Structural health monitoring of civil structures: A diagnostic framework powered by deep metric learning

Torzoni, Matteo; Manzoni, Andrea; Mariani, Stefano

doi:10.1016/j.compstruc.2022.106858

Cited by 21 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolution is a key component of CNN for SDI. Suppose that the size of input data I and convolution kernel k are [I h , I w , I d ] = [6,10,3] and [k h , k w , k d ] = [3,3,3] respectively. During convolution, the convolution kernel stride is s = 1, and the original data is filled with p = 0 leading to the size of feature map will be changed.…”

Section: Convolutionmentioning

confidence: 99%

“…Nowadays, steel and concrete engineering structures have been widely used in large projects, buildings, and other fields, whose resistance may be weakened, or damages may be accumulated with the influence of natural disasters, environmental erosion, sudden collision etc [1][2][3]. Thus, long-term structural health monitoring (SHM) for such structures is of great practical significance to find out the damage in time and evaluate the service status effectively.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A new convolutional neural network-based framework and data construction method for structural damage identification considering sensor placement

Yang

Peng

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

In the application of data driven Structural Damage Identification (SDI) based on supervised deep learning technology, valid data demarcation is the foundation; a convolutional neural network model with learning ability and capability of processing rich signal information is the core. Based on this understanding, this work makes three contributions: Firstly, the structural damage location and severity are jointly demarcated, and the SDI problem is transformed into a multi-classification task. Secondly, a 3D Signal processing Convolutional Neural Networks (3DS-CNN) is designed with an attempt to identify the complex and slight damages using the most basic network structure. Thirdly, a “Major and Subsidiary” Data Construction (MSDC) method integrating the key Intrinsic Mode Function (IMF) is proposed to construct 3D data. Then the proposed schemes are verified by two different structures. The results show that the 3DS-CNN has excellent damage identification ability for small-size data with noise pollution. MSDC method can enrich the feature information of the damage signals and help the network with deep feature excavation, even if the vibration signals are heavily polluted. Going one step further, the impact of sensor placement is discussed, and it is found that when external excitation is obvious, better SDI accuracy can be achieved even using a single sensor signal with slight noise. When the noise interference is obvious, the generalization ability and noise robustness of the network can be enhanced by optimizing sensor placement. In this case, the sensor placement criteria and the sensitive nodes of the structure should be comprehensively and carefully considered to avoid mutual “coupling” interference of data between sensors.

show abstract

Section: Convolutionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A new convolutional neural network-based framework and data construction method for structural damage identification considering sensor placement

Yang

Peng

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…The network input is defined as the predictor data. Each fully connected layer handles the input data by means of a weight matrix and a bias vector; an activation function (e.g., the rectified linear unit, hyperbolic tangent, sigmoid function, and linear function) can provide nonlinear transformations of the information/data, see [24][25][26]. A backpropagation algorithm is adopted to tune the weights of the RANN, managing a loss function (as a prediction error between the input and the output) to be minimized with the stochastic gradient descent algorithm.…”

Section: Network Configurationmentioning

confidence: 99%

A Parsimonious Yet Robust Regression Model for Predicting Limited Structural Responses of Remote Sensing

Entezami,

Behkamal,

De Michele

et al. 2023

Ecsa 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…By understanding how the structures respond to the external forces, it can be ensured that they withstand such loads as well as the relevant environmental conditions [4]. Modal analysis serves as a crucial tool used in model order reduction techniques [5,6] and structural health monitoring (SHM) [7]. In recent times, the use of vision-based measurements has emerged as a highly effective method for full-field identification [8,9], damage detection [10], model updating [11], and response measurement [12,13].…”

Section: Introductionmentioning

confidence: 99%

Vision-Based Structural Identification Using an Enhanced Phase-Based Method

Azizi,

Karami,

Mariani

2023

Ecsa 2023

Self Cite

View full text Add to dashboard Cite

show abstract

Structural health monitoring of civil structures: A diagnostic framework powered by deep metric learning

Cited by 21 publications

References 43 publications

A new convolutional neural network-based framework and data construction method for structural damage identification considering sensor placement

A new convolutional neural network-based framework and data construction method for structural damage identification considering sensor placement

A Parsimonious Yet Robust Regression Model for Predicting Limited Structural Responses of Remote Sensing

Vision-Based Structural Identification Using an Enhanced Phase-Based Method

Contact Info

Product

Resources

About