[논문]협동로봇의 건전성 관리를 위한 머신러닝 알고리즘의 비교 분석

김재은; 장길상; 임국화

doi:10.12812/ksms.2021.23.4.093

협동로봇의 건전성 관리를 위한 머신러닝 알고리즘의 비교 분석
Comparative Analysis of Machine Learning Algorithms for Healthy Management of Collaborative Robots 원문보기

대한안전경영과학회지 = Journal of the Korea safety management & science, v.23 no.4, 2021년, pp.93 - 104

김재은 (울산대학교 대학원) , 장길상 (울산대학교 경영정보학과) , 임국화 (울산대학교 대학원)

Abstract ▼ AI-Helper

In this paper, we propose a method for diagnosing overload and working load of collaborative robots through performance analysis of machine learning algorithms. To this end, an experiment was conducted to perform pick & place operation while changing the payload weight of a cooperative robot with a payload capacity of 10 kg. In this experiment, motor torque, position, and speed data generated from the robot controller were collected, and as a result of t-test and f-test, different characteristics were found for each weight based on a payload of 10 kg. In addition, to predict overload and working load from the collected data, machine learning algorithms such as Neural Network, Decision Tree, Random Forest, and Gradient Boosting models were used for experiments. As a result of the experiment, the neural network with more than 99.6% of explanatory power showed the best performance in prediction and classification. The practical contribution of the proposed study is that it suggests a method to collect data required for analysis from the robot without attaching additional sensors to the collaborative robot and the usefulness of a machine learning algorithm for diagnosing robot overload and working load.

주제어

표/그림 (36)

그림 [Figure 1] Multilayer Perceptron
그림 [Figure 2] Network Node
그림 [Figure 3] Cooperative robot data collection configuration
그림 [Figure 4] Torque Histogram
표 Neural Network Parameters
표 Decision Tree, Random Forest, Gradient Boosting Parameters
그림 [Figure 5] Position Histogram
그림 [Figure 6] Velocity Histogram
그림 [Figure 7] Torque box plot by axis and load(7~13kg)
그림 [Figure 8] Torque box plot, not exceeding payload group and exceeding payload group
표 ANOVA results from torque in every load
표 t-test results from 2 groups of torque, not exceeding payload group and exceeding payload group
그림 [Figure 9] Torque box plot by axis and load(7~10kg)
그림 [Figure 10] Torque box plot by axis and load(11~13kg)
그림 [Figure 11] Position box plot by axis and load(7~13kg)
표 ANOVA results from torque in not exceeding payload
표 ANOVA results from torque in exceeding payload
표 ANOVA results from position in every load
그림 [Figure 12] Position box plot, not exceeding payload group and exceeding payload group
그림 [Figure 13] Position box plot by axis and load(7~10kg)
그림 [Figure 14] Position box plot by axis and load(11~13kg)
그림 [Figure 15] Velocity box plot by axis and load(7~13kg)
표 t-test results from 2 groups of position, not exceeding payload group and exceeding payload group
표 ANOVA results from position in not exceeding payload
표 ANOVA results from position in exceeding payload
그림 [Figure 16] Velocity box plot, not exceeding payload group and exceeding payload group
그림 [Figure 17] Velocity box plot by axis and load(7~10kg)
그림 [Figure 18] Velocity box plot by axis and load(11~13kg)
표 ANOVA results from position in every load
표 t-test results from 2 groups of velocity, not exceeding payload group and exceeding payload group
표 ANOVA results from velocity in not exceeding payload
표 ANOVA results from velocity in exceeding payload
그림 [Figure 19] Neural Network Structures
표 Predicting Algorithm Train & Validation Results
표 Classification Algorithm Train & Validation Results
표 Variable importance

참고문헌 (26)

S. M. Chun, S. Y. Suk(2019), "Development and implementation of smart manufacturing big-data platform using opensource for failure prognostics and diagnosis technology of industrial robot." IEMEK Journal of Embedded Systems and Applications, 14(4):187-195. https://doi.org/10.14372/IEMEK.2019.14.4.187

원문보기 상세보기
G. Xu et al.(2019), "Bearing fault diagnosis method based on deep convolutional neural network and random forest ensemble learning." Sensors, 19(5):1088. https://doi.org/10.3390/s19051088

상세보기
J. Lee et al.(2014), "Prognostics and health management design for rotary machinery systems-Reviews, methodology and applications." Mechanical Systems and Signal Processing, 42(1-2):314-334. https://doi.org/10.1016/j.ymssp.2013.06.004

상세보기
J. H. Jang et al.(2011), "Propose the method for monitoring of LCD conveyance robot condition using vibration signal." Proceedings of the Korean Society for Noise and Vibration Engineering Conference, Korea, 584-585.
H. Yoon(2019), "DBSCAN parameter optimization of predictive maintenance system for wafer transfer robot using design of experiment." Master's thesis, Myongji University.
A. A. Jaber, R. Bicker(2016), "Fault diagnosis of industrial robot gears based on discrete wavelet transform and artificial neural network." Insight-Non-Destructive Testing and Condition Monitoring, 58(4):179-186. https://doi.org/10.1784/insi.2016. 58.4.179
Y. H. Lee et al.(2019), "Seq2Seq model-based prognostics and health management of robot arm." The Journal of Korea Institute of Information, Electronics, and Communication Technology, 12(3):242-250. https://doi.org/10.17661/jkiiect.2019.12.3.242

원문보기 상세보기
T. Borgi et al.(2017), "Data analytics for predictive maintenance of industrial robots." 2017 International Conference on Advanced Systems and Electric Technologies(IC_ASET), Hammamet, Tunisia. https://doi.org/10.1109/ASET.2017.7983729
R. N. A. Algburi, H. Gao(2019), "Health assessment and fault detection system for an industrial robot using the rotary encoder signal." Energies, 12(14): 2816. https://doi.org/10.3390/en12142816

상세보기
M. Zhao et al.(2018), "Instantaneous speed jitter detection via encoder signal and its application for the diagnosis of planetary gearbox." Mechanical Systems and Signal Processing, 98:16-31. https://doi.org/10.1016/j.ymssp.2017.04.033

상세보기
A. C. Bittencourt et al.(2011), "Modeling and identification of wear in a robot joint under temperature uncertainties." IFAC Proceedings, 44(1):10293-10299. https://doi.org/10.3182/20110828-6-IT-1002.01078

상세보기
C. Deb et al.(2016), "Fault diagnosis of a single point cutting tool using statistical features by random forest classifier." Indian Journal of Science and Technology, 9(33):1-8. https://doi.org/10.17485/ijst/2016/v9i33/101340

상세보기
Z. Guo, M. Liu, Z. Xiong(2019), "Fault diagnosis of motor based on VMD-sample entropy-random forest." Journal of Physics: Conference Series, 1345(3). https://doi.org/10.1088/1742-6596/1345/3/032099

상세보기
K. Bhakta et al.(2019), "Fault diagnosis of induction motor bearing using cepstrum-based preprocessing and ensemble learning algorithm." 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE), Cox's Bazar, Bangladesh. https://doi.org/ 10.1109/ECACE.2019.8679223
Y. Liu et al.(2020), "Fault diagnosis of power transformer based on tree ensemble model." IOP Conference Series: Materials Science and Engineering, 715(1). https://doi.org/10.1088/1757-899X/715/1/012032

상세보기
S. P. Curram, J. Mingers(1994), "Neural networks, decision tree induction and discriminant analysis: An empirical comparison." Journal of the Operational Research Society, 45(4):440-450. https://doi.org/10.1057/jors.1994.62

상세보기
P. Cao, S. Zhang, J. Tang(2018), "Preprocessing-free gear fault diagnosis using small datasets with deep convolutional neural network-based transfer learning." IEEE Access, (6):26241-26253. https://doi.org/10.1109/ACCESS.2018.2837621

상세보기
S. Nawar, A. M. Mouazen(2017), "Comparison between random forests, artificial neural networks and gradient boosted machines methods of on-line Vis-NIR spectroscopy measurements of soil total nitrogen and total carbon." Sensors, 17(10):2428. https://doi.org/10.3390/s17102428

상세보기
C. Krauss, X. A. Do, N. Huck(2017), "Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500." European Journal of Operational Research, 259(2):689-702. https://doi.org/10.1016/j.ejor.2016.10.031

상세보기
E. Raczko, B. Zagajewski(2017), "Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images." European Journal of Remote Sensing, 50(1):144-154. https://doi.org/10.1080/22797254.2017.1299557

상세보기
I. Nitze, U. Schulthess, H. Asche(2012), "Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification." Proceedings of the 4th GEOBIA, Rio de Janeiro, Brazil, p. 035.
D. W. Ruck, S. K. Rogers, M. Kabrisky(1990), "Feature selection using a multilayer perceptron." Journal of Neural Network Computing, 2(2):40-48.
S. T. Han et al.(2011), "A study on the judgement rating for level of need for long-term care insurance using a decision tree." CSAM (Communications for Statistical Applications and Methods), 18(1):137-146.
L. Breiman(2001), "Random forests." Machine Learning, 45(1):5-32.
S. Bae, J. Yu(2018), "Estimation of the apartment housing price using the machine learning methods: The case of Gangnam-gu, Seoul." Journal of the Korea Real Estate Analysts Association, 24(1):69-85. https://doi.org/10.19172/KREAA.24.1.5

상세보기
J. Park, M. Chae, S. Jung(2016), "Classification model of types of crime based on random-forest algorithms and monitoring interface design factors for real-time crime prediction." KIISE Transactions on Computing Practices, 22(9):455-460. https://doi.org/10.5626/KTCP.2016.22.9.455

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증