SUNConferences, COMA '13

Font Size: 
Genetic Algorithm for Artificial Neural Network Training for the Purpose of Automated Part Recognition
Theo van Niekerk, Stefan Buys

Last modified: 2013-08-20

Abstract


Object or part recognition is of major interest in industrial environments. Current methods implement expensive camera based solutions. There is a need for a cost effective alternative to be developed. One of the proposed methods is to overcome the hardware, camera, problem by implementing a software solution.  Artificial Neural Networks (ANN) is to be used as the underlying intelligent software as they have high tolerance for noise and have the ability to generalize. As an initial concept basic ANN software has been implemented within an industrial programmable logic control (PLC) system.  This is not practical for industrial use in a production environment where there are a large quantity of different parts to be identified that change relatively regularly. The ability to easily and accurately train more parts is required. Difficulties associated with traditional mathematically guided training methods are highlighted, which leads to the development of a Genetic Algorithm (GA) based evolutionary training method that overcomes these difficulties and makes accurate part recognition possible. An ANN hybridised with GA training is introduced and a general solution encoding scheme which is used to encode the required ANN connection weights. Experimental tests were performed in order to determine the ideal GA performance and control parameters as studies have indicated that different GA control parameters can lead to large differences in training efficiency and accuracy. After performing these tests, the training accuracy was analyzed by investigation into GA performance as well as hardware based part recognition performance. This analysis identified the ideal GA control parameters when training an ANN for the purpose of part recognition and showed that the ANN generally trained well and could generalize well on data not presented to it during training.


Full Text: PDF