• 대한안전경영과학회지
• /
• 제2권3호
• /
• pp.185-195
• /
• 2000

Increased complexity of products and their manufacturing processing demans higher quality control and monitoring than ever before. Therefore, flexible automatization or flexible manufacturing systems (FMS) offer numerous advantages over alternative manufacturing methods. In this state, a in-process monitoring is one of the important flexible automatino system. And as use of NC and CNC machine tool has been increasing, cutting work has automating and it is necessary to develop the automatic production system combined a couple of machine tool. Thus, in this paper to search examination it can measure the tool wear and the tool life and can be more practical research subject.

• 융합신호처리학회논문지
• /
• 제23권2호
• /
• pp.84-90
• /
• 2022

공작기계 상태 진단은 기계의 상태를 자동으로 감지하는 프로세스이다. 실제로 가공의 효율과 제조공정에서 제품의 품질은 공구 상태에 영향을 받으며 마모 및 파손된 공구는 공정 성능에 보다 심각한 문제를 일으키고 제품의 품질 저하를 일으킬 수 있다. 따라서 적절한 시기에 공구가 교체될 수 있도록 공구 마모 진행 및 공정 중 파손 방지 시스템 개발이 필요하다. 본 논문에서는 공구의 적절한 교체 시기 등을 진단하기 위해 딥러닝 기반의 계층적 컨볼루션 신경망을 이용하여 5가지 공구 상태를 진단하는 방법을 제안한다. 기계가 공작물을 절삭할 때 발생하는 1차원 음향 신호를 주파수 기반의 전력스펙트럼밀도 2차원 영상으로 변환하여 컨볼루션 신경망의 입력으로 사용한다. 학습 모델은 계층적 3단계를 거쳐 5가지 공구 상태를 진단한다. 제안한 방법은 기존의 방법과 비교하여 높은 정확도를 보였고, 실시간 연동을 통해 다양한 공작기계를 모니터링할 수 있는 스마트팩토리 고장 진단 시스템에 활용할 수 있을 것이다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 춘계학술대회 논문집
• /
• pp.805-810
• /
• 1997

In this paper the technique to predict tool were theoretically in the sheet metal shearing process is suggested. The were in sheet metal tool affects the tolerances of final parts, metal flows and costs of processes. In order to predict the tool were the deformation of workpiece during the process is analyzed by using non-isothermal finite element program. The ductile fracture criterion and the element kill method are also used to estimate if and where a fracture will occur and to investigate the features of the sheared surface in shearing process. Results obtained form finite element simulation such as node velocities and node forces are transformed into sliding velocity and normal pressure on tool monitoring points respectively. The monitoring points are automatically generated and the were rates on these points are accumulated during a process. It is assumed that the wear depth on the tool surface are linear function of the lot sizes based upon the known experimental results. The influence of clearance between die and punch upon tool wear is were is also discussed during the process.

• 대한기계학회논문집A
• /
• 제34권1호
• /
• pp.11-18
• /
• 2010

공구상태 감시기술은 지능형 생산시스템 구축을 위하여 중요한 요소 기술이다. 다양한 생산 공정 분야에 걸쳐 연구가 진행되었지만 기어 세이빙 공정에서 공구파손을 검출하는 연구가 발표된 바가 없다. 본 연구에서는 기어 세이빙 공정 중에 세이빙 공구의 상태를 검출하기 위하여 베타확률분포를 활용하는 통계적 기법을 제안하였다. 신뢰성 있는 공구상태 감시를 위하여 선행되어야 할 특징값 추출을 위하여 공정 중에 발생하는 진동 신호를 베타확률분포로 모델링하였다. 신호의 양봉 분포를 단봉 분포로 변환한 후 모멘트법을 사용하여 베타확률분포의 파라미터들을 추정함으로써 특징값들을 추출하였다. 특징값들의 유효성을 평가 결과, 베타분포 모델의 파라미터 중 모드가 우수한 세이빙 공구상태 감시 성능을 갖고 있음을 확인하였다.

• 융합신호처리학회논문지
• /
• 제5권4호
• /
• pp.281-286
• /
• 2004

FMS, FMC, FA, IMS의 구축에 있어서 최하위 단위인 공작기계의 자동화가 중요하다. 이를 위해서는 공작기계의 공구 감시기능(tool monitoring system)이 수행되어야 한다. 본 논문은 공구 감시기능의 자동화를 위해 종전의 공구마모 검출방법과는 달리 엔드밀의 마모상태에 따라 발생하는 절삭음의 음향주파수 분석을 통해 마모정도를 검출하는 방법을 제안하였다. 즉, 머시닝센터에서 공구마모가 잘되는 합금공구강재를 사용하고 이때 발생하게 되는 절삭음(cutting sound)을 음향 분석하여 공구 마모와 관련이 있는 가진 주파수(tooth passing frequency)를 찾아내고 또한 이 주파수의 크기 값과 공구마모(flank wear) 변화를 연구하여 엔드밀의 마모 상태를 추정하였다 이를 위해 본 연구에서는 실험 장비를 구성하고 절삭속도, 엔드밀마모, 공구직경을 절삭조건으로 하여 측정된 절삭음을 FFT 처리하였다. 또한 측정된 값을 회귀분석으로 모델링한 결과 엔드밀 마모 검출오차범위가 5.8% 이내로 나타나 음향주파수 분석에 의한 엔드밀 마모검출 방법의 유효성을 확인할 수 있었다.

• 한국시뮬레이션학회논문지
• /
• 제12권3호
• /
• pp.69-81
• /
• 2003

To manage a cluster of distributed server systems, a number of management aspects should be considered in terms of configuration management, fault management, performance management, and user management. System performance monitoring and reporting take an important role for performance and fault management. In this paper, we present distributed system architecture modeling of a performance monitoring and reporting tool. Modeling architecture of four subsystems are introduced: node agent, data collection, performance management & report, and DB schema. The performance-related information collected from distributed servers are categorized into performance counters, event data for system status changes, service quality, and system configuration data. In order to analyze those performance information, we use a number of ways to evaluate data corelation. By using some results from a real site of a company and from simulation of artificial workload, we show the example of performance collection and analysis. Since our report tool detects system fault or node component failure and analyzes performances through resource usage and service quality, we are able to provide information for server load balancing, in short term view, and the cause of system faults and decision for system scale-out and scale-up, in long term view.

• 한국철도학회논문집
• /
• 제3권3호
• /
• pp.147-153
• /
• 2000

The train control and monitoring system (TCMS) is an on board computer system in railway vehicles performing the control, supervisory and diagnostic functions of the complete train system. This system replaces a lot of hard-wired relays and minimizes the necessary vehicle wiring thus increasing the reliability of the train. It is also one of more important equipment on vehicle to implement much higher safety and reliability train system. We studied a software design technique of TCMS using a CASE tool that is a kind of safety critical software engineering tool (SCADE). This tool has mainly four functions such as the graphical editor, the document maker, tile automatically code generator, and the test simulator. The several functions of TCMS are implemented in this software easily programmed using a functional block diagram and a graphic programming language. We applied to automatically generated TCMS modules on the SCADE each functional block for the Standard type EMU in Korea. We performed the combination test using TCMS simulator and the running test in Seoul subway 7 Line. We proved that this technique is more useful for the software design of TCMS in urban transit

• 한국기계가공학회지
• /
• 제3권3호
• /
• pp.24-31
• /
• 2004

A successful on-line monitoring system for conventional machining operations has the potential to reduce cost, guarantee consistency of product quality, improve productivity and provide a safer environment for the operator. In fine-shape machining, typical signs of tool problems such as vibration, noise, chip flow characteristics and visual signs are almost unnoticeable without the use of special equipment. These characteristics increase the importance of automatic monitoring in fine-shape machining, however, sensing and interpretation of signals ar more complex. In addition, the shafts of the mini-tools break before the typical extensive cutting edge of the tool gets damaged. In this study, the existence of a relationship between the characteristics of the cutting force and tool usage was investigated, and tool breakage detection algorithm by LabVIEW was developed and the following results are obtained. It was possible to use a relative error compare which mainly used in established experiment and investigated tool breakage detection algorithm in time domain which can detect AE and cutting force signals more effective and accurate.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 춘계학술대회 논문집 전기설비전문위원
• /
• pp.96-99
• /
• 2008

On-line condition monitoring is a useful tool for maintaining and extending the longevity of power transformers. An intelligent diagnostic system is desirable for operational safety and reliability. Bringing these concepts together results in a powerful support tool for engineers, reducing the volume of data to deal with, and making the data more meaningful. This paper describes how a multi-agent system for diagnosing the cause of transformer partial discharge activity was coupled with a method of UHF partial discharge monitoring, creating an on-line condition monitoring system. The challenges presented by the on-site environment are discussed, along with the implications for the complete system.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.2006-2007
• /
• 2007

On-line condition monitoring is a useful tool for maintaining and extending the longevity of power transformers. An intelligent diagnostic system is desirable for operational safety and reliability. Bringing these concepts together results in a powerful support tool for engineers, reducing the volume of data to deal with, and making the data more meaningful. This paper describes how a multi-agent system for diagnosing the cause of transformer partial discharge activity was coupled with a method of UHF partial discharge monitoring, creating an on-line condition monitoring system. The challenges presented by the on-site environment are discussed, along with the implications for the complete system.