Neural network approach for automatic image analysis of cutting edge wear

Mikołajczyk, Tadeusz; Nowicki, Krzysztof; Kłodowski, Adam; Pimenov, Danil Yurievich

doi:10.1016/j.ymssp.2016.11.026

Cited by 85 publications

(38 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main implementation procedure of tool condition monitoring comprises the selection and mounting of a sensor, signal acquisition and processing, feature capture, and condition classification [ 1 , 2 ], and it can be classified into direct and indirect monitoring. Direct monitoring technologies use measuring instruments, such as three-dimensional surface profilers, optical microscopes, scanning electron microscopes, and charge-coupled device cameras, to inspect the cutting tool conditions directly [ 3 , 4 ]. Direct monitoring technologies have a higher judgment accuracy for tool condition classification than do the indirect types and are sometimes used for offline tool condition inspection.…”

Section: Introductionmentioning

confidence: 99%

Development of Insert Condition Classification System for CNC Lathes Using Power Spectral Density Distribution of Accelerometer Vibration Signals

Huang

Yeh

2020

Sensors

View full text Add to dashboard Cite

Insert conditions significantly influence the product quality and manufacturing efficiency of lathe machining. This study used the power spectral density distribution of the vibration signals of a lathe machining accelerometer to design an insert condition classification system applicable to different machining conditions. For four common lathe machining insert conditions (i.e., built-up edge, flank wear, normal, and fracture), herein, the insert condition classification system was established with two stages—insert condition modeling and machining model fusion. In the insert condition modeling stage, the magnitude features of the segmented frequencies were captured according to the power spectral density distributions of the accelerometer vibration signals. Principal component analysis and backpropagation neural networks were used to develop insert condition models for different machining conditions. In the machining model fusion stage, a backpropagation neural network was employed to establish the weight function between the machining conditions and insert condition models. Subsequently, the insert conditions were classified based on the calculated weight values of all the insert condition models. Cutting tests were performed on a computer numerical control (CNC) lathe and utilized to validate the feasibility of the designed insert condition classification system. The results of the cutting tests showed that the designed system could perform insert condition classification under different machining conditions, with a classification rate exceeding 80%. Using a triaxial accelerometer, the designed insert condition classification system could perform identification and classification online for four common insert conditions under different machining conditions, ensuring that CNC lathes could further improve manufacturing quality and efficiency in practice.

show abstract

Section: Introductionmentioning

confidence: 99%

Development of Insert Condition Classification System for CNC Lathes Using Power Spectral Density Distribution of Accelerometer Vibration Signals

Huang

Yeh

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…However, savings occurring when using dry machining need a lot of research and scientific works in order to reduce excessive wear of tools [3][4][5][6][7][8]. In 2001, the National Nanotechnology Initiative was enacted in the United States, which concentrates on the provision of nanostructural coatings and materials, which may be successfully applied on cutting tools in dry machining.…”

Section: Introductionmentioning

confidence: 99%

The Influence of the Type of Coating on the Cutting Tool Wear During Turning Of 316L Austenitic Stainless Steel

Maruda

Szczotkarz

2016

Archives of Mechanical Technology and Materials

View full text Add to dashboard Cite

The paper presents the influence of coatings applied with the use of PVD method on cutting tools on the wear of the tool and compares it with an uncoated P25 cemented carbide plate. During the experiment, two types of TiAlN coatings were used, applied in various proportions, as well as TiN coating. During the tests, the average width of the wear band on the flank face in B VBBzone and the width of KBcrater were monitored. Moreover, the scanning analysis of the tool was conducted in order to determine the intensity of adhesive wear. The lowest values of selected tool wear indicators were found out with the use of TiAlN coating applied in eight layers in the proportions 33/67% -TiN/TiAlN. The scanning analysis proved the highest adhesive wear of the uncoated P25 cemented carbide plate, as well as increased abrasive wear of the flank face and the formation of a crater in comparison with coated plates.

show abstract

“…Some researchers used another monitoring methods to achieve high quality and required surface roughness, i.e., Wu et al [31] used AE, vibration and temperature measurement. Mikołajczyk et al [32] propose an application of automatic detection of cutting edge wear on the basis of optical methods and artificial neural network in real-time monitoring systems. Li [33] presented the general state of knowledge on monitoring tool wear during turning by the AE method, summarizing achievements in this field up to 2002.…”

Section: Introductionmentioning

confidence: 99%

The Possibility of Applying Acoustic Emission and Dynamometric Methods for Monitoring the Turning Process

Dudzik

Labuda

2020

Materials

View full text Add to dashboard Cite

Ensuring optimal turning conditions has a huge impact on the quality and properties of the machined surface. The condition of the cutting tool is one of the factors to achieve this goal. In order to control its wear during the turning process, monitoring was used. In this study, the acoustic emission method and measure of cutting forces during turning were used for monitoring that process. The research was carried out on a universal lathe center (CU500MRD type) using a Kistler dynamometer with assembled removable insert CCET09T302R-MF by DIJET Industrial CO., LTD. A dynamometer allows to measure forces Fx (radial force), Fy (feed force) and Fz (cutting force). The turning process was performed on a shaft with 60 mm diameter made of 304L stainless steel. The AE research was carried at Physical Acoustics Corporation with the kit that includes: recorder USB AE Node, preamplifier, AE-sensor VS 150M and computer with dedicated software used for recording and analyzing AE data. The aim of this paper is to compare selected diagnostic methods: acoustic emission and cutting forces measurement for monitoring wear of cutting tool edge. Analysis of the research results showed that both selected methods of monitoring the turning process allowed the determination of the beginning of the tool damage process.

show abstract

Neural network approach for automatic image analysis of cutting edge wear

Cited by 85 publications

References 51 publications

Development of Insert Condition Classification System for CNC Lathes Using Power Spectral Density Distribution of Accelerometer Vibration Signals

Development of Insert Condition Classification System for CNC Lathes Using Power Spectral Density Distribution of Accelerometer Vibration Signals

The Influence of the Type of Coating on the Cutting Tool Wear During Turning Of 316L Austenitic Stainless Steel

The Possibility of Applying Acoustic Emission and Dynamometric Methods for Monitoring the Turning Process

Contact Info

Product

Resources

About