Prediction of Unmeasured Mode Shape Using Artificial Neural Network for Damage Detection

2013 ◽  
Vol 61 (1) ◽  
Author(s):  
L. D. Goh ◽  
N. Bakhary ◽  
A. A. Rahman ◽  
B. H. Ahmad
Keyword(s):  
Neural Network ◽  
Damage Detection ◽  
Mode Shape ◽  
Health Monitoring ◽  
Spline Interpolation ◽  
Measured Data ◽  
Mode Shapes ◽  
Modal Data ◽  
Artificial Neural ◽  
Shape Data

Artificial neural networks (ANNs) have received much attention in the field of vibration–based damage detection since the 1990s, due to their capability to predict damage from modal data. However, the accuracy of this method is highly dependent on the number of measurement points, especially when the mode shape is used as an indicator for damage detection. With a high number of measurement points, more information can be fed to the ANN to detect damage; therefore, more reliable results can be obtained. Nevertheless, in practice, it is uneconomical to install sensors on every part of a structure; thus the capability of ANNs to detect damage is quite limited. In this study, an ANN is applied to predict the unmeasured mode shape data based on a limited number of measured data. To demonstrate the accuracy of the proposed method, the results are compared with the Cubic Spline interpolation (CS) method. A parametric study is also conducted to investigate the sensitivity of the number of measurement points to the proposed method. The results show that the ANN provides more reliable results compared to the CS method as it is able to predict the magnitude of mode shapes at the unmeasured points with a limited number of measurement points. The application of a two–stage ANN showed results with a high potential for overcoming the issue of using a limited number of sensors in structural health monitoring.

scholarly journals Multiple Damage Detection of an Offshore Helideck through the Two-Step Artificial Neural Network Based on the Limited Mode Shape Data

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7357
Author(s):  
Byungmo Kim ◽  
Chanyeong Kim ◽  
Seung-Hyun Ha
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Damage Detection ◽  
Mode Shape ◽  
Structural Damage ◽  
Mode Shapes ◽  
Estimation Accuracy ◽  
The Neural Network ◽  
Artificial Neural ◽  
Shape Data

A helideck is an essential structure in an offshore platform, and it is crucial to maintain its structural integrity and detect the occurrence of damage early. Because helidecks usually consist of complex lattice truss members, precise measurements are required for structural health monitoring based on accurate modal parameters. However, available sensors and data acquisition are limited. Therefore, we propose a two-step damage detection process using an artificial neural network. Based on the mode shape database collected from 137,400 damage scenarios by finite element analysis, the neural network in the first step was trained to estimate the mode shapes of the entire helideck model using the selected mode shape data obtained from the limited measuring points. Then, the neural network in the second step is consecutively trained to detect the location and amount of structural damage to individual parts. As a result, it is shown that the proposed procedure provides the damage detection capability with only a quarter of the entire mode shape data, while the estimation accuracy is sufficiently high compared to the single network directly trained using all mode shape data. It was also found that, compared to the network directly trained from the same data, the proposed technique tends to detect minor damages more accurately.

An effective method for damage assessment based on limited measured locations in skeletal structures

2020 ◽  
Vol 24 (1) ◽  
pp. 183-195 ◽  
Author(s):  
Parsa Ghannadi ◽  
Seyed Sina Kourehli
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Damage Detection ◽  
Degrees Of Freedom ◽  
Truss Structures ◽  
Mode Shapes ◽  
Analysis Model ◽  
Test Analysis ◽  
Modal Test ◽  
Artificial Neural

This article proposes a new damage detection method using Modal Test Analysis Model and artificial neural networks. A challenge in damage detection problems is lack of measured degrees of freedom, as well as limitations of attached sensors. Modal Test Analysis Model has been used in order to estimate unmeasured degrees of freedom. An experimental cantilever beam was used to show Modal Test Analysis Model’s efficiency in estimation of unmeasured mode shapes. To solve the inverse problem of damage detection, mode shapes estimated by Modal Test Analysis Model were used as inputs, and characteristics of the damage served as outputs of the artificial neural network. The sensitivity analysis carried out for each example showing the performance of artificial neural network after mode shape expansion was efficiently improved. Three numerical examples for plane and space truss structures are considered, in order to verify effectiveness of the proposed method. Results demonstrate a high accuracy of Modal Test Analysis Model and artificial neural network for structural damage detection.

A Comparison of Artificial Neural Network Learning Algorithms for Vibration-Based Damage Detection

2010 ◽  
Vol 163-167 ◽  
pp. 2756-2760 ◽  
Author(s):  
Goh Lyn Dee ◽  
Norhisham Bakhary ◽  
Azlan Abdul Rahman ◽  
Baderul Hisham Ahmad
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Damage Detection ◽  
Conjugate Gradient ◽  
Learning Algorithms ◽  
Mode Shapes ◽  
Neural Network Learning ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Artificial Neural

This paper investigates the performance of Artificial Neural Network (ANN) learning algorithms for vibration-based damage detection. The capabilities of six different learning algorithms in detecting damage are studied and their performances are compared. The algorithms are Levenberg-Marquardt (LM), Resilient Backpropagation (RP), Scaled Conjugate Gradient (SCG), Conjugate Gradient with Powell-Beale Restarts (CGB), Polak-Ribiere Conjugate Gradient (CGP) and Fletcher-Reeves Conjugate Gradient (CGF) algorithms. The performances of these algorithms are assessed based on their generalisation capability in relating the vibration parameters (frequencies and mode shapes) with damage locations and severities under various numbers of input and output variables. The results show that Levenberg-Marquardt algorithm provides the best generalisation performance.

On the Identification of Localized Losses of Stiffness in Structures

1993 ◽  
Author(s):  
Ulrich Pabst ◽  
Peter Hagedorn
Keyword(s):  
Mathematical Model ◽  
Damage Detection ◽  
Mode Shape ◽  
Measurement Errors ◽  
Mode Shapes ◽  
Shape Functions ◽  
Modal Data ◽  
Order Of Magnitude ◽  
Eigen Frequencies ◽  
Local Stiffness

Abstract In damage detection it is common to use measured modal data and a mathematical model in connection with system identification. The part of the system undergoing the largest stiffness decrease is defined to contain damage. This approach is very sensitive to measurement errors. The measurement errors are much larger for mode shape functions than for the eigen-frequencies. The errors in the mode shapes are often of the same order of magnitude as the variations due to damage leading to poor results in damage detection. Thus, the use of the mode shape functions themselves instead of their small damage induced variations would dearly be preferable. In this paper we examine the relation between the changes in the eigenfrequencies, the local stiffness losses and the mode shape functions of the undamaged system. This relation is then utilized in a damage detection procedure.

scholarly journals Identification of Damage in a Beam Structure by Using Mode Shape Curvature Squares

2010 ◽  
Vol 17 (4-5) ◽  
pp. 601-610 ◽  
Author(s):  
S. Rucevskis ◽  
M. Wesolowski
Keyword(s):  
Damage Detection ◽  
Mode Shape ◽  
Dynamic Structure ◽  
Mode Shapes ◽  
Difference Approximation ◽  
Laser Vibrometer ◽  
Beam Structure ◽  
Central Difference ◽  
Modal Data ◽  
Healthy State

During the last decades a great variety of methods have been proposed for damage detection by using the dynamic structure characteristics, however, most of them require modal data of the structure for the healthy state as a reference. In this paper the applicability of the mode shape curvature squares determined from only the damaged state of the structure for damage detection in a beam structure is studied. To establish the method, two aluminium beams containing different-size mill-cut damage at different locations are tested by using the experimentally measured modal data. The experimental modal frequencies and the corresponding mode shapes are obtained by using a scanning laser vibrometer with a PZT actuator. From the mode shapes, mode shape curvatures are obtained by using a central difference approximation. With the example of the beams with free-free and clamped boundary conditions, it is shown that the mode shape curvature squares can be used to detect damage in the structures. Further, the extent of a mill-cut damage is identified via modal frequencies by using a mixed numerical-experimental technique. The method is based on the minimization of the discrepancy between the numerically calculated and experimentally measured frequencies.

scholarly journals VIBRATION-BASED DAMAGE DETECTION IN A BEAM STRUCTURE WITH MULTIPLE DAMAGE LOCATIONS

Aviation ◽  
2009 ◽  
Vol 13 (3) ◽  
pp. 61-71 ◽  
Author(s):  
Sandris Ručevskis ◽  
Miroslaw Wesolowski ◽  
Andris Chate
Keyword(s):  
Damage Detection ◽  
Mode Shape ◽  
Failure Modes ◽  
Mode Shapes ◽  
Difference Approximation ◽  
Laser Vibrometer ◽  
Shape Information ◽  
Modal Data ◽  
Damage Indices ◽  
Damage Extent

During the last two decades structural damage identification using dynamic parameters of the structure has become an important research area for civil, mechanical, and aerospace engineering communities. The basic idea of the vibration‐based damage detection methods is that a damage as a combination of different failure modes in the form of loss of local stiffness in the structure alters its dynamic characteristics, i.e., the modal frequencies, mode shapes, and modal damping values. A great variety of methods have been proposed for damage detection by using dynamic structure parameters; however, most of them require modal data of the healthy state of structure as a reference. In this paper a vibration‐based damage detection method, which uses the mode shape information determined from only the damaged state of the structure is proposed. To establish the method, two aluminium beams containing different sizes of mill‐cut damage at a single location as well as two aluminium beams containing different sizes of mill‐cut damage at multiple locations are examined. The experimental modal frequencies and the corresponding mode shapes for the first 15 flexural modes are obtained by using a scanning laser vibrometer with a PZT actuator. From the mode shapes, mode shape curvatures are obtained by using a central difference approximation. In order to exclude the influence of measurement noise on the modal data and misleading damage indices, it is proposed to use the sum of mode shape curvature squares for each mode. With the example of the beams with free‐free and clamped boundary conditions, it is shown that the mode shape curvature squares can be used to detect damage in the structures. The extent of mill‐cut damage is identified via the modal frequencies by using mixed numerical‐experimental technique. The method is based on the minimization of the discrepancy between the numerically calculated and the experimentally measured frequencies. The numerical frequencies are calculated by employing a finite‐element model for beam with introduced damage. Further, by using the response surface approach, a relationship (second‐order polynomial function) between the modal frequencies and the damage extent is constructed. The damage extent is obtained by solving the minimization problem. Santrauka Tyrimo metu buvo ieškomos sijines konstrukcijos pažeidimo frezuojant vietos, apimtis ir pažeidimo dydis pagal atlikto vibraciju eksperimento dinamines charakteristikas. Pažeidimo padetis ir apimtis buvo nustatomi pagal išlinkio formos virpesiu kvadrato dydi. Pažeidimo dydis buvo nustatomas skaitiniu‐eksperimentiniu metodu, taikant modalinius dažnius. Šio metodo efektyvumas ir patikimumas parodytas tiriant dvi aliuminio sijas, kurios buvo pažeistos frezos vienoje vietoje ir kurios buvo pažeistos skirtingose vietose.

Damage Detection of Offshore Platform Mooring Line Using Artificial Neural Network

2018 ◽  
Author(s):  
Djoni E. Sidarta ◽  
Jim O’Sullivan ◽  
Ho-Joon Lim
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Damage Detection ◽  
Total Mass ◽  
Offshore Platform ◽  
Mooring Line ◽  
Ann Model ◽  
Station Keeping ◽  
Mooring Lines ◽  
Artificial Neural

Station-keeping using mooring lines is an important part of the design of floating offshore platforms, and has been used on most types of floating platforms, such as Spar, Semi-submersible, and FPSO. It is of great interest to monitor the integrity of the mooring lines to detect any damaged and/or failures. This paper presents a method to train an Artificial Neural Network (ANN) model for damage detection of mooring lines based on a patented methodology that uses detection of subtle shifts in the long drift period of a moored floating vessel as an indicator of mooring line failure, using only GPS monitoring. In case of an FPSO, the total mass or weight of the vessel is also used as a variable. The training of the ANN model employs a back-propagation learning algorithm and an automatic method for determination of ANN architecture. The input variables of the ANN model can be derived from the monitored motion of the platform by GPS (plus vessel’s total mass in case of an FPSO), and the output of the model is the identification of a specific damaged mooring line. The training and testing of the ANN model use the results of numerical analyses for a semi-submersible offshore platform with twenty mooring lines for a range of metocean conditions. The training data cover the cases of intact mooring lines and a damaged line for two selected adjacent lines. As an illustration, the evolution of the model at various training stages is presented in terms of its accuracy to detect and identify a damaged mooring line. After successful training, the trained model can detect with great fidelity and speed the damaged mooring line. In addition, it can detect accurately the damaged mooring line for sea states that are not included in the training. This demonstrates that the model can recognize and classify patterns associated with a damaged mooring line and separate them from patterns of intact mooring lines for sea states that are and are not included in the training. This study demonstrates a great potential for the use of a more general and comprehensive ANN model to help monitor the station keeping integrity of a floating offshore platform and the dynamic behavior of floating systems in order to forecast problems before they occur by detecting deviations in historical patterns.

L1 Regularized Model Updating for Structural Damage Detection

2018 ◽  
Vol 18 (12) ◽  
pp. 1850157 ◽  
Author(s):  
Yu-Han Wu ◽  
Xiao-Qing Zhou
Keyword(s):  
Damage Detection ◽  
Structural Damage ◽  
Model Updating ◽  
Regularization Parameter ◽  
Structural Vibration ◽  
Mode Shapes ◽  
Modal Data ◽  
Vibration Data ◽  
Stiffness Reduction ◽  
Regularized Model

Model updating methods based on structural vibration data have been developed and applied to detecting structural damages in civil engineering. Compared with the large number of elements in the entire structure of interest, the number of damaged elements which are represented by the stiffness reduction is usually small. However, the widely used [Formula: see text] regularized model updating is unable to detect the sparse feature of the damage in a structure. In this paper, the [Formula: see text] regularized model updating based on the sparse recovery theory is developed to detect structural damage. Two different criteria are considered, namely, the frequencies and the combination of frequencies and mode shapes. In addition, a one-step model updating approach is used in which the measured modal data before and after the occurrence of damage will be compared directly and an accurate analytical model is not needed. A selection method for the [Formula: see text] regularization parameter is also developed. An experimental cantilever beam is used to demonstrate the effectiveness of the proposed method. The results show that the [Formula: see text] regularization approach can be successfully used to detect the sparse damaged elements using the first six modal data, whereas the [Formula: see text] counterpart cannot. The influence of the measurement quantity on the damage detection results is also studied.

Damage detection in steel-concrete composite bridge using vibration characteristics and artificial neural network

2019 ◽  
Vol 16 (9) ◽  
pp. 1247-1261 ◽  
Author(s):  
Zhi Xin Tan ◽  
David P. Thambiratnam ◽  
Tommy H. T. Chan ◽  
Meisam Gordan ◽  
Hashim Abdul Razak
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Damage Detection ◽  
Vibration Characteristics ◽  
Composite Bridge ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document