proposed a new real-time manufacturing process monitoring method to monitor and detect process shifts in manufacturing operations.Since real-time production process monitoring is critical in today’s smart manufacturing.The more robust the monitoring model,the more reliable a process is to be under control.In the past,many researchers have developed real-time monitoring methods to detect process shifts early.However,thesemethods have limitations in detecting process shifts as quickly as possible and handling various data volumes and varieties.In this paper,a robust monitoring model combining Gated Recurrent Unit(GRU)and Random Forest(RF)with Real-Time Contrast(RTC)called GRU-RF-RTC was proposed to detect process shifts rapidly.The effectiveness of the proposed GRU-RF-RTC model is first evaluated using multivariate normal and nonnormal distribution datasets.Then,to prove the applicability of the proposed model in a realmanufacturing setting,the model was evaluated using real-world normal and non-normal problems.The results demonstrate that the proposed GRU-RF-RTC outperforms other methods in detecting process shifts quickly with the lowest average out-of-control run length(ARL1)in all synthesis and real-world problems under normal and non-normal cases.The experiment results on real-world problems highlight the significance of the proposed GRU-RF-RTC model in modern manufacturing process monitoring applications.The result reveals that the proposed method improves the shift detection capability by 42.14%in normal and 43.64%in gamma distribution problems.

Exploration and Application Practice of Energy Conservation Theory and Method in Steel Manufacturing Process System

This article briefly discusses the theoretical basis and overall goals of energy conservation in the steel manufacturing process system.It is proposed that in the process of implementing system energy conservation,it is necessary to fully recognize and utilize the characteristics and functional advantages of the steel manufacturing process,pay more attention to energy quality,firmly grasp the overall goal of system optimization,focus on the integrated optimization of gas,steam,and waste heat systems,and propose the idea of constructing a"steel chemi-cal gas electricity heating cooling multi generation system".Based on practice,the main principles,models,and effects of implementing systematic energy conservation in steel enterprises have been proposed.

An Interpretable Light Attention-Convolution-Gate Recurrent Unit Architecture for the Highly Accurate Modeling of Actual Chemical Dynamic Processes

To equip data-driven dynamic chemical process models with strong interpretability,we develop a light attention–convolution–gate recurrent unit(LACG)architecture with three sub-modules—a basic module,a brand-new light attention module,and a residue module—that are specially designed to learn the general dynamic behavior,transient disturbances,and other input factors of chemical processes,respectively.Combined with a hyperparameter optimization framework,Optuna,the effectiveness of the proposed LACG is tested by distributed control system data-driven modeling experiments on the discharge flowrate of an actual deethanization process.The LACG model provides significant advantages in prediction accuracy and model generalization compared with other models,including the feedforward neural network,convolution neural network,long short-term memory(LSTM),and attention-LSTM.Moreover,compared with the simulation results of a deethanization model built using Aspen Plus Dynamics V12.1,the LACG parameters are demonstrated to be interpretable,and more details on the variable interactions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM.This contribution enriches interpretable machine learning knowledge and provides a reliable method with high accuracy for actual chemical process modeling,paving a route to intelligent manufacturing.

Challenges and opportunities in the production of magnesium parts by directed energy deposition processes

Mg-alloys have gained considerable attention in recent years for their outstanding properties such as lightweight,high specific strength,and corrosion resistance,making them attractive for applications in medical,aerospace,automotive,and other transport industries.However,their widespread application is hindered by their low formability at room temperature due to limited slip systems.Cast Mg-alloys have low mechanical properties due to the presence of casting defects such as porosity and anisotropy in addition to the high scrap.While casting methods benefit from established process optimization techniques for these problems,additive manufacturing methods are increasingly replacing casting methods in Mg alloys as they provide more precise control over the microstructure and allow specific grain orientations,potentially enabling easier optimization of anisotropy properties in certain applications.Although metal additive manufacturing(MAM)technology also results in some manufacturing defects such as inhomogeneous microstructural evolution and porosity and additively manufactured Mg alloy parts exhibit lower properties than the wrought parts,they in general exhibit superior properties than the cast counterparts.Thus,MAM is a promising technique to produce Mg alloy parts.Directed energy deposition processes,particularly wire arc directed energy deposition(WA-DED),have emerged as an advantageous additive manufacturing(AM)technique for metallic materials including magnesium alloys,offering advantages such as high deposition rates,improved material efficiency,and reduced production costs compared to subtractive processes.However,the inherent challenges associated with magnesium,such as its high reactivity and susceptibility to oxidation,pose unique hurdles in the application of this technology.This review paper delves into the progress made in the application of DED technology to Mg-alloys,its challenges,and prospects.Furthermore,the predominant imperfections,notably inhomogeneous microstructure evolution and porosity,observed in Mg-alloy components manufactured through DED are discussed.Additionally,the preventive measures implemented to counteract the formation of these defects are explored.

Mechanical and corrosion properties of full liquid phase sintered WE43 magnesium alloy specimens fabricated via binder jetting additive manufacturing

This study investigates full liquid phase sintering as a process of fabrication parts from WE43(Mg-4wt.%Y-3wt.%RE-0.7wt.%Zr)alloy using binder jetting additive manufacturing(BJAM).This fabrication process is being developed for use in producing structural or biomedical devices.Specifically,this study focused on achieving a near-dense microstructure with WE43 Mg alloy while substantially reducing the duration of sintering post-processing after BJAM part rendering.The optimal process resulted in microstructure with 2.5%porosity and significantly reduced sintering time.The improved sintering can be explained by the presence of Y_(2)O_(3)and Nd_(2)O_(3)oxide layers,which form spontaneously on the surface of WE43 powder used in BJAM.These layers appear to be crucial in preventing shape distortion of the resulting samples and in enabling the development of sintering necks,particularly under sintering conditions exceeding the liquidus temperature of WE43 alloy.Sintered WE43 specimens rendered by BJAM achieved significant improvement in both corrosion resistance and mechanical properties through reduced porosity levels related to the sintering time.

Advances of embedded resistive random access memory in industrial manufacturing and its potential applications

Embedded memory,which heavily relies on the manufacturing process,has been widely adopted in various industrial applications.As the field of embedded memory continues to evolve,innovative strategies are emerging to enhance performance.Among them,resistive random access memory(RRAM)has gained significant attention due to its numerousadvantages over traditional memory devices,including high speed(<1 ns),high density(4 F^(2)·n^(-1)),high scalability(~nm),and low power consumption(~pJ).This review focuses on the recent progress of embedded RRAM in industrial manufacturing and its potentialapplications.It provides a brief introduction to the concepts and advantages of RRAM,discusses the key factors that impact its industrial manufacturing,and presents the commercial progress driven by cutting-edge nanotechnology,which has been pursued by manysemiconductor giants.Additionally,it highlights the adoption of embedded RRAM in emerging applications within the realm of the Internet of Things and future intelligent computing,with a particular emphasis on its role in neuromorphic computing.Finally,the review discusses thecurrent challenges and provides insights into the prospects of embedded RRAM in the era of big data and artificial intelligence.

Laser-based bionic manufacturing

Over millions of years of natural evolution,organisms have developed nearly perfect structures and functions.The self-fabrication of organisms serves as a valuable source of inspiration for designing the next-generation of structural materials,and is driving the future paradigm shift of modern materials science and engineering.However,the complex structures and multifunctional integrated optimization of organisms far exceed the capability of artificial design and fabrication technology,and new manufacturing methods are urgently needed to achieve efficient reproduction of biological functions.As one of the most valuable advanced manufacturing technologies of the 21st century,laser processing technology provides an efficient solution to the critical challenges of bionic manufacturing.This review outlines the processing principles,manufacturing strategies,potential applications,challenges,and future development outlook of laser processing in bionic manufacturing domains.Three primary manufacturing strategies for laser-based bionic manufacturing are elucidated:subtractive manufacturing,equivalent manufacturing,and additive manufacturing.The progress and trends in bionic subtractive manufacturing applied to micro/nano structural surfaces,bionic equivalent manufacturing for surface strengthening,and bionic additive manufacturing aiming to achieve bionic spatial structures,are reported.Finally,the key problems faced by laser-based bionic manufacturing,its limitations,and the development trends of its existing technologies are discussed.

An Edge-Fog-Cloud Computing-Based Digital Twin Model for Prognostics Health Management of Process Manufacturing Systems

The prognostics health management(PHM)fromthe systematic viewis critical to the healthy continuous operation of processmanufacturing systems(PMS),with different kinds of dynamic interference events.This paper proposes a three leveled digital twinmodel for the systematic PHMof PMSs.The unit-leveled digital twinmodel of each basic device unit of PMSs is constructed based on edge computing,which can provide real-time monitoring and analysis of the device status.The station-leveled digital twin models in the PMSs are designed to optimize and control the process parameters,which are deployed for the manufacturing execution on the fog server.The shop-leveled digital twin maintenancemodel is designed for production planning,which gives production instructions fromthe private industrial cloud server.To cope with the dynamic disturbances of a PMS,a big data-driven framework is proposed to control the three-level digital twin models,which contains indicator prediction,influence evaluation,and decisionmaking.Finally,a case study with a real chemical fiber system is introduced to illustrate the effectiveness of the digital twin model with edge-fog-cloud computing for the systematic PHM of PMSs.The result demonstrates that the three-leveled digital twin model for the systematic PHM in PMSs works well in the system’s respects.

Simulation Research on the Effect of Spreading Process Parameters on the Quality of Lunar Regolith Powder Bed in Additive Manufacturing

Lunar surface additive manufacturing with lunar regolith is a key step in in-situ resource utilization.The powder spreading process is the key process,which has a major impact on the quality of the powder bed and the precision of molded parts.In this study,the discrete element method(DEM)was adopted to simulate the powder spreading process with a roller.The three powder bed quality indicators,including the molding layer offset,voidage fraction,and surface roughness,were established.Besides,the influence of the three process parameters,which are roller’s translational speed,rotational speed,and powder spreading layer thickness on the powder bed quality indicators was also analyzed.The results show that with the reduction of the powder spreading layer thickness and the increase of the rotational speed,the offset increased significantly;when the translational speed increased,the offset first increased and then decreased,which resulted in an extreme value;with the increase of the layer thickness and the decrease of the translational speed,the values for voidage fraction and surface roughness significantly reduced.The powder bed quality indicators were adopted as the optimization objective,and the multi-objective parameter optimization was carried out.The predicted optimal powder spreading parameters and powder bed quality indicators were then obtained.Moreover,the optimal values were then verified.This study can provide informative guidance for in-situ manufacturing at the moon in future deep space exploration missions.

Micro-scale Realization of Compliant Mechanisms:Manufacturing Processes and Constituent Materials-A Review

Compliant micromechanisms(CMMs)acquire mobility from the deflection of elastic members and have been proven to be robust by millions of silicon MEMS devices.However,the limited deflection of silicon impedes the realization of more sophisticated CMMs,which often require larger deflections.Recently,some novel manufacturing processes have emerged but are not well known by the community.In this paper,the realization of CMMs is reviewed,aiming to provide help to mechanical designers to quickly find the proper realization method for their CMM designs.To this end,the literature surveyed was classified and statistically analyzed,and representative processes were summarized individually to reflect the state of the art of CMM manufacturing.Furthermore,the features of each process were collected into tables to facilitate the reference of readers,and the guidelines for process selection were discussed.The review results indicate that,even though the silicon process remains dominant,great progress has been made in the development of polymer-related and composite-related processes,such as micromolding,SU-8 process,laser ablation,3D printing,and the CNT frameworking.These processes result in constituent materials with a lower Young’s modulus and larger maximum allowable strain than silicon,and therefore allow larger deflection.The geometrical capabilities(e.g.,aspect ratio)of the realization methods should also be considered,because different types of CMMs have different requirements.We conclude that the SU-8 process,3D printing,and carbon nanotube frameworking will play more important roles in the future owing to their excellent comprehensive capabilities.

Research on Business Processes Optimization for Agile Manufacturing

Based on macroscopic and synthetic approaches, especially information entropy approach, the quantification of the flexible degree and order degree of business processes is studied. According to the outcome of above analysis, a conceptual model of optimizing business processes is proposed which supports to construct dynamic stable business processes. The research above has been applied in project 863/SDDAC-CIMS, and achieved primary benefits.

WEB-BASED MANUFACTURING PROCESS DEVELOPER

Product and manufacturing process developments are knowledge intensive. For rapid product developments in today′s competitive global marketplace, we need tools to facilitate the effective utilization of critical design and manufacturing knowledge obtained during the previous product developments. The Internet technology has very rapidly evolved over past few years. The web is being increasingly used to support various activities of the pro duct development process. Java is a programming language that is highly tuned for the web environment. This paper is concerned with providing the solution of web based manufacturing process development. The architecture of web based application and the implementation of web based manufacturing process developer are discussed.

Fundamental Theories and Key Technologies for Smart andOptimal Manufacturing in the Process Industry

Given the significant requirements for transforming and promoting the process industry, we present themajor limitations of current petrochemical enterprises, including limitations in decision-making, produc-tion operation, efficiency and security, information integration, and so forth. To promote a vision of theprocess industry with efficient, green, and smart production, modern information technology should beutilized throughout the entire optimization process for production, management, and marketing. To focuson smart equipment in manufacturing processes, as well as on the adaptive intelligent optimization of themanufacturing process, operating mode, and supply chain management, we put forward several key scien-tific problems in engineering in a demand-driven and application-oriented manner, namely：intelligentsensing and integration of all process information, including production and management information; collaborative decision-making in the supply chain, industry chain, and value chain, driven by knowledge; cooperative control and optimization of plant-wide production processes via human-cyber-physical in-teraction; and Q life-cycle assessments for safety and environmental footprint monitoring, in addition totracing analysis and risk control. In order to solve these limitations and core scientific problems, we furtherpresent fundamental theories and key technologies for smart and optimal manufacturing in the processindustry. Although this paper discusses the process industry in China, the conclusions in this paper can beextended to the larocess industry around the world.

A Perspective on Smart Process Manufacturing Research Challenges forProcess Systems Engineers

The challenges posed by smart manufacturing for the process industries and for process systems engineering（PSE） researchers are discussed in this article. Much progress has been made in achieving plant- and site-wide optimization, hut benchmarking would give greater confidence. Technical challenges confrontingprocess systems engineers in developing enabling tools and techniques are discussed regarding flexibilityand uncertainty, responsiveness and agility, robustness and security, the prediction of mixture propertiesand function, and new modeling and mathematics paradigms. Exploiting intelligence from big data to driveagility will require tackling new challenges, such as how to ensure the consistency and confidentiality ofdata through long and complex supply chains. Modeling challenges also exist, and involve ensuring that allkey aspects are properly modeled, particularly where health, safety, and environmental concerns requireaccurate predictions of small but critical amounts at specific locations. Environmental concerns will requireus to keep a closer track on all molecular species so that they are optimally used to create sustainablesolutions. Disruptive business models may result, particularly from new personalized products, but that isdifficult to predict.

Calculating Method for Influence of Material Flow on Energy Consumption in Steel Manufacturing Process

From the viewpoint of systems energy conservation, the influences of material flow on its energy consumption in a steel manufacturing process is an important subject. The quantitative analysis of the relationship between material flow and the energy intensity is useful to save energy in steel industry. Based on the concept of standard material flow diagram, all possible situations of ferric material flow in steel manufacturing process are analyzed. The expressions of the influence of material flow deviated from standard material flow diagram on energy consumption are put forward.

Opportunities and Challenges of Artificial Intelligence for Green Manufacturing in the Process Industry

Smart manufacturing is critical in improving the quality of the process industry. In smart manufacturing, there is a trend to incorporate different kinds of new-generation information technologies into process- safety analysis. At present, green manufacturing is facing major obstacles related to safety management, due to the usage of large amounts of hazardous chemicals, resulting in spatial inhomogeneity of chemical industrial processes and increasingly stringent safety and environmental regulations. Emerging informa- tion technologies such as arti cial intelligence (AI) are quite promising as a means of overcoming these dif culties. Based on state-of-the-art AI methods and the complex safety relations in the process industry, we identify and discuss several technical challenges associated with process safety: ① knowledge acquisition with scarce labels for process safety;② knowledge-based reasoning for process safety;③ accurate fusion of heterogeneous data from various sources;and ④ effective learning for dynamic risk assessment and aided decision-making. Current and future works are also discussed in this context.

Advanced Data Collection and Analysis in Data‑Driven Manufacturing Process

The rapidly increasing demand and complexity of manufacturing process potentiates the usage of manufacturing data with the highest priority to achieve precise analyze and control,rather than using simplified physical models and human expertise.In the era of data-driven manufacturing,the explosion of data amount revolutionized how data is collected and analyzed.This paper overviews the advance of technologies developed for in-process manufacturing data collection and analysis.It can be concluded that groundbreaking sensoring technology to facilitate direct measurement is one important leading trend for advanced data collection,due to the complexity and uncertainty during indirect measurement.On the other hand,physical model-based data analysis contains inevitable simplifications and sometimes ill-posed solutions due to the limited capacity of describing complex manufacturing process.Machine learning,especially deep learning approach has great potential for making better decisions to automate the process when fed with abundant data,while trending data-driven manufacturing approaches succeeded by using limited data to achieve similar or even better decisions.And these trends can demonstrated be by analyzing some typical applications of manufacturing process.

Operation optimization of the steel manufacturing process: A brief review

Against the realistic background of excess production capacity, product structure imbalance, and high material and energy consumption in steel enterprises, the implementation of operation optimization for the steel manufacturing process is essential to reduce the production cost, increase the production or energy efficiency, and improve production management. In this study, the operation optimization problem of the steel manufacturing process, which needed to go through a complex production organization from customers' orders to workshop production, was analyzed. The existing research on the operation optimization techniques, including process simulation, production planning, production scheduling, interface scheduling, and scheduling of auxiliary equipment, was reviewed. The literature review reveals that, although considerable research has been conducted to optimize the operation of steel production, these techniques are usually independent and unsystematic.Therefore, the future work related to operation optimization of the steel manufacturing process based on the integration of multi technologies and the intersection of multi disciplines were summarized.

Data Analytics and Machine Learning for Smart Process Manufacturing: Recent Advances and Perspectives in the Big Data Era

Safe, ef cient, and sustainable operations and control are primary objectives in industrial manufacturing processes. State-of-the-art technologies heavily rely on human intervention, thereby showing apparent limitations in practice. The burgeoning era of big data is in uencing the process industries tremendously, providing unprecedented opportunities to achieve smart manufacturing. This kind of manufacturing requires machines to not only be capable of relieving humans from intensive physical work, but also be effective in taking on intellectual labor and even producing innovations on their own. To attain this goal, data analytics and machine learning are indispensable. In this paper, we review recent advances in data analytics and machine learning applied to the monitoring, control, and optimization of industrial processes, paying particular attention to the interpretability and functionality of machine learning mod- els. By analyzing the gap between practical requirements and the current research status, promising future research directions are identi ed.