머신 러닝을 이용한 PIC 로봇 암 강성 향상에 대한 연구
Stiffness Enhancement of Piecewise Integrated Composite Robot Arm using Machine Learning
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
PIC(Piecewise Integrated Composite)는 적층 복합재의 기계적 특성을 향상시키기 위해 다양한 적층 순서를 모자이크 방식으로 할당하여 복합 구조를 설계하는 새로운 개념이다. 또한 머신 러닝은 인공 지능의 하위 범주로, 컴퓨터가 데이터에서 지속적으로 학습하고 데이터를 기반으로 예측하는 능력을 개발한 다음 추가 프로그래밍 없이 조정하는 과정을 의미한다. 본 연구에서는 구조적 강성을 높이기 위해 기계학습을 기반으로 넓고 얇은 LCD 디스플레이를 운반 및 이송하기 위한 테이퍼 박스형 빔형 PIC 로봇 암이 설계되었다. 필수 학습 데이터는 예비 FE해석 과정에서 유한 요소 모델 중 의도적으로 배치된 참조 요소에서 수집되었다. 또한 인장, 압축 또는 전단과 같은 지배적인 외부 하중 유형을 판단하기 위해 각 유한 요소에 대한 3축 특성 값을 얻었다. 학습 데이터를 이용하여 머신 러닝 모델을 훈련하고 평가되었으며, 정확도 레벨을 만족한 머신 러닝 모델을 이용해 요소의 로딩 유형을 예측하였다. 특정 하중 유형에 대해 우세한 것으로 알려진 세 가지 유형의 적층 각도 순서가 PIC 로봇 암에 모자이크 방식으로 할당되었습니다. 이후 굽힘형 FE 해석을 수행한 결과 PIC 로봇 암이 기존의 단일 적층 각도 순서로 제작된 복합재 로봇 암에 비해 강성이 증가된 것으로 나타났다.
Abstract
PIC (Piecewise Integrated Composite) is a new concept for designing a composite structure with mosaically assigning various types of stacking sequences in order to improve mechanical properties of laminated composites. Also, machine learning is a sub-category of artificial intelligence, that refers to the process by which computers develop the ability to continuously learn from and make predictions based on data, then make adjustments without further programming. In the present study, the tapered box beam type PIC robot arm for carrying and transferring wide and thin LCD display was designed based on the machine learning in order to increase structural stiffness. Essential training data were collected from the reference elements, which were intentionally designated elements among finite element models, during preliminary FE analysis. Additionally, triaxiality values for each finite element were obtained for judging the dominant external loading type, such as tensile, compressive or shear. Training and evaluating machine learning model were conducted using the training data and loading types of elements were predicted in case the level accuracy was fulfilled. Three types of stacking sequences, which were to be known as robust toward specific loading types, were mosaically assigned to the PIC robot arm. Henceforth, the bending type FE analysis was carried out and its result claimed that the PIC robot arm showed increased stiffness compared to conventional uni-stacking sequence type composite robot arm.
참고문헌 (33)
- Liu, Y., "A Review on Tensegrity Structures-based Robots", Mechanism and Machine Theory, 168, pp.104571~ (2022)
- Mukherjee, D., "A Survey of Robot Learning Strategies for Human-Robot Collaboration in Industrial Settings", Robotics and Computer-Integrated Manufacturing, 73, pp.102231~ (2022)
- Oh, J. H., "Composite Robot end Effector for Manipulating Large LCD Glass Panels", Composite Structures, 47(1-4), pp.497~506 (1999)
- Lee, C. S., "Composite Wrist Blocks for Double Arm Type Robots for Handling Large LCD Glass Panels", Composite Structures, 57(1-4), pp.345~355 (2002)
- Lee, C. S., "Manufacturing of Composite Sandwich Robot Structures Using the Co-cure Bonding Method", Composite Structures, 65(3-4), pp.307~318 (2004)
- Oh, J. H., "Optimum Bolted Joints for Hybrid Composite Materials", Composite Structures, 38(1-4), pp.329~341 (1997)
- Kuo, J. L., "Multi-objective Optimal Design of Motion Precision for Fork Robot Arm in LCD Panel Manufacturing Process System", Microelectronics Reliability, 99, pp.19~30 (2019)
- Vo, T. P., "Flexural-torsional Behavior of Thinwalled Closed-section Composite Box Beams", Engineering Structures, 29(8), pp.1774~1782 (2007)
- Cook R. D., "Advanced Mechanics of Materials" (1985), Pearson Prentice Hall Pub
- Ghazavi, A., "A Comparison of the Control of a Flexible Robot Arm Constructed from Graphite", epoxy Versus Aluminum, 1995, pp.54(4), 621~632
- Bicos, A. S., "Design of Composite Boxbeam", Journal of Composite Materials, 20, pp.86~109 (1986)
- Wu, Y., "A Finite Beam Element for Analyzing Shear Lag and Shear Deformation Effects in Composite-laminated Box Girders", Computers & Structures, 82(9-10), pp.763~771 (2004)
- Wu, Y., "A Solution for Laminated Box Beams under Bending Loads Using the Principle of Complementary Energy", Composite Structures, 79(3), pp.376~380 (2007)
- Loughlan, J., "The Analysis of Carbon Fibre Composite Box Beams Subjected Torsion with Variable Twist", Computer Methods in Applied Mechanics and Engineering, 152(3-4), pp.373~391 (1998)
- Ghiasi, H., "Optimum Stacking Sequence Design of Composite Materials Part II : Variable Stiffness Design", Composite Structures, 93(1), pp.1~13 (2010)
- Jeong, C. H., "Crash Simulation of a Piecewisely-integrated Composite Bumper Beams", Mechanical and Production Engineering, 6, pp.37~40 (2018)
- 함석우, "머신 러닝을 통한 PIC 보의 강도 최적화", 대한기계학회논문집 A, 43(8), pp.521~528 (2019), 대한기계학회
- Lantz, B., "Machine Learning with R" (2015), Packt Pub
- Qi, Z., "Prediction of Mechanical Properties of Carbon Fiber Based on Cross-scale FEM and Machine Learning", Composite Structures, 212, pp.199~206 (2019)
- Gajowniczek, K., "ImbTreeAUC : An R Package for Building Classification Trees Using the Area under the ROC Curve(AUC)on Imbalanced Datasets", SoftwareX, 15, pp.100755~ (2021)
- Muller, M. P., "Can Routine Laboratory Tests Discriminate between Severe Acute Respiratory Syndrome and other Causes of Community-acquired Pneumonia?", Journal of Clinical Infectious Diseases, 40(8), pp.1079~1086 (2005)
- "2510 Prepreg System" (2017)[URL]
- Bai, Y., "On the Application of Stress Triaxiality Formula for Plane Strain Fracture Testing", Journal of Engineering Materials and Technology, Transactions of the ASME, 131(2), pp.0210021~ (2009)
- Bao, Y., "On Fracture Locus in the Equivalent Strain and Stress Triaxiality Space", International Journal of Mechanical Sciences, 46(1), pp.81~98 (2004)
- Gareth, J., "An Introduction to Statistical Learning: with Applications in R" (2013), Springer Pub. Co
- Vapnik, V., "The Nature of Statistical Learning Theory" (1999), Springer Pub. Co
- Konjevoda, P., "Open-source Tools for Data Mining in Social Science" (2012), IntechOpen Limited Pub. Co
- 김연중, "뉴럴 네트워크의 최적화에 따른 유사태풍 예측에 관한 연구", 한국해양공학회지, 33(5), pp.427~434 (2019), 한국해양공학회[DOI]
- 김석호, "IoT 센서 데이터를 이용한 단위실의 재실추정을 위한 Decision Tree 알고리즘 성능분석", 한국태양에너지학회 논문집, 37(2), pp.23~33 (2017), 한국태양에너지학회[DOI]
- 방명환, "랜덤 포레스트 기반 머신러닝 모델을 이용한 가스터빈 압축기 성능저하 분석", 대한기계학회논문집 B, 45(11), pp.605~612 (2021), 대한기계학회
- Feraboli, P., "LS-DYNA MAT54 Modeling of the Axial Crushing of a Composite Tape Sinusoidal Specimen", Composites Part A : Applied Science and Manufacturing, 42, pp.1809~1825 (2011)
- Denk, L., "Shear Fracture of C", C Composites with Variable Stacking Sequence, 2001, pp.39(10), 1505~1513
- 정찬희, "IIHS 충격해석에 근거한 구간 조합 복합재료 범퍼 빔 개발", Composites Research, 31(1), pp.37~41 (2018), 한국복합재료학회