Master’s in Predictive Maintenance for Robots & Cells Engineering
Online master's programme of 1,900 hours in predictive maintenance engineering for robots and cells. 12 modules covering robot failure modes, cell data acquisition, signal processing, component diagnosis, physical models and digital twins, anomaly detection, remaining useful life prognosis, deployment platforms and predictive planning, with an assigned technical tutor.
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
Understand the failure mechanisms of robots and robotic cells.
Design data acquisition systems for robot diagnosis.
Apply signal processing techniques to robotic components.
Develop anomaly detection models on controller data.
Estimate the remaining useful life of reducers and drives.
Deploy predictive solutions integrated with the CMMS.
Assess the economic return of predictive programmes in robotics.
Who it's for
- Predictive maintenance engineers.
- Industrial robotics specialists.
- Industrial data scientists.
- Cell reliability engineers.
- Robotic systems integrators.
- Maintenance 4.0 managers.
- Engineering or science graduates seeking to enter the automotive sector.
What you'll work with
- ISO 13374-1 (condition monitoring and diagnostics: data processing, communication and presentation)
- ISO 17359 (condition monitoring and diagnostics of machines: general guidelines)
- ISO 10218-1 (safety requirements for industrial robots)
- ISO 13381-1 (condition monitoring and diagnostics: prognostics)
- IEC 62443-3-3 (system security requirements for industrial automation)
- ISO/TS 15066 (collaborative robots)
- IEC 63278-1 (Asset Administration Shell for industrial applications)
- ISO 20816-1 (measurement and evaluation of machine vibration)
- MATLAB Predictive Maintenance Toolbox
- Python with scikit-learn and PyTorch
- InfluxDB
- Node-RED
- ROS 2
12 modules · 1900 h
1.1Mechanical architecture of articulated robots1.2Harmonic and cycloidal reducers1.3Servomotors, encoders and brakes1.4Robot controllers and cabinets1.5Cabling, dress packs and hose fatigue1.6Robotic cells: peripherals and tooling1.7Typical failure modes of industrial robots1.8Preventive maintenance recommended by manufacturers1.9Safety during interventions according to ISO 102181.10Case study: stoppage history of a welding cell
2.1Internal signals from the robot controller2.2Motor torque, current and tracking error2.3External vibration and temperature sensors2.4OPC UA protocols and the Companion Specification for robotics2.5MQTT and edge architectures2.6Sampling rates and synchronisation2.7Contextualisation with programme and cycle2.8Storage in time-series databases2.9Data quality and event labelling2.10Lab: capturing axis torque via OPC UA
3.1Spectral analysis with FFT3.2Windowing, resolution and spectral leakage3.3Envelope analysis for bearings3.4Order analysis on variable-speed axes3.5Wavelet transform and time-frequency analysis3.6Statistical indicators: RMS, kurtosis and crest factor3.7Filtering and detrending3.8Normalisation by trajectory and load3.9Per-cycle feature extraction3.10Practical exercise: detecting backlash in a reducer
4.1Reducer wear and loss of stiffness4.2Lubricant degradation in reducers4.3Bearing failures in axes4.4Encoder drift and failures4.5Motor brake degradation4.6Cable and connector failures due to flexing4.7Wear of grippers, suction cups and tool changers4.8Problems in torches and process heads4.9Servo drive diagnosis4.10Workshop: symptom-cause matrix for a 6-axis robot
5.1Dynamic model of manipulators5.2Identification of friction parameters5.3Stiffness and backlash models5.4Residuals between model and measurement5.5Digital twin of the cell5.6Simulation of trajectories and loads5.7Observer-based detection5.8Hybrid physics-data models5.9Validating the twin with real data5.10Lab: friction identification on an axis
6.1Baseline of normal behaviour6.2Hotelling's T² multivariate statistical control6.3Principal component analysis6.4Isolation Forest and One-Class SVM6.5Autoencoders for torque signals6.6Adaptive thresholds and false positives6.7Per-cycle versus continuous detection6.8Explainability of alarms6.9Evaluation with imbalanced data6.10Practical exercise: autoencoder on pick-and-place cycles
7.1Health indicators and their construction7.2Stochastic degradation models7.3Wiener and gamma processes7.4Particle filters for prognosis7.5LSTM networks for RUL7.6Uncertainty in prognosis7.7Prognostic evaluation metrics7.8Benchmark datasets in prognostics7.9Transfer between similar robots7.10Lab: RUL estimation of a reducer
8.1RAMI 4.0 reference architecture8.2Edge, fog and cloud in predictive maintenance8.3Predictive services from robot manufacturers8.4Model orchestration on the shop floor8.5Integration with CMMS and automatic work orders8.6Fleet health dashboards8.7Cybersecurity according to IEC 624438.8Model lifecycle management8.9Scaling to multiple plants8.10Workshop: edge-to-cloud pipeline for a robot fleet
9.1Spot and arc welding cells9.2Painting cells and their specific features9.3Palletising and handling cells9.4Collaborative robots according to ISO/TS 150669.5AGVs and AMRs integrated into cells9.6Machine vision and its degradation9.7Pneumatic peripherals and conveyors9.8Cell availability as a system9.9Management of critical robot spare parts9.10Case study: predictive plan for a painting cell
10.1From prognosis to work order10.2Risk-based planning10.3Production windows and scheduled shutdowns10.4Cost of false positives and negatives10.5Optimisation of fleet interventions10.6Prioritisation by asset criticality10.7Technician feedback and relabelling10.8Return on investment of predictive maintenance10.9Availability-based service contracts10.10Practical exercise: optimal intervention schedule
11.1Pilots and scale-up of predictive maintenance11.2Selection of pilot robots and cells11.3Change management with maintenance technicians11.4Training and new roles11.5Programme success indicators11.6Machinery regulations and liability11.7Plant data governance11.8Success stories in automotive and logistics11.9Lessons learned and deployment risks11.10Case study: business case for a predictive programme
12.1Definition of the robot or cell to be studied12.2Data acquisition plan12.3Exploratory analysis and labelling12.4Development of health indicators12.5Detection and prognosis model12.6Proposed deployment architecture12.7Technical and economic validation12.8Conclusions and future work12.9Master's Thesis report12.10Master's Thesis: defence before a panel
How you'll learn
100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetables: you progress at your own pace within the intake, making it compatible with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is MATLAB Predictive Maintenance Toolbox, Python with scikit-learn and PyTorch, InfluxDB, Node-RED and ROS 2, in free, academic or evaluation versions. Exercises are based on real procedures for torque and current monitoring on articulated robots, early detection of reducer wear and remaining useful life prognosis in robotic cells. Assessment is continuous by module, plus the final Master's Thesis.
Standards covered: ISO 13374-1, ISO 17359, ISO 10218-1, ISO 13381-1, IEC 62443-3-3, ISO/TS 15066, IEC 63278-1, ISO 20816-1.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
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.
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 MATLAB Predictive Maintenance Toolbox, Python with scikit-learn and PyTorch, InfluxDB, Node-RED and ROS 2, 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.
Related programmes
Master’s in Advanced Manipulation Engineering
Online master's programme of 1,900 hours in advanced manipulation engineering. 12 modules covering manipulator kinematics and dynamics, motion planning, grippers, grasp theory, perception, contact-rich manipulation, robot…
Master’s in Cell and Line Digital Twins Engineering
Online master's programme of 1,900 hours in digital twin engineering for manufacturing cells and lines, structured in 12 modules covering geometric and kinematic modelling, robotic cell…
Master’s in Welding & Laser Automation
Online master's programme of 1,900 hours in welding and laser automation: cladding, cutting and optical safety. 12 modules covering ISO 10218-1 and -2, ISO/TS 15066, ISO…
More in Robotics, Automation & Control
All Robotics, Automation & Control programmes → · How to apply · Fees & financing · Scholarships