Understanding Control Technologies
AGENDA Instructors ADDITIONAL INFO ONLINE REGISTRATION
Fundamentals of AI and Machine Learning for Control Engineers
Introduction to AI for Practical Control and Condition Monitoring
9 - 11 September 2025, Glasgow
Overview
Artificial Intelligence (AI) and Machine Learning (ML) has received a new impetus in recent years and offers opportunities for services and products. There are many areas where artificial intelligence and machine learning is already having an impact that will affect industrial control systems design, ranging from the design procedures to the improvement in the performance and robustness of systems. AI and ML offer solutions to some of the most difficult problems. For example, how to reduce the design time and commissioning time for systems that have difficult dynamics.
Artificial intelligence can be utilised in control applications in two main ways. The first involves data analysis where big data can be used to inform management actions or initiatives. The second is focused on the use of AI to provide improvements in control or signal processing systems at an electro-mechanical machine or local plant level, including the use of digital twins for modelling, prediction and condition monitoring. The use of AI methods for data analysis is where much of the previous attention was focused but from a control engineers’ perspective it is the data driven machine leaning control methods that are of most interest. These provide opportunities to introduce new types of adaptive controllers, filters and condition monitoring tools that can introduce compensation for uncertainties in system or signal characteristics.
There are many developments in this area and one of the main aims of the course is to pick out the advances that are of most importance to control engineers. The course will introduce some of the most significant results and priority areas. For example, the influence of AI methods on system modelling and control design provides a different philosophical approach and therefore new opportunities to improve performance and reduce engineering design effort.
Both pure data driven black box AI based methods and those that combine AI and model-based methods will be described, and the relative advantages discussed. The latter are attractive since pure data driven modelling methods can be useful, but it is a pity to ignore good physical system model information. A benefit of combining AI and traditional model knowledge and control methods is that plant engineers may have great confidence in an existing controller, even if the performance is limited. They are therefore likely to be more receptive to enhancing such solutions rather than using a radically new approach. Improving solutions via the data available is a cautious step but it can provide significant performance improvements. Moreover, if under some conditions the data does not improve a solution, the system can revert to the original controller seamlessly.
The ways in which AI and ML will satisfy the practical demands of an engineering system will be covered including the requirements and physical constraints that must often be met. The main aim of a control system is often to provide reliable and consistent performance, in the presence of uncertainties. The effective use of data can at least partly address the uncertainty problem. The second most important aim of many systems is to optimize performance, and in this case the relatively new meta-heuristic AI inspired optimization algorithms can be valuable. Data driven methods can also be used to mitigate the deleterious effects of nonlinearities.
The course is introductory and aims to provide an intuitive understanding supported by hands-on simulation examples using MATLAB/Simulink. The PowerPoint presentations will include notes that can be used as an aide-memoire. There will also be software demonstrations and opportunities to discuss the material, or ask questions, at the end of the presentations and at the end of each session.
Instructors
Professor Michael Grimble
Professor Mike Grimble has a good understanding of the needs of industry having first worked for Ciba Geigy and then for Associated Electrical Industries which became GEC at Rugby. During his time on the Industrial Automation Group at Imperial College he worked on the modelling for control of cold rolling mills. He later set up industrial groups first at what is now Sheffield Hallam University and secondly at the University of Strathclyde where he still works as a Research Professor. His interests are on the design of high performance and robust control systems for applications across industrial sectors. His industrial background is valuable to provide motivation and insights on the industrial training courses.
Dr Pawel Majecki
Dr Pawel Majecki undertook his research studies in the Industrial Control Centre at Strathclyde University and later joined Industrial Systems and Control Ltd. ISC was established to encourage technology transfer and Pawel has worked for major international companies on the application of advanced control methods, often involving predictive or optimal controls. He has also been involved in control training courses run in the UK, Norway, Italy, Spain and USA. His extensive experience in the use of MATLAB/Simulink is valuable on the training courses hands-on where delegates often gain greater insight into these tools in addition to their value in explaining how the design methods are applied.
Dr Luca Cavanini
Dr Luca Cavanini is experienced in advanced control methods such as nonlinear model predictive control, optimisation, renewable power, mobile robotics, autonomous vehicle control, path planning, artificial intelligence, and machine learning techniques for control systems.
Delegates will find that all instructors are very happy to answer questions or discuss industrial problems they may have in coffee breaks, lunch breaks and at the end of the day.
Additional Information
Event Venue
Glasgow City Centre
Accommodation
Glasgow City Centre offers a wide range of accommodation, you can find our recommendations here.
Agenda (Download PDF)
Timings may change slightly.
Day 1: Artificial Intelligence Fundamentals |
|
| 9.00 | WELCOME |
| 9.10 | Introduction to Intelligent Control and Machine Learning I (Core ideas in artificial intelligence, motivation, terminology, brief history of AI systems, classification problems, big data, deep learning, importance of AI in control applications.) |
| 10.15 | TEA/COFFEE |
| 10.30 | Introduction to Intelligent Control and Machine Learning II (Historical perspective, main ideas and techniques, machine learning, reinforcement learning, developments in AI, multi-agent systems, possible application areas, benefits in applications.) |
| 11.30 | Different Approaches to Modelling Systems (Including the AI approach to modelling and the physical system model equation based methods (model based), and system descriptions, parameterization of models.) |
| 12.30 | LUNCH |
| 13.30 | Meta Heuristic Optimization and Gradient Algorithms (AI based optimization algorithms for linear and nonlinear systems, for training parameters, gradient methods.) |
| 14.30 | TEA/COFFEE |
| 14.45 | Neural Networks (Introduction to neural networks, neurons, activation functions, types of NN, forward and backward propagation, layers of neural networks, network structures, loss functions, advantages and disadvantages, and use in condition monitoring, fault detection and prognostics.) |
| 16.00 | Neural Networks Design Demonstration (Design and comparison of different NNs for torque demand prediction.) |
| 17.00 | CLOSE |
Day 2 - Artificial Intelligence in Modelling and Classical Control |
|
| 09.00 | Digital Twins for Control and Monitoring Applications (Digital Twin for modelling, condition monitoring, prediction, and control.) |
| 10.00 | TEA/COFFEE |
| 10.15 | Support Vector Machine Approach to System Identification (AI and SVM methods on modelling and system identification.) |
| 11.30 | Demonstration Support Vector Machine Approach to System Identification (SVM data-driven design tool demo/hand-on.) |
| 12.30 | LUNCH |
| 13.30 | Classical Control and use with AI/ML Methods (AI/ML methods for improving classical controllers, Neural Network Based Reinforcement, Learning for Automotive Control.) |
| 14.30 | TEA/COFFEE |
| 14.45 | AI in Control Systems: Limits and Advantages (Review of the role of AI in control system with discussion of limits, issues, and reasons for using together with advanced control.) |
| 15.45 | Relationship between Fuzzy Logic Based Algorithms and AI Methods (Introduction to Fuzzy Control and links to AI, Neuro-fuzzy application.) |
| 17.00 | CLOSE |
Day 3 - Artificial Intelligence in Advanced Controls |
|
| 09.00 | Optimisation and Optimal Control in AI Enhanced Systems (Introducing AI methods into Nonlinear and Predictive Controls, Use of Genetic Algorithms, Why AI is important in applications, such as automotive and examples.) |
| 10.00 | TEA/COFFEE |
| 10.15 | Introduction to Model Predictive Control (Motivational introduction to MPC methods and the solution approach, and why it is so successful, where it has advantages, and briefly overviews competing methods that are options such as classical, LQG, H∞ robust and nonlinear control design methods.) |
| 11.30 | AI Enhanced Model Predictive Control (The AI role in controllers design, AI for modelling/control/calibration, Introduction to the example AI predictor for LPV-MPC in automotive application.) |
| 12.30 | LUNCH |
| 13.30 | Hybrid-Electric Vehicle MPC-LPV Energy Management System Demonstration (Model Predictive Control-based Energy Management System and Benchmarking, the role of prediction and different predictor structures) |
| 14.30 | TEA/COFFEE |
| 14.45 | Review of the Current State of Combined AI and Control System Techniques (Review of the literature on combined AI and control techniques, new ideas and potential for modern control techniques and new developments.) |
| 16.00 | Discussion: Commercial Developments and Machine Learning Tools - Debate |
| 16.30 | CLOSE |
Prices and Discounts
- Registration before 1st August 2025: £1,428 + VAT per delegate
- Registration on/after 1st August 2025: £1,608 + VAT per delegate
For two or more places from the same organisation, each additional place is 10% off the single place fee.
Registration
Please complete the Online Registration Form.
Can't Find the Course You Need?
Try our bespoke course service.