Contact | Sitemap | Search
HomeAboutEducationResearchProject activitiesNetworks & Partnerships
top image
Back
Module
Computational Intelligence and Control Systems
I am in > Home > Module > Computational Intellig...  
Computational Intelligence and Control Systems

Computational Intelligence and Control Systems (WSE/HI/06/s)

Prerequisites

Basic Mathematics and Hydraulics


Learning objectives

After completing the module participants should be able to:

  • understand the main optimisation techniques;
  • understand and explain how real-time control systems work;
  • identify the potential of control to solve hydrological problems;
  • sketch a general plan for a regional real-time control system;
  • know the main techniques of data-driven modelling from machine learning (neural networks, model trees, fuzzy systems, etc.);
  • correctly classify a modelling problem as a physically-based, data-driven, or hybrid;
  • select proper methods and tools for building data-driven models.


Syllabus

Real Time Control of Water Systems (A. Lobbrecht and S.J. van Andel)
Introduction to Real-Time Control; Modelling hydrological systems and control problems with Aquarius; Control-systems functions and techniques; Hardware and software components; Control systems in industry; Identifying control system components; One day field trip to North-West Netherlands.
Introduction to Optimisation (D.P. Solomatine)
Classical optimisation. Linear and non-linear optimisation. Derivative-based and direct methods. Dynamic programming. Global (multi-extremum) optimisation. Genetic and evolutionary approaches. Multi-objective optimization. Applications in water sector. Exercises and workshops: optimal water allocation; automatic model calibration
Data Driven Modelling and Computational Intelligence (D.P. Solomatine, B. Bhattacharya)
Modelling in the framework of Hydroinformatics. Data-driven and physically based models. Overview of machine learning and computational intelligence.
Main types of machine learning: classification, association, clustering, numeric prediction. Decision, regression and model trees. Artificial neural networks. MLP and RBF networks. Instance-based learning. Fuzzy logic and fuzzy rule-based systems.
Exercises and workshops: using data driven methods in hydrological forecasting.


Didactics

Formal lectures; classroom exercises; home assignments; exercises and workshops in computer lab; classroom workshops on case study analysis


Lecturing materials

  • Solomatine. Lecture notes on Data-driven modelling.
  • Solomatine. Lecture notes on Global optimisation and evolutionary approaches.
  • Mitchell. Machine learning. McGraw-Hill, 1997.
  • Witten and Frank. Data mining. Morgan-Kaufman, 2000.
  • Lobbrecht: Lecture notes on Real time control of water systems
  • Modelling software: AQUARIUS; Exercises
  • Modelling software: WEKA; Exercises
  • Optimisation software: LINGO; Exercises
  • Additional reading material:
  • Proceedings of the Hydroinformatics Conferences. Selected papers.
  • Practical Hydroinformatics (Abrahart, See, Solomatine, eds.). Springer, 2008.
  • Artificial neural networks in hydrology, Govindaraju, Rao (eds). Kluwer, 2000.


Lecturers