Predictive Maintenance: IoT, AI & Machine Learning
Explore Predictive Maintenance through IoT, condition monitoring, machine learning, reliability and dashboards in a structured conceptual introduction. Includes 3h 31m of English Full HD video with subtitles. Basic Python knowledge is required. This course uses artificial intelligence.
Course Overview
Predictive Maintenance
Connect asset condition with data-informed maintenance thinking.
Explore Predictive Maintenance through IoT information, condition-monitoring techniques, machine learning and reliability concepts. This structured introduction connects maintenance approaches with analytics, dashboards and practical implementation considerations.
This course uses artificial intelligence.
Predictive Maintenance: 6 connected study areas
Follow the relationship between asset signals, analytical methods and the information used to support maintenance discussions.
Maintenance & reliability foundations
Compare preventive, predictive and condition-based approaches while exploring reliability, failure modes and patterns as context for maintenance decisions.
Connected assets & IoT data
Explore sensors, connected assets, data acquisition and pipelines, following how equipment-related information becomes input for analysis.
Condition-monitoring techniques
Study vibration monitoring, thermal imaging and thermography, and oil analysis as different approaches to understanding asset condition.
Machine learning & prediction
Explore data preparation, supervised and unsupervised learning, anomaly detection, failure prediction and remaining useful life as analytics topics.
KPIs, visualization & dashboards
Connect reliability and availability KPIs with data visualization and dashboard presentation, keeping analysis distinct from the display of its results.
AI & practical implementation
Consider AI decision support, Industry 4.0 and smart maintenance alongside practical implementation questions for bringing these ideas into a maintenance setting.
From connected assets to decision support
Understand how the pieces fit together
This Predictive Maintenance course explores how condition data, machine learning, reliability measures and dashboards relate. Use the conceptual framework to consider practical implementation choices and the questions involved in a data-informed maintenance approach.
Explore the course details
Maintenance, analytics & implementation coverage
- Maintenance approaches, reliability, failure modes and patterns; connected assets, sensors, acquisition and data pipelines.
- Vibration, thermal imaging/thermography and oil analysis as condition-monitoring topics.
- Data preparation, supervised and unsupervised machine learning, anomaly detection, failure prediction and remaining useful life (RUL).
- Reliability and availability KPIs, visualization, dashboards, AI decision support, Industry 4.0, smart maintenance and practical implementation considerations.
Starting point & who it is for
Basic Python knowledge is required, including variables, functions and loops, plus an interest in maintenance, reliability or data. No prior Grafana or PdM experience is needed. Have a computer and internet access, with the ability to install Python libraries and Grafana.
For engineers, technicians, asset managers and data students exploring the connections between equipment information, analytics and maintenance planning.
Video format & AI disclosure
- Duration
- 3 hours 31 minutes
- Language
- English; subtitles available
- Video
- MP4 / H.264, 1920 x 1080
- Audio
- AAC, 44.1 kHz, 2 channels
This course uses artificial intelligence.


