arXiv subjects

Mathias Kersemans

Publications and source records attributed to Mathias Kersemans.

6 recordsLinked to original sources

arXiv2024

k-space Physics-informed Neural Network (k-PINN) for Compressed Spectral Mapping and Efficient Inversion of Vibrations in Thin Composite Laminates

The vibrational response of structural components carries valuable information about their underlying mechanical properties, health status and operational conditions. This underscores the need for the development of efficient physics-based inversion algorithms which, given a limited set of sensing data points and in the presence of measurement noise, can reconstruct the response at locations where measurement data is not available and/or identify the unknown mechanical properties. Addressing this challenge, Physics-Informed Neural Networks (PINNs) have emerged as a promising approach. PINNs seamlessly integrate governing equations into their architecture and have gained significant interest in solving inversion problems. In the context of learning and inversion of multimodal, multiscale vibrational responses, this paper introduces a novel spectral extension of PINNs, utilizing Fourier basis functions in the wavenumber domain, commonly known as k-space. The proposed k-space PINN (k-PINN), offers a robust framework for adjusting complexity and wavenumber composition of the response. Notably, the spectral formulation of k-PINN, coupled with the generally sparse representation of vibrations in k-space, facilitate efficient reconstruction and learning of broadband vibrations and alleviate the spectral bias associated with standard PINN. Additionally, the spectral solution space introduced by k-PINN substantially reduces the computational cost associated with computing physics-informed loss terms. We evaluate the effectiveness of the proposed methodology on reconstructing the bending vibrational mode shapes of a thin composite laminate and identifying its effective bending stiffness coefficients. It is shown that the proposed k-PINN methodology outperforms the standard PINN in terms of both learning and computational efficiency.

physics.app-ph↗

arXiv2021

Vibrational quality classification of metallic turbine blades under measurement uncertainty

Non-destructive testing on metallic turbine blades is a challenging task due to their complex geometry. Vibrational test-ing such as Process Compensated Resonance Testing (PCRT) has shown an efficient approach, which first measures the vibrational response of the turbine blades, and then employs a classifier to determine if the quality of the turbine blades are good or bad. Our previous work mainly concentrated on the development of Mahalanobis distance-based classifiers which are fed by the measured vibrational features (such as resonant frequencies). In practice, however, measurement errors could lead to a biased trained classifier, potentially resulting in the wrong quality classifications of the turbine blade. In this study, we investigate the classification problem of turbine blades under measurement uncertainty. For this, the concept of Interval Mahalanobis Space is employed, leading to the Integrated Interval Mahalanobis Classification system (IIMCS) classifier which has high robustness against measurement uncertainty. The IIMCS employs Binary Particle Swarm Optimization (BPSO) to filter out those resonant frequencies which contrib-ute most to the information in the system. A Monte Carlo Simulation scheme is employed to analyze the sensitivity of the resonant frequencies to the measurement uncertainty. This yields an indicator of reliability, indicating the confidence level of the final classification results. The developed IIMCS methodology is applied to an experimental case study of equiaxed nickel alloy first-stage turbine blades, showing good and robust classification performance.

physics.data-an↗

arXiv2021

CNN-DST: ensemble deep learning based on Dempster-Shafer theory for vibration-based fault recognition

Nowadays, using vibration data in conjunction with pattern recognition methods is one of the most common fault detection strategies for structures. However, their performances depend on the features extracted from vibration data, the features selected to train the classifier, and the classifier used for pattern recognition. Deep learning facilitates the fault detection procedure by automating the feature extraction and selection, and classification procedure. Though, deep learning approaches have challenges in designing its structure and tuning its hyperparameters, which may result in a low generalization capability. Therefore, this study proposes an ensemble deep learning framework based on a convolutional neural network (CNN) and Dempster-Shafer theory (DST), called CNN-DST. In this framework, several CNNs with the proposed structure are first trained, and then, the outputs of the CNNs selected by the proposed technique are combined by using an improved DST-based method. To validate the proposed CNN-DST framework, it is applied to an experimental dataset created by the broadband vibrational responses of polycrystalline Nickel alloy first-stage turbine blades with different types and severities of damage. Through statistical analysis, it is shown that the proposed CNN-DST framework classifies the turbine blades with an average prediction accuracy of 97.19%. The proposed CNN-DST framework is benchmarked with other state-of-the-art classification methods, demonstrating its high performance. The robustness of the proposed CNN-DST framework with respect to measurement noise is investigated, showing its high noise-resistance. Further, bandwidth analysis reveals that most of the required information for detecting faulty samples is available in a small frequency range.

eess.SP↗

arXiv2021

A novel multi-classifier information fusion based on Dempster-Shafer theory: application to vibration-based fault detection

Achieving a high prediction rate is a crucial task in fault detection. Although various classification procedures are available, none of them can give high accuracy in all applications. Therefore, in this paper, a novel multi-classifier fusion approach is developed to boost the performance of the individual classifiers. This is acquired by using Dempster-Shafer theory (DST). However, in cases with conflicting evidences, the DST may give counter-intuitive results. In this regard, a preprocessing technique based on a new metric is devised in order to measure and mitigate the conflict between the evidences. To evaluate and validate the effectiveness of the proposed approach, the method is applied to 15 benchmarks datasets from UCI and KEEL. Further, it is applied for classifying polycrystalline Nickel alloy first-stage turbine blades based on their broadband vibrational response. Through statistical analysis with different noise levels, and by comparing with four state-of-the-art fusion techniques, it is shown that that the proposed method improves the classification accuracy and outperforms the individual classifiers.

cs.LG↗

arXiv2020

An ensemble classifier for vibration-based quality monitoring

Vibration-based quality monitoring of manufactured components often employs pattern recognition methods. Albeit developing several classification methods, they usually provide high accuracy for specific types of datasets, but not for general cases. In this paper, this issue has been addressed by developing a novel ensemble classifier based on the Dempster-Shafer theory of evidence. To deal with conflicting evidences, three remedies are proposed prior to combination: (i) selection of proper classifiers by evaluating the relevancy between the predicted and target outputs, (ii) devising an optimization method to minimize the distance between the predicted and target outputs, (iii) utilizing five different weighting factors, including a new one, to enhance the fusion performance. The effectiveness of the proposed framework is validated by its application to 15 UCI and KEEL machine learning datasets. It is then applied to two vibration-based datasets to detect defected samples: one synthetic dataset generated from the finite element model of a dogbone cylinder, and one real experimental dataset generated by collecting broadband vibrational response of polycrystalline Nickel alloy first-stage turbine blades. The investigation is made through statistical analysis in presence of different levels of noise-to-signal ratio. Comparing the results with those of four state-of-the-art fusion techniques reveals the good performance of the proposed ensemble method.

cs.CV↗

arXiv2020

Vibro-Thermal Wave Radar: Application of Barker coded amplitude modulation for enhanced low-power vibrothermographic inspection of composites

This paper investigates the performance of the thermal wave radar imaging technique in low-power vibrothermography, so-called vibro-thermal wave radar (VTWR), for non-destructive inspection of composites. VTWR is applied by binary phase modulation of the vibrational excitation using a 5 bit Barker coded waveform, followed by matched filtering of the thermal response. The depth resolvability of VTWR is analyzed by a 1D analytical formulation in which defects are modeled as subsurface heating sources. The obtained results reveal the outperformance of VTWR compared to the classical lock-in vibrothermography (LVT), i.e. a sinusoidal amplitude modulation. Furthermore, the VTWR technique is experimentally demonstrated on a 5.5 mm thick carbon fiber reinforced polymer coupon with barely visible impact damage. A local defect resonance frequency of a backside delamination is selected as the vibrational carrier frequency. This allows for implementing VTWR in the low-power regime (input power < 1 Watt). It is shown that the Barker coded amplitude modulation and the resultant pulse compression efficiency lead to an increased probing depth, and can fully resolve the deep backside delamination. It is also shown that VTWR approach allows depth-selective imaging of defects through the lag of the compressed pulse.

physics.app-ph↗