Two-stage Damage Detection Method Research Articles

A 2D-CNN-Based Two-Stage Structural Damage Localization and Quantification Technique Using Time Domain Vibration Data

The conventional approaches for detecting structural degradation are time-consuming, labor-intensive, and costly. The physical monitoring of the structure also poses risks to the health and safety of supervisors. Therefore, damage estimation of any structure using artificial intelligence (AI), more specifically deep learning (DL), is becoming more significant in civil infrastructure. In the presented research article, an efficient two-stage damage detection method is proposed for structural damage detection (SDD) from time domain vibration signals. The proposed method utilizes two-dimensional convolutional neural network (2D-CNN) architecture as a DL algorithm for damage detection. Here, a computer-aided damage detection method for steel beam and frame-type structures is developed using 2D-CNN algorithm in the Google Colab platform. The effectiveness of the proposed method is first verified, and it provides more than 90% accuracy for identifying the damage location and severity of a cantilever beam for single- and multi-damage scenarios from numerically simulated noisy displacement data. The algorithm is also experimentally validated through the raw acceleration data of damaged steel frame joints collected from the Qatar University Grandstand simulator (QUGS). The proposed 2D-CNN algorithm performs better than other DL algorithms by achieving 100% accuracy within 10 epochs for damage detection of steel frames using QUGS data. It demonstrates significant potential for detecting damage location and quantifying damages for single- and multi-damage scenarios using noise-free and noisy datasets. The primary contribution of this study resides in the implementation of two-stage damage detection algorithm utilizing 2D-CNN with time domain vibration response for multiclass damage identification and quantification.

Combination of wavelet transform and extreme learning machine for detecting damages in composite plates

This paper reports a two-stage damage detection method for effectively identifying multi-damage in composite plate structures. The first stage focuses on detecting damage locations using the wavelet transform to reveal the singularities from a modal shape of the composite plate. In the second stage, extreme learning machine (ELM) is employed to search the damage severities from the pre-calculated damage evaluation database (the relationship between the natural frequencies and severities). Using finite element method (FEM) and experimental modal analysis (EMA), the numerical simulations and experimental investigations are executed to verify the effectiveness of the combination method for simply supported composite plates structures with various damages. Results show that the proposed two-stage method is effectively to identify multiple damages in composite plate structures with reasonable precision might be extend to real-world applications.

A novel model order reduction-based two-stage damage detection paradigm for trusses using time–history acceleration

This paper presents a novel model order reduction (MOR)-based two-stage damage detection method for trusses employing time-series acceleration measured by limited sensors. In the first step, an acceleration-based strain energy indicator (ASEI) is newly proposed to evaluate the most doubtfully damaged candidates. Accordingly, the number of design variables defined in an inverse optimization problem of the second phase is reduced significantly. The location and severity of damaged members are then determined by minimizing an objective function with a newly added dynamic penalty parameter to achieve a faster convergence speed and better optimal solutions. Since acceleration signals are incompletely measured at limited sensors, the second-order Neumann series expansion (SNSE) is firstly employed to condense the proportionally damped trusses for inferring the unmeasured time–history information. An adaptive hybrid evolutionary firefly algorithm (AHEFA) is utilized to resolve the above inverse optimization problem. Four numerical examples of 2D and 3D trusses with various damage scenarios including noises are examined to demonstrate the reliability of the proposed methodology. Attained outcomes indicate that the suggested paradigm can reliably diagnose both multidamage sites and extents of trusses with only relatively short time histories and a few measurement sensors.

A fast and robust method for damage detection of truss structures

• This paper proposes a two-stage damage detection method for truss structures. • First stage focused on the damage localization and in the second stage, the damage severities are evaluated. • To localize the suspected damaged elements, using the concept of residual force vector, a new index is proposed. • To evaluate the damage severities, the damage detection problem formulated as an optimization problem and solved by GA. Use of optimization search algorithms is recognized as an efficient method for solving structural damage identification problems. Although these algorithms demonstrated their robustness to identify the location and extent of multiple damages in structural systems, they impose so much computational efforts to the damage assessing process that it reduces their attraction. In this paper by utilizing the concept of residual force vector, an efficient approach based on a Truss Element Damage Index (TEDI) is defined to assist in a fast and reliable prediction of damaged elements. Based on the proposed technique, the first step focuses on location detection of most probable damaged members. The healthy members will then be eliminated from the total list of variables. This can reduce the computational effort significantly. In the second step to identify damaged locations and severities, the Genetic Algorithm is employed to search for the optimum solution in the new search space resulted from the first step. Three test examples are considered to investigate the efficiency of proposed method for damage identification.

Multidamage Detection of Bridges Using Rough Set Theory and Naive-Bayes Classifier

This paper is intended to introduce a two-stage detection method to solve the multidamage problem in bridges. Vibration analysis is conducted to acquire the dynamic fingerprints which are regarded as information sources. Bayesian fusion is used to integrate these sources and preliminarily locate the damage. Then, the RSNB method which combines rough set theory and Naive-Bayes classifier is proposed to simplify the sample dimensions and fuse the remaining attributes for damage extent detection. A numerical simulation of a real structure, the Sishui Bridge in Shenyang, China, is conducted to validate the effectiveness of the proposed detection method. Data fusion based method is compared with single-valued index method at the damage localization stage. The proposed RSNB method is compared with the Back Propagation Neural Network (BPNN) method at the damage qualification stage. The results show that the proposed two-stage damage detection method has better performances in regard to transparency, accuracy, efficiency, noise robustness, and stability. Furthermore, an ambient excitation modal test was carried out on the bridge to obtain the vibration responses and assess the damage condition with the proposed method. This novel approach is applicable for early damage detection and provides a basis for bridge management and maintenance.

Damage assessment in plate-like structures using a two-stage method based on modal strain energy change and Jaya algorithm

ABSTRACTThe paper presents an effective two-stage approach based on modal strain energy change and Jaya algorithm for damage assessment in plate-like structures. In the first stage, a newly developed damage indicator, named as normalized modal strain energy-based damage index (nMSEBI), is proposed to help locate potential damage elements more effectively. After eliminating most of the healthy elements, the actual damaged sites and its extent in plate structure are determined in the second stage by minimizing an objective function, which is solved using Jaya algorithm. For finding a suitable objective function used in optimization process, two different objective functions are considered to examine their effects on the performance of the utilized optimization algorithm. The efficiency and accuracy of the proposed two-stage damage detection method are investigated by two numerical examples comprising a concrete plate and a four-layer (0°/90°/90°/0°) laminated composite plate with multiple damage locations. All of the obtained results indicate that even under measurement noise, the proposed method can identify the actual damage sites and estimate the extent of damage with high precision. In addition, the numerical results also show that the computational cost of the optimization process using the objective function based on modal flexibility change is much lower than that using the objective function based on mode shapes change.

Enhanced optimization-based structural damage detection method using modal strain energy and modal frequencies

To identify the location and severity of structural damages precisely, a two-stage damage detection method is proposed here. In the first stage, the most probable elements that maybe damaged are determined using the modal strain energy concept of structure. For such purpose, an efficient modal strain energy conversion-based index is proposed. In the second stage, the structural damage identification problem is defined as an optimization problem that to be solved by a modified genetic algorithm. In the optimization problem, the damage extents of structure’s elements which are determined in the previous stage are considered as the variables. An efficient objective function considering the first few modal frequencies of the structure, before and after damage occurrence, is utilized for optimization. The robustness of the proposed method is assessed by several benchmark examples. The numerical results exhibit the effectiveness of the proposed method for precisely determining the location and severity of multiple structural damages.

Structural multi-damage identification based on strain energy and micro-search artificial fish swarm algorithm

A two-stage damage detection method based on strain energy and micro-search artificial fish swarm algorithm (MSAFSA) is presented for solving structural multi-damage problem. First, structural modal strain energy and energy dissipation process are analyzed and an improved modal strain energy dissipation ration index (IMSEDRI) is proposed to preliminarily detect suspected damage elements. Then, artificial fish swarm algorithm (AFSA) is used to identify damage extent of suspected damage elements. In general, the search efficiency of a basic AFSA isn’t very efficient for the search procedure. So, a micro-search artificial fish swarm algorithm is presented in this paper. The simulation results demonstrate that the damage detection method can estimate the damage locations and extent with good accuracy, and the calculated results of the proposed MSAFSA are obviously superior to those of both the basic AFSA and the AFSA with visual-step change strategy.

A two-stage damage detection method for truss structures using a modal residual vector based indicator and differential evolution algorithm

A two-stage method for damage detection in truss systems is proposed. In the first stage, a modal residual vector based indicator (MRVBI) is introduced to locate the potentially damaged elements and reduce the damage variables of a truss structure. Then, in the second stage, a differential evolution (DE) based optimization method is implemented to find the actual site and extent of damage in the structure. In order to assess the efficiency of the proposed damage detection method, two numerical examples including a 2D-truss and 3D-truss are considered. Simulation results reveal the high performance of the method for accurately identifying the damage location and severity of trusses with considering the measurement noise.

Two-Stage Damage Identification Based on Modal Strain Energy and Revised Particle Swarm Optimization

This paper presents a novel two-stage damage detection method by integrating modal strain energy and revised particle swarm optimization (RPSO). In the first stage, the modal strain energy change ratio (MSECR) is used to roughly identify the locations of damaged elements via an appropriate MSECR threshold which is determined through parameter estimation. In the second stage, RPSO that integrates evolutionary theory with general PSO is used to precisely locate and quantify the damage with the gravity position of the selected excellent particles in the current entire population taken into consideration. Two numerical simulations and a seven-story steel frame experiment in laboratory conditions are performed to validate the proposed method, and a comparison is made between the proposed approach and existing methods. The results show that: (1) the proposed method can not only effectively locate damage, but also accurately evaluate the extent of damage. Meanwhile, it also enjoys good noise-tolerance and adaptability; (2) the damage threshold of the MSECR presented in this paper can be determined by the parameter estimation and reliability index, and then used to reduce the number of elements to be analyzed and to improve the computation efficiency in the second stage; and (3) compared with general PSO algorithm, RPSO is more efficient and robust for damage detection with a better noise-tolerance. This study shows that the proposed method can provide a reliable and fast tool to accurately identify, locate and quantify single- and multi-damage of complex engineering structures.

Structural damage identification based on Bayesian theory and improved immune genetic algorithm

In order to solve structural multi-damage identification problem, a two-stage damage detection method based on Bayesian theory and immune genetic algorithm (IGA) is presented. First, structural modal strain energy and frequency are considered as two kinds of information sources, and Bayesian theory is utilized to integrate the two information sources and preliminarily identify structural damage locations. After the damaged locations are determined, immune genetic algorithm is used to identify structural damage extent. Considering the search efficiency of the simple IGA is still not very good, some improved strategies are presented, such as culture vaccine, concentration control of the best antibody, and two termination conditions etc. Simulation results show that the two-stage method can precisely identify structural damage locations and extent, and the calculated results of the proposed improved IGA are obviously better than those of both the simple IGA and the genetic algorithm with elitist strategy.

A two-stage method for damage detection using frequency responses and statistical theory

In order to precisely identify the location and extent of structural damage, a two-stage damage detection method using frequency responses and statistical theory is presented in this paper. First, a damage index, which comes from the product of the stiffness changes and measured responses, is proposed. We can utilize degree-of-freedom (d.f.) damage index to localize the damage locations. Then, in order to calculate the extent of damage, a damage quantification formula is deduced from a reduced degree-of-freedom system. Finally, the effect of measurement noise is taken into account in the identification process and the measurement noise sensitivity formula based on statistical theory is presented. The numerical example and analysis demonstrate the excellent performance of the proposed two-stage method to identify damage locations and extent compared with other methods, such as the directness generalized inverse method.

Two-Stage Multi-damage Detection Method Based on Energy Balance Equation

In order to solve structural multi-damage identification problem, a two-stage damage detection method based on energy balance equation and evidence fusion is presented. First, a Frequency Change Identification (FCI) method and Modal Strain Energy Dissipation Ratio (MSEDR) method are utilized to preliminarily identify structural damage locations, and then a Fusion Damage Localization (FDL) method based on evidence theory is proposed to precisely detect damage locations. The FDL method mainly utilizes evidence theory to combine both the FCI localization information and the MSEDR localization information. Thus, more precise damage localization information can be acquired. After the damaged locations are determined, an Energy Balance Equation (EBE) index is presented to identify structural damage extent. Considering that strain energy dissipation should be equal to the change of modal strain energy, a quartic EBE equation is deduced, and structural damage extent can be obtained through the solution of the equation. An average quantification index is also proposed to improve identification precision. The simulation results demonstrate that the FDL method can perfectly detect structural damage locations, and the EBE index and average index can identify structural damage extent.

A two-stage damage detection approach based on subset selection and genetic algorithms

A two-stage damage detection method is proposed and demonstrated for structural health monitoring. In the first stage, the subset selection method is applied for the identification of the multiple damage locations. In the second stage, the damage severities of the identified damaged elements are determined applying SSGA to solve the optimization problem. In this method, the sensitivities of residual force vectors with respect to damage parameters are employed for the subset selection process. This approach is particularly efficient in detecting multiple damage locations. The SEREP is applied as needed to expand the identified mode shapes while using a limited number of sensors. Uncertainties in the stiffness of the elements are also considered as a source of modeling errors to investigate their effects on the performance of the proposed method in detecting damage in real-life structures. Through a series of illustrative examples, the proposed two-stage damage detection method is demonstrated to be a reliable tool for identifying and quantifying multiple damage locations within diverse structural systems.