Damage pattern recognition research represents one of the most challenging tasks in structural health monitoring (SHM). The vagueness in defining damage and the significant overlap between damage states contribute to the challenges associated with proper damage classification. Uncertainties in the damage features and how they propagate during the damage detection process also contribute to uncertainties in SHM. This paper introduces an integrated method for damage feature extraction and damage recognition. We describe a robust damage detection method that is based on using artificial neural network (ANN) to compute the wavelet energy of acceleration signals acquired from the structure. We suggest using the wavelet energy as a damage feature to classify damage states in structures. A case study is presented that shows the ability of the proposed method to detect and pattern damage using the American Society of Civil Engineers (ASCEs) benchmark structure. It is suggested that an optimal ANN architecture can detect damage occurrence with good accuracy and can provide damage quantification with reasonable accuracy to varying levels of damage.

With the aging of infrastructure worldwide and the increasing availability of cost efficient sensing equipment, the necessity to implement damage identification and classification systems on civil structures has become imperative. Structural health monitoring (SHM) is the nonintrusive collection and analysis of data from structures for damage detection and diagnosis. The intention of SHM is to characterize the structure’s performance and to help maintain the structural performance over its years of service. SHM also helps reduce operation costs through early damage detection. Successful SHM techniques have been applied to other engineering disciplines where the mass of the structure is small compared with civil structures. Vibration-based SHM assumes that the structural dynamic response will depart from its normal pattern when damage occurs in the structure. Thus, damage detection is contingent upon successfully extracting sensitive damage feature(s), patterning such feature(s) and realizing changes in these patterns as damage develops.

Over the past two decades numerous research methods with the objective of extracting sensitive damage feature(s) have been suggested and tested on several structures [

Summary of damage detection methods for the ASCE benchmark structure.

Reference | Author(s) | Damage detection method |
---|---|---|

Reference document—No data | Johnson et al. [ | Detailed Description of Phase I—Simulated |

Dyke et al. [ | Detailed Description of Phase II—Experimental | |

Phase I: Simulated data | Dyke et al. [ | Loss of stiffness of members byoptimizing modal parameters |

Hera et al. [ | Spikes in Level 1 details of wavelet decomposed signals | |

Yang et al. [ | Spectral analysis to identify stiffness parameters | |

Hera and Hou [ | Spikes in Level 1 details of wavelet decomposed signals | |

Sun and Chang [ | Covariance of response using wavelet packets | |

Lam et al. [ | Loss of stiffness using modal update and identification | |

Yuen et al. [ | Loss of stiffness of members using modal parameter extraction and Bayesian modal updating | |

Lus et al. and Caicedo et al. [ | State space model, eigensystem realization algorithm and optimization using modal parameters | |

Bernal and Gunes [ | Extraction of a matrix proportional to structure flexibility | |

Lin et al. [ | Time-frequency features obtained using Hilbert-Huang transform of the intrinsic mode functions | |

Chase et al. [ | Recursive least square to identify changes in stiffness matrix | |

Wu and Li [ | Eingen-sensitive FE for damage detection in ambient vibration | |

Yang and Huang [ | A recursive nonlinear estimation method is used | |

Mizuno and Fujino [ | Haar wavelet decomposition, quantization, and dissimilarity | |

Zhou et al. [ | Residual values from subspace-modal identification | |

Phase II: Simulated data | Hou and Hera [ | Spikes in Level 1 details of wavelet decomposed signals using Daubechies and Meyer wavelets |

Barroso and Rodriguez [ | Comparison of healthy to damage curvature in the mode shapes | |

Casciati [ | Discrepancy between healthy and damaged states using sum of squared errors | |

Phase II: Simulated and experimental data | Hera and Hou [ | Modal parameters determined using continuous wavelet transform |

Dincal and Raich [ | Minimization of error term between FRF of experimental & simulated data | |

Nair et al. [ | Structural stiffness change based on poles; pattern classification with autoregressive coefficients | |

Phase II: experimental data only | Ching and Beck [ | Expectation-Maximization algorithm used to find most probable stiffness parameters—Config. 2–9 |

Giraldo et al. [ | Loss of stiffness of members—Config 2–6 | |

Lynch [ | Pole location using system identification, Config. 1–5 | |

Liu et al. [ | Time-frequency obtained using Hilbert-Huang transform of intrinsic modes—Config. 7 & 8 | |

McCuskey et al. [ | Neural-wavelet module—All Configurations | |

Carden and Brownjohn [ | Autoregressive moving average (ARMA) to build damage classifiers for different damage configurations |

More recently, a few researchers have focused on the use of artificial neural networks (ANN) for damage pattern recognition. ANN consists of a group of interconnected processing units called neurons. Each neuron performs a simple computational process and has a transfer function associated with the layer that operates at the node level. ANN has the capability to learn from example datasets by changing the numerical biases and weights of the network [

The application of such stiffness-based techniques to large civil structures has been challenging because of the insignificant effect of the relatively small changes in stiffness due to damage compared with the large mass of these structures. Elkordy et al. [

Several signal processing methods have been promoted for feature extraction such as Fourier transform, Wavelet transform and Wavelet Multi-Resolution Analysis (WMRA) [

Much of the above noted research was focused on damage feature extraction rather than on damage pattern recognition. Sohn et al. [

In this paper, we suggest using available damage observations to identify the optimal ANN structure (i.e., number of hidden layers and number of neurons in each hidden layer). An optimization process is suggested to identify the optimal ANN structure for successful damage pattern classification. Here we used acceleration data collected experimentally from Phase II of the ASCE benchmark structure to develop and test the proposed damage pattern recognition method. Our motivation was to demonstrate the possible use of an optimized neural-wavelet module to detect and quantify damage with reasonable accuracy in the ASCE benchmark structure. The proposed framework is extendable for damage detection and quantification in other structures.

The American Society of Civil Engineers (ASCE) benchmark study was conducted by the International Association for Structural Control (IASC) ASCE Structural Health Monitoring Task Group as a resource for validating damage detection techniques. The ASCE Benchmark Group generated structural response data from a 2

(a) 3D schematic of the ASCE benchmark structure. (b) Location of the accelerometers and shaker on the ASCE benchmark structure.

Phase I of the ASCE benchmark study was generated by means of a finite element model considering varying levels of damage [

As presented in Table

The ASCE benchmark structure was built at approximately one-third scale and is located at the University of British Columbia [

Damage cases and quantified damage metric (

Structure Configuration | Damage class | |
---|---|---|

( | 0 | Healthy |

( | 28.4 | PD |

( | 21.3 | PD |

( | 8.5 | PD |

( | 31.2 | PD |

( | 85.1 | FD |

( | 100 | FD |

( | 91.1 | FD |

E: East, SE: South-East, N: North, PD: Partially Damaged, FD: Fully Damaged.

Our proposed damage severity metric, denoted

Here we suggest a computational method for feature extraction and damage recognition based on integrating ANN and WMRA. The proposed method is used for damage feature extraction by realizing the changes in the energy of structural acceleration signals computed in the wavelet domain as a result of damage. The proposed method has been previously validated using simulated and experimental data on bridge structures [

The development of the integrated damage pattern recognition method outlined in this paper includes the following steps: (

The acceleration signals, denoted

WMRA enables the decomposition of the acceleration signal in the time domain into component signals at different frequency levels named approximations and details. Scaling a wavelet simply means stretching or compressing it. The smaller the scale, the more the wavelet will be compressed while the larger the scale, the more the wavelet will be stretched. Therefore, low scales allow analyzing rapidly changing details (high frequency components) and high-scales allow analyzing slowly changing features (low-frequency components).

In civil structures, it has been shown that most of the main frequency components are low-frequency components (ranging 5–30 Hz) [

Schematic representation of wavelet multi-resolution analysis showing the decomposition of the original signal into

Consider the discrete acceleration signal

The proposed framework aims at establishing the complex relationship relating the structural dynamics (here accelerations) between different zones of the healthy structure. This general framework is shown schematically in Figure

Schematic representation of the neural-wavelet damage detection method (a) general application of method to any structure divided to

We suggest a damage feature denoted

The damage feature was obtained by comparing the monitored acceleration signal at sensor 13 and the signal predicted by ANN. The damage feature denoted

Here, we only considered the structure’s response data from accelerometers 5, 6, 9, 12, 13 and 15 shown on the benchmark structure plans described in Figure

ANNs use an iterative process to learn a pattern and generate a nonlinear mapping system between system inputs and output. Here, ANN is used to learn the complex healthy signal of the structure at sensor 13 by observing the signals at sensors 5, 6, 9, 12 and 15. The input layer of ANN in this study has five neurons corresponding to the five acceleration data inputs acquired by accelerometers (5, 6, 9, 12 and 15) and one neuron at the output layer acquired by accelerometer 13. Each neuron has a transfer function associated with the layer that operates at the node level. All layers use the log-sigmoid transfer function, with the exception of the output layer, which has a linear transfer function. The choice of these transfer functions was based on a parametric investigation conducted on the benchmark data [

The neural network’s ability to accurately mimic the healthy signal is dependent upon the architecture of ANN. In this study we target identifying the optimal architecture of ANN and defining the number of hidden layers and the number of neurons per layer such that damage detection is maximized. Design of ANN usually targets achieving a minimum training error which is considered a modeling tool criterion for acceptance of a neural network. Successful damage detection necessitates that the damage feature (

Successful development shall enable ANN to function as a damage classifier in addition to its role in damage feature extraction. This can be achieved by finding the optimal ANN architecture such that the maximum success rate of the damage classification is achieved. The process of successful classification rate maximization is performed here in the context of system optimization where the objective function that is used for defining the classifier is minimized. The optimization process can be described by defining the objective function, the design variables, the design parameters and the optimization constraints.

The

The

Considering the ASCE benchmark Phase II-E data,

Schematic representation of the acceleration signals and the 15 windows in the signals.

Raw acceleration signal (red) observed at sensor 9 in the benchmark structure versus the third approximation of the acceleration signal (black) used for damage detection.

The optimal ANN architecture and the damage classifier were tested using the testing data including Configurations 2, 3, 4 and 9. These data sets were not used in developing the damage classifier. To consider uncertainty in damage recognition, the probability of damage is used as the damage metric to represent the level of damage in the structure for each testing configuration. The damage metric denoted

Schematic representation of probability of damage. Hatched area represents the cumulative probability of damage representing the neural-wavelet damage metric

The optimization process determined that the optimal ANN architecture includes three hidden layers consisting of 2, 7 and 10 neurons on the first, second and third hidden layers respectively. A schematic representation of the optimal network is shown in Figure

Optimal ANN for damage detection using the neural-wavelet method.

Number of neurons versus classifier objective function. (a) One hidden layer for classifier (

A comparison between the three optimal neural network architectures with one hidden layer denoted NN1 (

Comparison between three optimal neural networks using one hidden layer denoted NN1 (

Figure

Neural-wavelet damage metric (

The above results provide a damage detection method that can detect damage in eight damage configurations of Phase II-E in the ASCE benchmark structure; the proposed damage metric can also be used to classify/quantify damage severity in the benchmark structure with reasonable accuracy. This is attributed to the fact that the damage feature was optimized for classification of damage. The optimization process correctly categorized the “partially damaged” benchmark configurations resulting in probabilities of damage that range from between 40 and 60 percent. The “fully damaged” configurations were also correctly classified for having probabilities of damage ranging between 90 and 100 percent. The optimal neural-wavelet method has proven capable of detecting damage occurrence and showed good sensitivity in quantifying damage severity for low and high damage configurations. However, the model showed less accuracy in quantifying partially damaged cases which might be enhanced if other configurations of partially damage data were used in establishing the classifier.

Finally, the proposed neural-wavelet framework can be applied to damage detection and classification of real world structures. This requires developing a finite element model to simulate the structure dynamic behavior and validate this model using historical data observed from the structure. Damage can then be introduced to the finite element model with different levels of damage severity and at different locations. This simulated data can be used to optimize the ANN and establish the neural-wavelet module. The developed neural-wavelet module can then be used to detect and classify damage in the real structure.

We need to emphasize, however, that the overall damage metric is not unique but provides an indicator to damage severity. It is important to realize that damage is a nonmeasurable quantity and damage metrics cannot be directly compared. This damage quantification inaccuracy is an intrinsic characteristic of damage related to the definition of damage as suggested by many researchers [

We demonstrated that it is possible to establish a damage pattern recognition method by designing a damage classifier that integrates ANN and WMRA. An optimization technique using derivative free optimization (genetic algorithm) was used to identify the optimal ANN architecture. A neural network, including three hidden layers with 2, 7, and 10 neurons in the first, second and third hidden layers respectively, was capable of successfully detecting and quantifying damage in the ASCE benchmark structure with a reasonable sensitivity.

The neural-wavelet method aimed at establishing the underlying relationships between the structural dynamic responses (acceleration signals) at the different locations of the structure during healthy performance then recognized changes in such relationships as damage advanced in the structure. While the use of ANN to learn the underlying relation of structural dynamics proved successful, some drawbacks of ANN are related to their intolerance to uncertainty in training data. It is therefore suggested that other learning methods with higher tolerance to classification uncertainty such as neural-fuzzy inference systems, adaptive fuzzy learning from examples [

The author greatly appreciates the financial support by Defense Threat Reduction Agency (DTRA). Special thanks to research assistants: Scott Horton, Molly McCuskey and Erdogan Altunok for their efforts in the SHM research projects with the author.