Course in Machine Learning for Machinery Maintenance
Online 300-hour course in Machine Learning for machinery maintenance. 6 modules covering ISO 13374-1 (data processing for condition monitoring), ISO 13381-1 (prognostics in condition monitoring) and Python (scikit-learn, PyTorch). Personal tutor assigned and enrolment open.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Explain the fundamentals of condition-based maintenance.
Extract variables from vibration, pressure and temperature signals.
Train supervised models to classify failure modes.
Apply anomaly detection techniques and remaining useful life estimation.
Validate models with workshop experience and measure their performance.
Deploy and maintain models in production under governance criteria.
Develop a machine learning project using real machinery data.
Who it's for
- Industrial machine learning engineer looking to specialise in Machine Learning for machinery maintenance.
- Maintenance data scientist looking to specialise in Machine Learning for machinery maintenance.
- Reliability engineer looking to specialise in Machine Learning for machinery maintenance.
- Condition-based maintenance specialist looking to specialise in Machine Learning for machinery maintenance.
- MLOps engineer looking to specialise in Machine Learning for machinery maintenance.
- Machinery telemetry analyst looking to specialise in Machine Learning for machinery maintenance.
- Engineering or science graduates looking to enter the mining sector.
What you'll work with
- ISO 13374-1 (data processing for condition monitoring)
- ISO 13381-1 (prognostics in condition monitoring)
- ISO 17359 (condition monitoring and diagnostics)
- ISO 20816-1 (measurement and evaluation of vibration)
- Regulation (EU) 2024/1689 (Artificial Intelligence Act)
- ISO/IEC 23053 (framework for AI systems using machine learning)
- ISO/IEC 25012 (data quality model)
6 modules · 300 h
1.1Failure modes and degradation mechanisms1.2Degradation curve and detection window1.3Signals that reveal an incipient fault1.4Vibration, temperature, pressure and acoustics1.5Oil analysis and wear particles1.6What machine learning can contribute1.7What must be solved with engineering rather than models1.8Minimum data and labelling requirements1.9Business metrics for maintenance1.10Workshop: selecting a component and its signals
2.1Sampling, aliasing and filtering2.2Time domain: statistical and shape values2.3Frequency domain and transforms2.4Envelope and frequency band analysis2.5Variables derived from vibration signals2.6Normalisation by operating regime and load2.7Signal alignment and time windows2.8Dimensionality reduction2.9Selection of informative variables2.10Practice: feature extraction from a real signal
3.1State and failure mode classification3.2Regression to estimate degradation level3.3Tree-based and regularised linear models3.4Neural networks on signals and spectra3.5Transfer across machines and conditions3.6Few failure examples: strategies3.7Synthetic data and data augmentation3.8Validation by machine and by period3.9Interpretability and maintainer confidence3.10Practice: bearing condition classifier
4.1Learning normality and deviations4.2Reconstruction and density models4.3Component health indices4.4Survival and hazard models4.5Remaining useful life estimation and its uncertainty4.6Censored data and prior preventive maintenance4.7Sensor drift versus actual degradation4.8Reducing false alarms4.9Comparison with standard thresholds4.10Practice: health index and remaining life estimation
5.1Validating alerts with technical staff5.2Verification protocol after an alert5.3Case documentation and feedback5.4Decision thresholds based on the cost of error5.5Integration with maintenance management5.6Intervention and spare parts planning5.7Measuring savings and avoided failures5.8Change management and team confidence5.9Programme indicators5.10Practice: designing the alert and verification circuit
6.1Putting the model into production6.2Performance and drift monitoring6.3Retraining and version management6.4Reproducibility of calculations and documentation6.5Computing and storage costs6.6Manufacturer dependency and access to signals6.7Protection of data and technical information6.8Common mistakes in predictive maintenance projects6.9Maturity roadmap6.10Final project: condition-based maintenance system
How you'll learn
Fully 100 % online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetables: students progress at their own pace within the intake, making it possible to combine with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is Python (scikit-learn, PyTorch), MATLAB Predictive Maintenance Toolbox, Azure Machine Learning, Grafana, MLflow, in free, academic or evaluation versions. Practicals are based on real procedures for labelling failures with workshop data, anomaly detection in time series, and validation of remaining useful life models. Assessment is continuous per module, plus the final integrative project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Explain the fundamentals of condition-based maintenance.
Extract variables from vibration, pressure and temperature signals.
Train supervised models to classify failure modes.
Apply anomaly detection techniques and remaining useful life estimation.
Validate models with workshop experience and measure their performance.
Where this takes you
Requirements
- No prior degree is required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient command of Spanish to follow technical standards documentation.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme comprises 300 total hours spread over 3 to 5 months. That is between 10 and 15 hours per week on average, compatible with a full-time job.
Work is carried out with Python (scikit-learn, PyTorch), MATLAB Predictive Maintenance Toolbox, Azure Machine Learning, Grafana, MLflow. Free, academic or evaluation versions are used, and the tutor indicates a free alternative where one exists.
An own SEIUM diploma upon passing continuous assessment and the integrative project. It is in-house training, not an official qualification from the Ministry.
Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Check the recognition policy when you enrol.
Related programmes
International Off-Road Transport Regulations Course
Online 300-hour course in international Off-Road transport regulations. 6 modules covering Regulation (EU) 2023/1230 (machinery products), Directive 2006/42/CE (machinery) and AENORmás (standards management). Assigned tutor and…
Drones in Agricultural Machinery Monitoring Course
Online 300-hour course in drones for agricultural machinery monitoring. 6 modules covering Implementing Regulation (EU) 2019/947 (UAS operations), Delegated Regulation (EU) 2019/945 (unmanned aircraft systems) and…
Electronic Diesel Injection Diagnostics Course
Online 300-hour course in electronic diesel injection diagnostics. 6 modules covering ISO 14229 (Unified Diagnostic Services, UDS), SAE J1939 (CAN network for heavy vehicles) and Bosch…
More in Off-Road, Special Vehicles & Machinery
All Off-Road, Special Vehicles & Machinery programmes → · How to apply · Fees & financing · Scholarships