# Development of an AI-based acoustic disturbance-detection method for robotic arc welding processes

https://mdr.nims.go.jp/datasets/48e2c881-fd3a-4d9e-9aa2-3ddc0a850ed2

## File

- [Development of an AI-based acoustic disturbance-detection method for robotic arc welding processes.pdf](https://mdr.nims.go.jp/filesets/7b75ead7-2508-4e6e-a685-6b24aee52a17/download) ([Detail](https://mdr.nims.go.jp/filesets/7b75ead7-2508-4e6e-a685-6b24aee52a17.md))

## Id

48e2c881-fd3a-4d9e-9aa2-3ddc0a850ed2

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2026-06-25T00:26:26.833451Z

## Updated at

2026-06-25T00:51:40.267875Z

## Published at

2026-06-25T03:26:53.996100Z

## Doi



## First published url

https://doi.org/10.1080/27660400.2026.2688746

## Date published

2026-12-31

## Recorded date published

2026-12-31

## Resource type

journal_article

## Manuscript type

vor

## Collection



## Title

- title: Development of an AI-based acoustic disturbance-detection method for robotic
    arc welding processes
  title_type: original
  lang: en

## Description

- description: 'Disturbances generated during arc welding processes can be detrimental
    to the quality of welded structures, and existing automated disturbance-detection
    methods lack the capability for real-time deployment. This paper proposes an AI-based
    disturbance-detection framework for gas metal arc welding using microphone-recorded
    acoustic signals. Representative disturbances—shielding-gas interruption, tip
    wear, and cutting-oil contamination—were experimentally reproduced and acoustically
    recorded under three welding conditions. Acoustic features were then extracted
    from the Mel-spectrograms of the recorded welding sounds and combined with welding
    parameters (current, voltage, and travel speed) to train a multilayer perceptron
    classifier capable of identifying both the occurrence and type of disturbance.
    The trained model achieved an overall accuracy of 81.5% and a macro-F1 score of
    82.9%, demonstrating reliable generalization performance. Time-series evaluation
    indicated that the model could maintain a stable classification performance from
    the early stage of welding and immediately after the onset of disturbance. Furthermore,
    a SHAP (Shapley Additive exPlanations) analysis revealed that the decision criteria
    of the model were physically interpretable: high-frequency attenuation was dominant
    in shielding-gas interruption, while low-frequency vibration components were characteristic
    of tip wear. Both the spectral intensity and its variance were identified as key
    features for accurate disturbance classification. The proposed approach provides
    a low-cost, noncontact, and real-time monitoring solution that can be easily integrated
    into robotic welding systems and adapted to various industrial environments, thereby
    contributing to the realization of autonomous and explainable in-process quality
    assurance in smart manufacturing.'
  description_type: abstract
  lang: und

## Creator

- name: Houichi Kitano
  role: author
  orcid: https://orcid.org/0000-0002-0778-574X
  organization: National Institute for Materials Science
- name: Masaki Kobayashi
  role: author
  orcid: https://orcid.org/0000-0002-5161-2600
  organization: National Institute for Materials Science
- name: Masahiko Demura
  role: author
  orcid: https://orcid.org/0000-0002-7308-3041
  organization: National Institute for Materials Science

## Contact agent



## Publisher

organization: Informa UK Limited
ror: https://ror.org/

## Managing organization



## Keyword

- subject: Acoustic sensing
  schema: not_defined
- subject: in-process monitoring
  schema: not_defined
- subject: gas metal arc welding
  schema: not_defined
- subject: disturbance detection
  schema: not_defined
- subject: machine learning
  schema: not_defined
- subject: explainable AI
  schema: not_defined
- subject: smart manufacturing
  schema: not_defined

## Rights

- identifier: https://creativecommons.org/licenses/by/4.0/
  date_licensed: 2026-06-23

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: Science and Technology of Advanced Materials-Methods
  issn: '27660400'
  volume: '6'
  issue: '1'
  article_number: '2688746'

## Conference



## Related item



## Funding



## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: 7b75ead7-2508-4e6e-a685-6b24aee52a17
  filename: Development of an AI-based acoustic disturbance-detection method for robotic
    arc welding processes.pdf
  content_type: application/pdf
  size: 12906094
  md5: b41f57e644f3c53821206cd3dd33e369

## Thumbnail

fileset_id: 7b75ead7-2508-4e6e-a685-6b24aee52a17
filename: Development of an AI-based acoustic disturbance-detection method for robotic
  arc welding processes.pdf