Literature review of data analysis techniques for condition monitoring in digital twin-enabled condition-based maintenance
Year: 2026
Type: article
Study design: Systematic Review
Abstract: Condition-based maintenance (CBM) plays a vital role in extending the operational lifespan of physical assets by initiating maintenance actions based on quantifiable data. Digital Twins (DTs) have emerged as enablers for CBM by utilizing operational data captured in real-world operation. These data are analyzed using diverse techniques from fields such as statistics, machine learning, and simulation to monitor the condition of physical assets effectively. Despite the widespread application of such techniques in CBM research and practice, there is currently no comprehensive analysis that quantifies their recent prevalence in DT-enabled condition monitoring systems. This paper addresses this gap by conducting a systematic literature review of recent publications between 2022 and July 2025 to identify and evaluate prominent data analysis techniques utilized in DTs for condition monitoring in the domain of the manufacturing industry. The findings reveal that recurrent neural networks, convolutional neural networks, and simulation are currently preferred techniques. By offering a literature overview and discussion of data analysis techniques, this study contributes valuable insights toward advancing CBM strategies in manufacturing systems, fostering innovation in DT-enabled solutions, and optimizing lifecycle management for physical assets.
Source: Procedia CIRP
Authors: Alexander Wuttke, Julia Kunert, Joachim Hunker
Language: English
Subfield: Industrial and Manufacturing Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7207763531