센서 데이터의 시계열 특성을 고려한 딥러닝 모델 기반의 공압 실린더 고장 감지 시스템 구현
Real-time Fault Detection System of a Pneumatic Cylinder Via Deep-learning Model Considering Time-variant Characteristic of Sensor Data
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In recent automated manufacturing systems, compressed air-based pneumatic cylinders have been widely used for basic perpetra- tion including picking up and moving a target object. They are relatively categorized as small machines, but many linear or rotary cylinders play an important role in discrete manufacturing systems. Therefore, sudden operation stop or interruption due to a fault occurrence in pneumatic cylinders leads to a decrease in repair costs and production and even threatens the safety of workers. In this regard, this study proposed a fault detection technique by developing a time-variant deep learning model from multivariate sensor data analysis for estimating a current health state as four levels. In addition, it aims to establish a real-time fault detection system that allows workers to immediately identify and manage the cylinder’s status in either an actual shop floor or a remote management situation. To validate and verify the performance of the proposed system, we collected multi- variate sensor signals from a rotary cylinder and it was successful in detecting the health state of the pneumatic cylinder with four severity levels. Furthermore, the optimal sensor location and signal type were analyzed through statistical inferences.
Abstract
In recent automated manufacturing systems, compressed air-based pneumatic cylinders have been widely used for basic perpetra- tion including picking up and moving a target object. They are relatively categorized as small machines, but many linear or rotary cylinders play an important role in discrete manufacturing systems. Therefore, sudden operation stop or interruption due to a fault occurrence in pneumatic cylinders leads to a decrease in repair costs and production and even threatens the safety of workers. In this regard, this study proposed a fault detection technique by developing a time-variant deep learning model from multivariate sensor data analysis for estimating a current health state as four levels. In addition, it aims to establish a real-time fault detection system that allows workers to immediately identify and manage the cylinder’s status in either an actual shop floor or a remote management situation. To validate and verify the performance of the proposed system, we collected multi- variate sensor signals from a rotary cylinder and it was successful in detecting the health state of the pneumatic cylinder with four severity levels. Furthermore, the optimal sensor location and signal type were analyzed through statistical inferences.
참고문헌 (26)
- Ali, P. J. M., "Data normalization and standardization : A technical report", Mach Learn Tech Rep, 1(1), pp.1~6 (2014)
- Baek, S., "Fault pattern extraction via adjustable time segmentation considering inflection points of sensor signals for aircraft engine monitoring", J. Soc. Korea Ind. Syst. Eng, 44(3), pp.86~97 (2020)
- Gupta, A. K., "Industrial automation and robotics" (2011), Laxmi Publications
- Hadi, H. H., "Pneumatic control system of automatic production line using SCADA implement PLC", 4th Scientific International Conference Najaf (SICN), pp.37~42 (2019)
- Jeong, J. H., "Analysis of the control performance of 6 DoF simulator with pneumatic cylinder", Proceeding of the Korean Society of Power System Engineering, pp.278~281 (2006)
- Jimenez, M., "Experimental study of double-acting pneumatic cylinder", Experimental Techniques, 44, pp.355~367 (2020)
- Kalsoom, T., "Advances in sensor technologies in the era of smart factory and industry 4.0", Sensors, 20, pp.6783~ (2020)
- Kang, B. S., "Life Prediction of Cylinder Head Bolt using Accelerated Life Testing", Proceeding of 2012 Spring Conference of the Korean Society of Mechanical Engineers, pp.510~513 (2012)
- Kim, D. H., "Development of cyber-physical production system based manufacturing control system for aircraft parts plant", J. Soc. Korea Ind. Syst. Eng, 43(1), pp.143~150 (2020)
- Kim, N. G., "Hydraulic cylinder abnormal detection by facility data analysis", Proceeding of 2019 Autumn Conference of Korean Institute of Industrial Engineers, pp.3428~3432 (2019)
- Kim, S. H., "Incremental regression based on a sliding window for stream data prediction", Journal of KIISS : Databases, 34(6), pp.483~492 (2007)
- Kim, S., "Modified block diagonalization precoding with greedy approach", The Journal of Korean Information and Communication Society, 33(1), pp.79~85 (2008)
- Kim, Y., "Greedy-based neighbor generation methods of local search for the traveling salesman problem", Journal of the Korea Society of Computer and Information, 27(9), pp.69~76 (2022)
- Kwon, D. -H., "Predictive maintenance technology for smart factory", Proceeding of 2021 Spring Conference of Korea Institute of information and Communication Engineering, pp.172~174 (2021)
- Lee, H. J., "Development of raising device for greenhouse column using a pneumatic cylinder", Protected Horticulture and Plant Factory, 27(3), pp.206~212 (2018)
- Lee, H. R., "Comparative study of recommender systems based on deep learning algorithms", Journal of the Korean Data & Information Science Society, 35(1), pp.1~13 (2024)
- Lee, J., "Analyzing extreme diurnal temperature range in spring on the South Korea using a sliding window approach", Journal of the Korean Data &Information Sciences Society, 35(1), pp.75~97 (2024)
- Lee, K. J., "Using fuzzy-neural network to predict hedge fund survival", Journal of the Korean Data & Information Science Society, 26(6), pp.1189~1198 (2015)
- Lee, Y. -B., "A study on the accelerated life test of yaw gearbox for wind turbine", Journal of Drive and Control, 21(1), pp.16~21 (2024)
- Na, K., "Real-time batch size determination in the production line", J. Soc. Korea Ind. Syst. Eng, 42(1), pp.55~63 (2019)
- Ramasamy, S., "IoT visualization of smart factory for additive manufacturing System (ISFAMS) with visual inspection and material handling processes", IOP Conference Series: Materials Science and Engineering, 995, pp.012027~ (2020)
- Sherstinsky, A., "Fundamentals of recurrent neural network(RNN)and long short-term memory(LSTM)network", Physica D : Nonlinear Phenomena, 404, pp.132306~ (2020)
- Song, Y. -U., "Real-time fault detection in discrete manufacturing systems in via LSTM model based on PLC digital control signals", J. Soc. Korea Ind. Syst. Eng, 44(2), pp.115~123 (2021)
- Yoo, G. H., "Abnormal detection of the mold cylinder temperature cycle using 1D CNN", Proceeding of 2021 Spring Conference of Korean Institute of Industrial Engineers, pp.5873~5878 (2021)
- Yoon, Y. A., "A study on data preprocessing for developing remaining useful life predictions based on stochastic degradation models using air craft engine data", J. Soc. Korea Ind. Syst. Eng, 43(2), pp.48~55 (2020)
- Yu, Y., "A review of recurrent neural networks : LSTM cells and network architectures", Neural Computation, 31(7), pp.1235~1270 (2019)