Sequencing and control algorithm of pattern recognition for industrial processes

Marizan, Sulaiman and Hairol Nizam, Mohd Shah and Lim, Wee Teck (2010) Sequencing and control algorithm of pattern recognition for industrial processes. Project Report. UTeM, Melaka, Malaysia. (Submitted)

PDF (Full Text) Sequencing_And_Control_Algorithm_Of_Pattern_Recognition_For_Industrial_Processes.pdf - Submitted Version Restricted to Registered users only Download (8MB)

Abstract

A Flexible Manufacturing System (FMS) is an adaptive and dynamic system that caters a wide range of different jobs where each involves a set of operations that are required to be done at a predetermined workstation. Therefore this research is regarding the development of a vision system application to monitor and control the operations of the system in order to manage the decision making concerning jobs and work pieces recognition that are to be made during system operation in real time. This project stresses on the vision system which mainly focus on the shape matching properties of the product. The vision algorithm consists of two phases, the training phase and the recognition phase. The main focus of this research is on the development of an adaptive training phase of the vision system, which are capable of automatic feature detection and manual feature selection decision. The feature selection decision in the training phase comprises of a selection of training traits that can be included depending on the types of application and the main characteristics that are to be identified during the recognition phase. Another aspect of this research is to extend the flexibility and adaptability of the system to accommodate different types of FMS configurations. The control scheme must be able to be incorporated into a wide range of different configurations. This is done by exploiting a simple stand-alone control scheme instead of a centralized control scheme. The system is then tested on a number of different types of jobs and the images with various characteristics and properties were determined for the reliability, accuracy and the flexibility of the system with respect to different conditions and combination of different training traits. This system can be applied to the industrial sectors especially for processes and quality controls. Some advantages of this system are mainly on its user defined solutions, which the users can decide and manipulate how they want the system to react to the inputs that were predetermined. Besides, it also the eases of use that reduce set-up time during product change or new product introductions. Another advantage is the simple Graphical User Interface that lets normal users utilize the system without the help of a skilled user because there will be no complex programming involved.

Actions (login required)

View Item