The diploma project consists of an introduction, four main chapters, conclusions, and a list of references. The project contains 72 pages of main text, 32 figures, 1 table, and 16 references.
The purpose of this work is to describe the design of an automated defect detection system using machine learning methods and computer vision algorithms capable of ensuring optimal output product quality in manufacturing processes.
To accomplish the objectives of the diploma project, the following tasks were defined:
- to describe the general principles and concepts of automation and automated control;
- to develop a concept for an automated quality control system with visual defect detection and to create a structural diagram of the automated visual defect detection system based on the proposed concept;
- to select the components of the automated system, including the central computing unit, camera, actuators, and other elements, and to develop a block electrical diagram of the system with a detailed description of the connections between the blocks;
- to develop a training algorithm for an artificial neural network for visual defect recognition, evaluate the obtained results using new input data, and create a flowchart of the automated visual defect detection system algorithm.
Research advisor: I.Lysenko
