Apply now
Master'sData, AI, Simulation & Analytics Applications open

Master’s in AI-Based Predictive Maintenance Engineering

Online master's programme of 1,900 hours in AI-based predictive maintenance: 12 modules covering maintenance data, feature engineering, fault diagnosis, asset anomaly detection, remaining useful life prognosis, hybrid models and digital twins, deployment and MLOps, maintenance decision optimisation and generative AI governance, with an assigned technical tutor.

Duration1900 h
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

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.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Prepare maintenance data by combining sensors and the CMMS.

02

Build health indicators from asset signals.

03

Develop fault diagnosis models with machine learning.

04

Estimate remaining useful life with uncertainty quantification.

05

Integrate physical and data-driven models into digital twins.

06

Deploy predictive solutions using MLOps practices.

07

Turn prognoses into optimal maintenance decisions.

Profile

Who it's for

  • Predictive maintenance engineers moving from condition monitoring to AI.
  • Asset data scientists working with SCADA, vibration and CMMS data.
  • Reliability engineers who want data-driven prognostics.
  • Industrial MLOps engineers deploying models across asset fleets.
  • Asset management leads responsible for maintenance strategy and budgets.
  • Maintenance 4.0 consultants advising on digital transformation.
  • Engineering or science graduates aiming to move into wind energy.
Standards & tools

What you'll work with

  • ISO 17359 (condition monitoring and diagnostics of machines: general guidelines)
  • ISO 13374-1 (condition monitoring data processing, communication and presentation)
  • ISO 13381-1 (condition monitoring and diagnostics of machines: prognostics)
  • Regulation (EU) 2024/1689 (AI Act) (European Artificial Intelligence Regulation)
  • ISO 55001 (asset management systems)
  • IEC 60599 (interpretation of dissolved gas analysis in mineral-oil-filled equipment)
  • ISO/IEC 42001 (artificial intelligence management systems)
  • ISO 20816-1 (measurement and evaluation of machine vibration)
  • Python with scikit-learn and PyTorch
  • MATLAB Predictive Maintenance Toolbox
  • MLflow
  • Azure Machine Learning
  • Grafana
Syllabus

12 modules · 1900 h

  1. 1.1Maintenance strategies and their evolution
  2. 1.2Condition-based maintenance according to ISO 17359
  3. 1.3Data sources: sensors, CMMS and SCADA
  4. 1.4Mapping failure modes to measurable variables
  5. 1.5Asset criticality and prioritisation
  6. 1.6Digital maturity of maintenance
  7. 1.7Success stories in industry and energy
  8. 1.8Common mistakes in predictive projects
  9. 1.9Building the business case
  10. 1.10Case study: selecting assets for a predictive pilot
  1. 2.1Extracting CMMS history
  2. 2.2Free text in work orders
  3. 2.3Natural language processing of breakdowns
  4. 2.4Aligning events with signals
  5. 2.5Labelling failures and pre-failure windows
  6. 2.6Handling missing data
  7. 2.7Imbalanced failure data
  8. 2.8Operating condition data
  9. 2.9Information leakage in labelling
  10. 2.10Lab: labelling failures from work orders
  1. 3.1Band-based vibration features
  2. 3.2Temperature and current indicators
  3. 3.3Process and load features
  4. 3.4Temporal aggregates and trends
  5. 3.5Physics-based features
  6. 3.6Composite health indicators
  7. 3.7Selection by monotonicity and prognosability
  8. 3.8Normalisation by operating regime
  9. 3.9Feature automation
  10. 3.10Practical: health indicator for a turbomachine
  1. 4.1Tree-based classifiers and gradient boosting
  2. 4.2Support vector machines
  3. 4.3Convolutional networks on spectrograms
  4. 4.4Multi-class fault diagnosis
  5. 4.5Learning with few labels
  6. 4.6Transfer learning between machines
  7. 4.7Validation by asset and by time
  8. 4.8Confusion matrices and costs
  9. 4.9Interpretability of the diagnosis
  10. 4.10Lab: bearing fault diagnosis with a CNN
  1. 5.1Normal behaviour models
  2. 5.2Model residual regression
  3. 5.3Autoencoders on SCADA data
  4. 5.4Isolation Forest under operating conditions
  5. 5.5Thresholds and alarm persistence
  6. 5.6Separating process anomalies from equipment anomalies
  7. 5.7Fusion of multiple detectors
  8. 5.8Reducing false alarms
  9. 5.9Validation with experts
  10. 5.10Workshop: normal behaviour model of a wind turbine
  1. 6.1Formulating the RUL problem
  2. 6.2Survival models and Cox regression
  3. 6.3Stochastic degradation processes
  4. 6.4Direct RUL regression
  5. 6.5LSTMs and CNNs for RUL
  6. 6.6The C-MAPSS dataset and benchmarks
  7. 6.7Uncertainty quantification in RUL
  8. 6.8Bayesian models and bootstrapping
  9. 6.9Prognostic metrics
  10. 6.10Practical: RUL on the C-MAPSS dataset
  1. 7.1Rotating machinery and electric motors
  2. 7.2Transformers and dissolved gas analysis
  3. 7.3Pumps and compressors
  4. 7.4Wind turbines and SCADA
  5. 7.5Railway rolling stock
  6. 7.6Oil and gas assets
  7. 7.7Civil infrastructure and structures
  8. 7.8Vehicle fleets
  9. 7.9HVAC equipment
  10. 7.10Case study: dissolved gas analysis with machine learning
  1. 8.1Physical degradation models
  2. 8.2Physics-informed neural networks
  3. 8.3Calibrating models with data
  4. 8.4Digital twins for maintenance
  5. 8.5Failure simulation to generate data
  6. 8.6Synthetic data and augmentation
  7. 8.7Surrogate models of degradation simulations
  8. 8.8Validating hybrid models
  9. 8.9Scaling to fleets
  10. 8.10Lab: hybrid wear model
  1. 9.1Edge and cloud architectures
  2. 9.2Periodic inference pipelines
  3. 9.3Integration with the CMMS and notification generation
  4. 9.4Monitoring model drift
  5. 9.5Retraining on new failures
  6. 9.6Managing models per asset
  7. 9.7Commercial industrial platforms
  8. 9.8OT cybersecurity in predictive solutions
  9. 9.9Solution scalability
  10. 9.10Workshop: inference pipeline integrated with the CMMS
  1. 10.1From prognosis to decision
  2. 10.2Prescriptive maintenance and action recommendations
  3. 10.3Constrained schedule optimisation
  4. 10.4Spare parts management with forecasts
  5. 10.5Cost-benefit analysis of alerts
  6. 10.6Decision theory under uncertainty
  7. 10.7Reinforcement learning in maintenance
  8. 10.8Programme value indicators
  9. 10.9Communicating with senior management
  10. 10.10Practical: optimising interventions with RUL forecasts
  1. 11.1LLM assistants for maintenance technicians
  2. 11.2Retrieval of manuals and maintenance histories
  3. 11.3Generating breakdown reports
  4. 11.4Hallucination risks in critical environments
  5. 11.5The AI Act and human oversight
  6. 11.6AI management according to ISO/IEC 42001
  7. 11.7Accountability and traceability of decisions
  8. 11.8Change management in technical teams
  9. 11.9Ethics and employment
  10. 11.10Case study: RAG assistant for equipment manuals
  1. 12.1Defining the asset and the problem
  2. 12.2Data preparation
  3. 12.3Features and health indicators
  4. 12.4Diagnosis and prognosis models
  5. 12.5Integration into decision-making
  6. 12.6Deployment architecture
  7. 12.7Technical and economic evaluation of the programme
  8. 12.8Conclusions and scaling plan
  9. 12.9Thesis report
  10. 12.10Master's Thesis: defence before a panel
Methodology, software & labs

How you'll learn

100% online training on the SEIUM campus, with downloadable materials, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so the programme fits around your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is Python with scikit-learn and PyTorch, MATLAB Predictive Maintenance Toolbox, MLflow, Azure Machine Learning and Grafana, in free, academic or evaluation versions. Real procedures are studied, such as engine remaining useful life prognosis with the C-MAPSS dataset, normal behaviour models with SCADA data and transformer diagnosis by dissolved gas analysis. Assessment is continuous by module, plus the final Master's Thesis.

Standards covered: ISO 17359, ISO 13374-1, ISO 13381-1, Regulation (EU) 2024/1689 (AI Act), ISO 55001, IEC 60599, ISO/IEC 42001, ISO 20816-1.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of ISO 17359, ISO 13374-1 and ISO 13381-1 applied to real cases, not as a theoretical annex.
Industry software:Python with scikit-learn and PyTorch, MATLAB Predictive Maintenance Toolbox, MLflow, Azure Machine Learning and Grafana, in free, academic or evaluation versions.
Master's Thesis with defence:a predictive maintenance programme for a real asset, from data preparation and health indicators to diagnosis, prognosis, deployment and technical and economic evaluation, defended before a panel.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Define the asset
Select the asset and failure modes and prepare sensor and CMMS data.
Build health indicators
Engineer features and a composite health indicator for the asset.
Diagnose and forecast
Develop fault diagnosis and RUL models with uncertainty quantification.
Deploy and decide
Integrate the models with the CMMS and optimise maintenance interventions.
Master's Thesis
Present the technical and economic evaluation and scaling plan, defended before a panel.
Career opportunities

Where this takes you

Predictive maintenance engineerAsset data scientistReliability engineerIndustrial MLOps engineerAsset management leadMaintenance 4.0 consultant
Admissions & scholarships

Requirements

  • University degree in engineering, science or architecture, or equivalent demonstrable professional experience.
  • Internet connection and a computer capable of running the programme software.
  • English sufficient to read technical standards.

Ready to start?

Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.

Apply now Scholarships
FAQ

Frequently asked questions

The programme totals 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with Python with scikit-learn and PyTorch, MATLAB Predictive Maintenance Toolbox, MLflow, Azure Machine Learning and Grafana, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.

A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.

Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.

A university degree in engineering, science or architecture (or equivalent professional experience), a computer able to run the software and English sufficient to read technical standards.

Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.

Keep exploring

Related programmes

See all in Data, AI, Simulation & Analytics
Master's9,970 $

Master’s in Optimisation, Operations Research and Decision Engineering

Online master's programme of 1,900 hours in optimisation, operations research and decision-making: 12 modules covering modelling, linear, integer and non-linear programming, metaheuristics, constraint programming and scheduling,…

1900 hOnlineData, AI, Simulation & Analytics
Master's7,730 $

Master’s in Visual Analytics and Technical BI Engineering

Online master's programme of 1,900 hours in visual analytics and technical BI engineering. 12 modules covering visual analytics, perception and visual design, complex data visualisation, data…

1900 hOnlineData, AI, Simulation & Analytics
Master's11,090 $

Master’s in Technical NLP Engineering and Engineering Assistants

Online master's programme of 1,900 hours in technical NLP engineering and engineering assistants: 12 modules covering computational linguistics, Transformer models, RAG over technical documentation, information extraction,…

1900 hOnlineData, AI, Simulation & Analytics
Master’s in AI-Based Predictive Maintenance EngineeringEnrol
Related programmes

More in Data, AI, Simulation & Analytics

Master’s in Time Series, Signals and Anomaly Detection EngineeringView programme →Master’s in Digital Twins and Operations Analytics EngineeringView programme →Master’s in AI Governance and Compliance EngineeringView programme →Master’s in Optimisation under Uncertainty EngineeringView programme →Master’s in HPC & GPU Engineering for Simulation and AIView programme →Master’s in Digital Twin Engineering for Energy and GridsView programme →

All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.