Using neural networks to identify annoying noises in vehicles

Previous papers have developed a methodology to characterise squeaks and rattles. Thus, for each noise, its origin and the means for eliminating it, are known. This paper describes the work done towards the development of a tool, based on neural networks, that determines if a squeak or rattle corresponds to any of the noises already characterised. Different types of neural networks have been evaluated. Preliminarily, it was found that for this application the best topology is a net 100-50-4. Additionally, it was found that the best training method is the gradient descent back-propagation method with a learning rate of 0.05.(A)

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/14791471
• Authors:
  • ANTELIS, J M
  • HUERTAS, J I
• Publication Date: 2006

Language

• English

Media Info

• Pagination: 177-190
• Serial:
  • International Journal of Vehicle Noise and Vibration
  • Volume: 2
  • Issue Number: 3
  • Publisher: Inderscience Enterprises Limited
  • ISSN: 1479-1471
  • EISSN: 1479-148X
  • Serial URL: http://www.inderscience.com/jhome.php?jcode=IJVNV

Subject/Index Terms

• TRT Terms: Data collection; Electromagnetic spectrum; Frequency (Electromagnetism); Methodology; Motion; Noise; Prevention; Properties of materials; Transducers; Vehicles
• Uncontrolled Terms: Inside
• ITRD Terms: 8623: Data acquisition; 6997: Frequency; 9033: Inside; 9102: Method; 9050: Moving; 2492: Noise; 9149: Prevention; 5925: Properties; 6776: Spectrum; 6140: Transducer; 1255: Vehicle
• Subject Areas: Environment; Materials; Security and Emergencies; Vehicles and Equipment; I90: Vehicles; I91: Vehicle Design and Safety;

Filing Info

• Accession Number: 01043444
• Record Type: Publication
• Source Agency: Transport Research Laboratory
• Files: ITRD
• Created Date: Mar 6 2007 9:11AM