Multiple Input CNN Architecture for Tool State Recognition in the Milling Process Based on Time Series Signals

The study presents a tailored application of a multiple-input convolutional neural network (CNN) for tool state recognition in the milling process. Our approach uniquely applies an 11-input CNN to classify tool wear in chipboard milling, utilizing scalogram images derived from time-series signals. T...

Full description

Saved in:
Bibliographic Details
Main Authors: Michał Bukowski, Izabella Antoniuk, Karol Szymanowski, Artur Krupa, Jarosław Kurek
Format: Article
Language:English
Published: Wrocław University of Science and Technology 2024-01-01
Series:Operations Research and Decisions
Online Access:https://ord.pwr.edu.pl/assets/papers_archive/ord2024vol34no3_3.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428294260228096
author Michał Bukowski
Izabella Antoniuk
Karol Szymanowski
Artur Krupa
Jarosław Kurek
author_facet Michał Bukowski
Izabella Antoniuk
Karol Szymanowski
Artur Krupa
Jarosław Kurek
author_sort Michał Bukowski
collection DOAJ
description The study presents a tailored application of a multiple-input convolutional neural network (CNN) for tool state recognition in the milling process. Our approach uniquely applies an 11-input CNN to classify tool wear in chipboard milling, utilizing scalogram images derived from time-series signals. The primary objective was to categorize tool wear into three classes: green, yellow, and red, signifying the progression of wear. The study involved 75 samples (25 samples per class), each comprising 11 signals transformed into scalograms via continuous wavelet transform. The dataset of 825 scalogram images enabled the development of a CNN-based diagnostic model, achieving a notable accuracy of 96.00%, which is an improvement over a previous methods (93.33%). (original abstract)
format Article
id doaj-art-7117448766c844e09cfe30ec0fae946e
institution Kabale University
issn 2081-8858
2391-6060
language English
publishDate 2024-01-01
publisher Wrocław University of Science and Technology
record_format Article
series Operations Research and Decisions
spelling doaj-art-7117448766c844e09cfe30ec0fae946e2025-08-20T03:28:44ZengWrocław University of Science and TechnologyOperations Research and Decisions2081-88582391-60602024-01-01vol. 34no. 34160171700322Multiple Input CNN Architecture for Tool State Recognition in the Milling Process Based on Time Series SignalsMichał Bukowski0Izabella Antoniuk1Karol Szymanowski2Artur Krupa3Jarosław Kurek4Warsaw University of Life Sciences, Warsaw, PolandWarsaw University of Life Sciences, Warsaw, PolandWarsaw University of Life Sciences, Warsaw, PolandWarsaw University of Life Sciences, Warsaw, PolandWarsaw University of Life Sciences, Warsaw, PolandThe study presents a tailored application of a multiple-input convolutional neural network (CNN) for tool state recognition in the milling process. Our approach uniquely applies an 11-input CNN to classify tool wear in chipboard milling, utilizing scalogram images derived from time-series signals. The primary objective was to categorize tool wear into three classes: green, yellow, and red, signifying the progression of wear. The study involved 75 samples (25 samples per class), each comprising 11 signals transformed into scalograms via continuous wavelet transform. The dataset of 825 scalogram images enabled the development of a CNN-based diagnostic model, achieving a notable accuracy of 96.00%, which is an improvement over a previous methods (93.33%). (original abstract)https://ord.pwr.edu.pl/assets/papers_archive/ord2024vol34no3_3.pdf
spellingShingle Michał Bukowski
Izabella Antoniuk
Karol Szymanowski
Artur Krupa
Jarosław Kurek
Multiple Input CNN Architecture for Tool State Recognition in the Milling Process Based on Time Series Signals
Operations Research and Decisions
title Multiple Input CNN Architecture for Tool State Recognition in the Milling Process Based on Time Series Signals
title_full Multiple Input CNN Architecture for Tool State Recognition in the Milling Process Based on Time Series Signals
title_fullStr Multiple Input CNN Architecture for Tool State Recognition in the Milling Process Based on Time Series Signals
title_full_unstemmed Multiple Input CNN Architecture for Tool State Recognition in the Milling Process Based on Time Series Signals
title_short Multiple Input CNN Architecture for Tool State Recognition in the Milling Process Based on Time Series Signals
title_sort multiple input cnn architecture for tool state recognition in the milling process based on time series signals
url https://ord.pwr.edu.pl/assets/papers_archive/ord2024vol34no3_3.pdf
work_keys_str_mv AT michałbukowski multipleinputcnnarchitecturefortoolstaterecognitioninthemillingprocessbasedontimeseriessignals
AT izabellaantoniuk multipleinputcnnarchitecturefortoolstaterecognitioninthemillingprocessbasedontimeseriessignals
AT karolszymanowski multipleinputcnnarchitecturefortoolstaterecognitioninthemillingprocessbasedontimeseriessignals
AT arturkrupa multipleinputcnnarchitecturefortoolstaterecognitioninthemillingprocessbasedontimeseriessignals
AT jarosławkurek multipleinputcnnarchitecturefortoolstaterecognitioninthemillingprocessbasedontimeseriessignals