ACIT4810 Advanced Methods in Modelling, Simulation, and Control Emneplan

The course covers several aspects related to modelling, simulation and control. The focus is on industrial applications, implementation, real life problems, and hands-on experience. The course gives an overview of state-of-the-art techniques, and provides students with tools to analyse and solve further industrial and research problems. Strong emphasis is given to the use of numerical simulation and scientific programming with Matlab/Simulink or similar.

We are witnessing the era of Big Data where data is generated, collected, and processed at an unprecedented scale and data-driven decisions influence many aspects of modern life.

Data mining is the process of discovering patterns in large data sets involving methods in statistics and database systems. A large number of applications such IoT sensors generate large amounts of data streams. The necessity of data stream mining and learning from the data is increasingly becoming more prevalent and urgent.

Extracting knowledge from data sets requires not only computational power but also programming abstractions as well as analytical skills. In this course, the students will be exposed to the different approaches for data mining and stream processing such as association rules learning, anomaly detection, data clustering, visualizations, and extracting statistical features on the fly from large data streams. The students will be exposed to concrete data mining and neural network architectures including deep learning models for handling large data streams such as convolutional neural networks, recurrent neural networks, autoencoders, transformers and attentions. In this course, the student will also be exposed to different data mining systems, working end-to-end pipelines including performance evaluation, detecting overfitting, underfitting, and data defects. With a focus on data mining applications, we will study some powerful numerical linear algebra methods.

No formal requirements over and above the admission requirements.

Upon successful completion of the course, the student:

Knowledge:

• is familiar with data-driven dynamic modelling methods
• is familiar with state estimation techniques
• is familiar with multivariable feedback control algorithms
• is familiar with predictive control algorithms

Skills:

• can obtain dynamic models with data-driven dynamic modelling methods for a chosen industrial application
• can implement some techniques for state estimation
• can implement some multivariable feedback control algorithms
• can implement some predictive control algorithms
• can choose an advanced control algorithm suitable for a chosen industrial application.
• can implement and test the algorithm in a simulation environment.

General competence:

• can evaluate different methods for advanced control for a chosen industrial application.
• can choose a suitable method, develop and implement it for a chosen industrial application.

Weekly lectures and exercises, one project work in groups of between 2 - 5 students. Two guest lectures on selected topics given by experts from industry and academia.

The following required coursework must be approved before the student can take the exam:

Four individual compulsory assignments and one group project. The project groups will be between 2 and 5 students. The resulting project report is about 15-25 pages.

Exam autumn 2020 due to Covit-19:

3 days written digital home exam.

The exam grade can be appealed.

In the event of a resit or rescheduled exam, an oral examination may be used instead. In case an oral exam is used, the examination result cannot be appealed.

[Exam earlier]:

Written exam, 3 hours.

The exam grade can be appealed.

In the event of a resit or rescheduled exam, an oral examination may be used instead. In case an oral exam is used, the examination result cannot be appealed.

Aids autumn 2020:

All aids allowed

[Aids earlier:]

Open book exam, computer with MATLAB and Simulink.

For the final assessment a grading scale from A to E is used, where A denotes the highest and E the lowest pass grade, and F denotes a fail.

Two internal examiners. External examiner is used periodically.

Associate Professor Tiina Komulainen