Robot arm damage detection using vibration data and deep learning
Pages 1727 - 1739
Abstract
During robot operation, robot components like links and joints may experience collisions or excess loads that can lead to structural damages or cracks. A crack in a structural component can degrade the overall performance of the structure. This study examines the influence of cracks on the vibration characteristics of a baseline robot link. The approach uses the finite element method to simulate the dynamics of planar robot link models with and without artificial cracks with different sizes, locations, and orientations in the ABAQUS software. The robot link models include one intact model and five defective models with cracks. A rectangular crack with a fixed length of 1 mm and a varying width from 0.001 to 0.1 mm is applied to a specific location along the robot link. Finite element analysis and machine learning are used to simulate and characterize the vibration of each robot link with one fixed end and one free end. The vibration responses are measured at the free end. The measured vibration data are then transformed into two-dimensional (2D) image data using the Gramian Angular Summation Field method. A convolutional neural network is then trained with the image data for crack detection and analysis. The results indicate that the proposed method demonstrates 98.25% accuracy on the data generated by the simulation experiments.
References
[1]
Qiao G and Weiss BA Industrial robot accuracy degradation monitoring and quick health assessment J Manuf Sci Eng 2019 141 7 071006
[2]
Boldsaikhan E Measuring and estimating rotary joint axes of an articulated robot IEEE Trans Instrum Meas 2020 69 10 8279-8287
[3]
Hasan A, Tahavori M, and Midtiby HS Model-based fault diagnosis algorithms for robotic systems IEEE Access 2023 11 2250-2258
[4]
Djordjević V, Stojanović V, Pršić D, Dubonjić L, and Morato MM Observer-based fault estimation in steer-by-wire vehicle Eng Today 2022 1 1 7-17
[5]
Zhuang Z, Tao H, Chen Y, Stojanovic V, Paszke W (2022) An optimal iterative learning control approach for linear systems with nonuniform trial lengths under input constraints. IEEE Transactions on Systems, Man, and Cybernetics: Systems
[6]
Biglari H, Golmohammadi M, Hayati S, and Hemmati S Vibration reduction of a flexible robot link using a frictional damper J Vib Control 2021 27 9–10 985-997
[7]
Sarkhel P, Dikshit MK, Pathak VK, Saxena KK, Prakash C, and Buddhi D Robust deflection control and analysis of a fishing rod-type flexible robotic manipulator for collaborative robotics Robot Auton Syst 2023 159 104293
[8]
Xu P, Yao X, Liu S, Wang H, Liu K, Kumar AS, Lu WF, and Bi G Stiffness modeling of an industrial robot with a gravity compensator considering link weights Mech Mach Theory 2021 161 104331
[9]
Frej A, Chiementin X, Fakher C, Bolaers F, Haddar M (2023) Dynamic modeling and vibration analysis for defect identification of single-stage gearboxes in the joints of industrial robots with six DOF. Proc Inst Mech Eng Part C 09544062231152347
[10]
Yan Y, Guo Y, Liu X (2023) Tooth root crack detection of planet gear in industrial robot RV reducer. Meas Control 00202940231180619
[11]
Shi M, Rong B, Liang J, Zhao W, and Pan H Dynamics analysis and vibration suppression of a spatial rigid-flexible link manipulator based on transfer matrix method of multibody system Nonlinear Dyn 2023 111 2 1139-1159
[12]
Ambaye GA and Lemu HG Dynamic analysis of spur gear with backlash using ADAMS Mater Today Proc 2021 38 2959-2967
[13]
Kouritem SA, Abouheaf MI, Nahas N, and Hassan M A multi-objective optimization design of industrial robot arms Alex Eng J 2022 61 12 12847-12867
[14]
Hu M, Wang H, Pan X, Liao L, and Sun H Elastic deformation modeling of series robots with consideration of gravity Intell Serv Robot 2022 15 3 351-362
[15]
Seth A, Kuruvilla JK, Sharma S, Duttagupta J, and Jaiswal A Design and simulation of 6-DOF cylindrical robotic manipulator using finite element analysis Mater Today Proc 2022 62 1521-1525
[16]
Ambaye GA, Lemu HG (2021) Effect of backlash on transmission error and time varying mesh stiffness. In: Advanced manufacturing and automation, Springer, vol X 10, pp 18–28
[17]
Guo S, He Y, Shi L, Pan S, Tang K, Xiao R, and Guo P Modal and fatigue analysis of critical components of an amphibious spherical robot Microsyst Technol 2017 23 2233-2247
[18]
Phanden RK, Sharma P, and Dubey A A review on simulation in digital twin for aerospace, manufacturing and robotics Mater Today Proc 2021 38 174-178
[19]
Sha G, Radzieński M, Cao M, and Ostachowicz W A novel method for single and multiple damage detection in beams using relative natural frequency changes Mech Syst Signal Process 2019 132 335-352
[20]
Altunışık AC, Okur FY, Karaca S, and Kahya V Vibration-based damage detection in beam structures with multiple cracks: modal curvature vs modal flexibility methods Nondestruct Test Eval 2019 34 1 33-53
[21]
Song M, Gong Y, Yang J, Zhu W, and Kitipornchai S Nonlinear free vibration of cracked functionally graded graphene platelet-reinforced nanocomposite beams in thermal environments J Sound Vib 2020 468 115115
[22]
Sahu S and Das P Experimental and numerical studies on vibration of laminated composite beam with transverse multiple cracks Mech Syst Signal Process 2020 135 106398
[23]
Wei C and Shang X Analysis on nonlinear vibration of breathing cracked beam J Sound Vib 2019 461 114901
[24]
Long H, Liu Y, and Liu K Nonlinear vibration analysis of a beam with a breathing crack Appl Sci 2019 9 18 3874
[25]
Tam M, Yang Z, Zhao S, and Yang J Vibration and buckling characteristics of functionally graded graphene nanoplatelets reinforced composite beams with open edge cracks DMaterials 2019 12 9 1412
[26]
Chinka SSB, Putti SR, Adavi BK (2021) Modal testing and evaluation of cracks on cantilever beam using mode shape curvatures and natural frequencies. In: Structures, Elsevier, vol 32, pp 1386–1397
[27]
Taima MS, El-Sayed TA, Shehab MB, Farghaly SH, Hand RJ (2022) Vibration analysis of cracked beam based on Reddy beam theory by finite element method. J Vib Control 10775463221122122
[28]
Zhao K, Liu Y, Du J (2023) Vibration characteristics and power flow analysis of a constant cracked beam with general boundary conditions. Int J Appl Mech
[29]
Teyi N and Singh S A review of application of data science tools in crack identification and localization Procedia Struct Integr 2022 39 608-623
[30]
Zeng J, Chen K, Ma H, Duan T, and Wen B Vibration response analysis of a cracked rotating compressor blade during run-up process Mech Syst Signal Process 2019 118 568-583
[31]
Mian T, Choudhary A, Fatima S (2023) Multi-sensor fault diagnosis for misalignment and unbalance detection using machine learning. IEEE Transactions on Industry Applications
[32]
Mian T, Choudhary A, and Fatima S Vibration and infrared thermography based multiple fault diagnosis of bearing using deep learning Nondestruct Test Eval 2023 38 2 275-296
[33]
Tao H, Qiu J, Chen Y, Stojanovic V, and Cheng L Unsupervised cross-domain rolling bearing fault diagnosis based on time-frequency information fusion J Frankl Inst 2023 360 2 1454-1477
[34]
Bukovsky I Deterministic behavior of temperature field in turboprop engine via shallow neural networks Neural Comput Appl 2021 33 19 13145-13161
[35]
Asteris PG and Mokos VG Concrete compressive strength using artificial neural networks Neural Comput Appl 2020 32 15 11807-11826
[36]
Kalaiselvi T, Padmapriya S, Somasundaram K, and Praveenkumar S E-tanh: a novel activation function for image processing neural network models Neural Comput Appl 2022 34 19 16563-16575
[37]
Rodriguez-Conde I, Campos C, and Fdez-Riverola F Optimized convolutional neural network architectures for efficient on-device vision-based object detection Neural Comput Appl 2022 34 13 10469-10501
[38]
Alsalemi A, Amira A, Malekmohamadi H, and Diao K Lightweight Gramian angular field classification for edge internet of energy applications Clust Comput 2023 26 2 1375-1387
[39]
Qin Z, Zhang Y, Meng S, Qin Z, and Choo K-KR Imaging and fusing time series for wearable sensor-based human activity recognition Inf Fusion 2020 53 80-87
[40]
Abidi A, Ienco D, Abbes AB, and Farah IR Combining 2d encoding and convolutional neural network to enhance land cover mapping from satellite image time series Eng Appl Artif Intell 2023 122 106152
[41]
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Preprint arXiv:1409.1556
[42]
Amin A, Bibo A, Panyam M, and Tallapragada P Vibration based fault diagnostics in a wind turbine planetary gearbox using machine learning Wind Eng 2023 47 1 175-189
[43]
Rao SS Vibration of continuous systems 2019 USA Wiley
[44]
Lee U Spectral element method in structural dynamics 2009 Republic of Korea Wiley
[45]
Sarvestan V, Mirdamadi HR, and Ghayour M Vibration analysis of cracked Timoshenko beam under moving load with constant velocity and acceleration by spectral finite element method Int J Mech Sci 2017 122 318-330
[46]
Boldsaikhan E, Corwin E, Antonette L, and Arbegast W The use of neural network and discrete Fourier transform for real-time evaluation of friction stir welding App Soft Comput 2011 11 8 4839-4846
[47]
Emmanuel S, Yihun Y, Nili Ahmedabadi Z, and Boldsaikhan E Planetary gear train microcrack detection using vibration data and convolutional neural networks Neural Comput Appl 2021 33 17223-17243
Index Terms
- Robot arm damage detection using vibration data and deep learning
Index terms have been assigned to the content through auto-classification.
Recommendations
Magnetorheological damper for vibration reduction in a robot arm
AbstractIn this study, we develop a novel damper prototype for robot manipulators of a mobile robot to perform rescue operations in extreme environments like battlefields. Shock vibrations occur when such robots drive over rugged terrain, adversely ...
Damage detection of circular hollow cylinder using modal strain energy and scanning damage index methods
The detection of surface crack in a circular hollow cylinder is presented in this paper. Experimental modal analysis is conducted on the cylinder to obtain the modal displacements used to compute the modal strain energy. For all measured mode shapes, a ...
A deep learning framework for constitutive modeling based on temporal convolutional network
AbstractA novel and efficient deep learning framework adopting the Temporal Convolutional Network (TCN) model is proposed to simulate the ultra-long-history-dependent stress-strain constitutive model. First, the practical requirements for the ...
Comments
Information & Contributors
Information
Published In
© This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply 2023.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 15 November 2023
Accepted: 17 October 2023
Received: 20 June 2023
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 16 Jan 2025