• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.982-986
• /
• 1997

A method using cutting force signal and neural network for detection tool damage is proposed. Cutting force signal is gained by tool dynamometer and the signal is prepocessed to normalize. Cutting force signal is changed by tool state. When tool damage is occurred, cutting force signal goes up in comparison with that in normal state. However,the signal goes down in case of catastrophic fracture. These features are memorized in neural network through nomalizing couse. A new nomalizing method is introduced in this paper. Fist, cutting forces are sumed up except data smaller than threshold value, which is the cutting force during non-cutting action. After then, the average value is found by dividing by the number of data. With backpropagation training process, the neural network memorizes the feature difference of cutting force signal between with and without tool damage. As a result, the cutting force can be used in monitoring the condition of cutting tool and neural network can be used to classify the cutting force signal with and without tool damage.

• Tunnel and Underground Space
• /
• v.32 no.6
• /
• pp.386-396
• /
• 2022

To analyze the influence of variables of roadheaders, the linear cutting testing data of pick cutter were collected from the former literatures. The input factors were set up as uniaxial compressive strength, cutting depth, cutting spacing, attack angle, skew angle, and output factors were determined as specific energy, average cutting force, maximum cutting force, average vertical force, and maximum vertical force. After composing a table of the design of experiment (DOE). The contribution level of each factor was calculated by analysis of variance (ANOVA). As a result, the factors having greatest influence on cutting force and specific energy were uniaxial compressive strength and cutting spacing.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.26 no.4
• /
• pp.402-409
• /
• 2017

Selection of optimal cutting conditions is important for improving productivity and implementing efficient process control in metal machining. In this study, improvement of cutting conditions in machining using end-mills is studied by using deep-layered neural networks, which comprise an input layer, output layer, and two hidden layers. System networks are designed with inputs as cutting conditions, and they output the cutting force. A pseudo-inverse network is designed that has the adjustable cutting condition as output and cutting force and other cutting conditions as input. The combination of the system network and pseudo-inverse network enables selection or improvement of cutting conditions that results in the expected cutting force.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.7 no.4
• /
• pp.104-116
• /
• 1998

This paper provides a review of the performance for SM45C using the CNC lathe. Under the constant cutting area, the tool wear for large feed rate is more than the small feed rate, and the progress goes more rapidly as the cutting speed is increased. This is caused by the friction between the workpiece and the bite. The average cutting force increases as the feedrate increases, and decreases as the cutting speed increases. This is because the effective rake/shear angle becomes smaller as the feedrate becomes larger. The higher is the cutting speed and the aspect ratio (the ratio for depth of cut to feedrate), the lower is the cutting force and the surface roughness. Also, for the optimal selection of the cutting conditions, many experimental graphical data were obtained. That is, the cutting force, the tool life, and the surface roughness were measured and investigated as the depth of cut and the feedrate changed. And the size effect was examined as the depth of the cut varied.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.20 no.3
• /
• pp.225-231
• /
• 2011

In this paper, a new end-milling force modelling technique was suggested by considering runout, and its result was compared with real measured force. The specific cutting force is the multiplication of cutting force coefficient and uncut chip thickness. This parameter was used for experimental modelling and prediction of theoretical force. These coefficients, which can be obtained by fitting measured average forces in several conditions, were used for the formulation of theoretical force. The mechanism of end-milling force with runout was developed in this research and its result was verified by comparing the fluctuating theoretical force and its measured one. The fluctuation of force was incurred by a geometric shape of workpiece and its runout in holding. The result of suggested force considering runout shows a good consistency with measured one. So this modelling method can be used effectively for a prediction of end-milling force with runout effect.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.13 no.4
• /
• pp.9-15
• /
• 2004

A reasonable analysis of cutting force in end milling may give much advantage to improvement of productivity and cutting tool life. In order to analyze cutting force, the cutting dynamics was modelled mathematically by using chip load, cutting geometry, and the relationship between cutting forces and the chip load. The specific cutting constants of the cutting dynamics model were obtained by average cutting forces, tool diameter, cutting speed, feed, axial depth, and radial depth of cut. The model is verified through comparisons of model predicted cutting forces with measured cutting forces obtained from machining experiments. The results showed good agreement and from that we could predict reasonably the cutting forces in end milling.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.12
• /
• pp.151-157
• /
• 1996

The tool condition monitoring is one of the most important aspects to improve productivity and quality of workpiece. In this study, the wear of ceramic tool (A1$_{2}$0$_{3}$-TiC Series) cutting the hardened die material(SKD11) was investigated. Flank wear was more dominant than crater wear. Therefore the modeling of cutting force related to flank wear has been performed. The cutting force model was construct- ed by an assumption that the stress distribution on the tool face is affected by tool wear. The relationship between characteristics as cutting force and tool wear can be suggested by machining parameters depending on cutting conditions. Experiments were performed under the various cutting conditions to ensure the validity of force models. The theoretical predictions on the flank wear are approximately in good agreement with experimental results.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.3 s.180
• /
• pp.39-46
• /
• 2006

In this work a dynamic cutting force model in ball end milling of inclined surface is introduced. To represent the complex cutting geometry in ball end milling of inclined surface, workpiece is modeled with Z-map method and cutting edges are divided into finite cutting edge elements. As tool rotates and vibrates, a finite cutting edge element makes two triangular sub-patches. Using the number of nodes in workpiece which are in the interior of sub-patches, instant average uncut chip thickness is derived. Instant dynamic cutting forces are computed with the chip thickness and cutting coefficients. The deformation of cutting tool induced by cutting farces is also computed. With iterative computation of these procedures, a dynamic cutting force model is generated. The model is verified with several experiments.

• Journal of Mechanical Science and Technology
• /
• v.14 no.6
• /
• pp.622-632
• /
• 2000

In a high precision vertical machining center, the estimation of cutting forces is important for many reasons such as prediction of chatter vibration, surface roughness and so on. The cutting forces are difficult to predict because they are very complex and time variant. In order to predict the cutting forces of end-milling processes for various cutting conditions, their mathematical model is important and the model is based on chip load, cutting geometry, and the relationship between cutting forces and chip loads. Specific cutting force coefficients of the model have been obtained as interpolation function types by averaging forces of cutting tests. In this paper the coefficients are obtained by neural network and the results of the conventional method and those of the proposed method are compared. The results show that the neural network method gives more correct values than the function type and that in the learning stage as the omitted number of experimental data increase the average errors increase as well.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.2
• /
• pp.85-94
• /
• 1994

The cutting mechanism of ultrasonic vibration machining is characterized as two phases, that is, an impact at the cutting edge and a reduction of cutting force due to non-contact interval between tool and workpiece. In this paper, in order to identify cutting dynamics of a system with ultrasonically vibrated cutting tool, an ARMA modeling is performed on experimental cutting force signals which have a dominant effect on cutting dynamics. The aim of this study is, through Dynamic Date System methodology, to find the inherent characteristics of an ultrasonic vibration cutting process by considering natural frequency and damping coefficient. Surface roughness and stability of cutting process under ultrasonic vibration are also considered