Automatic identification and classification of mechanical defects in electric fans

M. Egger, C. Cristalli, R. M. Rodriguez

Research output: Contribution to conferencePaperpeer-review

1 Citation (Scopus)

Abstract

A potential new method aimed at on-line quality control has been developed to accurately identify the presence and the type of manufacturing defects existing in electric fans. The diagnostic method is based on the measurement of the vibration signal acquired by the use of a quartz accelerometer in combination with advanced data analysis. A multidimensional feature vector is extracted from the time and frequency domains of the acceleration signal. In this way, a complete system for data acquisition combined with advanced techniques of Pattern Recognition is able to replace the subjectivity of human testing by an objective and accurate assessment. In this paper a set of representative defective and non defective products are analyzed and the results are presented.

Original languageEnglish
Pages1331-1338
Number of pages8
Publication statusPublished - 2003
EventProceedings of the Tenth International Congress on Sound and Vibration - Stockholm, Sweden
Duration: 7 Jul 200310 Jul 2003

Conference

ConferenceProceedings of the Tenth International Congress on Sound and Vibration
CountrySweden
CityStockholm
Period07.07.200310.07.2003

Fingerprint Dive into the research topics of 'Automatic identification and classification of mechanical defects in electric fans'. Together they form a unique fingerprint.

Cite this