Measuring Surface Characteristics in Sustainable Machining of Titanium Alloys Using Deep Learning-Based Image Processing
Küçük Resim Yok
Tarih
2023
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Ieee-Inst Electrical Electronics Engineers Inc
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
A crucial method of maintenance in the manufacturing industry is machine vision-based fault diagnostics and condition monitoring of machine tools. The friction that occurs between the tool and the workpiece has a greater influence on the surface properties of the material. Effective problem diagnosis is necessary for machine systems to continue operations safely. Data-driven approaches have recently exhibited great promise for intelligent fault diagnosis. Unfortunately, the data collected under real-world conditions may be imbalanced, making diagnosis difficult. In dry, minimum quantity lubrication (MQL), and cryogenic circumstances, the method of failure detection of the proposed design is novel. The purpose of this interrogation is to evaluate the roughness profiles obtained from the machined surfaces and class separation. Markov transition field (MTF) is adopted to encode the surface profiles. In addition to this, conditional generative adversarial network (CGAN) for augmentation and bidirectional long-short term memory (BLSTM), multilayer perceptron (MLP), and 2-D-convolutional neural network (CNN) models are used for surface profile classification and correlation with process parameters. According to the study's finding, the 2-D-CNN was significantly more accurate than the models in predicting surface profiles, with an average accuracy of above 99.6% in both training and testing. In the limelight, the suggested approach can demonstrate to be quite useful for categorizing and proposing appropriate machining circumstances, specifically in situations with minimal data.
Açıklama
Anahtar Kelimeler
Surface treatment, Machining, Surface morphology, Markov processes, Surface roughness, Rough surfaces, Predictive models, Conditional generative adversarial network (CGAN), cryogenic, deep learning (DL), machining, Markov transition field (MTF)
Kaynak
Ieee Sensors Journal
WoS Q Değeri
Q1
Scopus Q Değeri
Q1
Cilt
23
Sayı
12
