By Topic

Sound detection in noisy environment-locating drilling sound by using an artificial ear

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Bergstrand, K. ; Dept. of Technol., Univ. of Orebro, Sweden ; Carlsson, K. ; Wide, P. ; Lindgren, B.

In rock drilling, as in many industries today, the drive towards unmanned equipment and full automation is a big issue. A challenge in the automation process for rock drilling is the retraction of the drill steels when the drilling is completed. Today the drilling can be performed automatically to some extend, but a human ear is required for the final part: when the splices between the drill steels are opened up enough to allow retraction. This paper discusses a Fast Fourier Transform (FFT) method to search through audio data in order to detect and locate specific sounds appearing when retraction of the drill steels is possible, and to investigate if achieving full automation of the drilling process is possible. The use of Wavelets has also been evaluated. As far as the authors know, there is no system today for automatic retraction of the drill steels. By recording and analysing sounds from rock drill rigs, a comparison between a system implemented with an electronic ear and a human ear has been evaluated. The FFT has been applied as a pre-processing method and examines features of power spectrum for the detection of the sound, when the splices are opened up. This sound contains higher power spectrum than sounds from the rest of the drilling procedure. Using these features, a classification program has been designed. The experimental results shows that there is a good possibility to make a commercialized product that automatically detect when the drill steels are ready to be retracted.

Published in:

Robot Sensing, 2004. ROSE 2004. International Workshop on

Date of Conference:

24-25 May 2004