Experimental Identification of Structural Damage by Neural Networks

1995 ◽  
Author(s):  
Rosario Ceravolo ◽  
Alessandro De Stefano ◽  
Michel Grosjacques ◽  
Donato Sabia
Keyword(s):  
Neural Networks ◽  
Dynamic Response ◽  
Structural Damage ◽  
Dynamic Behaviour ◽  
Damage Identification ◽  
Numerical Models ◽  
Analysis Data ◽  
Simply Supported ◽  
Response Data ◽  
Experimental Identification

Abstract The problems involved in structural damage identification by means of pattern recognition neural techniques are addressed. As is known, mechanical system recognition can be achieved by making appropriate use of these connectionistic instruments. Recognition takes place on the basis of an incomplete set of data contained in the system’s dynamic response. Some methods, previously developed by the authors on the basis of numerical models, are validated through the use of noisy data. To this end, an experimental research was carried out on simply supported beams. The tests made it possible to acquire a wealth of dynamic response data from beams damaged artificially to produce defects of varying entity and position. The data obtained, appropriately normalised, are used as inputs for supervised neural networks. In particular, frequency analysis data are able to provide a summary characterisation of the distortion in a structure’s dynamic behaviour. Different signal processing and analysis procedures are compared in order to identify the best resolution and sensitivity capabilities in the diagnostic performance of neural networks.

Vibration-Based SHM of Ordinary Buildings: Detection and Quantification of Structural Damage

2015 ◽  
Author(s):  
Alessio Pierdicca ◽  
Francesco Clementi ◽  
Diletta Maracci ◽  
Daniela Isidori ◽  
Stefano Lenci
Keyword(s):  
Structural Damage ◽  
Damage Identification ◽  
Residual Life ◽  
Numerical Models ◽  
Natural Aging ◽  
Real Structure ◽  
Industrial Building ◽  
Ground Acceleration ◽  
Earthquake Scenario ◽  
Structural Health

One of the most important issues in civil and in mechanical engineering is the detection of structural damages, which are defined as changes of material properties, of boundary conditions and of system connectivity, which adversely affect the system’s performances. The damage identification process generally requires establishing existence, localization, type and intensity of the damage. During its service life, a structure, besides his natural aging, can be subjected to earthquakes. These events may have a deep impact on building safety and a continuous monitoring of the structure health conditions, through Structural Health Monitoring (SHM) techniques, is necessary in many cases. Within this a background, the purpose of this work is to propose an integrated novel approach for the diagnosis of structures after a seismic event. The proposed monitoring system is based on recording the accelerations of the real structure during a seismic input, and the reintroduction of them into a numerical model, suitably tuned, in order to outline a possible post-earthquake scenario. This approach provides an estimation of the health of the building and of its residual life, and to detect and quantify the damage, some of the crucial aspects of SHM. Actually, we also get both online and self-diagnosis of the structural health. The technique is applied to a real structure, an industrial building liable of some seismic vulnerabilities. It it did not undergo an earthquake, so we have not recordered accelerations, and get them from a different numerical models subjected to the ground acceleration of a realistic earthquake.

Artificial Neural Networks for Structural Health Monitoring of Helicopter Harsh Landings

2013 ◽  
Vol 390 ◽  
pp. 192-197
Author(s):  
Giorgio Vallone ◽  
Claudio Sbarufatti ◽  
Andrea Manes ◽  
Marco Giglio
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Structural Damage ◽  
Numerical Models ◽  
Damage State ◽  
Operational Conditions ◽  
Structural Health ◽  
Artificial Neural

The aim of the current paper is to explore fuselage monitoring possibilities trough the usage of Artificial Neural Networks (ANNs), trained by the use of numerical models, during harsh landing events. A harsh landing condition is delimited between the usual operational conditions and a crash event. Helicopter structural damage due to harsh landings is generally less severe than damage caused by a crash but may lead to unscheduled maintenance events, involving costs and idle times. Structural Health Monitoring technologies, currently used in many application fields, aim at the continuous detection of damage that may arise, thereby improving safety and reducing maintenance idle times by the disposal of a ready diagnosis. A landing damage database can be obtained with relatively little effort by the usage of a numerical model. Simulated data are used to train various ANNs considering the landing parameter values as input. The influence of both the input and output noise on the system performances were taken into account. Obtained outputs are a general classification between damaged and undamaged conditions, based on a critical damage threshold, and the reconstruction of the fuselage damage state.

Application of BP Neural Network in Structural Damage Diagnosis of Bridge behind Abutment

2016 ◽  
Vol 847 ◽  
pp. 440-444 ◽  
Author(s):  
Yu Hui Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bp Neural Network ◽  
Structural Damage ◽  
Damage Identification ◽  
Current Knowledge ◽  
Horizontal Displacement ◽  
Structural Deformation ◽  
Bp Network ◽  
Damage Location

BP neural network is introduced and applied to identify and diagnose both location and extent of bridge structural damage; static load tests and dynamic calculations are also made on bridge structural damage behind abutment. The key step of this method is to design a reasonably perfect BP network model. According to the current knowledge, three BP neural networks are designed with horizontal displacement rate and inherent frequency rate as damage identification indexes. The neural networks are used to identify the measurement of structure behind abutment and the calculation of damage location and extent, at the same time, they can also be used to compare and analyze the results. The test results show that: taking the two factors (static structural deformation rate and the change rate of natural frequency in dynamic response) as input vector, the BP neural network can accurately identify the damage location and extent, implying a promising perspective for future applications.

Structural Damage Detection Using Parameters Combined with Changes in Flexibility Based on BP Neural Networks

2011 ◽  
Vol 243-249 ◽  
pp. 5475-5480
Author(s):  
Zhang Jun
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Damage Detection ◽  
Bp Neural Network ◽  
Structural Damage ◽  
The State ◽  
Structural Damage Detection ◽  
Bp Neural Networks ◽  
Simply Supported ◽  
Modal Flexibility

Modals of BP neural networks with different inputs and outputs are presented for different damage detecting schemes. To identify locations of structural damages, the regular vectors of changes in modal flexibility are looked on as inputs of the networks, and the state of localized damage are as outputs. To identify extents of structural damage, parameters combined with changes in flexibility and the square changes in frequency are as inputs of the networks, and the state of damage extents are as outputs. Examples of a simply supported beam and a plate show that the BP neural network modal can detect damage of structures in quantitative terms.

Sign in / Sign up

Export Citation Format

Share Document