AI2030 Responsible AI Tools Marketplace

Key Takeaways

Knowledge graphs can make AI maintenance decisions understandable: The paper demonstrates that combining AI predictions with structured knowledge graphs allows wind turbine operators to understand why a maintenance action is recommended, not just what is predicted to fail—addressing a critical gap in current automated decision support systems.
Explainability requires integrating multiple types of information: XAI4Wind combines sensor data (SCADA parameters), text descriptions of past maintenance actions, images, and alarm records. This multimodal approach reflects how human experts actually make decisions, making AI recommendations more trustworthy and actionable for maintenance teams.
Knowledge graphs have been underutilized in wind energy despite proven success elsewhere: While knowledge graphs have demonstrated value in healthcare and finance for decision support, the wind industry has largely overlooked this technology—suggesting significant potential for improving operations and maintenance planning through better knowledge organization.
Interactive querying enables human oversight of AI systems: The paper shows that operators can query the knowledge graph to explore relationships between failures, maintenance actions, and turbine conditions, allowing humans to verify AI recommendations and catch potential errors before acting on them.
Better maintenance decisions could reduce downtime and costs: By providing explainable, evidence-based recommendations for maintenance actions tied to specific predicted failures, this approach enables more targeted interventions rather than reactive or overly cautious maintenance strategies.

Abstract

Condition-based monitoring (CBM) has been widely utilised in the wind industry for monitoring operational inconsistencies and failures in turbines, with techniques ranging from signal processing and vibration analysis to artificial intelligence (AI) models using Supervisory Control & Acquisition (SCADA) data. However, existing studies do not present a concrete basis to facilitate explainable decision support in operations and maintenance (O&M), particularly for automated decision support through recommendation of appropriate maintenance action reports corresponding to failures predicted by CBM techniques. Knowledge graph databases (KGs) model a collection of domain-specific information and have played an intrinsic role for real-world decision support in domains such as healthcare and finance, but have seen very limited attention in the wind industry. We propose XAI4Wind, a multimodal knowledge graph for explainable decision support in real-world operational turbines and demonstrate through experiments several use-cases of the proposed KG towards O&M planning through interactive query and reasoning and providing novel insights using graph data science algorithms. The proposed KG combines multimodal knowledge like SCADA parameters and alarms with natural language maintenance actions, images etc. By integrating our KG with an Explainable AI model for anomaly prediction, we show that it can provide effective human-intelligible O&M strategies for predicted operational inconsistencies in various turbine sub-components. This can help instil better trust and confidence in conventionally black-box AI models. We make our KG publicly available and envisage that it can serve as the building ground for providing autonomous decision support in the wind industry.

Updated version of knowledge graph resource paper - updates include additions to the Appendix on more properties in the knowledge graph, corrected typos/grammatical errors etc

Key Takeaways

Knowledge graphs can make AI maintenance decisions understandable: The paper demonstrates that combining AI predictions with structured knowledge graphs allows wind turbine operators to understand why a maintenance action is recommended, not just what is predicted to fail—addressing a critical gap in current automated decision support systems.
Explainability requires integrating multiple types of information: XAI4Wind combines sensor data (SCADA parameters), text descriptions of past maintenance actions, images, and alarm records. This multimodal approach reflects how human experts actually make decisions, making AI recommendations more trustworthy and actionable for maintenance teams.
Knowledge graphs have been underutilized in wind energy despite proven success elsewhere: While knowledge graphs have demonstrated value in healthcare and finance for decision support, the wind industry has largely overlooked this technology—suggesting significant potential for improving operations and maintenance planning through better knowledge organization.
Interactive querying enables human oversight of AI systems: The paper shows that operators can query the knowledge graph to explore relationships between failures, maintenance actions, and turbine conditions, allowing humans to verify AI recommendations and catch potential errors before acting on them.
Better maintenance decisions could reduce downtime and costs: By providing explainable, evidence-based recommendations for maintenance actions tied to specific predicted failures, this approach enables more targeted interventions rather than reactive or overly cautious maintenance strategies.

Abstract

Updated version of knowledge graph resource paper - updates include additions to the Appendix on more properties in the knowledge graph, corrected typos/grammatical errors etc

XAI4Wind: A Multimodal Knowledge Graph Database for Explainable Decision Support in Operations & Maintenance of Wind Turbines

Key Takeaways

Abstract

Paper Info

Responsible AI Topics

Links

XAI4Wind: A Multimodal Knowledge Graph Database for Explainable Decision Support in Operations & Maintenance of Wind Turbines

Key Takeaways

Abstract

Paper Info

Responsible AI Topics

Links