Reference no: EM133296094 , Length: 2500 Words
Modelling and Optimisation
Aim:
To establish an appreciation for the role of modelling and optimisation within modern science and engineering practice and to provide evidence that modelling and optimisation is an integrated tool kit (that includes analytical, simulation, and statistical methods met at earlier FHEQs) for addressing, evaluating, and improving multiple solutions to complex science and engineering-based problems.
Learning Outcome 1: Demonstrate a critical understanding of design of experiments and response surface methodology in theory and practice as applied to engineering problem-solving, problem prevention and product development.
a. Plan and run statistically based experiments appropriate to a wide variety of engineering scenarios. b. Fit and validate empirical transfer functions to the resulting data. c. Use transfer functions to understand the impact of variation on system performance.
Demonstrate advanced statistical experimentation skills, use of specialised packages for DoE analysis, communicate effectively in a project team and contribute to teamwork facilitation.
Collate and manage data, and apply scientific method, IT skills and complex systematic problem-solving strategies.
Modelling Coursework Portfolio
The coursework component for the Modelling & Optimisation module (50% of the overall assessment) is based on an independent student led experiment and analysis - as described below.
Task brief
You are expected to submit a technical report no longer than 2,500 words length (circa 10-12 pages of text including tables and graphical output from the software used for modelling), based on an engineering modelling / metamodelling Case Study chosen by the students*. The report is expected to cover the analysis of the technical problem identifying:
• engineering factors (as modelling parameters likely to have significant influence on the response of interest);
• critical discussion / planning of the modelling strategy - justifying the choice of the experimentation strategy (screening experiments followed by detailed optimal experiments, or space filling design of experiments);
• evaluation of the DoE plan;
• collection of data from the chosen Case Study;
• fit a response surface model - arguing the model choice, and evaluate the model quality using statistical indicators - with interpretation;
• use the model to derive an optimal solution against a set of criteria.
*A typical experiment would be based on a computer simulation, similar to the catapult simulation experiment used in class.
Students can use any parametric CAE models that they have previously developed (e.g. part of their final year project), or any simulation models available in Matlab or Simulink - with the aim of developing metamodels by applying the methodology covered in the course.