Prediction Of Delamination Research Articles

Stacked generalization ensemble learning strategy for multivariate prediction of delamination and maximum thrust force in composite drilling

The complexity of drilling carbon fiber reinforced polymers (CFRP) requires accurate predictive models. This study addresses the challenge using an ensemble machine learning (ML) approach with stacked generalization. The model captures the relationships between key input variables—such as graphene nanoplatelet (GNP) content, ultrasonic assistance, tool type, stacking sequence, and feed rate—and output parameters, specifically thrust force and delamination. A nested feature scoring (NFS) method was employed for importance analysis, revealing tooling type and feed rate as key features for minimizing delamination and reducing thrust force, respectively. The machinability results revealed that ultrasonic drilling lowered thrust force by improving chip evacuation and reducing fiber breakage. HSS tools with cobalt content, alongside symmetrical stacking sequence, helped to further minimize both thrust force and delamination. However, the inclusion of GNPs led to an increase in thrust force and delamination, attributed to the increased strength of the CFRP/GNP composite. The process involved meticulous training, resulting in four optimal-fit models serving as inputs for the stacked meta-model. Iterative enhancements fortified the ensemble robustness, with fine-tuning of hyperparameters through Bayesian optimization. The ensemble superiority over individual models manifested in a remarkable reduction of mean absolute error (MAE) and root mean squared error (RMSE) by up to 97% and 124% for delamination, and 205% and 154% for thrust force, compared to the best base learner. Visual and statistical assessments effectively illuminated the intricate interactions between variables in the drilling process. The methodology resulted in a highly adaptable predictive model with applications across diverse manufacturing contexts.

Predicting delamination in composite laminates through semi-analytical dynamic analysis and vibration-based quantitative assessment

Delamination is a frequent failure mode of laminated fiber-reinforced polymer (FRP) composites structure in aeronautical and other industries, leading to changes in vibration characteristics. Vibration-based techniques evaluate and compare the dynamic response between damaged and undamaged structures, and guarantee the non-destructive measurement with reliability and repeatability. Previous studies typically concentrate on using finite element method to obtain vibration characteristics and enhance the database for intelligent algorithms. This paper presents a semi-analytical result using the Chebyshev−Ritz method to expand delamination prediction. Vibration frequency serves as a global damage indicator, and multi-order frequency characteristics are utilized to identify the delamination length and location of FRP composite plates. A database of natural frequencies corresponding to damage parameters for FRP laminated plates is generated based on the established model using the region approach. An intelligent approach, known as a genetic algorithm optimization-based back-propagation (GA-BP) artificial neural network, is utilized for system identification. The network model is subjected to a sensitivity analysis, where artificial noise is added to vibration frequency to distinguish between the actual structure and the numerical model. The results indicate that the GA-BP algorithm shows good accuracy and stable performance against the standard neural networks for delamination analysis.

A simulation strategy for fatigue modeling of delamination in composite structures under multiple loading conditions considering loading history and [formula omitted]-curve effects

This work evaluates the ability of cohesive zone modeling-based approaches to predict delamination in composite materials that develop large process zones under complex loading conditions. The R-curve effects subjected to static and fatigue loading under multiple loading modes, considering the loading history, are analyzed. To this end, the delamination predictions of a state-of-the-art CZM-based simulation strategy are evaluated by blind simulation of a validation benchmark test. The validation test promotes a non-self-similar delamination scenario, including a process zone that evolves under different loading mode conditions with a non-straight leading delamination front. Good delamination prediction accuracy is achieved. In addition, insights into the relationship between the features of the simulation strategy and the physics of the delamination process are discussed. With regard to the limitations of the simulation strategy, particular attention should be paid to modeling the contribution of an evolving process zone based on the loading mode history.

Vibration-based detection of non-overlapping delaminations in FRP beams using frequency shifts

Extensive research has been carried out on the detection of single delamination in fibre-reinforced polymer (FRP) structures using different structural health monitoring (SHM) approaches, including the vibration-based assessment methods. However, there are limited studies that on the detection of multiple delaminations, which could occur in many real-world scenarios. To address this research gap, this paper aims at developing a vibration-based method to assess the two non-overlapping delaminations in FRP beams based on changes in natural frequencies. A theoretical model of vibrating FRP beams with two non-overlapping delaminations was constructed and used for generating the multiple frequencies of the delaminated beams. By analysing the frequency shifts of the FRP beams before and after the occurrence of damage, the delamination characteristics (location and severity) can be inversely predicted using optimisation algorithms. The accuracy and efficiency of the frequency-based inverse algorithm were verified experimentally by modal testing on FRP beam specimens with one and two non-overlapping delaminations. It is interesting to observe that using the proposed vibration-based method, the single delamination in FRP specimens can also be predicted as two non-overlapping delaminations, with a major one matching the original single delamination and a minor one that can be neglected. Thus, the current vibration-based delamination assessment approach is flexible in identifying the prediction of either single or double non-overlapping delaminations in FRP beams, and therefore, it potentially has wider applicability than the existing single delamination detection methods.

Structural health monitoring of aircraft through prediction of delamination using machine learning.

Structural health monitoring (SHM) is a regular procedure of monitoring and recognizing changes in the material and geometric qualities of aircraft structures, bridges, buildings, and so on. The structural health of an airplane is more important in aerospace manufacturing and design. Inadequate structural health monitoring causes catastrophic breakdowns, and the resulting damage is costly. There is a need for an automated SHM technique that monitors and reports structural health effectively. The dataset utilized in our suggested study achieved a 0.95 R2 score earlier. The suggested work employs support vector machine (SVM) + extra tree + gradient boost + AdaBoost + decision tree approaches in an effort to improve performance in the delamination prediction process in aircraft construction. The stacking ensemble method outperformed all the technique with 0.975 R2 and 0.023 RMSE for old coupon and 0.928 R2 and 0.053 RMSE for new coupon. It shown the increase in R2 and decrease in root mean square error (RMSE).

Expression of concern: “Effect of friction and shear strength enhancement on delamination prediction”

Expression of concern: “Effect of friction and shear strength enhancement on delamination prediction”

Understanding and mitigating delamination in composite materials: A comprehensive review

Delamination significantly undermines the integrity and performance of composite materials, impacting their application in engineering structures. This comprehensive review synthesizes current research on the mechanisms of delamination in composite materials, with a focus on identifying critical factors contributing to this failure mode. It also examines recent advances in detection, prediction, and mitigation strategies. Key findings include the identification of manufacturing processes, moisture absorption, and mechanical loading as primary initiators of delamination. Additionally, innovative methodologies for delamination prediction and prevention are highlighted, showcasing advancements in experimental techniques and computational modeling. This review underscores the importance of understanding delamination to enhance the durability and reliability of composite structures. This analysis aims to guide future research directions and inform the development of more resilient composite structures.

Multimodal 1D CNN for delamination prediction in CFRP drilling process with industrial robots

There is a growing demand for carbon fiber-reinforced plastics (CFRPs) in the aerospace and automotive industries. Consequently, the assembly and repair of CFRP components has garnered considerable attention. However, at industrial sites, there are potential difficulties in the CFRP drilling process. These challenges arise from the anisotropic properties of CFRP and the limitations of using an optical microscope to assess the quality of millions of drilled holes. Therefore, this study introduced an advanced indirect prediction method for the CFRP hole quality based on multisensor data. During the drilling process, data including force, torque, acceleration, voltage, current, sound, and images of the hole exits were acquired via a robotic machining system. The delamination factors, Fd and Fa, which quantify the quality of the hole, can be calculated from the hole images. Preprocessing was employed to segment the sensor data into discrete drilling trials and extract spectral features from the data. This paper proposed a multimodal one-dimensional convolutional neural network (1D CNN) that predicts delamination factors from time series multi-sensor data. A case study, using a test set of 100 trials, validated the proposed model. The performance of the proposed model was evaluated by the mean squared error (MSE) and inference time, yielding 8.42 ± 0.167 × 10−2 and 3.48 ± 0.192 s for Fd, and 6.1 ± 0.729 × 10−2 and 3.13 ± 0.098 s for Fa, respectively, across the entire test set with 100 trials. This result exceeds those of previous studies in terms of both the MSE value and inference time for multimodality, emphasizing the predictive accuracy and real-time operational capabilities of the proposed model in industrial settings. Furthermore, this approach provides practicality and flexibility, facilitating the easy integration or removal of sensors through data-driven preprocessing and a multimodal learning scheme.

Model-experiment comparison of quasi static loading on a composite overwrap pressure vessel (Part 2)

A methodology to develop a 3D Finite Element (FE) model of a full metal-lined Composite Overwrapped Pressure Vessel (COPV) was developed and is presented in this paper. The model is intended for prediction of the metal-composite delamination and residual dent depth developed in the metal liner as a result of quasi-static indentation loading. Cohesive elements are used to model the composite and the metal-composite interfaces. Experimental and numerical comparisons of force–displacement curves, delamination area and residual dent depth are presented. Numerical results are in good agreement to the experimental data.

Modelling of Mode I delamination using a stress intensity factor enhanced cohesive zone model

Cohesive zone modelling is a common approach to capture delamination in composite laminate structures. Recent experimental advancements now enable the direct measurement of Mode I traction-separation responses (TSRs) from a single specimen using the composite rigid double cantilever beam (cRDCB), overcoming a major obstacle in using cohesive zone modelling to model delamination. However, TSRs measured experimentally with the cRDCB specimen capture damage response as well as the stiffness contribution of the adjacent laminae, which can introduce significant artificial compliance into numerical models when modelling delamination separately from intralaminar behaviour. A two-stage analysis procedure utilizing a crack tip compensation function is presented to enhance the TSRs measured with the cRDCB specimen to accurately model Mode I delamination. The analysis procedure is demonstrated to improve the accuracy of delamination prediction within the statistical variation of published experimental data. Furthermore, the transferability of TSRs measured with cRDCB specimens is explored using available experimental DCB data. It is shown that the onset of damage and early damage behaviours measured with the cRDCB specimen appear to be transferable between geometries, whilst large-scale damage mechanics remain geometry dependent.

Review and Assessment of Fatigue Delamination Damage of Laminated Composite Structures.

Fatigue delamination damage is one of the most important fatigue failure modes for laminated composite structures. However, there are still many challenging problems in the development of the theoretical framework, mathematical/physical models, and numerical simulation of fatigue delamination. What is more, it is essential to establish a systematic classification of these methods and models. This article reviews the experimental phenomena of delamination onset and propagation under fatigue loading. The authors reviewed the commonly used phenomenological models for laminated composite structures. The research methods, general modeling formulas, and development prospects of phenomenological models were presented in detail. Based on the analysis of finite element models (FEMs) for laminated composite structures, several simulation methods for fatigue delamination damage models (FDDMs) were carefully classified. Then, the whole procedure, range of applications, capability assessment, and advantages and limitations of the models, which were based on four types of theoretical frameworks, were also discussed in detail. The theoretical frameworks include the strength theory model (SM), fracture mechanics model (FM), damage mechanics model (DM), and hybrid model (HM). To the best of the authors' knowledge, the FDDM based on the modified Paris law within the framework of hybrid fracture and damage mechanics is the most effective method so far. However, it is difficult for the traditional FDDM to solve the problem of the spatial delamination of complex structures. In addition, the balance between the cost of acquiring the model and the computational efficiency of the model is also critical. Therefore, several potential research directions, such as the extended finite element method (XFEM), isogeometric analysis (IGA), phase-field model (PFM), artificial intelligence algorithm, and higher-order deformation theory (HODT), have been presented in the conclusions. Through validation by investigators, these research directions have the ability to overcome the challenging technical issues in the fatigue delamination prediction of laminated composite structures.

NUMERICAL AND ANALYTICAL PREDICTION OF THE PROPAGATION OF DELAMINATION OF BONDED COMPOSITE REPAIR PLATES UNDER MECHANICAL LOADING

This study presents a numerical and analytical prediction of delamination of a repaired joint due to a defect in the composite under tensile loading. The three-dimensional finite element method is used to predict the delamination of a repaired plate with the VCCT method. The effects of the position of the delamination, percentage of the delaminated area, thickness and properties of the patch are presented. It can be noted that the propagation of delamination is significant only at node A and the analyzed model delaminated in mode I. The numerical results are in good agreement compared with the analytical solution found in the literature. It can be seen that the stiffness of the reinforcement material is strongly dependent on the mechanical properties of the patch interface. These results make it possible to choose the carbon/epoxy patch for the repair even if the graphite/epoxy has a high modulus of elasticity. The thickness and the mechanical properties parameter have a significant effect on increasing the durability of the structure.

Prediction and Regulation of Delamination at Flexible Film/Finite-Thickness-Substrate Structure Interfaces

Prediction and Regulation of Delamination at Flexible Film/Finite-Thickness-Substrate Structure Interfaces

An adaptive modelling approach using a novel modified AOA/SVR for prediction of drilling-induced delamination in CFRP/Ti stacks

Delamination is the most critical damage in drilling the CFRP/Ti stacks under the impact of drilling parameters and tool structure, which makes the traditional theoretical or empirical models not have enough accuracy and be time-consuming due to the multi variables, while the machine learning model would suffer the unsuitable hyper-parameters and have a bad accuracy and generalization ability. This paper proposed an adaptive modelling approach to predict the delamination while drilling the CFRP/Ti stacks. This approach adapted the original arithmetic optimization algorithm (AOA) by adding a random disturbance phase to update the penalty coefficient C and the kernel coefficient γ of the support vector regression (SVR) automatically. In the meanwhile, the approach made use of the energy of the 5 stages in drilling the CFRP/Ti stacks and predicted the delamination damage both at the entrance and exit. The modified AOA optimized the training mean squared error(MSE) in predicting the entrance and exit delamination by 10.27 % and 33.63 %, while the accuracy of the proposed model can reach 96.7 % and 97.17 % respectively. The model got validated, and had a comprehensive ability containing the accuracy and generalization ability.

Effect of Cohesive Properties on Low-Velocity Impact Simulations of Woven Composite Shells

The effect of the interface stiffness and interface strength on the low-velocity impact response of woven-fabric semicylindrical composite shells is studied using finite element (FE) models generated with continuum shell elements and cohesive surfaces. The intralaminar damage is accounted for using the constitutive model provided within the ABAQUS software, while the interlaminar is addressed utilising cohesive surfaces. The results show that the interface stiffness has a negligible effect on the force and energy histories for values between 101 N/mm3 and 2.43 × 106 N/mm3. However, it has a significant impact on the delamination predictions. It is observed that only the normal interface strength affects the maximum impact force and the delamination predictions. Increasing its value from 15 MPa to 30 MPa resulted in an 8% growth in the maximum force, and a substantial reduction in the delaminated area. The obtained results serve as guidelines for the accurate and efficient computation of delamination. The successful validation of the FE models establishes a solid foundation for further numerical investigations and offers the potential to significantly reduce the time and expenses associated with experimental testing.

Theoretical study about influence of geometry and mechanical load on the delamination in tungsten disulfide/poly(methyl methacrylate) nanocomposite structure under axial load

The influence of the geometry and the magnitude of axially applied mechanical load on the delamination in three-layer tungsten disulphide (WS2)/SU-8/poly(methyl methacrylate) (PMMA) nanocomposite, is investigated theoretically. First, for considered nanostructures with thinner and thicker PMMA layer two different analytical solutions (Case 1 and Case 2) for the interface shear stress (ISS) in the middle layer of the structure are obtained, based on the application of two-dimensional stress-function method and minimization of the strain energy. Second, the theoretical criterion for delamination in the interface layer, based on the model ISS, is formulated and the obtained non-linear equation in respect to debond length is solved numerically, for both solutions, at different values of mechanical load and geometry of the structure layers. It was found that delamination doesn't appear at fixed WS2 length of 10 μm, if the loading is up to 5 GPa for Case 1 and up to 1.175 GPa for Case 2, respectively. With increasing WS2 length, the delamination occurs at increasingly higher values of the applied external load, for Case 2. For Case 1 a delamination is not occurs. At fixed applied load, it was found for Case 2, that as the length of WS2 increases, the debonding length increases, too. The obtained results could be used for fast prediction of delamination in similar nanostructured devices.

Support Vector Regression approach for prediction of delamination at entry and exit during drilling of GFRP Composites

The demand for Composites in the modern era have increased immensely due to its vast applications and superior properties over conventional materials. Glass Fibre Reinforced Plastic (GFRP) is one of the economic alternative to conventional engineering materials due to its high specific modulus of elasticity, high specific strength, good corrosion resistance, high fatigue strength and lightweight. Components made out from GFRP composites are usually near net shaped and require holes for assembly integration. Drilling is an important process as concentrated forces can cause major damage to the composite. Drilling of GFRP causes various damage such as thermal degradation, fibre breakage, matrix cracking and delamination. A substantial damage is caused by delamination which can occur both on the entry and exit sides of the composite, exit side delamination considered more severe. Therefore, selection of proper process parameters during drilling operation is very much essential. In the present work, a support vector regression (SVR) model is developed to predict the delamination at entry and exit during the drilling of GFRP composites. The model is developed based on the data obtained from experimentation. The model accuracy is evaluated by the three performance criteria including root mean square error (RMSE), Nash–Sutcliffe efficiency co-efficient (E) and co-efficient of determination (R2). The model provides an inexpensive and time saving alternative to study the delamination at entry and exit of the GFRP composite actual drilling operation.

Artificial neural network based delamination prediction in composite plates using vibration signals

Dynamic loading on composite components may induce damages such as cracks, delaminations, etc. and development of an early damage detection technique for delaminations is one of the most important aspects in ensuring the integrity and safety of composite components. The presence of damages such as delaminations on the composites reduces its stiffness and further changes the dynamic behaviour of the structures. As the loss in stiffness leads to changes in the natural frequencies, mode shapes, and other aspects of the structure, vibration analysis may be the ideal technique to employ in this case. In this research work, the supervised feed-forward multilayer back-propagation Artificial Neural Network (ANN) is used to determine the position and area of delaminations in GFRP plates using changes in natural frequencies as inputs. The natural frequencies were obtained by finite element analysis and results are validated by experimentation. The findings show that the suggested technique can satisfactorily estimate the location and extent of delaminations in composite plates.

Stochastic modeling of inhomogeneities in the aortic wall and uncertainty quantification using a Bayesian encoder–decoder surrogate

Inhomogeneities in the aortic wall can lead to localized stress accumulations, possibly initiating dissection. In many cases, a dissection results from pathological changes such as fragmentation or loss of elastic fibers. But it has been shown that even the healthy aortic wall has an inherent heterogeneous microstructure. Some parts of the aorta are particularly susceptible to the development of inhomogeneities due to pathological changes, however, the distribution in the aortic wall and the spatial extent, such as size, shape and type, are difficult to predict. Motivated by this observation, we describe the heterogeneous distribution of elastic fiber degradation in the dissected aortic wall using a stochastic constitutive model. For this purpose, random field realizations, which model the stochastic distribution of degraded elastic fibers, are generated over a non-equidistant grid. The random field then serves as input for a uniaxial extension test of the pathological aortic wall, solved with the finite element method. To include the microstructure of the dissected aortic wall, a constitutive model developed in a previous study is applied, which also includes an approach to model the degradation of interlamellar elastic fibers. To then assess the uncertainty in the output stress distribution due to the proposed stochastic constitutive model, a convolutional neural network, specifically a Bayesian encoder–decoder, was used as a surrogate model that maps the random input fields to the output stress distribution obtained from the finite element analysis. The results show that the neural network is able to predict the stress distribution of the finite element analysis while also significantly reducing the computational time. In addition, this provides the probability for exceeding certain rupture stresses within the aortic wall, which could allow for the prediction of delamination or fatal rupture.

Experimental analysis and prediction of CFRP delamination caused by ice impact

The delamination of Carbon Fiber Reinforced Polymer (CFRP) laminates under ice impact is a common damage feature, and it intensely threatens engineering application. However, the delamination mechanism and the prediction are extremely challenging to clarify, due to the complexity of the dynamic response of anisotropic CFRP laminates under ice impact. In this study, systematic experimental studies of CFRP laminates impacted by ice balls and C-scan non-destructive detection are performed to elucidate the delamination mechanism. To this end, multiple CFRP laminates of different thicknesses (2.4 mm and 3.6 mm) are manufactured, and then impacted by ice balls of different diameters (30 mm and 50 mm) using a gas gun system, where the ice balls are frozen with distilled water and the impact velocities vary from 46 m/s to 152 m/s. At last, a non-consistent deformation mechanism of CFRP delamination is proposed to explain the mesoscopic delamination behaviors via dynamic deformation analysis of CFRP laminates, and it is validated by the experimental results. Furthermore, the delamination prediction of CFRP laminates is obtained using the non-consistent deformation mechanism and a corresponding prediction model. This study can contribute to understand and efficiently predict the delamination of CFRP laminates under low-energy ice impact.