Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Supply Risk-Aware Alloy Discovery and Design

Mrinalini Mulukutla, Robert Robinson, Danial Khatamsaz, Brent Vela, Nhu Vu, Raymundo Arróyave

Abstract

Materials design is a critical driver of innovation, yet overlooking the technological, economic, and environmental risks inherent in materials and their supply chains can lead to unsustainable and risk-prone solutions. To address this, we present a novel risk-aware design approach that integrates Supply-Chain Aware Design Strategies into the materials development process. This approach leverages existing language models and text analysis to develop a specialized model for predicting materials feedstock supply risk indices. To efficiently navigate the multi-objective, multi-constraint design space, we employ Batch Bayesian Optimization (BBO), enabling the identification of Pareto-optimal high entropy alloys (HEAs) that balance performance objectives with minimized supply risk. A case study using the MoNbTiVW system demonstrates the efficacy of our approach in four scenarios, highlighting the significant impact of incorporating supply risk into the design process. By optimizing for both performance and supply risk, we ensure that the developed alloys are not only high-performing but also sustainable and economically viable. This integrated approach represents a critical step towards a future where materials discovery and design seamlessly consider sustainability, supply chain dynamics, and comprehensive life cycle analysis.

Supply Risk-Aware Alloy Discovery and Design

Abstract

Materials design is a critical driver of innovation, yet overlooking the technological, economic, and environmental risks inherent in materials and their supply chains can lead to unsustainable and risk-prone solutions. To address this, we present a novel risk-aware design approach that integrates Supply-Chain Aware Design Strategies into the materials development process. This approach leverages existing language models and text analysis to develop a specialized model for predicting materials feedstock supply risk indices. To efficiently navigate the multi-objective, multi-constraint design space, we employ Batch Bayesian Optimization (BBO), enabling the identification of Pareto-optimal high entropy alloys (HEAs) that balance performance objectives with minimized supply risk. A case study using the MoNbTiVW system demonstrates the efficacy of our approach in four scenarios, highlighting the significant impact of incorporating supply risk into the design process. By optimizing for both performance and supply risk, we ensure that the developed alloys are not only high-performing but also sustainable and economically viable. This integrated approach represents a critical step towards a future where materials discovery and design seamlessly consider sustainability, supply chain dynamics, and comprehensive life cycle analysis.
Paper Structure (21 sections, 6 equations, 11 figures, 1 table)

This paper contains 21 sections, 6 equations, 11 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Supply Risk Assessment Method
  4. Modern Approaches to Alloy Design
  5. High Throughput Computational Tools and Experimentation
  6. Visualisation of High Dimensional Spaces
  7. Bayesian Optimization in Alloy Design
  8. Indicator Extraction using Large Language Models
  9. Incorporating Supply Chain Risk Considerations in Alloy Discovery and Development - A Case Study for MPEA
  10. Definition of Design Problem for Case Study
  11. Models for constraints
  12. Models for Objectives
  13. Multi-Objective Batch Bayesian Optimisation Framework
  14. Results
  15. Conclusion
  16. ...and 6 more sections

Figures (11)

  • Figure 1: Overview of the main considerations in Alloy Design Workflow
  • Figure 2: Supply Risk Categories
  • Figure 3: A high-level overview of the main steps of the text extraction workflow. Indicators are defined, which are then used for data collection. The collected data is filtered and reduced before going to a LLM for text extraction and data validation.
  • Figure 4: (a) UMAP visualisation for supply risk mean, (b) Box-whisker plots summarizing supply risk index as a function of individual alloying element concentrations, and (c) trends for price history of system of interest over the past decade
  • Figure 5: Schematic of a bi-objective optimization illustrating three candidate points, each with associated uncertainty ellipses, demonstrating varying levels of hypervolume improvement (HVI) relative to a reference point, with areas of improvement highlighted for each point.
  • ...and 6 more figures