Related Experiment Video
Updated: Aug 29, 2025

Author Spotlight: A Machine-Vision Approach to Transmission Electron Microscopy Workflows, Results Analysis and Data Management
Published on: June 23, 2023
Systematic Literature Review on Visual Analytics of Predictive Maintenance in the Manufacturing Industry
Xiang Cheng1, Jun Kit Chaw1, Kam Meng Goh2
1Institute of IR4.0, Universiti Kebangsaan Malaysia (UKM), Bangi 43600, Selangor, Malaysia.
This review explores predictive maintenance (PdM) with visual aids in Industry 4.0. Most studies focus on anomaly detection, but a comprehensive framework integrating data and knowledge, with human feedback, is lacking for manufacturing.
Area of Science:
- Industrial Engineering
- Data Science
- Manufacturing Systems
Background:
- Industry 4.0 adoption drives the need for advanced manufacturing analytics.
- Sensors in industrial settings generate vast data, requiring effective analysis for actionable insights.
- Predictive Maintenance (PdM) is crucial for optimizing operations and preventing failures.
Purpose of the Study:
- To systematically review and synthesize evidence on visual analytics in PdM.
- To identify knowledge gaps in PdM applications across utilities, power generation, and manufacturing.
- To explore the role of visual aids in enhancing PdM strategies.
Main Methods:
- Systematic literature review of 37 relevant documents.
- Identification and categorization of visual analytics techniques in PdM.
- Analysis of research trends in anomaly detection, planning, EDA, and XAI.
Main Results:
- Anomaly detection is the most prevalent application of visual analytics in PdM.
- Existing literature shows a lack of integrated frameworks combining data-driven and knowledge-driven PdM approaches.
- Visual analytics are applied in various PdM aspects, including exploratory data analysis and explainable AI.
Conclusions:
- Further research is needed to develop comprehensive PdM frameworks for manufacturing.
- Integrating maintenance personnel feedback into PdM systems requires more investigation.
- Achieving minimal human involvement in PdM requires addressing current research gaps and limitations.
Related Concept Videos
Introduction to Statistical Process Control
Interpreting Run Charts
Mechanical Efficiency of Real Machines
However, in reality, no machine can be truly ideal, and all of them experience some...
Distribution Reliability and Automation
Fatigue
Methods of Documentation VI: Case Management Model
For example, a patient with a chronic...

