Course on AI in Nuclear Equipment Diagnostics
Online course of 300 h in AI in Nuclear Equipment Diagnostics. 6 modules covering Regulation (EU) 2024/1689 (Artificial Intelligence Act), ISO/IEC 23894 (artificial intelligence risk management) and Python (scikit-learn, pandas). Dedicated tutor and enrolment open.
Course on AI in Nuclear Equipment Diagnostics — studying from India
India's nuclear programme is state-led and centred on the Department of Atomic Energy, with operations managed by the Nuclear Power Corporation of India and research carried out at the Bhabha Atomic Research Centre. Reactor sites are located at places such as Tarapur, Kakrapar, Kudankulam and Rawatbhata. Regulation is handled by the Atomic Energy Regulatory Board, which sets safety standards for reactors and fuel facilities. Engineers in this field work on reactor systems, fuel cycle technologies, radiation safety and materials, with expertise supported by institutions such as the Indira Gandhi Centre for Atomic Research.
Fees for India: ₹57,900 (Indian Rupee), with instalments and employer sponsorship available.
Relevant bodies in India
Typical roles
Questions from India
Who regulates nuclear engineering work in India and does this course satisfy them?
The Atomic Energy Regulatory Board (AERB) regulates nuclear safety in India, and the Department of Atomic Energy runs the sector. SEIUM's qualification is private, not an official degree, and is not accredited by any national body. It does not satisfy any regulatory requirement, and AERB or the employer will decide what qualifications they require.
Which Indian employers work in nuclear engineering and the fuel cycle?
Public sector nuclear organisations and their associated industries are the main employers, and entry normally follows government recruitment and vetting processes. Private employers in the sector also exist. Because hiring is tightly controlled, a private online qualification is unlikely to be the deciding factor, and recognition depends on the employer.
Is this programme workable with a job in India, and how is it funded?
The programme is online and taught in English, so you can study from home across India without a student visa. Each student is assigned a technical tutor and completes a final project. Fees are payable in instalments, and employer sponsorship is possible, which is often the practical route for working engineers.
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 failure modes of the main plant equipment and their measurable symptoms.
Extract relevant features from vibration, temperature and process signals.
Train and compare machine learning models for fault classification.
Estimate the remaining useful life of components using prognostic models.
Apply explainability techniques to justify model decisions.
Analyse the qualification and regulatory requirements for deploying AI in nuclear environments.
Develop a prototype diagnostic system using real or simulated data.
Who it's for
- Nuclear predictive maintenance engineer looking to specialise in AI in Nuclear Equipment Diagnostics.
- Industrial data scientist looking to specialise in AI in Nuclear Equipment Diagnostics.
- Condition monitoring specialist looking to specialise in AI in Nuclear Equipment Diagnostics.
- Equipment reliability engineer looking to specialise in AI in Nuclear Equipment Diagnostics.
- Industrial AI solutions developer looking to specialise in AI in Nuclear Equipment Diagnostics.
- Component life management analyst looking to specialise in AI in Nuclear Equipment Diagnostics.
- Engineering or science graduates looking to move into nuclear power plants.
What you'll work with
- Regulation (EU) 2024/1689 (Artificial Intelligence Act)
- ISO/IEC 23894 (artificial intelligence risk management)
- ISO 13381-1 (condition monitoring: prognostics)
- ISO 17359 (condition monitoring and diagnostics of machines)
- IEC 60880 (software for category A I&C systems)
- ISO/IEC 42001 (AI management systems)
- ISO 13374 (condition monitoring data processing)
6 modules · 300 h
1.1Critical equipment: pumps, valves, turbines and motors1.2Corrective, preventive and predictive maintenance1.3Condition-based maintenance1.4The Maintenance Rule 10 CFR 50.651.5Ageing management according to IAEA SSG-481.6Failure modes and FMECA of nuclear equipment1.7Data sources: vibration, thermography and oil analysis1.8Online monitoring systems1.9Equipment reliability indicators1.10Case study: failure history of a reactor coolant pump
2.1Signal acquisition and pre-processing2.2Spectral analysis and FFT of vibrations2.3Envelope analysis for bearings2.4Wavelets and time-frequency analysis2.5Neutron noise and core diagnostics2.6Acoustic emission in pressure components2.7Motor current signature analysis (MCSA)2.8Diagnostics of motor-operated valves2.9Feature selection and reduction2.10Lab: vibration feature extraction in Python
3.1Supervised classification: SVM and random forests3.2Anomaly detection: Isolation Forest and autoencoders3.3Multivariate state estimation (MSET)3.4Convolutional networks on spectrograms3.5Recurrent networks and LSTM for time series3.6Imbalanced data and scarcity of failures3.7Transfer learning between equipment3.8Cross-validation and diagnostic metrics3.9Public datasets: CWRU and NASA3.10Lab: anomaly detector for a turbine generator
4.1Physical and statistical degradation models4.2Remaining useful life (RUL) estimation4.3Weibull models and survival analysis4.4Particle filters for prognostics4.5Hybrid physics- and data-driven models4.6Uncertainty quantification in prognostics4.7Prognostics for cables and transformers4.8Fatigue estimation in primary circuit components4.9Risk-based maintenance prioritisation4.10Practice: RUL estimation with C-MAPSS data
5.1Architecture of an on-site diagnostic system5.2Integration with maintenance systems5.3Explainability: SHAP and LIME5.4Cybersecurity of connected systems5.5Software safety classification according to IEC 612265.6Verification and validation of AI models5.7NRC guidance on AI for regulators5.8Data drift and model maintenance5.9EPRI experience and international programmes5.10Case study: justification to the regulator
6.1Selecting the equipment and failure modes6.2Dataset preparation6.3Feature extraction6.4Model training and comparison6.5Remaining useful life estimation6.6Explainability and validation6.7Proposal for on-site deployment6.8Summary of results6.9Report and presentation6.10Final review with the tutor
How you'll learn
100% online training on the SEIUM campus, with downloadable materials, recorded classes and a dedicated technical tutor. No fixed timetable: students progress at their own pace within the intake period, making it easy to combine with work.
Each module combines theory, guided reading of the original standards and applied exercises. The software used is Python (scikit-learn, pandas), PyTorch, MATLAB Predictive Maintenance Toolbox, AVEVA PI System, SHAP (explicabilidad de modelos), in free, academic or trial versions. Testing is studied through real procedures from analysis of pump vibration signals and motors, plant monitoring datasets, validation of predictive models with historical data. Assessment is continuous for each module, plus a final capstone project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Identify the failure modes of the main plant equipment and their measurable symptoms.
Extract relevant features from vibration, temperature and process signals.
Train and compare machine learning models for fault classification.
Estimate the remaining useful life of components using prognostic models.
Apply explainability techniques to justify model decisions.
Where this takes you
Requirements
- No previous qualification is required.
- An internet connection and a computer able to run the programme software.
- A level of 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 300 hours spread over 3 to 5 months. That is an average of 10 to 15 hours per week, compatible with a full-time job.
You will work with Python (scikit-learn, pandas), PyTorch, MATLAB Predictive Maintenance Toolbox, AVEVA PI System, SHAP (explicabilidad de modelos). Free, academic or trial versions are used, and your tutor will point out a free alternative where one exists.
A SEIUM Institute diploma, awarded on passing the continuous assessment and the capstone project. It is SEIUM's own qualification, not an official state-accredited degree.
Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Check the recognition policy when you enrol.
Related programmes
Course in Nuclear Reactor Thermal-Hydraulics
Online 300-hour course in nuclear reactor thermal-hydraulics. 6 modules covering IAEA SSG-2 Rev. 1 (deterministic safety analysis), 10 CFR 50.46 (ECCS acceptance criteria) and RELAP5-3D. Personal…
Ethics in Academic Use of Simulators Course
Online 300-hour course in ethics in the academic use of simulators. 6 modules covering ANSI/ANS-10.4 (verification and validation of scientific software), Directive 2009/24/EC (legal protection of…
International Governance of Nuclear Waste Course
Online 300-hour course in international governance of nuclear waste. 6 modules covering the Joint Convention on the Safety of Spent Fuel Management and on the Safety…
More in Nuclear Engineering & Nuclear Fuel Cycle Technologies
All Nuclear Engineering & Nuclear Fuel Cycle Technologies programmes → · How to apply · Fees & financing · Scholarships