A Framework for Anomaly Classification and Segmentation in Remanufacturing using Autoencoders and Simulated Data
Research output: Journal contributions › Conference article in journal › Research › peer-review
Standard
In: Procedia CIRP, Vol. 126, 2024, p. 1005-1010.
Research output: Journal contributions › Conference article in journal › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - A Framework for Anomaly Classification and Segmentation in Remanufacturing using Autoencoders and Simulated Data
AU - Kaiser, Jan Philipp
AU - Enslin, Carl Leandro
AU - Barczak, Erik Tabuchi
AU - Stamer, Florian
AU - Heizmann, Michael
AU - Lanza, Gisela
N1 - Conference code: 17
PY - 2024
Y1 - 2024
N2 - In remanufacturing, reusable end-of-life products must be separated from those for which remanufacturing is not economical. In this process, the focus is initially on the detection and evaluation of surface defects of the used product. Due to the use phase of the product, these show a great variety with strongly differing degrees of severity. Deep-learning-based autoencoders offer the advantage of defect-independent detection of anomalies by detecting deviations from a defect-free product condition. In the present work, anomaly detection based on synthetically generated image data is investigated. In addition, a framework for classification and segmentation is developed and presented. The results show that the approach presented in the paper is effective in detecting anomalies with potential for improvement through adjustments such as perceptual loss or image processing methods. However, challenges remain in accurately detecting anomalies in the presence of missing parts, large anomalies, and image data with high variance.
AB - In remanufacturing, reusable end-of-life products must be separated from those for which remanufacturing is not economical. In this process, the focus is initially on the detection and evaluation of surface defects of the used product. Due to the use phase of the product, these show a great variety with strongly differing degrees of severity. Deep-learning-based autoencoders offer the advantage of defect-independent detection of anomalies by detecting deviations from a defect-free product condition. In the present work, anomaly detection based on synthetically generated image data is investigated. In addition, a framework for classification and segmentation is developed and presented. The results show that the approach presented in the paper is effective in detecting anomalies with potential for improvement through adjustments such as perceptual loss or image processing methods. However, challenges remain in accurately detecting anomalies in the presence of missing parts, large anomalies, and image data with high variance.
KW - Anomaly Detection
KW - Convolutional Autoencoder
KW - Remanufacturing
KW - Unsupervised Learning
KW - Engineering
UR - http://www.scopus.com/inward/record.url?scp=85208581634&partnerID=8YFLogxK
U2 - 10.1016/j.procir.2024.08.383
DO - 10.1016/j.procir.2024.08.383
M3 - Conference article in journal
AN - SCOPUS:85208581634
VL - 126
SP - 1005
EP - 1010
JO - Procedia CIRP
JF - Procedia CIRP
SN - 2212-8271
T2 - 17th CIRP Conference on Intelligent Computation in Manufacturing Engineering - CIRP ICME 2023
Y2 - 12 July 2023 through 14 July 2023
ER -