Genetic justification of COVID-19 patient outcomes using DERGA, a novel data ensemble refinement greedy algorithm.

Complement inhibition has shown promise in various disorders, including COVID-19. A prediction tool including complement genetic variants is vital. This study aims to identify crucial complement-related variants and determine an optimal pattern for accurate disease outcome prediction. Genetic data from 204 COVID-19 patients hospitalized between April 2020 and April 2021 at three referral centres were analysed using an artificial intelligence-based algorithm to predict disease outcome (ICU vs. non-ICU admission). A recently introduced alpha-index identified the 30 most predictive genetic variants. DERGA algorithm, which employs multiple classification algorithms, determined the optimal pattern of these key variants, resulting in 97% accuracy for predicting disease outcome. Individual variations ranged from 40 to 161 variants per patient, with 977 total variants detected. This study demonstrates the utility of alpha-index in ranking a substantial number of genetic variants. This approach enables the implementation of well-established classification algorithms that effectively determine the relevance of genetic variants in predicting outcomes with high accuracy.

Early prediction of COVID-19 outcome using artificial intelligence techniques and only five laboratory indices.

We aimed to develop a prediction model for intensive care unit (ICU) hospitalization of Coronavirus disease-19 (COVID-19) patients using artificial neural networks (ANN). We assessed 25 laboratory parameters at first from 248 consecutive adult COVID-19 patients for database creation, training, and development of ANN models. We developed a new alpha-index to assess association of each parameter with outcome. We used 166 records for training of computational simulations (training), 41 for documentation of computational simulations (validation), and 41 for reliability check of computational simulations (testing). The first five laboratory indices ranked by importance were Neutrophil-to-lymphocyte ratio, Lactate Dehydrogenase, Fibrinogen, Albumin, and D-Dimers. The best ANN based on these indices achieved accuracy 95.97%, precision 90.63%, sensitivity 93.55%. and F1-score 92.06%, verified in the validation cohort. Our preliminary findings reveal for the first time an ANN to predict ICU hospitalization accurately and early, using only 5 easily accessible laboratory indices.

Embedded Ultrasonic Inspection on the Mechanical Properties of Cold Region Ice under Varying Temperatures.

The mechanical properties of ice in cold regions are significantly affected by the variation in temperature. The existing methods to determine ice properties commonly rely on one-off and destructive compression and strength experiments, which are unable to acquire the varying properties of ice due to temperature variations. To this end, an embedded ultrasonic system is proposed to inspect the mechanical properties of ice in an online and real-time mode. With this system, ultrasonic experiments are conducted to testify to the validity of the system in continuously inspecting the mechanical properties of ice and, in particular, to verify its capabilities to obtain ice properties for various temperature conditions. As an extension of the experiment, an associated refined numerical model is elaborated by mimicking the number, size, and agglomeration of bubbles using a stochastic distribution. This system can continuously record the wave propagation velocity in the ice, giving rise to ice properties through the intrinsic mechanics relationship. In addition, this model facilitates having insights into the effect of properties, e.g., porosity, on ice properties. The proposed embedded ultrasonic system largely outperforms the existing methods to obtain ice properties, holding promise for developing online and real-time monitoring techniques to assess the ice condition closely related to structures in cold regions.

Color Recurrence Plots for Bearing Fault Diagnosis.

This paper presents bearing fault diagnosis using the image classification of different fault patterns. Feature extraction for image classification is carried out using a novel approach of Color recurrence plots, which is presented for the first time. Color recurrence plots are created using non-linear embedding of the vibration signals into delay coordinate space with variable time lags. Deep learning-based image classification is then performed by building the database of the extracted features of the bearing vibration signals in the form of Color recurrence plots. A Series of computational experiments are performed to compare the accuracy of bearing fault classification using Color recurrence plots. The standard bearing vibration dataset of Case Western Reserve University is used for those purposes. The paper demonstrates the efficacy and the accuracy of a new and unique approach of scalar time series extraction into two-dimensional Color recurrence plots for bearing fault diagnosis.

Preisach Elasto-Plastic Model for Mild Steel Hysteretic Behavior-Experimental and Theoretical Considerations.

The Preisach model already successfully implemented for axial and bending cyclic loading is applied for modeling of the plateau problem for mild steel. It is shown that after the first cycle plateau disappears an extension of the existing Preisach model is needed. Heat dissipation and locked-in energy is calculated due to plastic deformation using the Preisach model. Theoretical results are verified by experiments performed on mild steel S275. The comparison of theoretical and experimental results is evident, showing the capability of the Presicah model in predicting behavior of structures under cyclic loading in the elastoplastic region. The purpose of this paper is to establish a theoretical background for embedded sensors like regenerated fiber Bragg gratings (RFBG) for measurement of strains and temperature in real structures. In addition, the present paper brings a theoretical base for application of nested split-ring resonator (NSRR) probes in measurements of plastic strain in real structures.

Identification of Multiple Cracks in Composite Laminated Beams Using Perturbation to Dynamic Equilibrium.

Identification of cracks in beam-type components is significant to ensure the safety of structures. Among the approaches relying on mode shapes, the concept of transverse pseudo-force (TPF) has been well proved for single and multiple crack identification in beams made of isotropic materials; however, there is a noticeable gap between the concept of TPF and its applications in composite laminated beams. To fill this gap, an enhanced TPF approach that relies on perturbation to dynamic equilibrium is proposed for the identification of multiple cracks in composite laminated beams. Starting from the transverse equation of motion, this study formulates the TPF in a composite laminated beam for the identification of multiple cracks. The capability of the approach is numerically verified using the FE method. The applicability of the approach is experimentally validated on a carbon fiber-reinforced polymer laminated beam with three cracks, the mode shapes of which are acquired through non-contact vibration measurement using a scanning laser vibrometer. In particular, a statistic manner is utilized to enable the approach to be feasible to real scenarios in the absence of material and structural information; besides, an integrating scheme is utilized to enable the approach to be capable of identifying cracks even in the vicinity of nodes of mode shapes.

Seismic Damage Identification Method for Curved Beam Bridges Based on Wavelet Packet Norm Entropy.

Curved beam bridges, whose line type is flexible and beautiful, are an indispensable bridge type in modern traffic engineering. Nevertheless, compared with linear bridges, curved beam bridges have more complex internal forces and deformation due to the curvature; therefore, this type of bridge is more likely to suffer damage in strong earthquakes. The occurrence of damage reduces the safety of bridges, and can even cause casualties and property loss. For this reason, it is of great significance to study the identification of seismic damage in curved beam bridges. However, there is currently little research on curved beam bridges. For this reason, this paper proposes a damage identification method based on wavelet packet norm entropy (WPNE) under seismic excitation. In this method, wavelet packet transform is adopted to highlight the damage singularity information, the Lp norm entropy of wavelet coefficient is taken as a damage characteristic factor, and then the occurrence of damage is characterized by changes in the damage index. To verify the feasibility and effectiveness of this method, a finite element model of Curved Continuous Rigid-Frame Bridges (CCRFB) is established for the purposes of numerical simulation. The results show that the damage index based on WPNE can accurately identify the damage location and characterize the severity of damage; moreover, WPNE is more capable of performing damage location and providing early warning than the method based on wavelet packet energy. In addition, noise resistance analysis shows that WPNE is immune to noise interference to a certain extent. As long as a series of frequency bands with larger correlation coefficients are selected for WPNE calculation, independent noise reduction can be achieved.

Structural Damage Identification Based on Integrated Utilization of Inverse Finite Element Method and Pseudo-Excitation Approach.

The attempt to integrate the applications of conventional structural deformation reconstruction strategies and vibration-based damage identification methods is made in this study, where, more specifically, the inverse finite element method (iFEM) and pseudo-excitation approach (PE) are combined for the first time, to give rise to a novel structural health monitoring (SHM) framework showing various advantages, particularly in aspects of enhanced adaptability and robustness. As the key component of the method, the inverse finite element method (iFEM) enables precise reconstruction of vibration displacements based on measured dynamic strains, which, as compared to displacement measurement, is much more adaptable to existing on-board SHM systems in engineering practice. The PE, on the other hand, is applied subsequently, relying on the reconstructed displacements for the identification of structural damage. Delamination zones in a carbon fibre reinforced plastic (CFRP) laminate are identified using the developed method. As demonstrated by the damage detection results, the iFEM-PE method possesses apparently improved accuracy and significantly enhanced noise immunity compared to the original PE approach depending on displacement measurement. Extensive parametric study is conducted to discuss the influence of a variety of factors on the effectiveness and accuracy of damage identification, including the influence of damage size and position, measurement density, sensor layout, vibration frequency and noise level. It is found that different factors are highly correlated and thus should be considered comprehensively to achieve optimal detection results. The application of the iFEM-PE method is extended to better adapt to the structural operational state, where multiple groups of vibration responses within a wide frequency band are used. Hybrid data fusion is applied to process the damage index (DI) constructed based on the multiple responses, leading to detection results capable of indicating delamination positions precisely.

Identification of Damage on Sluice Hoist Beams Using Local Mode Evoked by Swept Frequency Excitation.

As a global vibration characteristic, natural frequency often suffers from insufficient sensitivity to structural damage, which is associated with local variations of structural material or geometric properties. Such a drawback is particularly significant when dealing with the large scale and complexity of sluice structural systems. To this end, a damage detection method in sluice hoist beams is proposed that relies on the utilization of the local primary frequency (LPF), which is obtained based on the swept frequency excitation (SFE) technique and local resonance response band (LRRB) selection. Using this method, the local mode of the target sluice hoist beam can be effectively excited, while the vibrations of other components in the system are suppressed. As a result, the damage will cause a significant shift in the LPF of the sluice hoist beam at the local mode. A damage index was constructed to quantitatively reflect the damage degree of the sluice hoist beam. The accuracy and reliability of the proposed method were verified on a three-dimensional finite element model of a sluice system, with the noise resistance increased from 0.05 to 0.2 based on the hammer impact method. The proposed method exhibits promising potential for damage detection in complex structural systems.

Use of Bispectrum Analysis to Inspect the Non-Linear Dynamic Characteristics of Beam-Type Structures Containing a Breathing Crack.

A breathing crack is a typical form of structural damage attributed to long-term dynamic loads acting on engineering structures. Traditional linear damage identification methods suffer from the loss of valuable information when structural responses are essentially non-linear. To deal with this issue, bispectrum analysis is employed to study the non-linear dynamic characteristics of a beam structure containing a breathing crack, from the perspective of numerical simulation and experimental validation. A finite element model of a cantilever beam is built with contact elements to simulate a breathing crack. The effects of crack depth and location, excitation frequency and magnitude, and measurement noise on the non-linear behavior of the beam are studied systematically. The result demonstrates that bispectral analysis can effectively identify non-linear damage in different states with strong noise immunity. Compared with existing methods, the bispectral non-linear analysis can efficiently extract non-linear features of a breathing crack, and it can overcome the limitations of existing linear damage detection methods used for non-linear damage detection. This study's outcome provides a theoretical basis and a paradigm for damage identification in cracked structures.

A Critical Review of Nonlinear Damping Identification in Structural Dynamics: Methods, Applications, and Challenges.

In recent decades, nonlinear damping identification (NDI) in structural dynamics has attracted wide research interests and intensive studies. Different NDI strategies, from conventional to more advanced, have been developed for a variety of structural types. With apparent advantages over classical linear methods, these strategies are able to quantify the nonlinear damping characteristics, providing powerful tools for the analysis and design of complex engineering structures. Since the current trend in many applications tends to more advanced and sophisticated applications, it is of great necessity to work on developing these methods to keep pace with this progress. Moreover, NDI can provide an effective and promising tool for structural damage detection purposes, where the changes in the dynamic features of structures can be correlated with damage levels. This review paper provides an overview of NDI methods by explaining the fundamental challenges and potentials of these methods based on the available literature. Furthermore, this research offers a comprehensive survey of different applications and future research trends of NDI. For potential development and application work for nonlinear damping methods, the anticipated results and recommendations of the current paper can assist researchers and developers worldwide to find out the gaps and unsolved issues in the field of NDI.

A Data-Driven Damage Identification Framework Based on Transmissibility Function Datasets and One-Dimensional Convolutional Neural Networks: Verification on a Structural Health Monitoring Benchmark Structure.

Vibration-based data-driven structural damage identification methods have gained large popularity because of their independence of high-fidelity models of target systems. However, the effectiveness of existing methods is constrained by critical shortcomings. For example, the measured vibration responses may contain insufficient damage-sensitive features and suffer from high instability under the interference of random excitations. Moreover, the capability of conventional intelligent algorithms in damage feature extraction and noise influence suppression is limited. To address the above issues, a novel damage identification framework was established in this study by integrating massive datasets constructed by structural transmissibility functions (TFs) and a deep learning strategy based on one-dimensional convolutional neural networks (1D CNNs). The effectiveness and efficiency of the TF-1D CNN framework were verified using an American Society of Civil Engineers (ASCE) structural health monitoring benchmark structure, from which dynamic responses were captured, subject to white noise random excitations and a number of different damage scenarios. The damage identification accuracy of the framework was examined and compared with others by using different dataset types and intelligent algorithms. Specifically, compared with time series (TS) and fast Fourier transform (FFT)-based frequency-domain signals, the TF signals exhibited more significant damage-sensitive features and stronger stability under excitation interference. The utilization of 1D CNN, on the other hand, exhibited some unique advantages over other machine learning algorithms (e.g., traditional artificial neural networks (ANNs)), particularly in aspects of computation efficiency, generalization ability, and noise immunity when treating massive, high-dimensional datasets. The developed TF-1D CNN damage identification framework was demonstrated to have practical value in future applications.

Enhanced Intelligent Identification of Concrete Cracks Using Multi-Layered Image Preprocessing-Aided Convolutional Neural Networks.

Crack identification plays an essential role in the health diagnosis of various concrete structures. Among different intelligent algorithms, the convolutional neural networks (CNNs) has been demonstrated as a promising tool capable of efficiently identifying the existence and evolution of concrete cracks by adaptively recognizing crack features from a large amount of concrete surface images. However, the accuracy as well as the versatility of conventional CNNs in crack identification is largely limited, due to the influence of noise contained in the background of the concrete surface images. The noise originates from highly diverse sources, such as light spots, blurs, surface roughness/wear/stains. With the aim of enhancing the accuracy, noise immunity, and versatility of CNN-based crack identification methods, a framework of enhanced intelligent identification of concrete cracks is established in this study, based on a hybrid utilization of conventional CNNs with a multi-layered image preprocessing strategy (MLP), of which the key components are homomorphic filtering and the Otsu thresholding method. Relying on the comparison and fine-tuning of classic CNN structures, networks for detection of crack position and identification of crack type are built, trained, and tested, based on a dataset composed of a large number of concrete crack images. The effectiveness and efficiency of the proposed framework involving the MLP and the CNN in crack identification are examined by comparative studies, with and without the implementation of the MLP strategy. Crack identification accuracy subject to different sources and levels of noise influence is investigated.

Damage Quantification with Embedded Piezoelectric Aggregates Based on Wavelet Packet Energy Analysis.

Cement-based components have been widely used in civil engineering structures. However, due to wearing and deterioration, the cement-based components may have brittle failure. To provide early warning and to support predictive reinforcement, the piezoelectric materials are embedded into the cement-based components to excite and receive elastic waves. By recognizing the abnormalities in the elastic waves, hidden damage can be identified in advance. However, few research has been published regarding the damage quantification. In this paper, the wavelet packet analysis is adopted to calculate the energy of the transmitted elastic waves based on the improved piezoelectric aggregates (IPAs). Due to the growth of the damage, less elastic waves can pass through the damage zone, decreasing the energy of the acquired signals. A set of cement beams with different crack depths at the mid-span is tested in both numerical and experimental ways. A damage quantification index, namely the wavelet packet-based energy index (WPEI), is developed. Both the numerical and experimental results demonstrate that the WPEI decreases with respect to the crack depth. Based on the regression analysis, a strong linear relationship has been observed between the WPEI and the crack depth. By referring to the linear relationship, the crack depth can be estimated by the WPEI with a good accuracy. The results demonstrated that the use of the IPAs and the WPEI can fulfill the real-time quantification of the crack depth in the cement beams.

Damage Identification in Bridges by Processing Dynamic Responses to Moving Loads: Features and Evaluation.

The detection of damage in bridges subjected to moving loads has attracted increasing attention in the field of structural health monitoring. Processing the dynamic responses induced by moving loads to characterize damage is the key to identifying damage in bridges. On this topic, various methods of processing dynamic responses to moving loads have been developed in recent decades, with respective strengths and weaknesses. These methods appear in different applications and literatures and their features have not been comprehensively surveyed to form a profile of this special area. To address this issue, this study presents a comprehensive survey of methods for identifying damage by processing dynamic responses of cracked bridges subjected to moving loads. First, methods utilizing the Fourier transform to process dynamic responses to moving loads for damage detection in bridges are examined. Second, methods using wavelet transform to process the dynamic responses to moving loads for damage characterization are examined. Third, methods of employing the Hilbert-Huang transform to process the dynamic responses to moving loads for damage identification are examined. Fourth, methods of dynamic response-driven heuristic interrogation of damage in bridges subjected to moving loads are examined. Finally, we recommend future research directions for advancing the development of damage identification relying on processing dynamic responses to moving loads. This study provides a profile of the state-of-the-art and state-of-the-use of damage identification in bridges based on dynamic responses to moving loads, with the primary aim of helping researchers find crucial points for further exploration of theories, methods, and technologies for damage detection in bridges subjected to moving loads.

Wavelet Packet Singular Entropy-Based Method for Damage Identification in Curved Continuous Girder Bridges under Seismic Excitations.

Curved continuous girder bridges (CCGBs) have been widely adopted in the civil engineering field in recent decades for complex interchanges and city viaducts. Unfortunately, compared to straight bridges, this type of bridge with horizontal curvature is relatively vulnerable to earthquakes characterized by large energy and short duration. Seismic damage can degrade the performance of CCGBs, threatening their normal operation and even resulting in collapse. Detection of seismic damage in CCGBs is thus significantly important but is still not well resolved. To this end, a new method based on wavelet packet singular entropy (WPSE) is proposed to identify seismic damage by analyzing the dynamic responses of CCGBs to seismic excitation. This WPSE-based approach features characterizing damage using synergistic advantage of the wavelet packet transform, singular value decomposition, and information entropy. To testify the algorithm, a finite element model of a typical CCGB with two types of seismic damage is built, in which the seismic damage is individually modeled by stiffness reductions at the bottom of piers and at pier-girder connections. The displacement responses of the model to El Centro seismic excitation is used to identify the damage. The results show that damage indices in the WPSE-based approach can correctly locate the seismic damage in CCGBs. Furthermore, the WPSE-based method is competent to identify damage with higher accuracy in comparison with the wavelet packet energy based method, and has a strong immunity to noise revealed by robustness analysis. An array of responses used in this approach paves the way of developing practical technologies for detecting seismic damage using advanced distributed sensing techniques, typically the optical sensors.

Permutation Entropy Based on Non-Uniform Embedding.

A novel visualization scheme for permutation entropy is presented in this paper. The proposed scheme is based on non-uniform attractor embedding of the investigated time series. A single digital image of permutation entropy is produced by averaging all possible plain projections of the permutation entropy measure in the multi-dimensional delay coordinate space. Computational experiments with artificially-generated and real-world time series are used to demonstrate the advantages of the proposed visualization scheme.

Automatic High-Resolution Operational Modal Identification of Thin-Walled Structures Supported by High-Frequency Optical Dynamic Measurements.

High-frequency optical dynamic measurement can realize multiple measurement points covering the whole surface of the thin-walled structure, which is very useful for obtaining high-resolution spatial information for damage localization. However, the noise and low calculation efficiency seriously hinder its application to real-time, online structural health monitoring. To this end, this paper proposes a novel high-resolution frequency domain decomposition (HRFDD) modal identification method, combining an optical system with an accelerometer for measuring high-accuracy vibration response and introducing a clustering algorithm for automated identification to improve efficiency. The experiments on the cantilever aluminum plate were carried out to evaluate the effectiveness of the proposed approach. Natural frequency and damping ratios were obtained by the least-squares complex frequency domain (LSCF) method to process the acceleration responses; the high-resolution mode shapes were acquired by the singular value decomposition (SVD) processing of global displacement data collected by high-speed cameras. Finally, the complete set of the first nine order modal parameters for the plate within the frequency range of 0 to 500 Hz has been determined, which is closely consistent with the results obtained from both experimental modal analysis and finite element analysis; the modal parameters could be automatically picked up by the DBSCAN algorithm. It provides an effective method for applying optical dynamic technology to real-time, online structural health monitoring, especially for obtaining high-resolution mode shapes.

Shear Strain Singularity-Inspired Identification of Initial Delamination in CFRP Laminates: Multiscale Modulation Filter for Extraction of Damage Features.

Identification of initial delamination is crucial to ensure the safety of the fiber-reinforced laminated composite structures. Amongst the identification approaches based on mode shapes, the concept of multiscale shear-strain gradient (MSG) has an explicit physical sense of characterizing delamination-induced singularity of shear strains; moreover, it is robust against noise interference owing to the merits of multiscale analysis. However, the capacity of the MSG for identifying initial delamination is insufficient because the delamination-induced singularity peak can be largely obscured by the global component of the MSG. Addressing this problem, this study proposes an enhanced approach for identifying initial delamination in fiber-reinforced composite laminates. In particular, the multiscale modulation filter (MMF) is proposed to modulate the MSG with the aim of focusing on damage features, by which a new concept of enhanced MSG (EMSG) is formulated to extract damage features. By taking advantage of the MMF with the optimal frequency translation parameters, the EMSG is concentrated in a narrow wavenumber band, which is dominated by the damage-induced singularity peak. As a consequence, the delamination-induced singularity peak in the EMSG can be isolated from the global component. The capacity of the approach for identifying initial delamination is experimentally validated on a carbon fiber reinforced polymer (CFRP) laminate, whose mode shapes are acquired via non-contact laser measurement. The experimental results reveal that the EMSG-based approach is capable of graphically characterizing the presence, location, and size of initial delamination in CFRP laminates.

Structural damage detection using finite element model updating with evolutionary algorithms: a survey.

Structural damage identification based on finite element (FE) model updating has been a research direction of increasing interest over the last decade in the mechanical, civil, aerospace, etc., engineering fields. Various studies have addressed direct, sensitivity-based, probabilistic, statistical, and iterative methods for updating FE models for structural damage identification. In contrast, evolutionary algorithms (EAs) are a type of modern method for FE model updating. Structural damage identification using FE model updating by evolutionary algorithms is an active research focus in progress but lacking a comprehensive survey. In this situation, this study aims to present a review of critical aspects of structural damage identification using evolutionary algorithm-based FE model updating. First, a theoretical background including the structural damage detection problem and the various types of FE model updating approaches is illustrated. Second, the various residuals between dynamic characteristics from FE model and the corresponding physical model, used for constructing the objective function for tracking damage, are summarized. Third, concerns regarding the selection of parameters for FE model updating are investigated. Fourth, the use of evolutionary algorithms to update FE models for damage detection is examined. Fifth, a case study comparing the applications of two single-objective EAs and one multi-objective EA for FE model updating-based damage detection is presented. Finally, possible research directions for utilizing evolutionary algorithm-based FE model updating to solve damage detection problems are recommended. This study should help researchers find crucial points for further exploring theories, methods, and technologies of evolutionary algorithm-based FE model updating for structural damage detection.