Representation Learning of Complex Assemblies, An Effort to Improve Corporate Scope 3 Emissions Calculation

TL;DR

This work tackles the challenge of measuring Scope 3 emissions in complex electronics by leveraging a semi-supervised ensemble framework that builds a Machine Knowledge Graph (MKG) from Bill of Materials data and a small set of qualified substitutes. It casts substitute discovery as a link-prediction problem on a non-homophilous graph and integrates topology-based embeddings with node-feature refinements, augmented by biased negative sampling to improve generalization. The approach yields superior link-prediction performance and disentangles latent component similarities, enabling estimation of environmental impacts for data-poor substitutes and improving process life cycle assessment. The results support more accurate Scope 3 calculations and open avenues for broader applications in manufacturing sustainability and data-gap identification across diverse product domains.

Abstract

Climate change is a pressing global concern for governments, corporations, and citizens alike. This concern underscores the necessity for these entities to accurately assess the climate impact of manufacturing goods and providing services. Tools like process life cycle analysis (pLCA) are used to evaluate the climate impact of production, use, and disposal, from raw material mining through end-of-life. pLCA further enables practitioners to look deeply into material choices or manufacturing processes for individual parts, sub-assemblies, assemblies, and the final product. Reliable and detailed data on the life cycle stages and processes of the product or service under study are not always available or accessible, resulting in inaccurate assessment of climate impact. To overcome the data limitation and enhance the effectiveness of pLCA to generate an improved environmental impact profile, we are adopting an innovative strategy to identify alternative parts, products, and components that share similarities in terms of their form, function, and performance to serve as qualified substitutes. Focusing on enterprise electronics hardware, we propose a semi-supervised learning-based framework to identify substitute parts that leverages product bill of material (BOM) data and a small amount of component-level qualified substitute data (positive samples) to generate machine knowledge graph (MKG) and learn effective embeddings of the components that constitute electronic hardware. Our methodology is grounded in attributed graph embeddings and introduces a strategy to generate biased negative samples to significantly enhance the training process. We demonstrate improved performance and generalization over existing published models.

Figures (6)

• Figure 1: Machine Knowledge Graph Creation
• Figure 2: Node Embedding Generation Workflow.
• Figure 3: Comparison of Embeddings projection before (left) and after (right) fine-tuning. Different colors represents different component type.
• Figure 4: Empirical study on the impact of Negative samples selection.
• Figure 5: MKG Compatibility Measure