Fault Diagnosis for an Automatic Shell Magazine Using FDA and ELM

• Published in: Advanced Data Mining and Applications Vol. 11323; pp. 255 - 262
• Main Authors: Zhao, Qiangqiang, Tao, Lingfeng, Li, Maosheng, Hong, Peng
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2018; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Automatic shell magazine; Extreme learning machine; Fault diagnosis; Functional data analysis
• ISBN: 9783030050894; 3030050890
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-05090-0_22

A fault diagnosis method for an automatic shell magazine based on Functional Data Analysis (FDA) and Extreme Learning Machine (ELM) is presented in this paper. A virtual prototype model of the automatic shell magazine includes a mechanical model and control model is built in RecurDyn and Simulink. The failure mechanism of the automatic shell magazine is analyzed, and the corresponding fault factors are selected. Due to an insufficient number of fault samples, a large number of fault samples are generated by the virtual prototype model and the fault samples are analyzed by FDA. Then, the eigenvalues from FDA are used to train ELM to obtain a diagnostic machine. The diagnostic machine is used for the fault diagnosis of the automatic shell magazine and is proved to be very effective.