EER4165 Advanced Topics in Machine Intelligence

EER4165  Advanced Topics in Machine Intelligence
The objective of this design study is to devise a solution for detecting defects in a mechatronic system. Two types of defects are considered, named as Fault_1 and Fault_2. For the purpose of this assignment 11 different features were generated to describe the system under investigation. 1200 simulations of these features were executed for four possible different combinations of the two faults, including simulations for the system without any faults. All the results have been logged in the TrainingData table. The corresponding TrainingData.mat file is available from the Blackboard. The TrainingData table consists of 1200 rows, representing each simulation, and 14 columns. The first 11 columns contain computed features. Subsequent two columns (12-13) provide a ground truth labels annotating presence of each of the two faults (Fault_1, Fault_2), with ‘true’ (logical 1) indicating a presence of the defect and ‘false’ (logical 0) indicting an absence of the defect. The last, 14th column (faultCode) encodes one of the four possible combinations present in the given experiment, calculated as: faultCode=Fault_1+2*Fault_2 The additional TestData.mat file is also available from the Blackboard. That file contains the TestData table consisting of 50 additional simulation results, with recorded values of the 11 features. However, although the fault ground truth labels are known for the TestData, you will not have access to that information before the submission deadline. Design Study Requirements You are asked to design a solution for the above described problem of faults recognition present in the simulated mechatronic system. In your design you should: consider a need for feature selection or feature dimensionality reduction; data outliers detection; apply suitable feature selection/reduction algorithm; select a machine learning (MI) algorithm suitable for the task; training of the selected MI algorithm; quantitatively evaluate the design solution.This design studyis to give you an insight into selected aspects of machine intelligence (MI) applied to detection and classification of faults in a mechatronic system. You are asked to solve various tasks related to design of anMI system, including features selection, dimensionality reduction, outliers detection, classification and the MI systemquantitative evaluation.This design study will test your ability to:Design methods and processes necessary for deployment of an artificial intelligence system for quantitative evaluations of a mechatronic system.Recognize software design challenges behind implementations of machine learning algorithms.Design and optimise software to meet specified requirements.•Design and provide a working solution for faults detection in a mechatronicsystem.
Read less