Anomaly detection for each industrial machine is recognized as one of the essential techniques for machine condition monitoring and preventive maintenance. Anomaly detection of industrial machinery relies on various diagonal data from equipped sensors, such as temperature, pressure, electric current, vibration, and sound, to name a few. Among these data, sound data are easy to collect in the factory due to the relatively low installation cost of microphones to existing facilities. We develop a real time anomalous sound detection (ASD) system with the use of Autoencoder (AE) models in the industrial environments. The proposed processing pipeline makes use of the audio features extracted from the streaming audio signal captured by a single-channel microphone. The pipeline trains AE model by the collected normal sound. In real factory applications, the reconstruction error generated by the trained AE model with new input sound streaming is calculated to measure the degree of abnormality of the sound event. The sound is identified as anomalous if the reconstruction error exceeds the preset threshold. In our experiment on the CNC milling machining, the proposed system shows 0.9877 area under curve (AUC) score.

In the process of cutting large aircraft parts, the tool may be abnormally worn or damaged due to various factors such as mechanical vibration, disturbances such as chips, and physical properties of the workpiece, which may result in deterioration of the surface quality of the workpiece. Because workpieces used for large aircrafts parts are expensive and require strict processing quality, a maintenance plan is required to minimize the deterioration of the workpiece quality that can be caused by unexpected abnormalities of the tool and take maintenance measures at an earlier stage that does not adversely affect the machining. In this paper, we propose a method to indirectly monitor the tool condition that can affect the machining quality of large aircraft parts through real-time monitoring of the current signal applied to the spindle motor during machining by comparing whether the monitored current shows an abnormal pattern during actual machining by using this as a reference pattern. First, 30 types of tools are used for machining large aircraft parts, and three tools with relatively frequent breakages among these tools were selected as monitoring targets by reflecting the opinions of processing experts in the field. Second, when creating the CNC machining program, the M code, which is a CNC auxiliary function, is inserted at the starting and ending positions of the tool to be monitored using the editing tool, so that monitoring start and end times can be notified. Third, the monitoring program was run with the M code signal notified from the CNC controller by using the DAQ (Data Acquisition) device, and the machine learning algorithms for detecting abnormality of the current signal received in real time could be used to determine whether there was an abnormality. Fourth, through the implementation of the prototype system, the feasibility of the method proposed in this paper was shown and verified through an actual example.

Aluminum alloys are the light weight materials, they are commonly used in many industrial applications such as electronic, aerospace, automotive, and medical industry. Because they are used in these such applications. Therefore, their light weight and high surface quality are required. In this paper, the surface improvement round flat aluminum alloy using lapping finishing method was explored. In order to find the optimal condition, lapping parameters such as, rotational speeds, abrasive grain sizes of pad, processing times, and lapping oils were investigated in this study. The improvement in surface roughness was found to be highest with optimal condition at 200 rpm of rotational speed, 1 ㎛ abrasive grain size of pad, 0.5ml of light oil for 720 sec. By using the optimal condition, the initial surface roughness Ra of round flat aluminum alloy can be enhanced from 2.59㎛ to 0.02 ㎛. This can be concluded that the small CNC machine with lapping finishing method can be used to enhance the surface roughness of round flat aluminum alloy effectively.

CNC cutting process has been mainly used for processing metal materials, and wood processing is also changing to machining by CNC machine. But the researches on the CNC machining of wood and its characteristics were rarely carried out. In this study, we analyzed the machined surface according to the cutting conditions such as the cutting direction, spindle speed, feed rate, cutting depth, chip removal in the CNC machining of wood. The consideration of cutting conditions and their effects on the surface finish will provide possibilities for improving the wood machining processes.

The Cellulose Nanocrystal (CNC) of dispersion condition is important factor when reinforce concrete or cement composite as CNC, because it is closely related to the strength reinforcement. Before the CNC is utilized to reinforcement of concrete or cement composite, it is essential to evaluate the dispersion properties. Therefore, the objective of the present study is to evaluate the dispersion of CNC. In this experiment, the specimen was prepared to the type of CNC suspension in accordance with weight ratio of CNC and the dispersion time of sonication. The first property, the dispersion properties of CNC, was evaluated by measuring turbidity and absorbance. The second property, the dispersion stability, was measured through the sediment time.

5-axis laser cutting has great advantages when it is applied to three dimensional machining requiring high cutting quality. For developing 5-axis CNC laser cutting systems, however, many problems such as rotating a laser head or a working table, 5-axis se

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.

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 automation 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.

Real time CCD differential photometry was performed for BT Cnc in Praesepe cluster from February to March, 1994. New 885 differential V magnitudes were obtained for thirteen nights. From the frequency analysis, we have detected two distinct pulsational frequencies of f1=9.7783c/d and f2=7.0153c/d. The first frequency is nearly equal to the previous result(Breger 1980), but the second one is much different. Our reanalysis of the previous data obtained by Guerrero el al.(1979) indicates that the previous result of f3=5.95c/d might be uncertain; it was not detected in the power spectrum. Also it turns out that our second frequency could not be fitted to the previous data and the reanalyzed frequency(f2=7.8813c/d) of the previous data was poor-fitted to our data. Therefore we suggest that the second frequency which might be newly excited in the nonradial mode, has been changed over the last eighteen years.

Among powder metallurgy products, complex shaped parts are difficult to be produced. Even i9f it shall be compacted until pet shape, the parts are easily apt to crack. thus it causes inferior productivity.It is present condition that net ahaped parts are obtained by adding after treatment. Clutch hub, pulley, representative partawifh upper 2 steps, tower 3 steps parts are corresponded to the above case. In recent years. muired parts are get to be thinner and thinner, and therefore extremely high compacting techniaues are required. Definition of most preferable com~actingp arts are I) Uniform density 2) Non crack and 3) Realization of net shape or near net shape productlon. For the above purpose, YOSHIZUKA baa developed n now oreas applying hydraulic servo control system.

전통적으로 수작업에 의존하던 목공예는 최근 일정 부분 산업화 단계를 거치게 되었다. 본 연구는 이러한 시장 환경 변화에 대처하기 위한 방안으로 기존의 전통목공예의 제작방식에 대량생산이 유리한 기계화 단계를 접목시키는데 목적이 있다. 연구범위는 이론적, 학문적 연구부분은 제외한 기술적 제작부분에 중점을 두었다. 제작상품으로는 형태적, 기능적 특성을 고려한 다과접시를 대상으로 조선시대 화형어문호족반을 선정하였다. 연구방법은 컴퓨터와 기계공정의 단계적 적용으로 작품을 재현하는 실증적 연구에 의한다. 연구내용은 시작품 제작에 적합한 전통목공예 작품을 선정하여 이를 대상으로 대량생산이 가능한 CNC 기계를 사용한 데이터 편집, 모델링, 그리고 조각에 이르는 일련의 과정에 따른 제작공정을 통해 전통목공예 작품을 제작하는 과정을 담고 있다. 즉, 컴퓨터에 의해 Type3 data 생성과 편집을 거쳐 모델링을 완성하였고 MultiCAM 모듈에서 CNC에 의한 조각 즉, Engraving Process를 거쳐 커팅가공이 최종 완성함으로서, 전통목공예 작품을 컴퓨터와 CNC기술에 의해 제작하였다. 연구결과 조선시대 전통목공예품인 화형호족반은 컴퓨터와 기계에 의해 완성되었고 옻칠에 의해 최종작품으로 마무리되었다. 본 연구는 완성된 작품의 사후평가가 진행되지 않은 한계점과 시장에서의 소비자 반응을 파악하지 못한 점이 미흡하지만, 후속연구를 통해 깊이 있게 연구함으로서 생산단계에 반영한다면 더욱 바람직한 결과를 기대할 수 있을 것이다.