Research on Tool Cutting Monitoring System Based on Cutting Force and Workpiece Surface Image Texture

Abstract

Aim at the problem of tool cutting monitoring system between tool wear estimate by gradual information and judgment of tool failure by sharp signal, this study is to construct an integration measurement. It puts forward density parameter E of outline peak of machined surface image texture to estimate tool wear condition. It researches tool failure judgment with cutting force monitoring. Hence real-time monitoring of cutting process can be implemented to represent cutting-tool wear, failure and rationality of parameter selection in cutting state.

Machine Cutting Tool Condition Monitoring Method of Aeroplane Composite Material Processing

“…Antoshchuk Svetlana in Ukraine put the hierarchical spatial relationship and hyperbolic Wavelet transform theory together to process the image, but the image processing effect is not good, which is described in [9]. Peng Wang of Harbin University of Science and Technology used the density parameter to assess the state of the cutting tool, but the method is only applicable to the serious wear stage, which is pointed out in [10]. Sichang Xiong of Zhejiang University presented Markov Random Field texture model based on Markov Random Field (MRF) theory to analyse the workpiece surface texture images, but the research was not risen to the level of monitoring method, which is pointed out in [11].…”

Low-loss image compression techniques for cutting tool images: a comparative study of compression quality measures

“…In recent years, the use of computer visionbased systems and artificial intelligence techniques as such, artificial neural network, to estimate tool's lifetime in metal cutting process has been aimed by many researches (ALAJMI et al, 2005;PATRA et al, 2007;CHAO and HWANG, 1997;ALAJMI and ALFARES, 2007;VOLKAN ATLI et al, 2006;GADELMAWLA et al, 2008;INOUE, KONISHI and IMAI, 2009;WANG et al, 2009). Usually, the lifetime is predicted by detecting visible -sometimes very small -degeneration in images of a cutting tool, which is supplied by a typical experiment in the turning process.…”

Editorial

“…In recent years, the use of computer visionbased systems and artificial intelligence techniques as such, artificial neural network, to estimate tool's lifetime in metal cutting process has been aimed by many researches (ALAJMI et al, 2005;PATRA et al, 2007;CHAO and HWANG, 1997;ALAJMI and ALFARES, 2007;VOLKAN ATLI et al, 2006;GADELMAWLA et al, 2008;INOUE, KONISHI and IMAI, 2009;WANG et al, 2009). Usually, the lifetime is predicted by detecting visible -sometimes very small -degeneration in images of a cutting tool, which is supplied by a typical experiment in the turning process.…”