Postgraduate Diploma in Material Classification and Defect Detection
Online 800 h Postgraduate Diploma in Material Classification and Defect Detection. 8 modules covering ISO 9712, ISO 17640 and HALCON. Assigned tutor and open enrolment.
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
Characterise the physical and spectral signatures of different materials.
Apply material classification technologies such as NIR, XRF and eddy currents.
Develop chemometric and machine learning models for classification.
Detect surface defects using vision and specialised lighting.
Apply deep learning and anomaly detection to inspection.
Integrate non-destructive testing for internal defects.
Evaluate inspection systems using metrics and error costs.
Who it's for
- Machine vision engineer who wants to specialise in Material Classification and Defect Detection.
- Non-destructive testing specialist who wants to specialise in Material Classification and Defect Detection.
- Production quality engineer who wants to specialise in Material Classification and Defect Detection.
- Industrial data scientist who wants to specialise in Material Classification and Defect Detection.
- Recycling plant engineer who wants to specialise in Material Classification and Defect Detection.
- Automated inspection technician who wants to specialise in Material Classification and Defect Detection.
- Graduates in engineering or science who want to enter recycling and waste management.
What you'll work with
- ISO 9712
- ISO 17640
- ISO 10893-11
- ISO 11469
- ISO 15270
- ISO 2859-1
- Directive 2008/98/EC
- ASTM E1316
8 modules · 800 h
1.1Metals, polymers, ceramics and composites1.2Optical properties of materials1.3Spectral signatures of recyclable polymers1.4Electrical and magnetic properties for classification1.5Density and mechanical properties1.6Defect typologies by material1.7Origin of defects in manufacturing processes1.8Standardised defect catalogues1.9Reference spectral libraries of materials1.10Practical: building a spectral library of polymers
2.1NIR classification in recycling plants2.2Separation by eddy currents2.3X-ray fluorescence and LIBS for metals2.4Classification by colour and shape2.5Induction sensors for metals2.6Glass and ceramic classification2.7Pneumatic air-jet sorting2.8Purity and product recovery2.9Construction waste classification2.10Laboratory: NIR classification of polymers
3.1PLS-DA discriminant analysis3.2SIMCA and class modelling3.3Support vector machines3.4Random forests and gradient boosting3.51D neural networks for spectra3.6Cross-validation and test sets3.7Confusion matrices and metrics3.8Model transfer between sensors3.9Variable and spectral region selection3.10Workshop: PLS-DA model with cross-validation
4.12D vision for surface defects4.2Dark-field and structured illumination4.3Photometric stereo for surface relief4.4Active thermography for subsurface defects4.5Crack detection by induced currents4.6Defects in textiles and continuous strips4.7Weld inspection4.8Severity classification4.9Inspection of painted and coated surfaces4.10Practical: scratch detection with photometric stereo
5.1Convolutional neural networks for classification5.2YOLO object detection5.3U-Net semantic segmentation5.4Unsupervised anomaly detection5.5Autoencoders and PatchCore5.6Data augmentation and synthetic data5.7Class imbalance5.8Explainability with activation maps5.9Efficient labelling with active learning5.10Laboratory: anomaly detection with PatchCore
6.1Ultrasonics and phased array6.2Digital radiography of castings6.3Thermography for delaminations6.4Induced currents in conductive materials6.5Composite inspection6.6Defect acceptance criteria6.7NDT personnel qualification6.8Fusion of inspection techniques6.9Pulsed induced currents in metallic structures6.10Case study: delamination inspection in composites
7.1False rejection rate metrics7.2ROC curves and threshold selection7.3Attribute agreement studies7.4Inline integration in production7.5Process feedback7.6Model maintenance7.7Cost of misclassification7.8Audit of the inspection system7.9Acceptance tests with reference batches7.10Case study: threshold adjustment on a sheet metal line
8.1Definition of materials and defects8.2Data acquisition8.3Sensor design and set-up8.4Development of the classification model8.5Development of the defect detector8.6Validation with real data8.7Study of error costs8.8Analysis of results8.9Report and presentation8.10Final review with the tutor
How you'll learn
100 % online training on the SEIUM Institute campus, with downloadable material, recorded lectures and an assigned technical tutor. No fixed timetables: students progress at their own pace within the enrolment period, which makes it possible to combine study with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is HALCON, PyTorch, Anomalib, MATLAB, The Unscrambler X, in free, academic or evaluation versions. Tests are studied on real procedures for classifying polymers in recycling plants, detecting surface defects on steel coils, and inspecting composites with active thermography. Assessment is continuous per 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.
Characterise the physical and spectral signatures of different materials.
Apply material classification technologies such as NIR, XRF and eddy currents.
Develop chemometric and machine learning models for classification.
Detect surface defects using vision and specialised lighting.
Apply deep learning and anomaly detection to inspection.
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.
- Sufficient Spanish to follow technical standards documentation.
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 comprises 800 hours in total, spread over 6 to 8 months. That is an average of 10 to 15 hours per week, compatible with a full-time job.
The programme uses HALCON, PyTorch, Anomalib, MATLAB and The Unscrambler X. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
A SEIUM Institute diploma upon passing the continuous assessment and the integrating project. This is an in-house programme, not an official qualification from the Ministry.
Yes. Modules passed in a course or postgraduate diploma in the same area can be credited towards the advanced programme. Please check the credit transfer policy when you enrol.
Related programmes
Diploma in Automated Fulfillment and Slotting
Online postgraduate diploma of 800 hours in automated fulfilment and slotting: 8 modules covering fulfilment operations, logistics data analysis, slotting, automation technologies, warehouse control software, simulation…
Postgraduate Diploma in Torque/6D Sensors and Control Strategies
Online 800-hour Postgraduate Diploma in Torque/6D Sensors and Control Strategies. 8 modules covering ISO/TS 15066, ISO 10218-1 and ATI Industrial Automation NET F/T and configuration software.…
Diploma in Sectoral Regulation and Validation
Online postgraduate diploma of 800 hours in sector regulation and validation: 8 modules covering the regulatory framework, quality risk management, the validation lifecycle, computerised systems, validation…
More in Robotics, Automation & Control
All Robotics, Automation & Control programmes → · How to apply · Fees & financing · Scholarships