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.

Various cutting technologies are being developed for dismantling nuclear power plants. these technologies are including mechanical and thermal methods. For example, mechanical cutting methods include sawing, drilling and milling. But, due to the strength of material, mechanical cutting methods have limits of cutting depth and tool life. Therefore, this milling machine assisted plasma torch was developed to improve the limits. And this machine has the principle of softening effect caused by the high temperature. In this work, this developed device was evaluated in view of the cutting depth and tool life in cutting process. For this process, a plasma torch was attached to the front of the endmill processing path to heat the Inconel 600. As results, compare to conventional milling, when the plasma torch power is 6.4 kW, the cutting depth was increased by 4 mm at condition (feed rate is 100 mm·min−1, tool diameter is 10 mm, rotating speed is 1,000 rpm). And cutting length increase 2 times from 300 mm to 600 mm at 16 mm of tool diameter.

본 연구에서는 절삭식 정미기 도입에 따른 실효성을 분석하기 위해 개발된 절삭식 정미기의 경제성을 비용/편익 분석(B/C ratio), 손익분기점, 기존의 정미기와의 비교 및 수입대체효과의 4가지 측면에서 분석하였다. 절삭식 정미기의 가동률에 따른 비용/편익 비율은 가동률 60%, 80%에서 모두 1 초과로 추정되었다. 손익분기점은 가동률 60%에서는 절삭식 정미기 운용을 시작한 지 3.4년 정도 경과한 시점부터 순이익이 발생하였다. 또한 가동률 80%의 경우 정백미 생산을 시작한 지 66일째부터 수익이 발생하여 절삭식 정미기 운용 후 2.56년 정도부터 순이익이 발생하는 것으로 나타났다. 개발된 절삭식 정미기를 기존의 국산 및 수입 정미기 4종과 비교한 결과 국산에 비해서 가격 및 수리비용에서는 다소 높은 값을 보였으나, 에너지 소비량이 적고 설치공간이 작은 장점을 보였다. 수입된 정미기에 비해서는 에너지 소비량, 가격, 설치공간 및 수리비용에서 충분한 경쟁력을 보였다. 이에 따라 수입된 정미기 100대를 개발된 정미기로 대체할 경우 668억 수준의 높은 수입대체효과를 기대할 수 있을 것으로 나타났으며, 국내 시장에서 절삭식 정미기의 시장점유율을 높일 수 있을 것으로 시사되었다.

This study aimed to identify milling characteristics depending on the number of a cutting roller’s air vent and blowing velocity to remove rice bran by the cutting type milling machine which can minimize the conventional milling process. The level of whiteness was found to be 38±0.5 in all the conditions, showing consistent whiteness levels during milling. The rice temperatures turned out to be 15.4 and 14.6oC which were rather low-level under the conditions of the cutting roller with 3 vents and blowing velocities of 35 and 40 m/s respectively. Cracked rice ratio was 2.13% under the conditions of the cutting roller with 3 vents and a blowing velocity of 35 m/s. Broken rice ratio showed the range of 0.762-0.869%, reflecting a low level. Turbidity after milling was decreased, as blowing velocity became faster. Energy consumption for milled rice production was decreased, as blowing velocity became faster. The optimum milling condition for cutting type milling machine depending on air vent number of cutting roller and blowing velocity was found to be 3 vents and 35 m/s.

This study aimed to identify milling characteristics depending on the number of a cutting roller’s air vent and blowing velocity to remove rice bran by the cutting type milling machine which can minimize the conventional milling process. The level of whiteness was found to be 38±0.5 in all the conditions, showing consistent whiteness levels during milling. The rice temperatures turned out to be 15.4 and 14.6oC which were rather low-level under the conditions of the cutting roller with 3 vents and blowing velocities of 35 and 40 m/s respectively. Cracked rice ratio was 2.13% under the conditions of the cutting roller with 3 vents and a blowing velocity of 35 m/s. Broken rice ratio showed the range of 0.762-0.869%, reflecting a low level. Turbidity after milling was decreased, as blowing velocity became faster. Energy consumption for milled rice production was decreased, as blowing velocity became faster. The optimum milling condition for cutting type milling machine depending on air vent number of cutting roller and blowing velocity was found to be 3 vents and 35 m/s.