Damage Severity Identification Research Articles

Leveraging multimodal deep learning for natural disaster event classification and its damage severity analysis through social media posts

Accurate and timely information is essential for coordinating an effective disaster response. Traditional methods have struggled to efficiently categorize disaster events and assess damage severity due to the variety and complexity of data sources. Previous research has focused on specific tasks, such as information gathering or humanitarian assistance, but has not adequately addressed the assessment of disaster damage severity. This paper proposes a hybrid learning model to improve disaster event classification and damage severity identification. The model combines image and text data in a cooperative way, using ResNet50 to extract features from images and a LSTM with attention mechanism to learn sequences from text. This combination allows for a more contextual and informative representation of the input data. Compared to existing approaches, the proposed multimodal approach achieves significantly better results in disaster event classification. Apart from the proposed model also shows promising outcome for damage severity of disaster. These advancements are especially important for real-world applications such as disaster management and response coordination, where accuracy and reliability are essential. The comprehensive methodology and empirical results presented in this paper demonstrate the effectiveness and potential of using hybrid learning models to leverage multimodal data for unique and sophisticated analytical tasks in disaster scenarios

Damage Detection in Bridge Structures through Compressed Sensing of Crowdsourced Smartphone Data

Traditional bridge health monitoring methods that necessitate sensor installation are not only costly but also time-consuming. In contrast, utilizing smartphone data collected from vehicles as they traverse bridges offers an efficient and cost-effective alternative. This paper introduces a cutting-edge damage detection framework for indirect monitoring of bridge structures, leveraging a substantial volume of acceleration data collected from smartphones in vehicles passing over the bridge. Our innovative approach addresses the challenge of collecting and transmitting high-frequency data while preserving smartphone battery life and data plans through the integration of compressed sensing (CS) into the crowdsensing-based monitoring framework. CS employs random sampling and signal recovery from a significantly reduced number of samples compared to the requirements of the Nyquist–Shannon sampling theorem. In the proposed framework, acceleration signals from vehicles are initially acquired using smartphone sensors, undergo compression, and are then transmitted for signal reconstruction. Subsequently, feature extraction and dimensionality reduction are performed using Mel-frequency cepstral coefficients and principal component analysis. Damage indexes are computed based on the dissimilarity between probability distribution functions utilizing the Wasserstein distance metric. The efficacy of the proposed methodology in bridge monitoring has been substantiated through the utilization of numerical models and a lab-scale bridge. Furthermore, the feasibility of implementing the framework in a real-world application has been investigated, leveraging the smartphone data from 102 vehicle trips on the Golden Gate Bridge. The results demonstrate that damage detection using the reconstructed signals obtained through compressed sensing achieves comparable performance to that obtained with the original data sampled at the Nyquist measurement sampling rate. However, it is observed that to retain severity information within the signals for accurate damage severity identification, the compression level should be limited to 20%. These findings affirm that compressed sensing significantly reduces the data collection requirements for crowdsensing-based monitoring applications, without compromising the accuracy of damage detection while preserving essential damage-sensitive information within the dataset.

Advanced structural health monitoring in carbon fiber-reinforced plastic using real-time self-sensing data and convolutional neural network architectures

In this study, advanced structural health monitoring (SHM) using a non-destructive self-sensing methodology was proposed for large-sized carbon fiber-reinforced plastic (CFRP). Cyclic point bending tests were performed on three types of CFRPs. The damage severity identification and localization were classified and investigated using four different convolutional neural network (CNN) architectures. Electrical resistance images were used to train each CNN architecture for damage analysis. An optimized CNN architecture for the damage analysis of CFRPs using electrical resistance data was proposed and compared with traditional damage analysis CNN architectures. The applicability of the proposed SHM methodology was verified by analyzing unseen damage in the CFRPs. This study addresses the limitations of previous self-sensing methods by reducing the number of electrodes, which reduces data complexity and increases the sensible area of CFRPs. Thus, this study successfully designed an efficient SHM methodology with a high accuracy of over 90 % for analyzing CFRP damage, including the severity and location, regardless of the type of carbon fiber and stacking sequence of composite structures that showed high applicability.

Damaged cable identification in cable-stayed bridge from bridge deck strain measurements using support vector machine

A new two-step approach is developed for damaged cable identification in a cable-stayed bridge from deck bending strain responses using Support Vector Machine. A Damaged Cable Identification Machine (DCIM) based on support vector classification is constructed to determine the damaged cable and a Damage Severity Identification Machine (DSIM) based on support vector regression is built to estimate the damage severity. A field cable-stayed bridge with a long-term monitoring system is used to verify the proposed method. The three-dimensional Finite Element Model (FEM) of the cable-stayed bridge is established using ANSYS, and the model is validated using the field testing results, such as the mode shape, natural frequencies and its bending strain responses of the bridge under a moving vehicle. Then the validated FEM is used to simulate the bending strain responses of the longitude deck near the cable anchors when the vehicle is passing over the bridge. Different damage scenarios are simulated for each cable with various severities. Based on damage indexes vector, the training datasets and testing datasets are acquired, including single damaged cable scenarios and double damaged cable scenarios. Eventually, DCIM is trained using Support Vector Classification Machine and DSIM is trained using Support Vector Regression Machine. The testing datasets are input in DCIM and DSIM to check their accuracy and generalization capability. Different noise levels including 5%, 10%, and 20% are considered to study their anti-noise capability. The results show that DCIM and DSIM both have good generalization capability and anti-noise capability.

One-dimensional convolutional neural network for damage detection of jacket-type offshore platforms

Vibration-based damage detection techniques play an important role in health monitoring of offshore structures. This study explores the possibility to use the one-dimensional convolutional neural network (CNN) to extract the damage sensitive features automatically from the raw strain response data of a structure under a certain excitation without requiring any hand-crafted feature extraction. The validity of the proposed method is verified by using a numerical simulation of a jacket-type offshore platform under a regular and a random wave excitations in different directions, respectively. The damage localization and damage severity identification are conducted with considering several damage cases including different damage locations and the effect of noise. The data preprocessing procedure based on convolution and deconvolution for noisy data is proposed to enhance the capability of feature extraction and noise immunity of CNN. Furthermore, the experimental studies of a jacket-type offshore platform model subjected to a sinusoidal excitation, a white noise excitation and an impulse excitation are respectively investigated to check the applicability of the method, in which the major damage and minor damage on single and multiple locations are involved. Results indicate this approach has an excellent performance on structural damage detection.

Damage Identification of Bridge Based on Modal Flexibility and Neural Network Improved by Particle Swarm Optimization

An approach to identify damage of bridge utilizing modal flexibility and neural network optimized by particle swarm optimization (PSO) is presented. The method consists of two stages; modal flexibility indices are applied to damage localizing and neural network optimized by PSO is used to identify the damage severity. Numerical simulation of simply supported bridge is presented to demonstrate feasibility of the proposed method, while comparative analysis with traditional BP network is for its superiority. The results indicate that curvature of flexibility changes can identify damages with both single and multiple locations. The optimization of bias and weight for neural network by fitness function of PSO algorithm can realize favorable damage severity identification and possesses more satisfactory accuracy than traditional BP network.

Experimental and numerical studies on model updating method of damage severity identification utilizing four cost functions

SUMMARY As the final stage of damage identification, damage severity identification has great significance to structural safety assessment and decision-making in maintenance. Take the damage detection of truss structures for instance; the stochastic damage locating vector method has great advantages. However, the method is a localization technique designed to provide information in damage location only. Many present damage severity identification methods suffer from great error due to high noise. Therefore, it is imperative to develop a new identification method for truss structural health monitoring. To solve this problem, this paper presents the model updating method of damage severity identification based on four cost functions: (i) correlation coefficient of free vibration accelerations; (ii) correlation coefficient of local mode shapes; (iii) free vibration accelerations assurance criterion; and (iv) local modal assurance criterion. In these functions, correlation coefficient and correlation degree of free vibration accelerations of measured nodes are first proposed to identify damage severity. Moreover, a simple supported bailey steel-truss bridge Benchmark Model has been designed and constructed. The span is 8 m with the scaled ratio 1:25. Based on the model, both experimental and numerical simulation results using these procedures under pulse excitation indicate that they are feasible and effective. In addition, the proposed techniques exhibit high-noise insusceptibility. Copyright © 2011 John Wiley & Sons, Ltd.

Damage Severity Assessment Using Modified BP Neural Network

Damage severity identification is an important content among structural damage identification. In order to avoid the disadvantages of conventional BPNN, a modified BP neural network was proposed to identify structural damage severity in this paper. The modified BPNN was trained by using structural modal frequency qua BPNN input, and then used to forecast structural damage severity. Finally, the results of simulation experiment of composite material cantilever girder show that the improved method is very effective for damage severity identification and possess great applied foreground.