Review of robot-based damage assessment for offshore wind turbines

被引:60
作者
Liu, Y. [1 ]
Hajj, M. [1 ]
Bao, Y. [1 ]
机构
[1] Stevens Inst Technol, Dept Civil Environm & Ocean Engn, Hoboken, NJ 07030 USA
关键词
Automated detection; Computer vision; Damage assessment; Machine learning; Nondestructive evaluation; Offshore wind turbines; Robots; CRACK DETECTION; ACOUSTIC-EMISSION; CLIMBING ROBOTS; INSPECTION; SURFACE; SYSTEM; THERMOGRAPHY; TECHNOLOGIES; RECOGNITION; CHALLENGES;
D O I
10.1016/j.rser.2022.112187
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Offshore wind turbines are subjected to highly-varying dynamic loadings and accelerated material degradation, resulting in the need for structural health monitoring, which increases the operation and maintenance cost and ultimately the levelized cost of electricity. Recent advances in robotics and intelligent algorithms offer new opportunities for automated damage assessment that would minimize these costs. This review aims to establish a holistic understanding of robot-based damage assessment technologies and to promote the development and application of these technologies for automated condition assessment of offshore wind turbines. It covers robots as potential carriers of inspection devices, damage inspection approaches, and intelligent algorithms for damage detection, classification, localization, and quantification for offshore wind turbines. The robots include climbing and underwater varieties, and unmanned aerial vehicles, which carry optical and infrared cameras, and X-ray equipment. Advanced machine learning algorithms for analysis of inspection data are evaluated. Challenges and opportunities of robot-based damage assessment technologies are discussed.
引用
收藏
页数:15
相关论文
共 143 条
  • [1] 'In-situ' inspection technologies: Trends in degradation assessment and associated technologies
    Addepalli, Sri
    Roy, Rajkumar
    Axinte, Dragos
    Mehnen, Jorn
    [J]. PROCEEDINGS OF THE 5TH INTERNATIONAL CONFERENCE IN THROUGH-LIFE ENGINEERING SERVICES, 2017, 59 : 35 - 40
  • [2] Albrektsen SM, 2018, 2018 IEEE CONFERENCE ON CONTROL TECHNOLOGY AND APPLICATIONS (CCTA), P1338, DOI 10.1109/CCTA.2018.8511354
  • [3] Subsurface damage detection of a steel bridge using deep learning and uncooled micro-bolometer
    Ali, Rahmat
    Cha, Young-Jin
    [J]. CONSTRUCTION AND BUILDING MATERIALS, 2019, 226 : 376 - 387
  • [4] A new AUV navigation system exploiting unscented Kalman filter
    Allotta, B.
    Caiti, A.
    Costanzi, R.
    Fanelli, F.
    Fenucci, D.
    Meli, E.
    Ridolfi, A.
    [J]. OCEAN ENGINEERING, 2016, 113 : 121 - 132
  • [5] Comparison and analysis of non-destructive testing techniques suitable for delamination inspection in wind turbine blades
    Amenabar, I.
    Mendikute, A.
    Lopez-Arraiza, A.
    Lizaranzu, M.
    Aurrekoetxea, J.
    [J]. COMPOSITES PART B-ENGINEERING, 2011, 42 (05) : 1298 - 1305
  • [6] American Wind Energy Association, 2020, WIND POW AM 2 QUART
  • [7] American Wind Energy Association, 2020, US OFFSH WIND IND ST
  • [8] An R, IEEE INT C MECH AUT, P1222
  • [9] Audio Video Supply, 2021, POINT GREY GS3 U3 32
  • [10] Avdelidis NP., 2013, Non-Destructive Evaluation (NDE) of Polymer Matrix Composites, P634, DOI [DOI 10.1533/9780857093554, 10.1533/9780857093554.4.634, DOI 10.1533/9780857093554.4.634]