Particle Swarm Optimization approach to defect detection in armour ceramics

详细信息    查看全文

• 作者：Manasa Kesharaju ; ^{mkesharaju@swin.edu.au} ; Romesh Nagarajah
• 关键词：Binary Particle Swarm Optimization ; Artificial neural network ; Feature selection ; Ultrasonic testing ; Defect detection ; SiC ceramics
• 刊名：Ultrasonics
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：75
• 期：Complete
• 页码：124-131
• 全文大小：1033 K
• 卷排序：75

文摘

PSO not been explored especially in classifying high frequency ultrasonic signals. Binary Particle Swarm Optimization approach is proposed to perform feature selection. Dimensionality of the dataset is reduced and classification performance has been improved. Population data is used as input to ANN that serves as an evaluator of PSO fitness function. This technique do not need prior knowledge of desired number of features to carry out experiments.