Performance Assessment for Artificial Intelligence-Based Data Analysis in Ultrasonic Guided Wave-Based Inspection: A Comparison to Classic Path-Based Probability of Detection

被引:1
作者
Mueller, Inka [1 ]
Freitag, Steffen [2 ]
Memmolo, Vittorio [3 ]
Moix-Bonet, Maria [4 ]
Moellenhoff, Kathrin [5 ]
Golub, Mikhail [6 ]
Venkat, Ramanan Sridaran [7 ]
Lugovtsova, Yevgeniya [8 ]
Eremin, Artem [6 ]
Moll, Jochen [9 ]
Tschoeke, Kilian [10 ]
机构
[1] Bochum Univ Appl Sci, Bochum, Germany
[2] Karlsruhe Inst Technol, Karlsruhe, Germany
[3] Univ Naples Federico II, Naples, Italy
[4] DLR, Braunschweig, Germany
[5] Heinrich Heine Univ Dusseldorf, Dusseldorf, Germany
[6] Kuban State Univ, Krasnodar, Russia
[7] Saarland Univ, Saarbrucken, Germany
[8] BAM, Berlin, Germany
[9] Goethe Univ, Frankfurt, Germany
[10] Fraunhofer Inst Ceram Technol & Syst IKTS, Dresden, Germany
来源
EUROPEAN WORKSHOP ON STRUCTURAL HEALTH MONITORING (EWSHM 2022), VOL 2 | 2023年
关键词
D O I
10.1007/978-3-031-07258-1_96
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Performance assessment for GuidedWave (GW)-based Structural Health Monitoring (SHM) systems is of major importance for industrial deployment. With conventional feature extraction methods like damage indices, path-based probability of detection (POD) analysis can be realized. To achieve reliability quantification enough data needs to be available, which is rarely the case. Alternatives like methods for performance assessment on system level are still in development and in a discussion phase. In this contribution, POD results using an Artificial Intelligence (AI)-based data analysis are compared with those delivered by conventional data analysis. Using an open-access dataset from Open Guided Wave platform, the possibility of performance assessment for GW-based SHM systems using AI-based data analysis is shown in detail. An artificial neural network (ANN) classifier is trained to detect artificial damage in a stiffened CFRP plate. As input for the ANN, classical damage indicators are used. The ANN is tested to detect damage at another position, whose inspection data were not previously used in training. The findings show very high detection capabilities without sorting any specific path but only having a global view of current damage metrics. The systematic evaluation of the ANN predictions with respect to specific damage sizes allows to compute a probability of correct identification versus flaw dimension, somehow equivalent to and compared with the results achieved through classic path-based POD analysis. Also, sensitive paths are detected by ANN predictions allowing for evaluation of maximal distances between path and damage position. Finally, it is shown that the prediction performance of the ANN can be improved significantly by combining different damage indicators as inputs.
引用
收藏
页码:953 / 961
页数:9
相关论文
共 9 条
  • [1] Berens A., 1988, ASM Int., V17, P689
  • [2] Harding C.A., 2006, AIP C P, DOI [10.1063/1.2184746, DOI 10.1063/1.2184746]
  • [3] Statistically-based damage detection in geometrically-complex structures using ultrasonic interrogation
    Haynes, Colin
    Todd, Michael D.
    Flynn, Eric
    Croxford, Anthony
    [J]. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2013, 12 (02): : 141 - 152
  • [4] Meeker W.Q., 2019, INT WORKSHOP STRUCTU
  • [5] Guided wave based structural health monitoring: A review
    Mitra, Mira
    Gopalakrishnan, S.
    [J]. SMART MATERIALS AND STRUCTURES, 2016, 25 (05)
  • [6] Guided Waves for Damage Detection in Complex Composite Structures: The Influence of Omega Stringer and Different Reference Damage Size
    Moll, Jochen
    Kexel, Christian
    Kathol, Jens
    Fritzen, Claus-Peter
    Moix-Bonet, Maria
    Willberg, Christian
    Rennoch, Marcel
    Koerdt, Michael
    Herrmann, Axel
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (09):
  • [7] Open Guided Waves: online platform for ultrasonic guided wave measurements
    Moll, Jochen
    Kathol, Jens
    Fritzen, Claus-Peter
    Moix-Bonet, Maria
    Rennoch, Marcel
    Koerdt, Michael
    Herrmann, Axel S.
    Sause, Markus G. R.
    Bach, Martin
    [J]. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2019, 18 (5-6): : 1903 - 1914
  • [8] POD of NDT Techniques Using High Temperature Oxidized Fatigue Cracks in an Aero Engine Alloy
    Rentala, Vamsi Krishna
    Mylavarapu, Phani
    Kumar, Atul
    Gautam, Jai Prakash
    Gopinath, K.
    Jayakumar, T.
    [J]. JOURNAL OF NONDESTRUCTIVE EVALUATION, 2021, 40 (02)
  • [9] Feasibility of Model-Assisted Probability of Detection Principles for Structural Health Monitoring Systems Based on Guided Waves for Fiber-Reinforced Composites
    Tschoeke, Kilian
    Mueller, Inka
    Memmolo, Vittorio
    Moix-Bonet, Maria
    Moll, Jochen
    Lugovtsova, Yevgeniya
    Golub, Mikhail
    Venkat, Ramanan Sridaran
    Schubert, Lars
    [J]. IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL, 2021, 68 (10) : 3156 - 3173