Free course · AI and machine learning

Predictive Maintenance with Machine Learning

This free intermediate course builds predictive maintenance end to end: failure modes and what each sensor sees, signals to condition indicators, anomaly detection on healthy data, fault classification with grouped validation, deep learning on windows, and remaining useful life on NASA's C-MAPSS engines. It suits UK maintenance, reliability and data engineers in factories, utilities and asset-heavy firms. It helps with reliability engineer, condition monitoring engineer and data analyst roles. Wireless sensors are discussed, not required.

Predictive Maintenance with Machine Learning is a free online intermediate AI and machine learning course with 12 modules, about 16 hours of video lessons. Learning is free; an optional verifiable certificate costs £19 including VAT when you pass the final exam. Last updated 28 October 2026.

See the modules

Free to learn. Verifiable certificate £19 when you pass the final exam (optional, VAT included).

Level
Intermediate
Modules
12
Video
16 hours

Video time only: reading the notes, the quizzes and the final exam take extra time, at your own pace.

Price
Free

Outcome

What you will be able to do

Choose sensors by the P-F curve; recognise bearing, imbalance, misalignment, rotor-bar and insulation signatures; compute spectra, envelopes and condition indicators from windows; build a per-asset anomaly detector with a percentile threshold and persistence; train a fault classifier with grouped validation and cost-aware thresholds; estimate remaining useful life on the C-MAPSS benchmark; design alerts that get acted on; and deploy and measure the whole loop.

  • Choose the sensor by the warning time you need, and name the failure mode from its spectrum
  • Turn windows into condition indicators — kurtosis, band energies, envelope peaks — and rank them
  • Build a per-asset anomaly detector on healthy data with a threshold and persistence that stop alert floods
  • Train a fault classifier with grouped validation and thresholds set by cost
  • Estimate remaining useful life on the NASA C-MAPSS benchmark with the right target and metrics
  • Design alerts a technician acts on, deploy the loop on an edge box, and measure the programme

Software

Google Colab; NumPy, SciPy, Pandas, scikit-learn; TensorFlow for the optional deep-learning module.

Hardware

None. Wireless vibration sensors and a gateway are discussed, not required.

Syllabus

12 modules

Each module has video lessons, notes and a short quiz. The final exam closes the course.

  1. 1Why predictive, and the P-F curve3 lessons
  2. 2Failure modes and what each sensor sees2 lessons
  3. 3Signals: sampling, windows, spectra1 lesson
  4. 4Condition indicators2 lessonsLab
  5. 5Anomaly detection on normal data3 lessonsLab
  6. 6Fault classification3 lessonsLab
  7. 7Deep learning on windows4 lessons
  8. 8Remaining useful life on NASA's engines3 lessonsLab
  9. 9The end-to-end workflow3 lessons
  10. 10Alerts that get acted on1 lesson
  11. 11Deploying and measuring2 lessons
  12. 12Final assessment0 lessons

How it works

How this course works

  1. Watch the video lessonsOne module at a time, at your own pace.
  2. Take the module quizA short quiz at the end of each module shows what stuck.
  3. Keep your notesWrite in My notes beside each module and ask the trainer if you are stuck.
  4. Practise in the labOptionalTry a task from the module in the EDWartens Lab, in your browser.
  5. Sit the final examPass it once you have been through the modules.
  6. Certificate, if you want oneOptionalPaid, and only after you pass. Anyone can check it online.

EDWartens Lab

Practise this in the EDWartens Lab

Train a model on plant data, move the decision threshold and weigh the cost of errors in the Lab's AI workbench.

Works alongside Predictive Maintenance with Machine Learning. The Lab is ai for industry practice in your browser: no install, no hardware, free to use. Sign in as a learner and it opens with your account.

AI for industry: Build AI models.

Levels to try with this course

Optional. Skip it whenever you like: it never blocks your progress or your certificate.

Why practise in a lab

Technical work is judged on what you can do: wiring, commissioning, finding a fault. Doing a task yourself teaches more than watching it a second time, and a lab lets you try it safely before you meet real equipment. It does not replace working on real hardware.

  • Practise safely, so a mistake costs nothing.
  • The lab checks your work like a site test, so you know when it is right.
  • Free, in your browser, with nothing to install.

Certificate

An optional certificate when you pass

Learning is free. Pass the final exam and you can have a certificate for £19, including VAT, with a number employers can check online. It records that you completed a free online course; it is not a regulated qualification or a CPD certificate.

  • Your name, the course, its study time and your final exam score
  • A unique certificate number and a QR code to its verification page
  • Issued by Wartens Ltd; add it to your LinkedIn profile in one click
  • Pay now or after you pass: it is issued the moment you pass the final

How the certificate works

Sample certificate for Predictive Maintenance with Machine Learning

Credits

Who made the lessons

The video lessons belong to their creators. EDWartens wrote the study plan, notes, quizzes and the final exam.

  • MATLAB

    the predictive maintenance series, the signal-processing talk and the prognostics case study

  • RealPars

    predictive maintenance explained and machine learning for predictive maintenance

  • ADASH

    vibration analysis for beginners

  • Intelligent Machines

    machine learning and deep learning for fault diagnosis, and the turbofan RUL videos

  • Dave Ebbelaar

    detecting outliers in sensor data

  • Data Science with Marco

    anomaly detection in time series

  • NeuralNine

    anomaly detection for time-series data

  • Victor Tan

    the end-to-end predictive maintenance workflow

  • Data Bowl Recipes

    predictive maintenance with machine learning

  • JCharisTech

    predictive maintenance with machine learning in Python

  • InfluxData

    a lesson in "Deploying and measuring"

  • AIEngineering

    a lesson in "Deploying and measuring"

Jobs

Jobs this course can lead to

The skills in this course are used in AI and machine learning work, for example as a reliability engineer, a condition monitoring engineer and a data analyst. No course can promise a job, and employers also look for experience, so read what live adverts ask for.

Questions

About this course

Last reviewed 28 October 2026.

Is this enough to get a predictive maintenance job in the UK?
No. It gives you a complete worked workflow and the habits that make models trustworthy. Employers also look for experience with real plant data, maintenance knowledge and clear communication, so use it to build a project you can explain.
Do I need sensors or my own plant data?
No. Nothing is required. Wireless vibration sensors and a gateway are discussed, not needed, and the exercises use public data such as NASA's run-to-failure engines. Your own data lets you apply the same steps afterwards.
Do I need machine learning experience first?
It helps. This is an intermediate course, and it moves from signals to models fairly quickly. If you are new, take the machine learning with Python course first, then return here for the maintenance application.
What does the Predictive Maintenance with Machine Learning course cover?
It has 12 modules. The first are “Why predictive, and the P-F curve”, “Failure modes and what each sensor sees”, “Signals: sampling, windows, spectra”, “Condition indicators” and “Anomaly detection on normal data”, and 7 more follow. Each module has video lessons, notes and a short quiz.
Where does Predictive Maintenance with Machine Learning start and where does it end?
It starts with “Why predictive, and the P-F curve” and the last module is “Final assessment”. The final exam closes the course, and passing it is what makes the optional £19 certificate available.
How long is Predictive Maintenance with Machine Learning?
12 modules with 27 lessons, about 16 hours of video lessons. The largest module is “Deep learning on windows” with 4 lessons. Video time only: reading the notes, the quizzes and the final exam take extra time, at your own pace.
Can I practise Predictive Maintenance with Machine Learning in the browser?
Yes. Some modules of Predictive Maintenance with Machine Learning have a practice level in the EDWartens Lab, marked Lab on the module list, so you can try the ideas in your browser without installing software.
Do I need vibration sensors?
No. The course uses the track's vibration windows and motor-fleet readings, and NASA's public engine dataset. The module on sensors tells you what to buy and where to mount it when you do.
What do I need before this course?
The Machine Learning with Python course, or equivalent: features, splits, cross-validation, metrics. Module 7 uses the Deep Learning course's tools but is optional.
What are the projects?
Remaining useful life on NASA's C-MAPSS FD001 engines, evaluated the way the benchmark is — and the two lower rungs on the track's own data: an anomaly detector with persistence on vibration windows and a fault classifier with cost-aware thresholds on the motor fleet, with alert text a technician could act on.
Is the course really free?
Yes. Every module, practice task, project and assessment. You create an account so your progress is saved and the assessments can be marked. The certificate is the only paid item, and only if you want it.
What certificate do I get?
An EDWartens Certificate of Completion, issued when you have finished the modules and passed the final assessment (the project is optional practice), with a verification code anyone can check. It is not a vendor credential and is never described as one.
Who made the video lessons?
The creators named in the Credits block at the foot of this page, on their own YouTube channels. EDWartens did not make the videos and the creators are not affiliated with EDWartens. What EDWartens wrote is the study plan, the notes, the practice tasks, the projects and the assessments.
How long does the course take?
Plan on about 16 hours in all, including the video lessons, notes and practice tasks. It is self-paced, so you work through the twelve modules at your own speed.

Want a live class and career support?

The Professional Module is five live days of Siemens PLC, HMI and SCADA with an instructor, then career sessions with our engineers and a CPD certificate.

Engineers talking beside an automation test rig, one looking up and smiling