• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.7 s.94
• /
• pp.1783-1793
• /
• 1993

Pattern recognition technique using fuzzy c-means algorithm and multilayer perceptron was applied to classify tool wear states in turning. The tool wear states were categorized into the three regions 'Initial', 'Normal', 'Severe' wear. The root mean square(RMS) value of acoustic emission(AE) and current signal was used for the classification of tool wear states. The simulation results showed that a fuzzy c-means algorithm was better than the conventional pattern recognition techniques for classifying ambiguous informations. And normalized RMS signal can provide good results for classifying tool wear. In addition, a fuzzy c-means algorithm(success rate for tool wear classification : 87%) is more efficient than the multilayer perceptron(success rate for tool wear classification : 70%).

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.10 no.5
• /
• pp.9-16
• /
• 2001

Turning experiments are conducted to investigate characteristics of acoustic emission due to wear of the coated tool. The AE signals are obtained with a sensor attached to tool holder side. Tool states are identified with scanning electron microscopy and optical microscopy. It is demonstrated that the AE signals provide reliable informations about the cutting processes and tool states. Moreover, tool wear can be detected successfully using the AE-RMS.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.4
• /
• pp.142-151
• /
• 1993

An intelligent mulitiple monitoring system to monitor tool/machining states synthetically was proposed and developed. It consists of 2 fundamental subsystems : the multiple sensor detection unit and the intellignet integrated diagnosis unit. Three signals, that is, spindle motor current, Z-axis motor current, and machining sound were adopted to detect tool/machining states more reliably. Based on the multiple sensor information, the diagnosis unit judges either tool breakage or degree of tool wear state using fuzzy reasoning. Tool breakage is diagnosed by the level of spindle/z-axis motor current. Tool wear is diagnosed by both the result of fuzzy pattern recognition for motor currents and the result of pattern matching for machining sound. Fuzzy c-means algorithm was used for fuzzy pattern recognition. Experiments carried out for drill operation in the machining center have shown that the developed system monitors abnormal drill/states drilling very reliably.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.5
• /
• pp.98-107
• /
• 1995

The in-process detection of drill wear and breakage is one of the most importnat technical problems in unmaned machining system. In this paper, the monitoring system is developed to monitor abnormal drilling states such as drill breakage, drill wear and unstable cutting using motor current. Drill breakage is detected by level monitoring. Tool wear is classified by fuzzy pattern recognition. The key feature for classification of tool wear is the estimated flank wear which is calculated by the proposed flank wear model. The characteristic of the model is not sensitive to the variation of cutting conditions but is sensitive to drill wear state. Unstable cutting states due to the unsmooth chip disposal and the overload are monitored by the variance/mean ratio of spindle motor current. Variance/mean ratio also includes the information about the prediction of drill wear and drill breakage. The evaluation experiments have shown that the developed system works very well.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.6
• /
• pp.16-21
• /
• 2005

The cutting characteristics of hardened steel(AISI 52100) by PCBN tools is investigated with respect to cutting force, workpiece surface roughness and tool flank wear by the vision system. Hard Owning is carried out with various cutting conditions; spindle rotational speed, depth of cut and feed rate. Backpropagation neural networks(BPNs) are used for detection of tool wear. The input vectors of neural network comprise of spindle rotational speed, feed rates, vision flank wear, and thrust force signals. The output is the tool wear state which is either usable or failure. The detection of the abnormal states using BPNs achieves $96.8\%$ reliability even when the spindle rotational speed and feedrate are changed.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.12
• /
• pp.120-129
• /
• 1995

This study introduces a tool wear monitoring technology in face milling operation comprised of an unsupervised neural network. The monitoring system employs two types of sensor signal such as cutting force and acceleration in sensory detection state. The RMS value and band frequency energy of the sensor signals are calculated for te input patterns of neural network. ART2 neural network, which is capable of self organizing without supervised learning, is used for clustering of tool wear states. The experimental results show that tool wear can be effectively detected under various cutting conditions without prior knowledge of cutting processes.

• Journal of the Korean Society for Precision Engineering
• /
• v.7 no.2
• /
• pp.47-57
• /
• 1990

In-process recognition of the cutting states is one of the very important technologies to increase the reliability of mordern machining process. In this study, practical methods which use the dynamic component of the cutting force are proposed to recognize cutting states (i.e. chip formation, tool wear, surface roughness) in turning process. The signal processing method developed in this study is efficient to measure the maximum amplitude of the dynamic component of cutting force which is closely related to the chip breaking (cut-off frequency : 80-500 Hz) and the approximately natural frequency of cutting tool (5, 000-8, 000 Hz). It can be clarified that the monitoring of the maximum apmlitude in the dynamic component of the cutting force enables the state of chip formation which chips can be easily hancled and the inferiority state of the machined surface to be recognized. The microcomputer in-process tool wear monitor- ing system introduced in this paper can detect the determination of the time to change cutting tool.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.05a
• /
• pp.653-657
• /
• 2000

Machining performance in hard turning of hardened AISI M2 steel has been studied. Ceramic tools were used in the cutting tests without coolants and workpiece was prepared by heat treatment to increase its hardness up to Rc 60. Cutting state parameters such as cutting forces, temperature, and tool wear were measured in the experiments and effects of tool wear on cutting states were investigated.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.452-455
• /
• 2005

The cutting characteristics of hardened steel by a PCBN tool is investigated with respect to workpiece surface roughness, cutting force and tool flank wear of the vision system. Backpropagation neural networks (BPNs) were used for detection of tool wear. The neural network consisted of three layers: input, hidden and output. The input vectors comprised of spindle rotational speed, feed rates, vision flank wear, and thrust force signals. The output was the tool wear state which was either usable or failure. Hard turning experiments with various spindle rotational speed and feed rates were carried out. The learning process was performed effectively by utilizing backpropagation. The detection of the abnormal states using BPNs achieved 96.4% reliability even when the spindle rotational speed and feedrate were changed.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.84-90
• /
• 2022

Machine tool state monitoring is a process that automatically detects the states of machine. In the manufacturing process, the efficiency of machining and the quality of the product are affected by the condition of the tool. Wear and broken tools can cause more serious problems in process performance and lower product quality. Therefore, it is necessary to develop a system to prevent tool wear and damage during the process so that the tool can be replaced in a timely manner. This paper proposes a method for diagnosing five tool states using a deep learning-based hierarchical convolutional neural network to change tools at the right time. The one-dimensional acoustic signal generated when the machine cuts the workpiece is converted into a frequency-based power spectral density two-dimensional image and use as an input for a convolutional neural network. The learning model diagnoses five tool states through three hierarchical steps. The proposed method showed high accuracy compared to the conventional method. In addition, it will be able to be utilized in a smart factory fault diagnosis system that can monitor various machine tools through real-time connecting.