Postgraduate Diploma in Edge Analytics for Predictive Maintenance
Online 800-hour Postgraduate Diploma in Edge Analytics for Predictive Maintenance. 8 modules with ISO 13374-1, ISO 17359:2018 and Eclipse Kuksa. Assigned tutor and open enrolment.
Postgraduate Diploma in Edge Analytics for Predictive Maintenance — studying from South Africa
South Africa's automotive plants are increasingly integrating advanced driver assistance and connected vehicle technologies, driven by global manufacturers' software strategies. Local firms and research groups at universities such as Stellenbosch and the University of Pretoria contribute to vehicle electronics, sensor fusion and embedded software. Local component suppliers and the national automotive industry require engineers who can work across vehicle software, safety and validation. Compliance with national vehicle standards and road safety rules shapes how these systems are deployed.
Fees for South Africa: R 24 000 (South African rand), with instalments and employer sponsorship available.
Relevant bodies in South Africa
Typical roles
Questions from South Africa
Is this qualification recognised by ECSA or other South African bodies for autonomous vehicle engineering?
ECSA is the statutory body that registers engineering professionals in South Africa, and it does not automatically recognise private online programmes. SEIUM's qualifications are its own private qualifications, not official state degrees, and are not accredited by a national body. Recognition depends on your employer or the relevant professional body, so confirm their position in writing before you enrol.
Are there South African employers who would value skills in ADAS and software-defined vehicles?
South Africa's automotive sector, including local manufacturers and tier-one suppliers, increasingly uses electronic and software systems in vehicles, and technology firms also work in this space. Employers generally value demonstrable skills, relevant experience and recognised qualifications. Completing this programme may help you show specialist knowledge, but it does not guarantee a job. Discuss the programme with target employers first.
Can I study at a practical pace alongside work, and what language level is needed?
Study is online and taught in English, so strong written and spoken English is essential. Because it is remote, you need no student visa to study from home. The workload is 1,900 hours for a master's, 800 hours for a postgraduate diploma or 300 hours for a specialist course, supported by a technical tutor. Consider instalment payments, and ask your employer about sponsorship to ease the financial load.
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
Design predictive maintenance programmes for vehicles.
Architect data analysis at the vehicle edge.
Pre-process signals and extract relevant features.
Build anomaly detection models.
Estimate remaining useful life with uncertainty.
Deploy optimised models on embedded hardware.
Integrate predictions into maintenance operations.
Who it's for
- Predictive maintenance engineer who wants to specialise in Edge Analytics for Predictive Maintenance.
- Fleet data scientist who wants to specialise in Edge Analytics for Predictive Maintenance.
- Edge computing engineer who wants to specialise in Edge Analytics for Predictive Maintenance.
- Fleet maintenance manager who wants to specialise in Edge Analytics for Predictive Maintenance.
- Reliability engineer who wants to specialise in Edge Analytics for Predictive Maintenance.
- Embedded software engineer who wants to specialise in Edge Analytics for Predictive Maintenance.
- Engineering or science graduates looking to enter fleet operators.
What you'll work with
- ISO 13374-1
- ISO 17359:2018
- ISO 13381-1:2015
- ISO 55001:2024
- Reglamento (UE) 2023/2854
- Reglamento (UE) 2016/679
- IEC 62443-4-2
- ISO 26262:2018
8 modules · 800 h
1.1Corrective, preventive and predictive maintenance1.2Condition-based maintenance according to ISO 173591.3ISO 13374 architecture for monitoring1.4Diagnosis versus prognosis1.5Remaining useful life (RUL)1.6Candidate components: battery, brakes, tyres and engine1.7Benefits for fleets and manufacturers1.8Return on investment of predictive maintenance1.9Success stories in heavy transport1.10Case study: prioritising components for a predictive programme
2.1Edge, fog and cloud in mobility2.2Computing resources in ECUs and telematics units2.3Embedded operating systems and containers2.4Eclipse Kuksa and COVESA VSS signals2.5Stream processing in the vehicle2.6Trade-off between local computing and transmission2.7Energy consumption of embedded analytics2.8Remote updating of analytical models2.9Security of workloads at the edge2.10Laboratory: analytics service with Kuksa on Raspberry Pi
3.1CAN signals, sensors and logs3.2Sampling frequency and anti-aliasing3.3Digital filtering and noise removal3.4Windowing and segmentation by operating conditions3.5Time-domain feature extraction3.6Spectral and envelope analysis3.7Wavelet transform for transients3.8Normalisation by load, temperature and speed3.9Feature compression for transmission3.10Practical: vibration features of a wheel bearing
4.1Statistical methods and control charts4.2Isolation forests4.3Autoencoders for time series4.4One-class models4.5Physics-based and residual models4.6Adaptive thresholds4.7Managing false alarms4.8Explainability of anomalies4.9Evaluation without abundant labels4.10Workshop: anomaly detector on brake data
5.1Degradation and reliability models5.2Weibull distribution and survival analysis5.3Particle filters for prognostics5.4LSTM networks and transformers for RUL5.5Guidelines of ISO 13381-15.6Prognostic uncertainty5.7State of health of traction batteries5.8Validation with failure histories5.9Prognostic metrics5.10Laboratory: RUL estimation with the C-MAPSS dataset
6.1Model quantisation and pruning6.2TensorFlow Lite and ONNX Runtime6.3Microcontrollers and TinyML6.4Federated learning across vehicles6.5Model lifecycle management in a fleet6.6Field performance monitoring6.7Cloud synchronisation6.8Model security and signing6.9Cost per vehicle6.10Practical: deploying a quantised model on a microcontroller
7.1From alert to work order7.2Integration with maintenance management systems7.3Workshop and spare parts planning7.4Asset management according to ISO 550017.5Alerts to the driver and fleet manager7.6Availability and cost indicators7.7Warranties and field quality7.8Data protection and the European Data Act7.9Continuous improvement of the programme7.10Case study: predictive programme for a bus fleet
8.1Selection of the component and the fleet8.2Data acquisition plan8.3Feature extraction8.4Anomaly model8.5Prognostic model8.6Deployment at the edge8.7Integration with maintenance8.8Economic analysis8.9Report and presentation8.10Final review with the tutor
How you'll learn
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 enrolment period, which makes it possible to combine the programme with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is Eclipse Kuksa, TensorFlow Lite, AWS IoT Greengrass, Apache Kafka, Python with scikit-learn, in free, academic or evaluation versions. Tests are studied using real procedures for anomaly detection on fleet data, estimation of the remaining useful life of components, and deployment of models on embedded hardware. Assessment is continuous, module by module, plus the final integrating project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Design predictive maintenance programmes for vehicles.
Architect data analysis at the vehicle edge.
Pre-process signals and extract relevant features.
Build anomaly detection models.
Estimate remaining useful life with uncertainty.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. A university degree is not required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient level of Spanish to follow technical regulatory texts.
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 800 hours, spread over 6 to 8 months. That is between 10 and 15 hours per week on average, compatible with full-time work.
The programme uses Eclipse Kuksa, TensorFlow Lite, AWS IoT Greengrass, Apache Kafka and Python with scikit-learn. Free, academic or evaluation versions are used, and the tutor indicates the open-source alternative where one exists.
An SEIUM diploma awarded upon passing the continuous assessment and the integrating project. This 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 towards the advanced programme. Check the recognition policy when you enrol.
Related programmes
Postgraduate Diploma in External Signalling (eHMI) and Passenger Acceptance
Online 800-hour Postgraduate Diploma in External Signalling (eHMI) and Passenger Acceptance. 8 modules covering ISO/TR 23049:2018, SAE J3134 and Unity. Assigned tutor and open enrolment.
Postgraduate Diploma in Trust/Over-trust and Communication of Intent
Online 800-hour Postgraduate Diploma in Trust/Over-trust and Communication of Intent. 8 modules covering ISO/TR 21959, SAE J3114 and Unity. Assigned tutor and open enrolment.
Postgraduate Diploma in AI Governance for AD and EU AI Act
Online 800-hour Postgraduate Diploma in AI Governance for AD and EU AI Act. 8 modules covering Regulation (EU) 2024/1689, ISO/PAS 8800:2024 and MLflow. Assigned tutor and…
More in Autonomous, ADAS & Software-Defined Vehicle
All Autonomous, ADAS & Software-Defined Vehicle programmes → · How to apply · Fees & financing · Scholarships