论文信息 - Detection of Structural Damage in Medium Density Fiberboard Panels using Neural Network Method

Detection of Structural Damage in Medium Density Fiberboard Panels using Neural Network Method

This research assessed the feasibility of using a neural network to detect low levels of damage in small samples of medium density fiberboard (MDF). The neural network was a three-layer back-propagation network. The undamaged stress wave frequency spectrum patterns were trained by the neural network. The trained patterns were then compared to stress waves patterns taken from MDF samples loaded to various percentages of their estimated failure load. In this experiment, if an application load is below the proportional limit, a small change in wave patterns occurs. The neural network has the unique ability to train data to recognize spectral patterns and has been used with success for the detection of structural damage.

Robert W. Rice | R. Rice | Way Long

[1] Miyoung Shin Shin,et al. A Radial Basis Function Approach to Pattern Recognition and Its Applications , 2000 .

[2] G C Lee,et al. NEURAL NETWORKS TRAINED BY ANALYTICALLY SIMULATED DAMAGE STATES , 1993 .

[3] James H. Garrett,et al. Use of neural networks in detection of structural damage , 1992 .

[4] R. D. Vanluchene,et al. Neural Networks in Structural Engineering , 1990 .

[5] R. Lippmann,et al. An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[6] S. H. Huang,et al. Artificial neural networks in manufacturing: concepts, applications, and perspectives , 1994 .

[7] Jozsef Bodig,et al. Mechanics of Wood and Wood Composites , 1982 .

[8] Y. S. Tarng,et al. Tool failure diagnosis in milling using a neural network , 1994 .

[9] R. Ross,et al. Nondestructive testing for assessing wood members in structures: a review , 1994 .

[10] R. E. Shannon,et al. A neural network to predict particleboard manufacturing process parameters , 1991 .

[11] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .