• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.15-19
• /
• 1994

The application of neural network for fault dection of cutting force in turning was introduced. This monitoring system consist of a RBF predicton model and a ART-1 pattern classifier. RBF prediction model predict a cutting force signal. Prediction error of predictor is used for a input vector of ART-1 pattern classifier. Prediction error could be successfully performed to fault signal monitoring of ART-1 pattern classifier.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.12
• /
• pp.78-85
• /
• 2002

The wavelet transform is a popular tool fer studying intermittent and localized phenomena in signals. In this study the wavelet transform of cutting force signals was conducted for the detection of a tool failure in turning process. We used the Daubechies wavelet analyzing function to detect a sudden change in cutting signal level. A preliminary stepped workpiece which had intentionally a hard condition was cut by the inserted cermet tool and a tool dynamometer obtained cutting force signals. From the results of the wavelet transform, the obtained signals were divided into approximation terms and detailed terms. At tool failure, the approximation signals were suddenly increased and the detailed signals were extremely oscillated just before tool failure.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.161-164
• /
• 1995

Nonlinear analysis of various phenomena has been developed with improvement of computer. The characteristics form nonlinear analysis are available in monitoring and diagnosis state of system. There are many nonlinear property in cutting process, but nonlinear signals have been considered as noise. In this study, nonlinear analysis technique is applied and it will be verified that cutting force is chaos by calculating Lyapunov exponents,fractal dimension and embedding dimension. The relation between characteristic parameter calculated form sensor signal and various cutting condition is investigated.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.4
• /
• pp.19-27
• /
• 1995

Face milling is required to study cutting process with a view of multipoint cutter. This experimental study mainly deals with the single and multi-insert cutting characteristics using coated tool. Because metal cutting of the single and multi-insert has a large relation to the improvement of productivity, the economic cutting process can be achieved by the analysis of proper metal cutting mechanism. Therefore, machining characteristics of face molling in this paper has been studied by investigating the role of different insert number which is concerned with mean cutting force, the RMS values of AE(acoustic emission) signal, tool life and surface roughness in milling SS 41 and SUS 304. The cutting force and AE signal are monitored to make an analysis of cutting process. The surface roughness of the specimens machined by inserts of different numbers is measured at different speeds, feeds and depth of cut. The width of flank wear is also observed.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.4
• /
• pp.43-53
• /
• 2016

In this paper, monitoring method of tool fracture using motor current was proposed for turning process. In order to take more reliable current signal, cutting force signal was compared as reference signal because cutting force signal is reliable, and analysis of signal correlation between cutting force and motor current was performed. The static components of the cutting force and motor current signals were correlated very well for different cutting conditions, and it was proven to use the motor current as an proper sensor for monitoring of tool fracture. To understand the characteristics of motor current, various kinds of cutting experiment were performed including tool fracture experiments. As a result, a new method to detect tool fracture using motor current in turing was proposed, and a large number of fracture experiments were carried out to evaluate the reliability of the proposed method. Finally, it can be possible to detect the tool fracture reliably.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.11a
• /
• pp.200-205
• /
• 1996

Recently, in order to achieve high flexibility of manufacture, monitoring and control strategies cf a new type have been developed. Since the generation of built-up edge on the cutting tool damages the surface finish of the workpiece, the monitoring system of built-up edge is an important process monitoring. In this study, the analyzing methods of cutting force signal to detect the built-up edge during cutting process are described. The cutting force signals are analyzed using the mean, standard deviation and mean to standard deviation of this cutting signals. We can obtain the guide to detect the built-up edge during turning process.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.7
• /
• pp.67-72
• /
• 1997

Recently, in order to achieve high flexibility of manufacture, monitoring and control strategies of a new type have been developed. Since the generation of built-up edge on the cutting tool damages the surface finish of the workpiece, the monitoring system of built-up edge is an important process monitoring. In this study, the analyzing methods of cutting force signal to detect the built-up edge during cutting process are described. The cutting force signals are analyzed using the mean, standard deviation and mean to standard deviation of this cutting signals. We can obtain the guide to detect the built-up edge during turning process.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.3 no.4
• /
• pp.20-29
• /
• 2004

A Tool wear monitoring system is indispensable for better machining productivity with guarantee of machining safety by informing the tool changing time in automated and unmanned CNC machining. Different from monitoring using other signals, the monitoring of spindle current has been used without requiring additional sensors on machine tools. For the reliable tool wear monitoring, current signal only of tool wear should be extracted from other parameters to avoid exhaustive analyses on signals in which all parameters are fused. In this paper, influences of force components of parameters on measured spindle current are investigated and a hybrid approach to cutting force regulation is employed for tool wear signal extraction in the spindle current. Finally, wear levels are verified with experimental results by means of real-time feedrate aspects changed to regulate the force component of tool wear.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.8 s.179
• /
• pp.2123-2130
• /
• 2000

Radial immersion ratio is an important factor to determine the threshold in face milling and should be estimated in process for automatic force regulation. In this paper, presented is a method of on-line estimation of the radial immersion ratio using cutting force. When a tooth finishes sweeping, sudden drop of cutting forces occurs. This force drop is equal to the cutting force that acts on a single tooth at the swept angle of cut and can be obtained from cutting force signal in feed and cross-feed direction. The ratio of cutting forces in feed and cross-feed directions acting on the single tooth at the swept angle of cut is a function of the swept angle of cut and the ratio of radial to tangential cutting force. In the research, it is found that the ratio of radial to tangential cutting force is not affected by cutting conditions and axial rake angle. Therefore, the ratio of radial to tangential cutting force determined by just one preliminary experiment can be used regardless of the cutting conditions. Using the measured cutting force and predetermined ratio, the radial immersion ratio is estimated. Various experiments show that the radial immersion ratio and instantaneous ratio of the radial to tangential direction cutting force can be estimated very well by the proposed method.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 1998.10a
• /
• pp.343-349
• /
• 1998

A modeling of machined geometry and cutting force was proposed for the case of round shape machining, and the effects of internally machined profile are analyzed and its realiability was verified by the experiments of roundness tester, especially in boring operation in lathe. Also, harmonic cutting force model was proposed with the parameter of specific cutting force, chip width and chip thickness, and in this study, we can see that bored workpiece profile was also mapped into cutting force signal with this model. In general, we can calculated the theoretical lobe profile with arbitrary multilobe. But in real experiments, the most frequently measured numbers are 3 and 5 lobe profile in experiments. With this results, we can predict that these results may be applied to round shape machining such as drilling, boring, ball screw and internal grinding operation with the same method.