Structural Damage Detection Using Signal Pattern-Recognition

2008 ◽  
Vol 400-402 ◽  
pp. 465-470 ◽  
Author(s):  
Long Qiao ◽  
Asad Esmaeily ◽  
Hani G. Melhem
Keyword(s):  
Pattern Recognition ◽  
Damage Detection ◽  
Structural Damage ◽  
Experimental Studies ◽  
Least Square ◽  
Structural Damage Detection ◽  
Damage Scenario ◽  
Damage Pattern ◽  
Damage Scenarios ◽  
Unknown Damage

Deterioration significantly affects the structure performance and safety. A signal-based pattern-recognition procedure is applied for structural damage detection with a limited number of input/output signals. The method is based on extracting and selecting the sensitive features of the structure response to form a unique pattern for any particular damage scenario, and recognizing the unknown damage pattern against the known database to identify the damage location and level (severity). In this study, two types of transformation algorithms are implemented separately for feature extraction: (1) Continuous Wavelet Transform (CWT); and (2) Wavelet Packet Transform (WPT). Three pattern-matching algorithms are also implemented separately for pattern recognition: (1) correlation, (2) least square distance, and (3) Cosh spectral distance. To demonstrate the validity and accuracy of the procedure, experimental studies are conducted on a simple three-story steel structure. The results show that the features of the signal for different damage scenarios can be uniquely identified by these transformations, and correlation algorithms can best perform pattern recognition to identify the unknown damage pattern. The proposed method can also be used to possibly detect the type of damage. It is suitable for structural health monitoring, especially for online monitoring applications.

A Multi-State Strategy for Structural Damage Detection Using Sensitivity of Weighted Transmissibility Function

2021 ◽  
pp. 2150144
Author(s):  
Ziwei Luo ◽  
Huanlin Liu ◽  
Ling Yu
Keyword(s):  
Damage Detection ◽  
Structural Damage ◽  
Model Updating ◽  
Structural Parameters ◽  
Experimental Studies ◽  
Fe Model ◽  
Limited Information ◽  
Structural Damage Detection ◽  
State Strategy ◽  
Output Only

In practice, a model-based structural damage detection (SDD) method is helpful for locating and quantifying damages with the aid of reasonable finite element (FE) model. However, only limited information in single or two structural states is often used for model updating in existing studies, which is not reasonable enough to represent real structures. Meanwhile, as an output-only damage indicator, transmissibility function (TF) is proven to be effective for SDD, but it is not sensitive enough to change in structural parameters. Therefore, a multi-state strategy based on weighted TF (WTF) is proposed to improve sensitivity of TF to change in parameters and in order to further obtain a more reasonable FE model for SDD in this study. First, WTF is defined by TF weighted with element stiffness matrix, and relationships between WTFs and change in structural parameters are established based on sensitivity analysis. Then, a multi-state strategy is proposed to obtain multiple structural states, which is used to reasonably update the FE model and detect structural damages. Meanwhile, due to fabrication errors, a two-stage scheme is adopted to reduce the global and local discrepancy between the real structure and the FE model. Further, the [Formula: see text]-norm and the [Formula: see text]-norm regularization techniques are, respectively, introduced for both model updating and SDD problems by considering the characteristics of problems. Finally, the effectiveness of the proposed method is verified by a simply supported beam in numerical simulations and a six-storey frame in laboratory. From the simulation results, it can be seen that the sensitivity to structural damages can be improved by the definition of WTF. For the experimental studies, compared with the FE model updated from the single structural state, the FE model obtained by the multi-state strategy has an ability to more reasonably describe the change of states in the frame. Moreover, for the given structural damages, the proposed method can detect damage locations and degrees accurately, which shows the validity of the proposed method and the reliability of the updated FE model.

Flexibility-Based Objective Functions for Constrained Optimization Problems on Structural Damage Detection

2011 ◽  
Vol 186 ◽  
pp. 383-387 ◽  
Author(s):  
Xi Chen ◽  
Ling Yu
Keyword(s):  
Damage Detection ◽  
Constrained Optimization ◽  
Objective Function ◽  
Structural Damage ◽  
Optimization Problems ◽  
Objective Functions ◽  
Structural Damage Detection ◽  
Constrained Optimization Problems ◽  
Modal Assurance Criterion ◽  
Damage Scenarios

Based on concepts of structural modal flexibility and modal assurance criterion (MAC), a new objective function is defined and studied for constrained optimization problems (COP) on structural damage detection (SDD) in this paper. Compared with traditionally objective function, which is defined based on natural frequencies and MAC, effect of objective functions on robustness of SDD calculation is evaluated through numerical simulation of a 2-storey rigid frame. Structural damages are identified by solving the COP on SDD based on an improved particle swarm optimization (IPSO) algorithm. Weak and multiple damage scenarios are mainly considered in various noise conditions. Some illustrated results show that the newly defined objective function is better than the traditional ones. It can be used to identify the damage locations but also to quantify the severity of weak and multiple damages in measurement noise conditions.

Structural Damage Detection Based on Fuzzy LS-SVM Integrated Quantum Genetic Algorithm

2010 ◽  
Vol 20-23 ◽  
pp. 1365-1371 ◽  
Author(s):  
Jian Hong Xie
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Fuzzy Logic ◽  
Damage Detection ◽  
Health Monitoring ◽  
Structural Damage ◽  
Least Square ◽  
Support Vector ◽  
Structural Damage Detection ◽  
Quantum Genetic Algorithm

Structural damage detection and health monitoring is very important in many applications, and a key related issue is the method of damage detection. In this paper, Fuzzy Least Square Support Vector Machine (FLS-SVM) is constructed by combining Fuzzy Logic with LS-SVM, and a real-coded Quantum Genetic Algorithm (QGA) is applied to optimize parameters of FLS-SVM. Then, the method of FLS-SVM integrated QGA is used to detect damages for fiber smart structures. The testing results show FLS-SVM possesses the higher detecting accuracy and the bitter dissemination ability than LS-SVM under the same conditions, and the parameters of FLS-SVM can be effectively optimized by the real-coded QGA. The proposed method of FLS-SVM integrated QGA is effective and efficient for structural damage detection.

Structural Damage Detection and Classification Algorithm Based on Artificial Immune Pattern Recognition

2014 ◽  
Vol 945-949 ◽  
pp. 1265-1269
Author(s):  
Dong Wei Zhang ◽  
Yong Ming Mao ◽  
Feng Long Kan ◽  
Nan Chen
Keyword(s):  
Pattern Recognition ◽  
Damage Detection ◽  
Structural Damage ◽  
Damage Model ◽  
Classification Algorithm ◽  
Immune Recognition ◽  
Structural Damage Detection ◽  
Classification Problems ◽  
Artificial Immune ◽  
Classification Rate

This paper studies the structural damage detection and classification problems by using the artificial immune system which has the extremely powerful capabilities of adaptive and the bionic principle between learning and memory. We proposed an artificial immune pattern recognition and structural detection classification algorithm through imitating the immune recognition and learning mechanism. With the structure of benchmark, the damage detection and classification are tested. The simulation results show the classification rate is very well. The algorithm based on the immune learning and evolution can produce the high quality memory cells which effectively identify all kinds of structural damage model.

Sign in / Sign up

Export Citation Format

Share Document