Abstract The automotive wiring harness forms the nervous system of the modern automobile and is dependent on electrical circuits joined together by a myriad of electrical connector designs. If a defect in a single connection occurs during vehicle assembly, the vehicle systems may not communicate correctly, and the entire vehicle can be sent for rework incurring a potentially significant added cost. Detection of these defects currently relies on human validation, and can be difficult to maintain consistent inspection reliability. In this work, the “clicking” sound corresponding to the successful connection of mating electrical connectors is analyzed in the presence of noise to quantify the ability to detect and classify these types of connections within a simulated work environment. The work herein investigates a methodology to separate this sound signal from background noise using spectral subtraction, and introduces a classification method, demonstrated in a controlled application. Experiments using lab sensing systems were performed to process and analyze signals and the results showed a significant reduction in noise, effectively distinguishing the signal of interest.
[1]
Nicholas W. D. Evans,et al.
On the fundamental limitations of spectral subtraction: An assessment by automatic speech recognition
,
2005,
2005 13th European Signal Processing Conference.
[2]
A.V. Oppenheim,et al.
Enhancement and bandwidth compression of noisy speech
,
1979,
Proceedings of the IEEE.
[3]
Yi Hu,et al.
Single and Multiple Microphone Noise Reduction Strategies in Cochlear Implants
,
2012,
Trends in amplification.
[4]
S. Boll,et al.
Suppression of acoustic noise in speech using spectral subtraction
,
1979
.
[5]
M. A. A. El-Fattah,et al.
Speech Enhancement Using an Adaptive Wiener Filtering Approach
,
2008
.
[6]
Antonio Luiz Schalata Pacheco,et al.
Vision system for detection of defects in the electrical connector of electric motors: test rig and algorithms
,
2017
.
[7]
Franco Failli,et al.
An Integrated Environment Based on Augmented Reality and Sensing Device for Manual Assembly Workstations
,
2016
.