Development of an automated diagnostic and inspection system based on artificial intelligence designed to eliminate risks in transport and industrial companies

Sága, Milan; Bartoš, Michal; Bulej, Vladimír; Stanček, Ján; Więcek, Dariusz

doi:10.1016/j.trpro.2021.07.048

Cited by 6 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The applicability of inspection systems is in the field of Industry 4.0 and the creation of cognitive control systems. Inspection processes may vary from inter-operational to final quality control of manufactured products [ 1 , 2 ]. The quality assessment or inspection objective can be diverse, from measurement and control procedures to defect monitoring.…”

Section: Introductionmentioning

confidence: 99%

From Anomaly Detection to Defect Classification

Klarák,

Andok,

Malík

et al. 2024

Sensors

View full text Add to dashboard Cite

This paper proposes a new approach to defect detection system design focused on exact damaged areas demonstrated through visual data containing gear wheel images. The main advantage of the system is the capability to detect a wide range of patterns of defects occurring in datasets. The methodology is built on three processes that combine different approaches from unsupervised and supervised methods. The first step is a search for anomalies, which is performed by defining the correct areas on the controlled object by using the autoencoder approach. As a result, the differences between the original and autoencoder-generated images are obtained. These are divided into clusters using the clustering method (DBSCAN). Based on the clusters, the regions of interest are subsequently defined and classified using the pre-trained Xception network classifier. The main result is a system capable of focusing on exact defect areas using the sequence of unsupervised learning (autoencoder)–unsupervised learning (clustering)–supervised learning (classification) methods (U2S-CNN). The outcome with tested samples was 177 detected regions and 205 occurring damaged areas. There were 108 regions detected correctly, and 69 regions were labeled incorrectly. This paper describes a proof of concept for defect detection by highlighting exact defect areas. It can be thus an alternative to using detectors such as YOLO methods, reconstructors, autoencoders, transformers, etc.

show abstract

Section: Introductionmentioning

confidence: 99%