Search Results for data-driven optimization

Process optimization is the discipline of adjusting a process to optimize a specified set of parameters without violating engineering constraints. This article reviews data-driven optimization methods based on genetic algorithms and stochastic models and demonstrates their use in powder-bed fusion and directed energy deposition processes. In the latter case, closed-loop feedback is used to control melt pool temperature and cooling rate in order to achieve desired microstructure.

This article presents the analytics challenges in additive manufacturing. It discusses the types and applications of data analytics. Data analytics can be classified into four types: descriptive, diagnostic, predictive, and prescriptive. The diverse applications of data analytics and machine learning include design, process-structure-properties (PSP) relationships, and process monitoring and quality control. The article also presents tools used for data analytics.

Data formats play an integral role in leveraging the flexibility of additive manufacturing and achieving consistent part quality. This article compares and contrasts data formats optimized for design, materials, processes, and inspection methods. It also discusses the types of data associated with the six phases of additive manufacturing, namely design, build, design with build plan, design with machine-specific build plan, post-processed part, and qualified part.

Additive manufacturing (AM) provides exceptional design flexibility, enabling the manufacture of parts with shapes and functions not viable with traditional manufacturing processes. The two paradigms aiming to leverage computational methods to design AM parts imbuing the design-for-additive-manufacturing (DFAM) principles are design optimization (DO) and simulation-driven design (SDD). In line with the adoption of AM processes by industry and extensive research efforts in the research community, this article focuses on powder-bed fusion for metal AM and material extrusion for polymer AM. It includes detailed sections on SDD and DO as well as three case studies on the adoption of SDD, DO, and artificial-intelligence-based DFAM in real-life engineering applications, highlighting the benefits of these methods for the wider adoption of AM in the manufacturing industry.

This article focuses specifically on material modeling applied to structure-property predictions. It provides general guidelines and considerations in terms of modeling the salient material features that ultimately impact the mechanical performance of parts produced by additive manufacturing (AM). Two of the primary ingredients needed to predict structure-property relationships via material modeling include a geometrical representation of the microstructural features of interest (e.g., grain structure and void defects) and a suitable constitutive model describing the material behavior, both of which can be scale and resource dependent. The article also presents modeling challenges to predict various aspects of (process-) structure-property relationships in AM.

This article focuses on the technologies and applications of additive manufacturing (AM) in the oil and gas industry. It then presents the challenges of AM and the oil and gas industry. The article provides a detailed description of the critical steps in the AM process chain, including part selection, design optimization, and process planning, control, and inspection. Qualification and certification standardization is discussed, as is a commitment to reduce the carbon footprint of the manufacturing sector through AM. It ends with the future outlook of AM in the oil and gas industry.

This datasheet provides information on key alloy metallurgy and processing effects on mechanical properties of Al-Li plate alloy 2195. A figure provides a performance comparison of 2195-T84 and 2219-T87 alloys.

The article provides an overview of the various types of testing machines: gear-driven or screw-driven machines and servohydraulic machines. It examines force application systems, force measurement, and strain measurement. The article discusses important instrument considerations and describes gripping techniques of test specimens. It analyzes test diagnostics and reviews the use of computers for gathering and reducing data. Emphasis is placed on universal testing machines with separate discussions of equipment factors for tensile testing and compressing testing. The influence of the machine stiffness on the test results is also described, along with a general assessment of test accuracy, precision, and repeatability of modern equipment.

In situ process monitoring includes any technologies that monitor or inspect during an additive manufacturing (AM) process. This article presents the types, process considerations, and challenges of in situ monitoring technologies that can be implemented during an AM process. The types include system health monitoring, melt pool monitoring, and layer monitoring. The article discusses data analysis, and provides an overview of the integration of sensors into AM machines.

This article provides an introduction to architected cellular materials, their design, fabrication, and application domain. It discusses design decisions involving the selection, sizing, and spatial distribution of the unit cell, property-scaling relationships, and the integration of cells within an external boundary. It describes how manufacturing constraints influence achievable feature resolution, dimensional accuracy, properties, and defects. It also discusses the mechanical behavior of architected cellular materials and the role of additive manufacturing in their fabrication.

This article focuses on the pneumatic extrusion-based system for biomaterials. It provides an overview of additive manufacturing (AM) processes, followed by sections covering steps and major approaches for the 3D bioprinting process. Then, the article discusses the types, processes, advantages, limitations, and applications of AM technology and extrusion-based approaches. Next, it provides information on the research on extrusion-based printing. Finally, the article provides a comparison of the extrusion-based approach with other approaches.

Additive manufacturing produces a change in the shape of a substrate by adding material progressively. This article discusses the simulation of laser deposition and three principal thermomechanical phenomena during the laser deposition process: absorption of laser radiation; heat conduction, convection, and phase change; and elastic-plastic deformation. It provides a description of four sets of data used for modeling and simulation of additive manufacturing processes, namely, material constitutive data, solid model, initial and boundary conditions, and laser deposition process parameters. The article considers three aspects of simulation of additive manufacturing: simulation for initial selection of process parameter setup, simulation for in situ process control, and simulation for ex situ process optimization. It also presents some examples of computational mechanics solutions for automating various components of additive manufacturing simulation.

Diffusion is the process by which molecules, atoms, ions, point defects, or other particle types migrate from a region of higher concentration to one of lower concentration. This article focuses on the diffusivity data and modeling of lattice diffusion in solid-state materials, presenting their diffusion equations. It discusses different methods for evaluating the diffusivity of a material, including the measurement of diffusion coefficients, composition profiles, and layer growth widths. The article reviews the various types of direct and indirect diffusion experiments to extract tracer, intrinsic, and chemical diffusivities. It provides information on the applications of single-phase and multiphase diffusion.

For forming processes, optimization goals range from tuning the process parameters while keeping geometry unchanged to finding optimal geometry for intermediate dies in a multistage forming operation. This article commences with a description on the three salient steps of optimization procedures: defining the objective function, calculating the objective function, and searching an optimum design. It concludes with an example illustrating the optimization of conical-die extrusion.

This article demonstrates the depth and breadth of commercial and third-party software packages available to simulate metals processes. It provides a representation of the spectrum of applications from simulation of atomic-level effects to manufacturing optimization. The article tabulates the software name, function or process applications, vendor or developer, and website information.

Neural-network (NN) modeling is most suitable for simulations of correlations that are hard to describe or cannot be accurately predicted by physical models. This article describes the principles and procedures of NN modeling. It discusses the use of NN modeling in general organization of software and graphical user interfaces. The article also provides information on the ways to improve and upgrade the NN models.

This article describes the process applications, advantages, and limitations of resistance seam welding. The fundamentals of lap seam welding are also reviewed. The article details the types of seam welds, namely, lap seam welds and mash seam welds, and the processing equipment used for lap seam welding. The primary factors used to determine the selection of electrodes, including alloy type and wheel configuration, are reviewed. The article also describes weld quality and process control procedures.

The use of additive manufacturing (AM) is increasing for high-value, critical applications across a range of disparate industries. This article presents a discussion of high-valued engineering components predominantly used in the aerospace and medical industries. Applications involving metal AM, including methods to identify pores and voids in AM materials, are the focus. The article reviews flaw formation in laser-based powder-bed fusion, summarizes sensors used for in situ process monitoring, and outlines advances made with in situ process-monitoring data to detect AM process flaws. It reviews investigations of ML-based strategies, identifies challenges and research opportunities, and presents strategies for assessing anomaly detection performance.

This article details findability, accessibility, interoperability, and reusability (FAIR) additive manufacturing data management principles and examines related motivations, benefits, and challenges. It explains opportunities to advance the state of the AM community efforts in fostering FAIR data management practices/principles and outlines the consequence of such efforts on technology maturation and industrialization for AM technologies.

Solid modeling is the act of creating the three-dimensional models of various components and system using a computer-aided design (CAD) tool. This article describes the fundamental approaches of solid modeling, such as manufacturing operation simulation, parametric approach, and reference entities. It discusses the application of solid modeling systems to create expressions or variables and various surfaces for components. The use of high-end CAD systems to afford a number of sheet metal functions is reviewed. The article explains the explicit-parametric modeling and model verification for the solid modeling. It provides information on the application of solid modeling in associativity and concurrent engineering, product lifecycle management, and collaborative engineering.