Neuro-symbolic AI for Predictive Maintenance (PdM) -- review and recommendations
Kyle Hamilton, Ali Intizar
TL;DR
This paper surveys the state-of-the-art in predictive maintenance (PdM) within industrial settings, highlighting the dominance of data-driven methods while noting critical limitations such as data scarcity, out-of-distribution generalization, and limited interpretability. It argues for a deeper integration of deep learning with symbolic knowledge—neuro-symbolic AI (NESY)—to achieve higher accuracy, robustness, and explainability, proposing concrete NESY architectures (nested, cooperative, compiled) and implementation strategies (NESY-CN, NESY-CL, NESY-CT) compatible with time-series sensor data and domain ontologies. The work reviews physics-based, knowledge-based, data-driven, and hybrid modeling paradigms, surveys challenges (data, modeling, operations), and outlines future directions including real-world validation, collaborative datasets, explainable AI, and agentic NESY systems for autonomous maintenance. By detailing concrete NESY architectures and integration pathways, the paper provides actionable research directions to overcome data scarcity and integration hurdles, with potential for significantly improved RCA, RUL estimation, and auditable decision-making in PdM contexts. Overall, NESY is presented as a central enabler of the next frontier in industrial maintenance: agentic, explainable, and robust autonomous maintenance systems grounded in physical and domain knowledge.}
Abstract
In this document we perform a systematic review the State-of-the-art in Predictive Maintenance (PdM) over the last five years in industrial settings such as commercial buildings, pharmaceutical facilities, or semi-conductor manufacturing. In general, data-driven methods such as those based on deep learning, exhibit higher accuracy than traditional knowledge-based systems. These systems however, are not without significant limitations. The need for large labeled data sets, a lack of generalizibility to new environments (out-of-distribution generalization), and a lack of transparency at inference time are some of the obstacles to adoption in real world environments. In contrast, traditional approaches based on domain expertise in the form of rules, logic or first principles suffer from poor accuracy, many false positives and a need for ongoing expert supervision and manual tuning. While the majority of approaches in recent literature utilize some form of data-driven architecture, there are hybrid systems which also take into account domain specific knowledge. Such hybrid systems have the potential to overcome the weaknesses of either approach on its own while preserving their strengths. We propose taking the hybrid approach even further and integrating deep learning with symbolic logic, or Neuro-symbolic AI, to create more accurate, explainable, interpretable, and robust systems. We describe several neuro-symbolic architectures and examine their strengths and limitations within the PdM domain. We focus specifically on methods which involve the use of sensor data and manually crafted rules as inputs by describing concrete NeSy architectures. In short, this survey outlines the context of modern maintenance, defines key concepts, establishes a generalized framework, reviews current modeling approaches and challenges, and introduces the proposed focus on Neuro-symbolic AI (NESY).