Kurumun Atıf Alan Makalesi
Atıf Alan Yayın
Investigation of progressive tool wear for determining of optimized machining parameters in turning
Scopus
Toplam 177 atıf DOI
On-line monitoring of tool wear and tool breakage are very important to reduce production costs through the optimization of machining parameters. Increasing cutting forces affect workpiece quality and tool condition that is the ultimate aim of production line and progressive tool wear which can trigger the tool breakage. Taguchi method is extensively used for determining number of experiment while variance analysis (ANOVA) deals with which parameter/s is/are effective on output. This study contains experiments and optimization processes during turning of AISI 1050 material with 3 input parameters (cutting speed, feed rate, tool tip) using Taguchi method. In order to determine the condition of the cutting tool, measurement of tangential cutting force and acoustic emission (AE) were carried out during metal removing. ANOVA results showed that cutting speed is the most effective about %45 and tool tip is the second about %35 on tool wear. On the other hand, the effect of feed rate on tangential cutting force (%88) and cutting speed on AE (%80) is remarkably higher than the other two parameters. In order to obtain the minimum tool wear value, the optimum cutting parameters have been selected as v 1 = 135 m/min, f 2 = 0,214 mm/rev, T 2 = P25. By implemented sensor system tool breakage can be successfully detected and used for producing high quality materials with low costs.
Atıf Kaynağı
Atıf Yapan Yayın
Milling cutter fault diagnosis using unsupervised learning on small data: A robust and autonomous framework
Scopus
Havuzumuzda Open Access 12 atıf almış
Tool condition affects the tolerances and the energy consumption and hence needs to be monitored. Artificial intelligence (AI) based data-driven techniques for tool condition determination are proposed. Unfortunately, the data-driven techniques are data-hungry. This paper proposes a methodology for classification based on unsupervised learning using limited unlabeled training data. The work presents a multi-class classification problem for the tool condition monitoring. The principal component analysis (PCA) is employed for dimensionality reduction and the principal components (PCs) are used as input for classification using k-means clustering. New collected data is then projected on the PC space, and classified using the clusters from the training. The methodology has been applied for classification of tool faults in 6 classes in a vertical milling center. The use of limited input parameters from the user makes the method ideal for monitoring a large number of machines with minimal human intervention. Furthermore, due to the small amount of data needed for the training, the method has the potential to be transferable.
Atıf Yapan Makale Bilgileri
Kurumlar (3)
COEP Technological University, Pune
Pune, India
Polskiej Akademii Nauk, Instytut Maszyn Przepływowych im. Roberta Szewalskiego
Gdansk, Poland
Selçuk Üniversitesi
Selçuklu, Turkey