Home » Explainable AI framework targets supplier disruption

Explainable AI framework targets supplier disruption

by BDigital_Admin

Researchers at Constructor University in Bremen, Germany, have developed an “explainable” artificial intelligence framework they claim will help manufacturers choose replacement suppliers when supply chains are disrupted.

Dr Omid Fatahi Valilai, professor of industrial engineering, and PhD researcher Omkar Vishwas Patil built the system within the university’s Emerging Technologies in Industrial Engineering research group.

It uses Answer Set Programming (ASP), a form of declarative AI, to turn procurement rules, supplier capacities, disruption conditions, and sustainability requirements into instructions that the system can evaluate transparently.

The researchers integrated ASP into Robotic Process Automation (RPA) and Enterprise Resource Planning (ERP) systems. This created a closed-loop system covering decision to execution, in which decisions are made and validated, repetitive tasks are automated, and procurement transactions are carried out.

Patil said: “Our goal was to move beyond developing an AI model that simply recommends a supplier, and instead demonstrate how logic-driven AI can support the complete decision-to-execution process. By building the decision layer on ASP with explicit rules for disruption and sustainability, we can make supplier-selection decisions that are responsive to changing supply chain conditions while remaining transparent and traceable.”

The system determines which suppliers remain available, whether they can meet demand, and whether backup suppliers are needed. It activates backups conditionally rather than automatically selecting every alternative, and enforces minimum social and environmental thresholds so selection is not based solely on lowest cost.

It also shows the chain of reasoning behind each recommendation, such as the disruption that made a supplier unavailable, the finding that remaining suppliers cannot meet demand, and the decision to activate backups. Procurement managers, auditors, and sustainability teams can use this audit trail to review, challenge, or adjust the recommendations.

The researchers tested the framework on a synthetic dataset of networks with 100, 500, and 1,000 primary suppliers, each with corresponding backups. Scenarios included partial supplier losses, the full loss of a high-capacity supplier, and multiple outages across different demand levels.

Across 27 simulated scenarios, the framework achieved a 100% fill rate while meeting the required social and environmental standards, and activated backup suppliers only when needed. A proof-of-concept demonstration showed the decisions being checked, translated into simulated purchase orders, and recorded in an audit log.

Fatahi Valilai and Patil said the work used synthetic data and a mock ERP environment. Deployment with real supplier information, live disruption signals, and commercial enterprise systems remains a goal for future research.

Fatahi Valilai said: “Supply chains are increasingly expected to be resilient, sustainable, transparent, and responsive at the same time. For me, the important question is therefore no longer only how AI can predict what may happen, but how intelligent systems can make operational decisions that remain explainable, auditable, and aligned with sustainability policies.”

The paper, A Logic-driven Integrated System for Resilient and Sustainable Supplier Selection in Supply Chains, was published in Engineering Applications of Artificial Intelligence.


Read next: Surveying skills gap hits mid-career, RICS finds

Are you a building professional? Sign up for a FREE MEMBERSHIP to upload news stories, post job vacancies, and connect with colleagues on our secure social feed.

Leave a Comment

Related News

Online building news, features and opinions

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More