Diploma in Industrial Data Architectures and Feature Stores
Online postgraduate diploma of 800 hours in industrial data architectures and feature stores. 8 modules covering IEC 62264 (ISA-95), IEC 62541 (OPC UA) and IEC 62443, with Apache Spark and Delta Lake, Feast, Apache Airflow and time-series databases, 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
Identify the sources and particular characteristics of industrial data.
Design lakehouse and Unified Namespace architectures for the plant.
Build robust ingestion and contextualisation pipelines.
Develop time-series features without information leakage.
Implement feature stores with consistency between training and serving.
Optimise platform performance and cost.
Secure and operate the data platform following good practice.
Who it's for
- Industrial data engineers.
- Data architects designing OT/IT platforms.
- Machine learning engineers who need reliable features from plant data.
- OT/IT integration specialists.
- Data platform engineers.
- Industrial analytics consultants.
- Engineering or science graduates aiming to enter discrete manufacturing.
What you'll work with
- IEC 62264 (ISA-95: enterprise-control system integration)
- IEC 62541 (OPC Unified Architecture)
- IEC 62443 (security of industrial automation and control systems)
- ISO/IEC 20547-3 (big data reference architecture)
- OASIS MQTT 5.0 (messaging protocol)
- ISO 8000 (data quality)
- Apache Spark with Delta Lake
- Feast
- Apache Airflow
- InfluxDB or TimescaleDB
- Databricks
8 modules
1.1Process, event, quality and maintenance data1.2The ISA-95 pyramid and data flows1.3Process historians1.4High-frequency time series1.5Batch data and production context1.6Metadata and asset hierarchies1.7Challenges: heterogeneity, latency and volume1.8OT data versus IT data1.9Analytical use cases on the shop floor1.10Workshop: data source inventory for a plant
2.1Lambda and kappa architectures2.2Data lake, data warehouse and lakehouse2.3Unified Namespace with MQTT2.4Medallion architecture: bronze, silver and gold2.5Edge, fog and cloud2.6Parquet, Delta Lake and Iceberg formats2.7Time-series databases2.8Semantic modelling of assets2.9OT/IT integration patterns2.10Lab: lakehouse with Delta Lake and Spark
3.1OPC UA, Modbus and MQTT connectors3.2Change data capture (CDC) from databases3.3Batch and streaming ingestion3.4Time alignment and resampling3.5Contextualisation with orders and batches3.6Tag management and naming conventions3.7Data quality at ingestion3.8Schemas and schema evolution3.9Orchestration with Airflow and Dagster3.10Practical: ingestion pipeline from a historian
4.1Time-series features4.2Sliding windows and aggregations4.3Frequency-domain features4.4Encoding categorical variables4.5Process context features4.6Temporal information leakage4.7Point-in-time correct joins4.8The tsfresh and featuretools libraries4.9Reusing features across models4.10Lab: features for quality prediction
5.1Concept and components of a feature store5.2Offline store and online store5.3Feature registry and discovery5.4Feast as an open-source feature store5.5Databricks, SageMaker and Vertex feature stores5.6Materialisation and refresh5.7Consistency between training and serving5.8Streaming features5.9Feature versioning and lineage5.10Practical: deploying Feast with plant data
6.1Table partitioning and clustering6.2Compaction and small-file management6.3Caching and in-memory storage6.4Online serving latency6.5Horizontal scaling of compute6.6Storage and compute costs6.7Retention and archiving6.8Load testing6.9Pipeline observability6.10Case study: optimising an industrial lakehouse
7.1Network segmentation according to IEC 624437.2Industrial demilitarised zones7.3Access control and roles7.4Encryption in transit and at rest7.5Secrets management7.6Deployment with infrastructure as code7.7CI/CD for data pipelines7.8Disaster recovery7.9Architecture documentation7.10Workshop: designing the data security architecture
8.1Use case and data platform requirements8.2Target platform architecture8.3Ingestion and contextualisation8.4Data model8.5Feature engineering8.6Feature store commissioning8.7Data platform performance testing8.8Data platform operation plan8.9Report and presentation8.10Final project: final review with the tutor
How you'll learn
Training is 100% online on the SEIUM campus, with downloadable material, 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 Apache Spark with Delta Lake, Feast, Apache Airflow, InfluxDB or TimescaleDB, and Databricks, in free, academic or evaluation versions. Practical work is based on real procedures: building a lakehouse with historian data, deploying a feature store with online serving, and point-in-time correctness tests for features. Assessment is continuous by module, plus the final project.
Standards covered: IEC 62264 (ISA-95), IEC 62541 (OPC UA), IEC 62443, ISO/IEC 20547-3, OASIS MQTT 5.0 and ISO 8000.
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
- Prior technical training or professional experience in the sector. No university degree is required.
- Internet connection and a computer capable of running the programme's 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 800 hours over 6–8 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with Apache Spark with Delta Lake, Feast, Apache Airflow, InfluxDB or TimescaleDB, and Databricks, 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 final project. 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 are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.
Prior technical training or professional experience in the sector (no university degree required), 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
Diploma in Scenarios, Trade-offs and Sensitivity Analysis
Online postgraduate diploma of 800 hours in scenarios, trade-offs and sensitivity analysis. 8 modules covering multi-criteria decision structuring, scenario planning, AHP, TOPSIS and PROMETHEE, multi-objective optimisation,…
Diploma in Risk Management and Regulatory Documentation
Online postgraduate diploma of 800 hours in risk management and regulatory documentation: 8 modules covering AI risk management, the European AI regulatory framework, risk assessment and…
Diploma in Real-Time Operational Analytics
Online postgraduate diploma of 800 hours in real-time operational analytics, with 8 modules covering real-time data architectures, messaging and event capture, stream processing, real-time analytical stores,…
More in Data, AI, Simulation & Analytics
All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships