20th IMEKO TC10 Conference on "Measurement for Diagnostics, Optimization and Control to Support Competitiveness and Innovation"

Fault location and identification in the RIAA equalizer based on the frequency analysis

Not scheduled

20m

Lisbon

Oral presentation T5 - Artificial intelligence, machine learning and data science for Diagnostics, Optimization & Control.

Speaker

Piotr Bilski (Warsaw University of Technology)

Description

The paper presents the approach to diagnose
the RIAA equalizer, which is widely used in the high
quality audio industry during the music recording. As
the circuit is discrete, it is possible to select the partially
accessible nodes for response measurement, therefore
analysis of their usefulness for the fault location and
identification. The cumulative power of the response at
each node was used as the source of diagnostic
information. Three classifiers (i.e. decision tree,
multilayered perceptron and the gaussian Naïve Bayes
Classifier) have been used to identify the faults.
Conclusions from the experiments show that it is
possible to diagnose the audio circuit using the minimal
information.

Presentation materials

IMEKO TC10_ps_gm_pb.pdf