협동로봇의 건전성 관리를 위한 머신러닝 알고리즘의 비교 분석

다국어 초록 (Multilingual Abstract)

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.

목차 (Table of Contents)

• Abstract
• 1. 서 론
• 2. 이론적 배경
• 3. 머신러닝 알고리즘의 고찰
• 3.1 Neural Network
• 3.2 Decision Tree
• 3.3 Random Forest
• 3.4 Gradient Boosting
• 3.5 적용된 Algorithm parameters
• 4. 통계분석을 통한 데이터 특성 분석
• 4.1 Data collection
• 4.2 Histogram 분석
• 4.3 t-test와 f-test 분석
• 5. 머신러닝 알고리즘의 성능비교 분석
• 5.1 가반하중 예측 모델링
• 5.2 가반하중 분류 모델링
• 5.3 영향 변수 중요도
• 6. 결론 및 향후연구
• 7. References

참고문헌 (Reference)

1 천승만, "제조로봇 고장예지진단을 위한 오픈소스기반 스마트 제조 빅데이터 플랫폼 구현" 대한임베디드공학회 14 (14): 187-195, 2019

2 박준영, "실시간 범죄 예측을 위한 랜덤포레스트 알고리즘 기반의 범죄 유형 분류모델 및 모니터링 인터페이스 디자인 요소 제안" 한국정보과학회 22 (22): 455-460, 2016

3 한상태, "노인 장기요양보험의 등급판정을 위한 의사결정나무 연구" 한국통계학회 18 (18): 137-146, 2011

4 배성완, "기계 학습을 이용한 공동주택 가격 추정: 서울 강남구를 사례로" 한국부동산분석학회 24 (24): 69-85, 2018

5 이영현, "Seq2Seq 모델 기반의 로봇팔 고장예지 기술" 한국정보전자통신기술학회 12 (12): 242-250, 2019

6 L. Breiman, "Random forests" 45 (45): 5-32, 2001

7 J. H. Jang, "Propose the method for monitoring of LCD conveyance robot condition using vibration signal" 584-585, 2011

8 J. Lee, "Prognostics and health management design for rotary machinery systems-Reviews, methodology and applications" 42 (42): 314-334, 2014

9 P. Cao, "Preprocessingfree gear fault diagnosis using small datasets with deep convolutional neural network-based transfer learning" 2018 (2018): 26241-26253, 2018

10 S. P. Curram, "Neural networks, decision tree induction and discriminant analysis : An empirical comparison" 45 (45): 440-450, 1994

11 A. C. Bittencourt, "Modeling and identification of wear in a robot joint under temperature uncertainties" 44 (44): 10293-10299, 2011

12 M. Zhao, "Instantaneous speed jitter detection via encoder signal and its application for the diagnosis of planetary gearbox" 98 : 16-31, 2018

13 R. N. A. Algburi, "Health assessment and fault detection system for an industrial robot using the rotary encoder signal" 12 (12): 2816-, 2019

14 D. W. Ruck, "Feature selection using a multilayer perceptron" 2 (2): 40-48, 1990

15 Y. Liu, "Fault diagnosis of power transformer based on tree ensemble model" 715 (715): 2020

16 Z. Guo, "Fault diagnosis of motor based on VMD-sample entropy-random forest" 1345 (1345): 2019

17 A. A. Jaber, "Fault diagnosis of industrial robot gears based on discrete wavelet transform and artificial neural network" 58 (58): 179-186, 2016

18 K. Bhakta, "Fault diagnosis of induction motor bearing using cepstrum-based preprocessing and ensemble learning algorithm" 2019

19 C. Deb, "Fault diagnosis of a single point cutting tool using statistical features by random forest classifier" 9 (9): 1-8, 2016

20 C. Krauss, "Deep neural networks, gradient-boosted trees, random forests : Statistical arbitrage on the S&P 500" 259 (259): 689-702, 2017

21 T. Borgi, "Data analytics for predictive maintenance of industrial robots" 2017

22 H. Yoon, "DBSCAN parameter optimization of predictive maintenance system for wafer transfer robot using design of experiment" Myongji University 2019

23 E. Raczko, "Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images" 50 (50): 144-154, 2017

24 I. Nitze, "Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification" 035-, 2012

25 S. Nawar, "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" 17 (17): 2428-, 2017

26 G. Xu, "Bearing fault diagnosis method based on deep convolutional neural network and random forest ensemble learning" 19 (19): 1088-, 2019