Delamination detection with error and noise polluted natural frequencies using computational intelligence concepts

Reliable delamination prediction scheme is indispensable in order to prevent potential risks of catastrophic failures in composite structures. The existence of delaminations changes the vibration characteristics of composite laminates and hence such indicators can be used to quantify the health characteristics of laminates. An approach for online health monitoring of in-service composite laminates is presented in this paper that relies on methods based on computational intelligence. Typical changes in the observed vibration characteristics (i.e. change in natural frequencies) are considered as inputs to identify the existence, location and magnitude of delaminations. The performance of the proposed approach is demonstrated using numerical models of composite laminates. Since this identification problem essentially involves the solution of an optimization problem, the use of finite element (FE) methods as the underlying tool for analysis turns out to be computationally expensive. A surrogate assisted optimization approach is hence introduced to contain the computational time within affordable limits. An artificial neural network (ANN) model with Bayesian regularization is used as the underlying approximation scheme while an improved rate of convergence is achieved using a memetic algorithm. However, building of ANN surrogate models usually requires large training datasets. K-means clustering is effectively employed to reduce the size of datasets. ANN is also used via inverse modeling to determine the position, size and location of delaminations using changes in measured natural frequencies. The results clearly highlight the efficiency and the robustness of the approach.

This research work deals with aspects concerned with delamination detection in composite structures as revealed by an approach based on vibration measurements. Variations in vibration characteristics generated in composite laminates indicate the existence of delaminations because degradation due to delamination causes reduction in flexural stiffness and strength of the material and as a result vibration parameters like natural frequency responses are changed. Hence, it is possible to monitor the variation in natural frequencies to identify the presence of delamination, and assess its size and location for online structural health monitoring (SHM). The approach to this paper, therefore, typically depends on undertaking the analysis of structural models implemented by finite element analysis (FEA). The numerical solutions using FE models known as the simulator computes the natural frequencies for the delaminated and undelaminated specimens of composite laminates. However, these FE models are computationally expensive, and surrogate (approximation) models are introduced to curtail the computational expense. The simulator is employed to solve the inverse problem using algorithms based on computational intelligence concepts. An artificial neural network (ANN) model is developed to also solve the inverse problem for delamination detection directly and to provide surrogate models integrated with optimization algorithms (the gradient-based local search and non-dominated sorting genetic algorithm-II) to contain the computationally expensive simulations by FEA. This approach is termed as surrogate assisted optimization and it is seen that the engagement of surrogate models in lieu of the FE models in the optimization loop greatly enhances the accuracy of delamination detection results within an affordable computational cost and provides control over handling different variables. Meanwhile, to aid with the building of effective surrogate models using substantial number of training datasets, K-means clustering algorithm is harnessed and this effectively reduces the large training datasets usually required for ANN training. This paper demonstrated that ANN and optimization algorithms with surrogates show immense potentialities for use in delamination damage detection scenarios. Prediction errors of the algorithms were quantified and they were shown to be satisfactory when applied to previously experimental data. The algorithms in their inverse formulations are capable of predicting accurately delamination parameters. Hence, these algorithms should be employed for application in the domain of SHM where their small computational requirements could be exploited for online damage detection.

In this paper, a new analytical model is presented to detect the presence, size, and location of a delamination embedded in a laminated composite beam. The sensors bonded on the top and bottom surfaces of a host beam are made from PZT piezoelectric layers. By employing this analytical model, the first three natural frequencies and sensor charge output distribution for the beams with different delamination length, axial and through-the-thickness delamination location, and delamination gap can be predicted, when a beam is excited by an external force. An approach is also proposed to obtain the sensor charge output distribution along the beam length using evenly distributed electrode strips. Subsequently, the present model is applied to a laminated plain weave composite beam with an embedded and through-width delamination, followed by an extensive numerical study. An investigation is carried out on the influence of the boundary condition, delamination length, axial delamination location, through-the-thickness delamination location, delamination gap on the first three natural frequency change and sensor charge output distribution along the beam length. The effects of number and size of electrode strips on the sensor charge output distribution is also studied. A comparison of the first three natural frequencies between the present predicted and finite element analysis results reveals that there is a good agreement between these two models.

In this study, the effects of location, size and number of delaminations, boundary conditions, orientation angles and stacking sequences on the natural frequency of laminated composite beams are investigated experimentally, analytically and numerically. Two-dimensional finite element models of the delaminated beams are obtained using ANSYS (Finite ElementMethod Code). The analytical method is developed using Euler–Bernoulli beam theory. Then, analytical results are compared with the results available in the literature and the numerical and experimental results in the present study. It has been seen that all results obtained are very close to each other. It is shown that the natural frequencies decrease when sizes and numbers of edge and middle delaminations in the beam increase, and the location of the delamination is also very important.The first natural frequency value of beam of [0°/90°]8 is found to be the highest as compared to the beamswith angles [30°]16 and [60°]16. However, the natural frequency values in the beams that have the angle-ply of [θ]16 are lower than those of [θ/−θ]8, [(θ/−θ)4]s and [(θ/−θ)s]4.

It is very important to monitor the occurrence of damage of various structures. By early detection of damage and by taking the proper corrective measures the failure of damage could be avoided. When damage occurs in structure it results in change in stiffness properties of the structure which in turn result in change in modal properties like natural frequency, mode shape change, mode shape curvature and strain energy of a structure. These parameters are used as an input to train the artificial neural network(ANN). The efficiency of the ANN to predict the damage at single and multiple damage cases using the change in natural frequency and strain energy was evaluated in this study. The efficiency of individual modes and combination of frequency and strain energy to detect damage is also considered in this study. The modal parameters were obtained by carrying out modal analysis using ANSYS 2021 R1 software and the ANN was developed using MATLAB software. The results indicated that the strain energy accurately predict the damage location and varies linearly with severity of damage. It is better to use combination of frequency and strain energy as indicator to detect damages.

Structural damage identification using static test data and changes in frequencies

<P>Structural health is a vital aspect of infrastructure sustainability. As a part of a vital infrastructure and transportation network, bridge structures must function safely at all times. However, due to heavier and faster moving vehicular loads and function adjustment, such as Busway accommodation, many bridges are now operating at an overload beyond their design capacity. Additionally, the huge renovation and replacement costs are a difficult burden for infrastructure owners. The structural health monitoring (SHM) systems proposed recently are incorporated with vibration-based damage detection techniques, statistical methods and signal processing techniques and have been regarded as efficient and economical ways to assess bridge condition and foresee probable costly failures. In this chapter, the recent developments in damage detection and condition assessment techniques based on vibration-based damage detection and statistical methods are reviewed. The vibration-based damage detection methods based on changes in natural frequencies, curvature or strain modes, modal strain energy, dynamic flexibility, artificial neural networks, before and after damage, and other signal processing methods such as Wavelet techniques, empirical mode decomposition and Hilbert spectrum methods are discussed in this chapter.   </P>

Vibration-based detection of skin-stiffener debonding on composite stiffened panels using surrogate-assisted algorithms

The presence of faults is common in engineering composite structures. Precise detection of faults prior to failure has been the focal point for researchers working in this domain. Detection of damage from the modal characteristics is an age-old promising technique besides the artificial intelligence techniques such as neural network (NN), Artificial neural network (ANN), recurrent neural network (RNN), and particle swarm optimization (PSO) methods. However, multiple detection techniques combined can give better results. In this regard, recurrent neural networks (RNN) and modified particle swarm optimization (mPSO) are combined to detect damages in a glass fiber reinforced polymer (GFRP) composite cantilever beam. The proposed hybrid model consists of two stages; indices of relative natural frequencies applied to locate crack parameters (position and severity) by recurrent neural network technique and optimization of the results (position and severity) by mPSO. The results illustrate this method can be implemented to predict multiple transverse cracks and their parameters in a composite beam, manifested in the change of natural frequencies where the error is limited to 0.97% only.

Securing the structural safety of blades has become crucial, owing to the increasing size and weight of blades resulting from the recent development of large wind turbines. Composites are primarily used for blade manufacturing because of their high specific strength and specific stiffness. However, in composite blades, joints may experience fractures from the loads generated during wind turbine operation, leading to deformation caused by changes in structural stiffness. In this study, 7132 debonding damage data, classified by damage type, position, and size, were selected to predict debonding damage based on natural frequency. The change in the natural frequency caused by debonding damage was acquired through finite element (FE) modeling and modal analysis. Synchronization between the FE analysis model and manufactured blades was achieved through modal testing and data analysis. Finally, the relationship between debonding damage and the change in natural frequency was examined using artificial neural network techniques.

This study presents a novel methodology that integrates piezoelectric actuation and sensing with regression models and neural networks for high-accuracy detection and localization of multiple delamination and crack defects in composite laminates. An eight-layer graphite/epoxy composite plate, instrumented with piezoelectric patches, is excited using random voltage stimuli, generating structural responses captured by sensors. The proposed framework employs six regression techniques and artificial neural networks, achieving localization accuracy with R^2 values exceeding 99.6%. Additionally, combining five signal decomposition methods with four classifiers enables defect type identification with up to 98.26% accuracy. The methodology demonstrates exceptional precision in detecting previously unseen delamination and crack defects down to the lamina level, optimized through grid search cross-validation. A comparative analysis highlights that piezoelectric sensor voltage signals outperform acceleration signals for defect characterization. This integrated piezoelectric-regression/neural network framework establishes a robust foundation for non-destructive evaluation, offering significant potential for real-time structural health monitoring applications.

Process control strategies for a steel making furnace using ANN with bayesian regularization and ANFIS

Icing condition prediction of wind turbine blade by using artificial neural network based on modal frequency

In this paper, we discuss the dynamics of beams with multiple delaminations. The objective of the study is to use the dynamic response of the delaminated beams in health monitoring of composite structures. As a first step, we present experimental results on the vibrations of a cantilever beam with multiple delaminations. These experiments are conducted by exciting the beam with piezoelectric actuators. The response is detected by using a high-speed video camera to study the existence of delamination opening modes in a beam with multiple delaminations. Then, an analysis of natural frequencies and mode shapes, for a delaminated beam, is presented by using analytical techniques. The measured dynamic responses of the beam with multiple delaminations are also presented. The experimentally detected nonlinear response is discussed. Introduction Delaminations or interlayer cracks and impact damages are typical defects observed in composite structures. The presence of these defects changes the dynamic characteristics of the structure . Some of the specific changes in the observed dynamic characteristics include changes in natural frequencies, changes in the mode shapes and changes in damping ratios. These changes can be used to identify the existence, location and magnitude of a delamination or an impact damage, before they can grow to their critical sizes. Studies, to date, are concerned with the dynamics of beams and plates with a single delamination. In this paper, we specifically discuss the structural dynamics of a beam with multiple delaminations. This information can be used to develop health-monitoring techniques for composite beams with multiple delaminations. In an earlier paper, Luo and Hanagud studied the effects of defects, like saw-cuts, impact damage and delamination, on the structural dynamic characteristics of composite beams. They have shown that perturbations in natural frequencies and modes of a beam, due to defects, can be used for health monitoring of structures. In particular, it has been shown that an integral equation that considers perturbations in curvature modes and natural frequencies can be very effectively used to detect local defects. To distinguish delaminations from other types of monitored (identified) defects Luo and Hanagud have discussed nonlinear effects like superharmonic response in the dynamic response of a harmonically excited delaminated beam. They considered only a single delamination. In this paper we study beams with multiple delaminations. More specifically, we discuss dynamic response and the changes in natural frequencies, mode shapes due to multiple delaminations in a composite beam. One of the earliest models for vibration analysis of composite beams with delaminations was proposed by Ramkumar et al. This model simply used four Timoshenko beams connected at the delamination edges to model a composite beam with one throughwidth delamination. The predicted frequencies, based on this model, were consistently lower than the results of experimental measurements. Wang et al. improved the analytical solution by including coupling between flexural and axial vibrations of the delaminated sublaminates. Using an isotropic beam with splits and the classical beam model, they found that the calculated natural frequencies were closer to experimental results. With similar considerations, Nagesh Gummadi and Hanagud formulated a finite element solution for arbitrary composite beams. In the finite element models, they considered a classical composite beam model as well as the beam model with high order shear deformations. Mujumdar and Suryanarayan have proposed a model which imposed a constraint between the delaminated sublaminates to force them to have the same flexural displacement. This model was unable to * Ph.D. Student, School of Aerospace Engineering † Professor, School of Aerospace Engineering, AIAA Member Copyright © 1999 The American Institute of Aeronautics and Astronautics Inc. All rights reserved

A study was initiated to predict water quality index (WQI) using artificial neural networks (ANNs) with respect to the concentrations of 16 groundwater quality variables collected from 47 wells and springs in Andimeshk during 2006–2013 by the Iran’s Ministry of Energy. Such a prediction has the potential to reduce the computation time and effort and the possibility of error in the calculations. For this purpose, three ANN’s algorithms including ANNs with early stopping, Ensemble of ANNs and ANNs with Bayesian regularization were utilized. The application of these algorithms for this purpose is the first study in its type in Iran. Comparison among the performance of different methods for WQI prediction shows that the minimum generalization ability has been obtained for the Bayesian regularization method (MSE = 7.71) and Ensemble averaging method (MSE = 9.25), respectively and these methods showed the minimum over-fitting problem compared with that of early stopping method. The correlation coefficients between the predicted and observed values of WQI were 0.94 and 0.77 for the test and training data sets, respectively indicating the successful prediction of WQI by ANNs through Bayesian regularization algorithm. A sensitivity analysis was implemented to show the importance of each parameter in the prediction of WQI during ANN’s modeling and showed that parameters like Phosphate and Fe are the most influential parameters in the prediction of WQI.