Structural Damage Identification Using Wavelet Packet Analysis and Neural Network

2006 ◽  
Vol 324-325 ◽  
pp. 205-208
Author(s):  
Qing Guo Fei ◽  
Ai Qun Li ◽  
Chang Qing Miao ◽  
Zhi Jun Li
Keyword(s):  
Neural Network ◽  
Structural Damage ◽  
Damage Identification ◽  
Wavelet Packet ◽  
Uniform Design ◽  
Network Models ◽  
Sampling Technique ◽  
Wavelet Packet Analysis ◽  
Neural Network Models ◽  
Network Training

This paper describes a study on damage identification using wavelet packet analysis and neural networks. The identification procedure could be divided into three steps. First, structure responses are decomposed into wavelet packet components. Then, the component energies are used to define damage feature and to train neural network models. Finally, in combination with the feature of the damaged structure response, the trained models are employed to determine the occurrence, the location and the qualification of the damage. The emphasis of this study is put on multi-damage case. Relevant issues are studied in detail especially the selection of training samples for multi-damage identification oriented neural network training. A frame model is utilized in the simulation cases to study the sampling techniques and the multi-damage identification. Uniform design is determined to be the most suitable sampling technique through simulation results. Identifications of multi-damage cases of the frame including different levels of damage at various locations are investigated. The results show that damages are successfully identified in all cases.

scholarly journals Enhancement of shearography-based damage identification using best tree wavelet packet analysis

2018 ◽  
Vol 204 ◽  
pp. 06002
Author(s):  
Andrzej Katunin ◽  
Hernani Lopes ◽  
José Viriato Araújo dos Santos
Keyword(s):  
Wavelet Transforms ◽  
Structural Damage ◽  
Damage Identification ◽  
Experimental Testing ◽  
Wavelet Packet ◽  
High Sensitivity ◽  
Industrial Applications ◽  
Wavelet Packet Analysis ◽  
Destructive Testing ◽  
Signal Processing Methods

Shearography found many industrial applications as a non-destructive testing method due to its high spatial resolution and contactless measurements. However, to detect small structural damage, shearography should be enhanced by applying advanced signal processing methods to results of experimental testing. In this paper, the authors present an enhanced method based on the best tree wavelet packet analysis, which allows for extraction of the most informative nodes from the 2D wavelet packet decomposition tree. The proposed method is more effective than typical wavelet transforms due to its ability of adaptive selection of the best basis. The efficiency of the method was verified experimentally on damaged plates. The obtained results clearly show high sensitivity to the introduced small damage, which make the method attractive for industrial applications.

scholarly journals Streaming Batch Gradient Tracking for Neural Network Training (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13813-13814
Author(s):  
Siyuan Huang ◽  
Brian D. Hoskins ◽  
Matthew W. Daniels ◽  
Mark D. Stiles ◽  
Gina C. Adam
Keyword(s):  
Neural Network ◽  
Matrix Multiplication ◽  
Network Models ◽  
Principal Component ◽  
Batch Size ◽  
Neural Network Models ◽  
Network Training ◽  
Very Large Datasets ◽  
Vector Matrix ◽  
Batch Data

Faster and more energy efficient hardware accelerators are critical for machine learning on very large datasets. The energy cost of performing vector-matrix multiplication and repeatedly moving neural network models in and out of memory motivates a search for alternative hardware and algorithms. We propose to use streaming batch principal component analysis (SBPCA) to compress batch data during training by using a rank-k approximation of the total batch update. This approach yields comparable training performance to minibatch gradient descent (MBGD) at the same batch size while reducing overall memory and compute requirements.

scholarly journals Neural Network Training for the Detection and Classification of Oceanic Mesoscale Eddies

2020 ◽  
Vol 12 (16) ◽  
pp. 2625 ◽  
Author(s):  
Oliverio J. Santana ◽  
Daniel Hernández-Sosa ◽  
Jeffrey Martz ◽  
Ryan N. Smith
Keyword(s):  
Neural Network ◽  
Performance Metrics ◽  
Network Models ◽  
Mesoscale Eddies ◽  
Neural Network Models ◽  
Network Training ◽  
Different Types ◽  
Better Than ◽  
Satellite Altimetry Data

Recent advances in deep learning have made it possible to use neural networks for the detection and classification of oceanic mesoscale eddies from satellite altimetry data. Various neural network models have been proposed in recent years to address this challenge, but they have been trained using different types of input data and evaluated using different performance metrics, making a comparison between them impossible. In this article, we examine the most common dataset and metric choices, by analyzing the reasons for the divergences between them and pointing out the most appropriate choice to obtain a fair evaluation in this scenario. Based on this comparative study, we have developed several neural network models to detect and classify oceanic eddies from satellite images, showing that our most advanced models perform better than the models previously proposed in the literature.

Patterns of Functional Damage in Neural Network Models of Associative Memory

1995 ◽  
Vol 7 (5) ◽  
pp. 1105-1127 ◽  
Author(s):  
Eytan Ruppin ◽  
James A. Reggia
Keyword(s):  
Neural Network ◽  
Associative Memory ◽  
Structural Damage ◽  
Scaling Laws ◽  
Network Models ◽  
Analytical Framework ◽  
Network Size ◽  
Focal Lesions ◽  
Neural Network Models ◽  
Total Network

Current understanding of the effects of damage on neural networks is rudimentary, even though such understanding could lead to important insights concerning neurological and psychiatric disorders. Motivated by this consideration, we present a simple analytical framework for estimating the functional damage resulting from focal structural lesions to a neural network model. The effects of focal lesions of varying area, shape, and number on the retrieval capacities of a spatially organized associative memory are quantified, leading to specific scaling laws that may be further examined experimentally. It is predicted that multiple focal lesions will impair performance more than a single lesion of the same size, that slit like lesions are more damaging than rounder lesions, and that the same fraction of damage (relative to the total network size) will result in significantly less performance decrease in larger networks. Our study is clinically motivated by the observation that in multi-infarct dementia, the size of metabolically impaired tissue correlates with the level of cognitive impairment more than the size of structural damage. Our results account for the detrimental effect of the number of infarcts rather than their overall size of structural damage, and for the "multiplicative" interaction between Alzheimer's disease and multi-infarct dementia.

Method of complex copper-zinc ore typification using neural network models

2020 ◽  
Vol 5 ◽  
pp. 140-147 ◽  
Author(s):  
T.N. Aleksandrova ◽  
◽  
E.K. Ushakov ◽  
A.V. Orlova ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Neural Network Models ◽  
Copper Zinc ◽  
Complex Copper

Digital twin of equipment as a basis for the consumer in digital production

2020 ◽  
Keyword(s):  
Neural Network ◽  
Tool Wear ◽  
Chip Formation ◽  
Network Models ◽  
Machining Accuracy ◽  
Neural Network Models ◽  
Digital Twin ◽  
The Neural Network ◽  
Digital Production ◽  
Cyberphysical System

The neural network models series used in the development of an aggregated digital twin of equipment as a cyber-physical system are presented. The twins of machining accuracy, chip formation and tool wear are examined in detail. On their basis, systems for stabilization of the chip formation process during cutting and diagnose of the cutting too wear are developed. Keywords cyberphysical system; neural network model of equipment; big data, digital twin of the chip formation; digital twin of the tool wear; digital twin of nanostructured coating choice

Sign in / Sign up

Export Citation Format

Share Document