Identification For Structures Research Articles

Unified method for fully automated modal identification and tracking with consideration of sensor deployment

Automated modal identification and tracking provides the key technique for modal parameters based structural condition evaluation. However, the existing automated modal identification and tracking methods have limitations for situation with very few sensors deployed and require manual intervention. This paper proposes a unified fully automated modal identification and tracking method that can be used for structures with many or very few sensors deployed, for closely spaced modes with severe spatial aliasing and for structures with high flexibility or rigidity. A new index, which is called Modified Modal Observability Correlation, is proposed to estimate the similarity of two modes. New spurious mode elimination method and fully automated mode separation and tracking methods are proposed to realize the automated modal identification and tracking. The feasibility and novelty of the proposed method are validated using in-field monitoring data from a long span suspension bridge with high flexibility and a short span bridge with high rigidity and closely spaced modes. Automated modal identification and tracking for situations with many and very few sensors deployed for the two bridges are conducted, and extreme situation of closely spaced modes with spatial aliasing in mode shape is also considered to prove the novelty of the proposed method. Comparisons with existing mainstream methods are also conducted. The results show that the proposed method yields the right identification and tracking results in all situations, showing novelty in automated modal identification and tracking for structures with closely spaced modes having severe spatial aliasing when only very few sensors are deployed.

Automated identification of compressive stress and damage in concrete specimen using convolutional neural network learned electromechanical admittance

For the first time, this paper proposed a simple two-dimensional convolutional neural network (2-D CNN) integrated with electromechanical admittance (EMA, inverse of impedance) to detect compressive stress and load-induced damages of concrete cubic structure subjected to applied loading, which was attempted to solve the difficulty for stress/damage quantification merely based on traditional EMA technique. It automatically resolved the raw EMA signatures with no need of complex transformation or manual feature extraction. In the experimentation, the whole process of the structural states from initial loading to fatal failure was monitored via using surface-bonded piezoelectric ceramic lead zirconate titanate (PZT) transducer. Independent EMA databases were established at each stress/damage state of the structure. Qualitative detection of stress development and cracking damage progression as three stages of failure mode was analysed via using characteristics of EMA spectra encompassing resonant frequency and amplitude values. Quantifiable assessment of stress level and damage severity was attempted using the raw EMA signatures learned by the proposed CNN model without signal pre-processing. Experimental results demonstrated that EMA signature was sensitive to stress variations in concrete and its cracking, expansion and propagation. The proposed approach possessed excellent accuracy and efficiency superior to traditional root mean square deviation (RMSD)-based one for quantification on compressive stress and damage state changes in the specimen, which potentially provided an alternative paradigm of data-driven stress/damage identification in concrete structures.

Semi‐supervised implementation of SVM‐based error‐correcting output code for damage‐type identification in structures

Semi‐supervised implementation of SVM‐based error‐correcting output code for damage‐type identification in structures

Supervised Deep Learning with Finite Element simulations for damage identification in bridges

This work proposes a supervised Deep Learning approach for damage identification in bridge structures. We employ a hybrid methodology that incorporates Finite Element simulations to enrich the training phase of a Deep Neural Network with synthetic damage scenarios. The neural network is based on autoencoders and its particular architecture allows to activate or deactivate nonlinear connections under need. The methodology intends to contribute to the progress towards the applicability of Structural Health Monitoring practices in full-scale bridge structures. The ultimate goal is to estimate the location and severity of damage from measurements of the dynamic response of the structure. The damages we seek to detect correspond to material degradations that affect wide areas of the structure by reducing its stiffness properties. Our method allows a feasible adaptation to large systems with complex parametrizations and structural particularities. We investigate the performance of the proposed method on two full-scale instrumented bridges, obtaining adequate results for the testing datasets even in presence of measurement uncertainty. Besides, the method successfully predicts the damage condition for two real damage scenarios of increasing severity available in one of the bridges.

Probability density field of acoustic emission events: Damage identification in concrete structures

This paper proposes a new damage identification method, namely, the probability density field of acoustic emission (AE) events. This new method provides a different perspective to deal with the uncertainties in the source localization process. We treat the source location as a random variable, and estimate its probability density field based on a probability density function. The function was found from simulations where various uncertainties were included. The probability of AE events falling in a certain space range is the integral of the probability densities over that range. We apply the new method in a failure test of a full-scale reinforced concrete beam. The resultant probability density field clearly reflects the crack patterns of the specimen and a close relationship with the crack width.

Kalman filter–random forest‐based method of dynamic load identification for structures with interval uncertainties

It is widely acknowledged that dynamic load identification is a powerful technology for structural health monitoring and reliability analysis. This paper investigates an uncertain dynamic load identification strategy with the combination of the Kalman filter (KF) algorithm and the random forest (RF) model. Enlightened by the concept of the KF, a one-step delayed identification of dynamic loads is completed in the state space domain. The previous loads can be calculated recursively utilizing the previous state estimation and the current displacement observation based on the least square method. In addition, the optimal state estimation will be achieved synchronously with the classical KF algorithm. In terms of inevitable uncertainties, the interval model is introduced to quantify uncertain system parameters and uncertain input loads. To determine the interval load process, the RF surrogate model is constructed to characterize their functional relationship, which is integrated by massive decision trees (DTs). Particularly, Latin hypercube sampling (LHS) and bootstrap sampling (BS) methods are employed to generate training samples for the RF model. The validity and feasibility of the developed methodology are eventually demonstrated by three numerical examples. The results indicate that the proposed approach has an excellent performance in both accuracy and efficiency.

Damage Identification for Shear-Type Structures Using the Change of Generalized Shear Energy

Structural damage identification has become an important topic in the field of civil engineering in recent years. The shear-type structure, such as shear frame structure, is a common type used in civil engineering. In this paper, a damage identification method based on the change of generalized shear energy is proposed for shear-type structures. The main steps of the proposed method are as follows. Firstly, the element stiffness matrix in the structural finite element model is decomposed to obtain the elementary shear force vector. Secondly, the elementary generalized shear energy is calculated by the dot product of the vibration mode shape vector and the elementary shear force vector. Thirdly, structural damage locations can be determined by the changes of elementary generalized shear energy. Finally, more accurate damage localization and quantification are achieved by solving the mode shape sensitivity equation. A 20-storey numerical example and a three-storey experimental model are used to demonstrate the proposed damage identification algorithm. From the numerical and experimental results, it was found that the proposed approach can accurately identify the location and extent of the damage in the shear structures even if the data contain noise. It has been shown that the presented algorithm may be useful in the damage identification of shear-type structures.

Joint Damage Identification in Frame Structures by Integrating a New Damage Index with Equilibrium Optimizer Algorithm

Beam-column joints are responsible for maintaining the integrity and stability of frame structures, and any damage to these critical components can endanger the overall safety and reliability of the structure. Hence, early detection of structural joint damage is of paramount importance. However, most of the available structural damage identification methods focus on identifying damage in structural members, and relatively fewer methods have been developed so far for assessing damage in structural joints. In view of this, the present study proposes a new two-stage method for joint damage identification of frame structures. In the first stage, an efficient damage indicator, called residual moment-based joint damage index (RMBJDI), is developed and applied to detect the location of potentially damaged joints. This damage indicator can help to reduce the number of involved damage variables by excluding healthy joints from the problem. In the second stage, the reduced dimension damage identification problem is formulated as an optimization problem and is further tackled by employing a robust meta-heuristic algorithm, namely equilibrium optimizer (EO), to determine the damage severity of suspected damaged joints. In order to assess the capability and effectiveness of the presented joint damage identification method, two numerical examples of frame structures are conducted under both noise-free and noisy conditions. The results demonstrate that the proposed two-stage method, which integrates RMBJDI with EO, is a highly accurate and powerful tool for localizing and quantifying the joint damage in frame structures.

Artificial Intelligence in Laser Powder Bed Fusion Procedures – Neural Networks for Live-Detection and Forecasting of Printing Failures.

Recently, many disruptive technologies like additive manufacturing were developed and have grown to production grade solutions. While such technologies can reduce the required time and amount of material, they require new methods to address long printing times and error identification in complex process structures. Such systems can be created using artificial intelligence (AI), such that operators can focus on supervising monitoring systems rather than the printing process and can decide upon preprocessed information.For the laser powder bed fusion process (LPBF), a main challenge lies in error detection per layer and in predicting the necessity of near-future operator interaction, to meet quality standards. Yet, only few works aim to automate the task of characterizing build layers.We propose an AI-driven approach to identify and forecast printing errors in LPBF using convolutional neural networks (CNNs) and the Cox proportional hazards (CPH) approach. For training and validation, layer wise greyscale images of 27 print jobs have been recorded. All print jobs’ results were qualitatively rated afterwards by experts. We then perform an autoencoder-based clustering and compare print jobs of high and low quality to create pseudo-labels. We finally train a CNN in a supervised fashion to classify layers as succeeded or faulty, as well as a CPH model to estimate remaining build time without errors. We achieve an overall accuracy of 94.9% for the CNN and statistically significant forecasts (p < 0.005) of the imposed hazard per layer using the CPH model. Our work demonstrates a novel approach of automated build part characterization, that reduces human operator effort and can be used for automated quality assurance and process monitoring.

Damage identification in plate structures based on the topological derivative method

Damage identification in plate structures based on the topological derivative method

A hybrid PSO and Grey Wolf Optimization algorithm for static and dynamic crack identification

This paper introduces an inverse problem for crack identification in two-dimensional structures using eXtend Finite Element Method (XFEM) associated with original Grey Wolf Optimization (GWO) and improved GWO using Particle Swarm Optimization (PSO) (IGWO). Static analysis with different boundary conditions and experimental modal analysis of cracked plates with varying crack length, positions, and orientation are used to test the accuracy of IGWO compared with the original GWO. The objective function is based on vertical measured strain and is computed at each iteration. The obtained results indicate that IGWO provides more accurate results than GWO based on convergence study and the error between exact and estimated results. Next, another application based on dynamic experimental cracked plates is used to improve Artificial Neural Network (ANN) parameters using GWO and IGWO. The frequencies and crack lengths are used as input and output for vertical and horizontal cracks in the plates. Thus, the model can be used for the prediction of crack length. IGWO can select the best parameters for better prediction compared with GWO.

Parametric system identification of large‐scale structure using decoupled synchronized signals

SummaryLarge‐scale structures are subjected to environmental loads or frequent seismic motion with irremediable effect. These loads have often multidirectional actions on structures, and it couples their responses and leads to multiple‐input multiple‐output (MIMO) problem. The complexity of MIMO model and the relative time‐delays in sensing networks are among major sources of error in dynamic properties identification in large scale structures. This study proposed a parametric‐time domain method to reduce the negative effect of these problems. For this purpose, the contribution of each input in the output signals is determined using QR decomposition and converts a MIMO problem into multiple single‐input multiple‐output (SIMO) ones. In this regard, an Autoregressive Moving Average with eXogenous (ARMAX) model is implemented on decoupled signals for modal identification. Further, for time synchronization of records, a cross‐correlation function has been used to achieve more precise results. The method was employed real strong‐motion response recorded by different sensors at a high rise 64‐story concrete building. Results demonstrate the promising precision of the proposed algorithm for identifying current structural modal properties under real earthquake excitations. Hence, structures can be monitored efficiently along seismic experiences to detect any possible variations in their structural features. The comparison between the output of the proposed method and previous study indicates a considerable improvement on accuracy of the estimated model property particularly on mode shapes.

Inverse analysis for damage detection in a rod using EMI method

The electro-mechanical impedance (EMI) method has been demonstrated to be a powerful tool to detect the small local damages in various engineering structures, due to its high-frequency vibration characteristics. However, this technique is difficult to accurately determine the degree and location of structural damages. In this paper, an inverse analysis combining the measured EMI signatures and the Transfer Matrix Method (TMM) is proposed to identify the damages in the steel rods. A milled groove is introduced into each steel specimen to simulate the local damage. By measuring the EMI signatures of the piezoelectric wafers bonded symmetrically on the upper and lower surfaces of the rectangular specimens respectively, the damage can be detected clearly, as well as natural frequencies being extracted in the relatively lower frequency range. The damage sizes and locations are further determined by connecting the frequency equations and any two measured natural frequencies. Tests on three samples show both damage sizes and locations are accurately detected, which indicates that the present method is quite feasible and effective for damage identification in the bar-type structures.

An efficient stochastic-based coupled model for damage identification in plate structures

Mode shape-based method has shown its dominance in failure identification of beams. However, it is a challenge for fault detection in a plate structure. It requires combined information in two directions to determine the damage location. In this study, a damage index, namely mode shape derivative based damage identification (MSDBDI), is applied to localize damage in fixed-free plate structures. Two-dimensional (2D) displacement mode shapes and their derivatives are used to identify the MSDBDI index. It is a fact that this indicator is stuck in indicating the damage severity. Hence, a coupled model between an artificial neural network (ANN) and antlion optimizer (ALO), so-called ALOANN is used to overcome this drawback. In this method, ALO instead of a backpropagation algorithm is used to look for the best initial values of learnable parameters of ANN i.e. weights and biases through mean squared error (MSE). These obtained parameters are added to ANN for damage identification. The efficiency of the proposed approach is tested with two numerical studies of the plate structures with single and multiple damage scenarios. In the first application, damage scenarios in a plate-like structure are detected. In the second application, ALO first is used to build a FE model of a composite structure based on a vibration experiment. Then the slab of the updated model is assumed to be suffered several damage scenarios. In both applications, failures are localized by using damage index. Then, the proposed approach is used to quantify the corresponding extent by means of changes in frequencies and displacement mode shapes. Values of damage index are achieved from modal properties of one or three out of the first five modes of the two considered structures. A conventional ANN also is investigated for comparison. Results of damage identification indicate that the damage indicator coupled with ALOANN show better performance compared with using ANN alone even when a noise level is assigned to modal properties.

Decentralized loop substructure identification for shear structures with virtual control system

Decentralized loop substructure identification for shear structures with virtual control system

Crack width identification for underwater concrete structures using temperature tracer method

Based on the particularity of underwater concrete structure, a temperature tracer method based on heat transfer theory for crack detection was proposed. The basic way to identify cracks is to change the thermodynamic boundary conditions around cracks after cracking, which will lead to the change of cooling rate of the heat source near cracks. Based on this idea, a set of crack monitoring system composed of a temperature sensing system, a heating system, a monitoring tube and multiple casing tubes was designed. By using this system, a series of crack monitoring tests were carried out on two kinds of concrete specimens. The results show that the monitoring scheme with casing tube can detect the crack position in still water, and this monitoring scheme can detect both crack position and width in flowing water. The sensitivity of it is higher than that of the monitoring scheme without casing tube.

A two-step method for additional mass identification in beam structures by measurements of natural frequencies and guided waves

This paper presents a two-step method for the identification of additional masses in beam structures. In the first step, relative natural frequency change (RNFC) curves are developed as an indicator for identifying the possible locations of additional masses at the global level. The RNFC curves based method allows detection of possible mass locations using natural frequencies alone and as such is a significant improvement over the state of the art. To further identify the precise locations of the masses, guided wavefield imaging is used for local mass detection in the second step. The two-step method is successfully applied for the precise localization of additional masses on a simply-supported beam. The paper firstly shows that additional mass-induced RNFC curves are different from those caused by cracks in beams. As a result, a theoretical formulation and validation of additional mass identification is needed and is the main novelty of the paper.

A new index for damage identification in beam structures based on modal parameters

A new index for damage identification in beam structures based on modal parameters

Phosphate binding sites prediction in phosphorylation-dependent protein-protein interactions.

Phosphate binding plays an important role in modulating protein-protein interactions, which are ubiquitous in various biological processes. Accurate prediction of phosphate binding sites is an important but challenging task. Small size and diversity of phosphate binding sites lead to a substantial challenge for developing accurate prediction methods. Here, we present the phosphate binding site predictor (PBSP), a novel and accurate approach to identifying phosphate binding sites from protein structures. PBSP combines an energy-based ligand-binding sites identification method with reverse focused docking using a phosphate probe. We show that PBSP outperforms not only general ligand binding sites predictors but also other existing phospholigand-specific binding sites predictors. It achieves ∼95% success rate for top 10 predicted sites with an average Matthews correlation coefficient value of 0.84 for successful predictions. PBSP can accurately predict phosphate binding modes, with average position error of 1.4 and 2.4 Å in bound and unbound datasets, respectively. Lastly, visual inspection of the predictions is conducted. Reasons for failed predictions are further analyzed and possible ways to improve the performance are provided. These results demonstrate a novel and accurate approach to phosphate binding sites identification in protein structures. The software and benchmark datasets are freely available at http://web.pkusz.edu.cn/wu/PBSP/. Supplementary data are available at Bioinformatics online.

Damage detection in structures using Particle Swarm Optimization combined with Artificial Neural Network

In this paper, a novel approach to damage identification in structures using Particle Swarm Optimization (PSO) combined with Artificial neural network (ANN) is proposed. With recent substantial advances, ANN has been extensively utilized in a wide variety of fields. However, because of the application of backpropagation algorithms based on gradient descent techniques, ANN may be trapped in local minima when seeking the best solution. This may reduce the accuracy of ANN. Therefore, we propose employing an evolutionary algorithm, namely PSO to deal with the local minimum problems of ANN. PSO is employed to improve the training parameters of ANN consisting of weight and bias ratios by reducing the deviation between calculated and desired results. These training parameters are then used to train the network. Since PSO applies global search techniques to look for the best solution, it can assist the network in avoiding local minima by looking for a beneficial starting point. In order to assess the effectiveness of the proposed approach, both numerical and experimental models with different damage scenarios are employed. The results show that ANN -PSO not only significantly reduces computational time compared to PSO but also possibly identifies damages in the considered structures more accurately than ANN and PSO separately.