Additive manufacturing (AM) has undergone significant development over the past decades, resulting in vast amounts of data that carry valuable information. Numerous research studies have been conducted to extract insights from AM data and utilize it for optimizing various aspects such as the manufacturing process, supply chain, and real-time monitoring. Data integration into proposed digital twin frameworks and the application of machine learning techniques is expected to play pivotal roles in advancing AM in the future. In this paper, we provide an overview of machine learning and digital twin-assisted AM. On one hand, we discuss the research domain and highlight the machine-learning methods utilized in this field, including material analysis, design optimization, process parameter optimization, defect detection and monitoring, and sustainability. On the other hand, we examine the status of digital twin-assisted AM from the current research status to the technical approach and offer insights into future developments and perspectives in this area. This review paper aims to examine present research and development in the convergence of big data, machine learning, and digital twin-assisted AM. Although there are numerous review papers on machine learning for additive manufacturing and others on digital twins for AM, no existing paper has considered how these concepts are intrinsically connected and interrelated. Our paper is the first to integrate the three concepts big data, machine learning, and digital twins and propose a cohesive framework for how they can work together to improve the efficiency, accuracy, and sustainability of AM processes. By exploring latest advancements and applications within these domains, our objective is to emphasize the potential advantages and future possibilities associated with integration of these technologies in AM. 

Big data, machine learning, and digital twin assisted additive manufacturing: a review

Current engineering processes are heavily document-centric, which can add time and cost to projects, limit data accessibility, and make it difficult to actively manage models and data consistency throughout the lifecycle of a product. Additionally, traditional data siloes limit data accessibility across departments. Similar issues exist with tools: departments use software with different standards and formats, making it time-consuming and difficult to accurately propagate changes and requirements throughout. Aerospace projects and vehicles are also often a level of magnitude more complex than products developed in other industries, requiring the coupling of multiple disciplines, which intensifies these problems. Digital Engineering and Model-Based Systems Engineering (MBSE) provide the context, methodologies and tools to address some of the aforementioned challenges. In particular, this paper presents the development and implementation of a Digital Thread proof-of-concept for a minimum viable product. In doing so this research demonstrates solutions to the challenges of data acquisition and management, model and data connectivity, tool and platform integration, eventually leading to the realization of an authoritative source of truth across the product’s lifecycle. Additionally, this research highlights some of the key benefits brought about by the Digital Thread, which include increased collaboration and communication, managed consistency across models and data, as well as the ability to conduct model verification, validation, and calibration - an important tenet of MBSE. 

/pdf/implementing-the-digital-thread-a-proof-of-concept-15vcdp8o.pdf

Implementing the Digital Thread - A Proof-of-Concept

Uncontrolled curing-induced residual stress is a significant limitation to the efficient design of thermoset composite structures, and a sufficiently high post-cure stress state can compromise their performance, durability, and geometrical tolerance. Experimentally validated multiscale process models aid in quantitatively describing the relation between process parameters and residual stress development across composite length scales, thereby allowing for an optimized manufacturing process and improved part performance. This work presents a novel numerical approach for the process modeling of fiber-reinforced thermosets, and is based on higher-order finite elements derived from the Carrera Unified Formulation. The process framework is experimentally validated at the macro-scale using cure-induced warpage data of fabricated cross-ply laminates. Micromechanical process analysis is performed to predict residual stress evolution at the micro-scale, and a comparison with reference 3D-FEA provides a verification of the proposed approach. The predicted laminate-level cure-induced warpage is found to be within 9% of experimental measurements, thereby validating the presented process model, while comparing the micromechanical analysis costs with conventional 3D-FEA demonstrates an order-of-magnitude improvement in computational efficiency. The performance of the proposed computational models constitutes a milestone towards enabling practically feasible multiscale process modeling for composites structures. 

Validation and verification of a novel higher-order FE Framework for process modeling of thermoset composites

Smart Buildings in the IoT Era – Necessity, Challenges, and Opportunities

With this paper we present the project MODEL-SI, which is funded by the Horizon Europe and managed by the European Union Aviation Safety Agency (EASA). It aims at assessing the goodness of state-of-art modelling techniques as they are applied to eVTOL aircraft and the potential savings in flight testing costs, if a digital twin is exploited during the certification process. The aim of the project could also be reformulated by saying that (i) eVTOL aircraft exhibit peculiar aerodynamics phenomena and may experience very interesting dynamic responses to perturbations such as wind gusts, and (ii) state of art modelling and multi-fidelity in particular may turn out to be an effective approach to the exploration of the flight envelope with all relevant configurations. As a matter of fact, we know that some fast, low-fidelity model is necessary to cover flight envelope and a number of configurations; moreover, we expect local, mid- and high-fidelity modelling to be indispensable to capture some of the flow mechanics patterns (typically, the interactions rotor-rotor and rotor-wing). Finally, we expect machine learning to play a role in our project or even to be instrumental. Trivially, we plan to exploit gaussian processes and / or neural networks to combine data from low-, mid- and high-fidelity physics-based models into a fast yet accurate surrogate model. However, pattern-recognition may also be exploited to acquire a deeper understanding of the physics involved; for instance, this can happen from CFD-generated or experimental data. The physics-based simulation model architecture is presented together with the workflow of the data-driven models and how they are integrated in a simulation environment. 

MODEL-SI: Modeling and Simulation - Multi-fidelity surrogate model of an eVTOL for certification

Organizations continuously develop Digital Twins across a wide number of applications and industries. While this represents a testimony to the benefits and opportunities Digital Twins provide (AIAA 2022), their development, maintenance and evolution still face major challenges (Bordeleau et al. 2020). Most past and current efforts focusing on the development of Digital Twins have relied on ad-hoc approaches, where most of the efforts start with building models without properly framing the problem (Martin 2019, Lu et al. 2020). More importantly it has led to the development of models that provide a solution to the wrong problem and consequently fail to address the core questions and needs of the stakeholders (Martin 2019)]. The development and implementation of Digital Twins also lack standardization (Shao 2021), instead relying on bespoke methods and technologies (Niederer et al. 2021), which in turns leads to a lack of consistency in their description and implementation, as well as limited interoperability across applications, tools and disciplines (Niederer et al. 2021, Piroumian 2021). The development of Digital Twins has been plagued by a lack of scalable approaches, leading to implementations that are highly specialized and require considerable resources in terms of subject matter expertise (Niederer et al. 2021). The development of standardized methodologies has been identified as a means to unleash the full potential of Digital Twins (Shao 2021, Piroumian 2021) and increase their adoption across a wider range of disciplines and applications (Niederer et al. 2021). To that end, this paper presents a domain agnostic and descriptive reference model, which builds on recognized industry practices and guidelines, to support the planning, description, and analysis of Digital Twins. It also introduces real-world examples of aerospace Digital Twin use cases and discusses how the generic reference model supports the various use case applications. Finally, this paper briefly discusses recommendations and next steps on how to realize value from Digital Twins more broadly. 

Digital Twin: Reference Model, Realizations, and Recommendations

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Scott Duncan

Author Tools

Chat about Author

Papers

Digital Twin: Reference Model, Realizations, and Recommendations