2025 SMSI Bannerklein

D2.2 Visualizing Neural Network Decisions for Industrial Sound Analysis

Event
SMSI 2020
-
(did not take place because of Covid-19 virus pandemic)
Band
SMSI 2020 - Measurement Science
Chapter
D2 AI-Approaches in Measurement
Author(s)
S. Grollmisch - University of Technology, Ilmenau (Germany), D. Johnson, J. Liebetrau - Fraunhofer Institute IDMT, Ilmenau (Germany)
Pages
267 - 268
DOI
10.5162/SMSI2020/D2.2
ISBN
978-3-9819376-2-6
Price
free

Abstract

Recent research has shown acoustic quality control using audio signal processing and neural networks to be a viable solution for detecting product faults in noisy factory environments. For industrial partners, it is important to be able to explain the network’s decision making, however, there is limited research on this area in the field of industrial sound analysis (ISA). In this work, we visualize learned patterns of an existing network to gain insights about the decision making process. We show that unwanted biases can be discovered, and thus avoided, using this technique when validating acoustic quality control systems.

Download