• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.12
• /
• pp.48-55
• /
• 1997

A useful method to detect tool breakage suing neural network of cutting force signal is porposed and implemented in a basic cutting process. Cutting signal is gathered by tool dynamometer and normalized as a preprocessing. The cutting force signal level is continually monitored and compared with the predefined level. The neural network has been trained normalized sample data of the normal operation and cata-strophic tool failure using backpropagation learning process. The develop[ed system is verified to be very effective in real-time usage with minor modification in conventional cutting processes.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.4
• /
• pp.707-722
• /
• 1992

Fracture of a cutting tool is one of the most serious problems in machining systems. Therefore, several methods have been proposed so far to detect cutting tool fracture. However, most of them have some problems from the viewpoint of practical applications. In this study, the feasibility of using acoustic emission and cutting force signals for the detection of massive tool breakages as well as small fracture of cutting tools were investigated. Turning experiments were performed using conventional carbide inset tools under realistic cutting conditions and the SM45C steel and heat treated SM45C steel were used as a workpiece. And the sensitivities of the AE and cutting force signals to the fracture of cutting tools were illustrated. Finally, a detection algortithm for the fracture of cutting tools was developed through the analysis of these dual signals in the several types of tool fracture.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.2
• /
• pp.120-126
• /
• 2019

Recently, there is an increasing need for highly precise processing with the rapid development of precision machinery, electrical and electronics, and semiconductor industries. Cutting machine control relies on the operator's sense and experience in tradition, but it has been greatly enhanced by the adoption of CNC(Computerized Numeric Controller). In addition, cutting dynamics technology has been paid attention to reflect the operating state of machine in real time. This paper presents a method to detect and stabilize tool vibration by attaching an acoustic sensor to a CNC machine. The sensed acoustic data is synchronized with the tool position and the abnormal vibration frequency is separated from the collected acoustic frequency, then analyzed to detect the tool vibration. Also the reliability the tool vibration detection and stabilization is improved by applying the cutting dynamic method. The proposed method is analyzed and evaluated in terms of the surface roughness.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.2
• /
• pp.5-16
• /
• 1994

NC 공작기계가 생산현장에 도입된 이래 이를 Computer와 연결함으로써 CAD/CAM/CAE의 결합이 실현되어가고 있다. 최근에는 CAD/CAM/CAE와 더불어 생산공정에 있었서 여러 대의 NC공작기계, 로보트, 운송장치를 결합하고 공구관리나 생산관리까지도 Computer를 이용하고자 하는 소위 CIM(Computer Intergrated Manufacturing)시스템에 관한 연구가 활발히 진행되고 있으며 여기에 생산가공 시스템의 상태 변화량의 감지를 통하여 공정상태를 종합적으로 감시, 진단할 수 있는 시스템(M & D : Monitoring and Diagnosis)에 대한 필요성도 증대되고 있다. 이는 생산 공정에 있어서의 궁극적 과제인 생산 자동화 혹은 무인 자동화의 가능성을 한층 높여준다.

• 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.