Structural Damage Identification Using Improved RBF Neural Networks in Frequency Domain

Vibration suppression of printed circuit boards using an external particle damper

Abstract: Particle damping is an effective method of passive vibration control, of recent research interest. The novel use of particle damper capsule on a Printed Circuit Board (PCB) and the development of Radial Basis Function neural network to accurately predict the acceleration response is presented here. The prediction of particle damping using this neural network is studied in comparison with the Back Propagation Neural network. Extensive experiments are carried out on a PCB for different combinations of particle damper parameters such as particle size, particle density, packing ratio, and the input force during the primary modes of vibration and the obtained results are used for training and testing of neural networks. Based on the prediction from the better trained network, useful design guidelines for the particle damper suitable for PCB are arrived at. The effectiveness of particle dampers for vibration suppression of PCB under random vibration environment is demonstrated based on these design guidelines.

Improved Complex-valued Radial Basis Function (ICRBF) neural networks on multiple crack identification

Abstract: Absolute mean percentage error (AMPE) of single crack and multiple crack identification using different RBF networks. A two-stage ICRBF neural network is developed for multiple crack identification.Conventional CRBF neural network is used in the first stage of ICRBF.Reduced search space moving technique is used in the second stage of ICRBF.Crack location and depth are identified using frequency domain vibration signals.ICRBF is more efficient followed by IRBF, CRBF, RBF and MLP neural networks. This paper introduces a new class of neural networks in complex space called Complex-valued Radial Basis Function (CRBF) neural networks and also an improved version of CRBF called Improved Complex-valued Radial Basis Function (ICRBF) neural networks. They are used for multiple crack identification in a cantilever beam in the frequency domain. The novelty of the paper is that, these complex-valued neural networks are first applied on inverse problems (damage identification) which come under the category of function approximation. The conventional CRBF network was used in the first stage of ICRBF network and in the second stage a reduced search space moving technique was employed for accurate crack identification. The effectiveness of proposed ICRBF neural network was studied first on a single crack identification problem and then applied to a more challenging problem of multiple crack identification in a cantilever beam with zero noise as well as 5% noise polluted signals. The results proved that, the proposed ICRBF and real-valued Improved RBF (IRBF) neural networks have identified the single and multiple cracks with less than 1% absolute mean percentage error as compared to conventional CRBF and RBF neural networks, mainly because of their second stage reduced search space moving technique. It appears that IRBF neural network is a good compromise considering all factors like accuracy, simplicity and computational effort.

Structural damage identification based on modified Cuckoo Search algorithm

Abstract: The Cuckoo search (CS) algorithm is a simple and efficient global optimization algorithm and it has been applied to figure out large range of real-world optimization problem. In this paper, a new formula is introduced to the discovering probability process to improve the convergence rate and the Tournament Selection Strategy is adopted to enhance global search ability of the certain algorithm. Then an approach for structural damage identification based on modified Cuckoo search (MCS) is presented. Meanwhile, we take frequency residual error and the modal assurance criterion (MAC) as indexes of damage detection in view of the crack damage, and the MCS algorithm is utilized to identifying the structural damage. A simply supported beam and a 31-bar truss are studied as numerical example to illustrate the correctness and efficiency of the propose method. Besides, a laboratory work is also conducted to further verification. Studies show that, the proposed method can judge the damage location and degree of structures more accurately than its counterpart even under measurement noise, which demonstrates the MCS algorithm has a higher damage diagnosis precision.

Application of RBF neural network in prediction of particle damping parameters from experimental data

Abstract: Particle damping is one of the recent passive damping methods and its relevance in space structural applications is increasing. This paper presents the novel application of a radial basis function (RBF) neural network to accurately predict the modal damping ratio of a particle damping system using system input parameters such as particle size, particle density, packing ratio, and their effect at different modes of vibration. The prediction of particle damping using the RBF neural network is studied in comparison with the back propagation neural (BPN) network on an aluminum alloy beam structure with extensive experimental tests. The prediction accuracy of the RBF neural network is significant with 9.83% error compared to 12.22% obtained by the BPN network for a best case. Limited experiments were also carried out on a mild steel beam to study and compare the trends predicted in earlier studies. The relationships obtained by the proposed method readily provide useful guidelines in the design of particle dam...

Prediction of Particle Damping Parameters Using RBF Neural Network

Abstract: Particle damping is one of the recent passive damping methods used for effective vibration suppression. This paper discusses two different Artificial Neural Networks - Feed Forward Back Propagation Network and Radial Basis Function - applied to determine the relationship between the damping ratio and system parameters based on extensive experiments carried out on an aluminium alloy beam. The experiments are carried out with different combinations of system parameters for the estimation of damping ratio. Based on the Neural Network predictions, the factors which affect the damping performances are studied in detail for the given combination of system parameters.

Neural network design

Abstract: This book, by the authors of the Neural Network Toolbox for MATLAB, provides a clear and detailed coverage of fundamental neural network architectures and learning rules. In it, the authors emphasize a coherent presentation of the principal neural networks, methods for training them and their applications to practical problems. Features Extensive coverage of training methods for both feedforward networks (including multilayer and radial basis networks) and recurrent networks. In addition to conjugate gradient and Levenberg-Marquardt variations of the backpropagation algorithm, the text also covers Bayesian regularization and early stopping, which ensure the generalization ability of trained networks. Associative and competitive networks, including feature maps and learning vector quantization, are explained with simple building blocks. A chapter of practical training tips for function approximation, pattern recognition, clustering and prediction, along with five chapters presenting detailed real-world case studies. Detailed examples and numerous solved problems. Slides and comprehensive demonstration software can be downloaded from hagan.okstate.edu/nnd.html.

Design and Analysis - A Researcher's Handbook

Abstract: I. INTRODUCTION. 1. Experimental Design. II. SINGLE FACTOR EXPERIMENTS. 2. Sources of Variability and Sums of Squares. 3. Variance Estimates and F Ratio. 4. Analytical Comparisons Among Means. 5. Analysis of Trend. 6. Simultaneous Comparisons. 7. The Linear Model and Its Assumptions. 8. Effect Size and Power. 9. Using Statistical Software. III. FACTORIAL EXPERIMENTS WITH TWO FACTORS. 10. Introduction to the Factorial Design. 11. The Principal Two-Factor Effects. 12. Main Effects and Simple Effects. 13. The Analysis of Interaction Components. IV. NONORTHOGONALITY AND THE GENERAL LINEAR MODEL. 14. General Linear Model. 15. The Analysis of Covariance. V. WITHIN-SUBJECT DESIGNS. 16. The Single-Factor Within-Subject Design. 17. Further Within-Subject Topics. 18. The Two-Factor Within-Subject Design. 19. The Mixed Design: Overall Analysis. 20. The Mixed Design: Analytical Analyses. VI. HIGHER FACTORIAL DESIGNS AND OTHER EXTENSIONS. 21. The Overall Three-Factor Design. 22. The Three-Way Analytical Analysis. 23. Within-Subject and Mixed Designs. 24. Random Factors and Generalization. 25. Nested Factors. 26. Higher-Order Designs. Appendix A: Statistical Tables.

Fast learning in networks of locally-tuned processing units

Abstract: We propose a network architecture which uses a single internal layer of locally-tuned processing units to learn both classification tasks and real-valued function approximations (Moody and Darken 1988). We consider training such networks in a completely supervised manner, but abandon this approach in favor of a more computationally efficient hybrid learning method which combines self-organized and supervised learning. Our networks learn faster than backpropagation for two reasons: the local representations ensure that only a few units respond to any given input, thus reducing computational overhead, and the hybrid learning rules are linear rather than nonlinear, thus leading to faster convergence. Unlike many existing methods for data analysis, our network architecture and learning rules are truly adaptive and are thus appropriate for real-time use.

Damage identification and health monitoring of structural and mechanical systems from changes in their vibration characteristics: A literature review

Abstract: This report contains a review of the technical literature concerning the detection, location, and characterization of structural damage via techniques that examine changes in measured structural vibration response. The report first categorizes the methods according to required measured data and analysis technique. The analysis categories include changes in modal frequencies, changes in measured mode shapes (and their derivatives), and changes in measured flexibility coefficients. Methods that use property (stiffness, mass, damping) matrix updating, detection of nonlinear response, and damage detection via neural networks are also summarized. The applications of the various methods to different types of engineering problems are categorized by type of structure and are summarized. The types of structures include beams, trusses, plates, shells, bridges, offshore platforms, other large civil structures, aerospace structures, and composite structures. The report describes the development of the damage-identification methods and applications and summarizes the current state-of-the-art of the technology. The critical issues for future research in the area of damage identification are also discussed.

Design and Analysis of Simulation Experiments

Abstract: Design and Analysis of Simulation Experiments (DASE)focuses on statistical methods for discrete-event simulation (such as queuing and inventory simulations). In addition, the book discusses DASE for deterministic simulation (such as engineering and physics simulations). The text presents both classic and modern statistical designs. Classic designs (e.g., fractional factorials) assume only a few factors with a few values per factor. The resulting input/output data of the simulation experiment are analyzed through low-order polynomials, which are linear regression (meta) models. Modern designs allow many more factors, possible with many values per factor. These designs include group screening (e.g., Sequential Bifurcation, SB) and space filling designs (e.g., Latin Hypercube Sampling, LHS). The data resulting from these modern designs may be analyzed through low-order polynomials for group screening and various metamodel types (e.g., Kriging) for LHS. Design and Analysis of Simulation Experimentsis an authoritative textbook and reference work for researchers, graduate students, and technical practitioners in simulation. Basic knowledge of simulation and mathematical statistics are expected; however, the book does summarize these basics, for the readers' convenience. In addition, the book provides relatively simple solutions for (a) selecting problems to simulate, (b) how to analyze the resulting data from simulation, and (c) computationally challenging simulation problems.