Integrating Materials and Manufacturing Innovation最新文献

Detecting anomaly in fatigue and fracture experimental materials science is an interesting yet challenging topic. The reasons are threefold. First, the anomalous microstructure feature that gives rise to structural failure is small, sometimes in the order of (10^{-7}) of the interrogated volume. This, in turn, results in a highly imbalanced classification problem in machine learning (ML). Second, the consequence is high, in the sense that the test specimen is destructed in such case. Third, the convolution between microstructure stochasticity and the small probability of void nucleation, growth, and coalescence makes failure and fracture a hard-to-predict and challenging problem in materials science due to its irreproducibility, even experimentally. In this paper, we developed a materials digital twin and applied anomaly detection methods to detect voids and anomaly in additive manufacturing (AM). The materials digital twin is driven by two integrated computational materials engineering (ICME) models, which are kinetic Monte Carlo (kMC) and crystal plasticity finite element method (CPFEM). We demonstrated that by using anomaly detection, it is possible to detect voids and other defects in materials digital twin, which paves way for future research in integrating materials digital twin with its physical counterpart.

Over the last few decades, globalization has weakened the US manufacturing sector. The COVID-19 pandemic revealed import dependencies and supply chain shocks that have raised public and private awareness of the need to rebuild domestic production. A range of new technologies, collectively called Industry 4.0, create opportunities to revolutionize domestic and local manufacturing. Success depends on further refinement of those technologies, broad implementation throughout private companies, and concerted efforts to rebuild the industrial commons, the national ecosystem of producers, suppliers, service providers, educators, and workforce necessary to regain a competitive, innovative manufacturing sector. A recent workshop sponsored by the Engineering Research Visioning Alliance (ERVA) identified a range of challenges and opportunities to build a resilient, flexible, scalable, and high-quality manufacturing sector. This paper provides a strategic roadmap for regaining US manufacturing leadership by briefly summarizing discussions at the ERVA-sponsored workshop held in 2023 and providing additional analysis of key technical and economic issues that must be addressed to achieve dynamic, high-value manufacturing in the USA. The focus of this presentation is on discrete manufacturing of production of structural components, a large subset of total manufacturing that produces high-value inputs and finished products for domestic consumption and export.

Additive manufacturing of metal alloys produces microstructures that are typically very different from those produced by more traditional manufacturing approaches. Computer simulations are useful for connecting processing, structure, and performance for these materials, but validation data that span this full range is difficult to produce. This research is part of a broad effort by the Additive Manufacturing Benchmark Test Series to produce such datasets for laser powder bed fusion builds of nickel Alloy 718. Here, single laser tracks produced with variations in laser power, scan velocity, and laser diameter, and arrays of adjacent laser tracks on bare wrought Alloy 718 plates are examined using optical microscopy, electron backscatter diffraction, and energy dispersive spectroscopy.

Algorithmic materials discovery is a multidisciplinary domain that integrates insights from specialists in alloy design, synthesis, characterization, experimental methodologies, computational modeling, and optimization. Central to this effort is a robust data management system paired with an interactive work platform. This platform should empower users to not only access others’ data but also integrate their analyses, paving the way for sophisticated data pipelines. To realize this vision, there is a need for an integrative collaboration platform, streamlined data sharing and analysis tools, and efficient communication channels. Such a collaborative mechanism should transcend geographical barriers, facilitating remote interaction and fostering a challenge-response dynamic. To further enhance precision and interoperability in this multifaceted research landscape, we must explore innovative ways to refine these processes and improve the integration of expertise and data across diverse domains. In this paper, we present our ongoing efforts in addressing the critical challenges related to an accelerated materials discovery framework as a part of the High-Throughput Materials Discovery for Extreme Conditions (HTMDEC) Initiative. Our BIRDSHOT (Batch-wise Improvement in Reduced Materials Design Space using a Holistic Optimization Technique) Center has successfully harnessed various tools and strategies, including the utilization of cloud-based storage, a standardized sample naming convention, a structured file system, the implementation of sample travelers, a robust sample tracking method, and the incorporation of knowledge graphs for efficient data management. Additionally, we present the development of a data collection platform, reinforcing seamless collaboration among our team members. In summary, this paper provides an illustration and insight into the various elements of an efficient and effective workflow within an accelerated materials discovery framework while highlighting the dynamic and adaptable nature of the data management tools and sharing platforms.

Recent advancements in large language models (LLMs) have paved the way for automated information extraction in the materials science domain. However, fine-tuning these models, crucial for effective machine learning pipelines in materials science, is hindered by a lack of pre-annotated data. Manual annotation, a laborious process, exacerbates the challenge. To address this, we introduce a tailored semi-automated annotation process, using Google’s Gemini Pro language model. Our approach focuses on two key tasks: extracting information in structured JSON format and generating abstractive summaries from materials science texts. The collaborative process, a symbiotic effort between human annotators and the LLM, driven by structured prompts and user-guided examples, enhances the annotation quality and augments the LLM’s capacity to comprehend materials science intricacies. Importantly, it streamlines human annotation efforts by leveraging the LLM’s proficient starting point.

The Additive Manufacturing Benchmark Series (AM Bench) is a NIST-led organization that provides a continuing series of additive manufacturing benchmark measurements, challenge problems, and conferences with the primary goal of enabling modelers to test their simulations against rigorous, highly controlled additive manufacturing benchmark measurement data. To this end, single-track (1D) and pad (2D) scans on bare plate nickel alloy 718 were completed with thermography, cross-sectional grain orientation and local chemical composition maps, and cross-sectional melt pool size measurements. The laser power, scan speed, and laser spot size were varied for single tracks, and the scan direction was varied for pads. This article focuses on the cross-sectional melt pool size measurements and presents the predictions from challenge problems. Single-track depth correlated with volumetric energy density while width did not (within the studied parameters). The melt pool size for pad scans was greater than single tracks due to heat buildup. Pad scan melt pool depth was reduced when the laser scan direction and gas flow direction were parallel. The melt pool size in pad scans showed little to no trend against position within the pads. Uncertainty budgets for cross-sectional melt pool size from optical micrographs are provided for the purpose of model validation.

The discovery of novel alloys, such as multi-principal element alloys (MPEAs)—inclusive of the so-called high-entropy alloys—remains essential for technological advancement. Multi-principal element alloys can manifest uniquely favorable mechanical properties, but the complexity of their compositions results in their design and performance being challenging to understand. With the emergence of the materials genome concept, there is potential to pursue novel materials using computational design approaches. However, the complexity of such design often requires immense computational power and sophisticated data analysis. In an attempt to address this, we introduce the application of a new framework, the non-dominant sorting optimization-based generative adversarial networks (NSGAN) in the discovery and exploration of novel MPEAs. By harnessing the power of genetic algorithms and generative adversarial networks (GANs), NSGANs offer an effective solution for high-dimensional multi-objective optimization challenges in alloy design. The framework is demonstrated to generate MPEAs according to specific alloy properties. Furthermore, an online web tool/software applies the NSGAN framework to disseminate the methodology to the broader scientific arena (along with the supporting code made available).

The structure–property hypothesis says that the properties of all materials are determined by an underlying crystal structure. The main obstacle was the ambiguity of conventional crystal representations based on incomplete or discontinuous descriptors that allow false negatives or false positives. This ambiguity was resolved by the ultra-fast pointwise distance distribution, which distinguished all periodic structures in the world’s largest collection of real materials (Cambridge structural database). State-of-the-art results in property prediction were previously achieved by graph neural networks based on various graph representations of periodic crystals, including the Crystal Graph with vertices at all atoms in a crystal unit cell. This work adapts the pointwise distance distribution for a simpler graph whose vertex set is not larger than the asymmetric unit of a crystal structure. The new Distribution Graph reduces mean absolute error by 0.6–12% while having 44–88% of the number of vertices when compared to the Crystal Graph when applied on the Materials Project and Jarvis-DFT datasets using CGCNN and ALIGNN. Methods for hyper-parameters selection for the graph are backed by the theoretical results of the pointwise distance distribution and are then experimentally justified.

The development and discovery of new materials can be significantly enhanced through the adoption of FAIR (Findable, Accessible, Interoperable, and Reusable) data principles and the establishment of a robust data infrastructure in support of materials informatics. A FAIR data infrastructure and associated best practices empower materials scientists to access and make the most of a wealth of information on materials properties, structures, and behaviors, allowing them to collaborate effectively, and enable data-driven approaches to material discovery. To make data findable, accessible, interoperable, and reusable to materials scientists, we developed and are in the process of expanding a materials data infrastructure to capture, store, and link data to enable a variety of analytics and visualizations. Our infrastructure follows three key architectural design philosophies: (i) capture data across a federated storage layer to minimize the storage footprint and maximize the query performance for each data type, (ii) use a knowledge graph-based data fusion layer to provide a single logical interface above the federated data repositories, and (iii) provide an ensemble of FAIR data access and reuse services atop the knowledge graph to make it easy for materials scientists and other domain experts to explore, use, and derive value from the data. This paper details our architectural approach, open-source technologies used to build the capabilities and services, and describes two applications through which we have successfully demonstrated its use. In the first use case, we created a system to enable additive manufacturing data storage and process parameter optimization with a range of user-friendly visualizations. In the second use case, we created a system for exploring data from cathodic arc deposition experiments to develop a new steam turbine coating material, fusing a combination of materials data with physics-based equations to enable advanced reasoning over the combined knowledge using a natural language chatbot-like user interface.

Abstract

To describe a new method for the automatic generation of process parameters for fused filament fabrication (FFF) across varying machines and materials. We use an instrumented extruder to fit a function that maps nozzle pressures across varying flow rates and temperatures for a given machine and material configuration. We then develop a method to extract real parameters for flow rate and temperature using relative pressures and temperature offsets. Our method allows us to successfully find process parameters, using one set of input parameters, across all of the machine and material configurations that we tested, even in materials that we had never printed before. Rather than using direct parameters in FFF printing, which is time-consuming to tune and modify, it is possible to deploy machine-generated data that captures the fundamental phenomenology of FFF to automatically select parameters.