Extraction of Environmental and Operational Conditions of Wind Turbines using Tower Response Data for Structural Health Monitoring

Many of the wave propagation based structural health monitoring techniques rely on some knowledge of the structure in a healthy state in order to identify damage. Baseline measurements are recorded when a structure is pristine and are stored for comparison to future data. A concern with the use of baseline subtraction methods is the ability to discern structural changes from the effects of varying environmental and operational conditions when analyzing the vibration response of a system. The use of a standard baseline subtraction technique may falsely indicate damage when environmental or operational variations are present between baseline measurements and new measurements. A procedure was outlined for the method, including excitation and recording of Lamb waves, and the use of damage detection algorithms. In this paper, several tests are performed and the results are used to help develop the damage detection algorithms previously described, and to evaluate the performance of the instantaneous baseline SHM technique. Analytical testing is first performed by feeding known input signals into each damage detection algorithm and analyzing the output data. The results of the analytical testing are used to help develop the damage detection algorithms.

Download Full-text

Artificial Neural Networks for Structural Health Monitoring of Helicopter Harsh Landings

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.390.192 ◽

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.

Download Full-text